vsh/biobox
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Build branch v0.2 with version v0.2 (f22ab0e)

Browse Source 
Build pipeline: viash-hub.biobox.v0.2-s4bkm

Source commit: f22ab0eab5

Source message: Prep v0.2.0
This commit is contained in:
CI
2024-09-12 13:07:11 +00:00
commit 884fc9474e
691 changed files with 402692 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

261
target/executable/agat/agat_convert_bed2gff/.config.vsh.yaml Normal file
View File

@@ -0,0 +1,261 @@
name: "agat_convert_bed2gff"
namespace: "agat"
version: "v0.2"
authors:
- name: "Leïla Paquay"
roles:
- "author"
- "maintainer"
info:
links:
email: "leila@data-intuitive.com"
github: "Leila011"
linkedin: "leilapaquay"
organizations:
- name: "Data Intuitive"
href: "https://www.data-intuitive.com"
role: "Software Developer"
argument_groups:
- name: "Inputs"
arguments:
- type: "file"
name: "--bed"
description: "Input bed file that will be converted."
info: null
example:
- "input.bed"
must_exist: true
create_parent: true
required: true
direction: "input"
multiple: false
multiple_sep: ";"
- name: "Outputs"
arguments:
- type: "file"
name: "--output"
alternatives:
- "-o"
- "--out"
- "--outfile"
- "--gff"
description: "Output GFF file. If no output file is specified, the output will\
\ be written to STDOUT."
info: null
example:
- "output.gff"
must_exist: true
create_parent: true
required: true
direction: "output"
multiple: false
multiple_sep: ";"
- name: "Arguments"
arguments:
- type: "string"
name: "--source"
description: "The source informs about the tool used to produce the data and is\
\ stored in 2nd field of a gff file. Example: Stringtie, Maker, Augustus, etc.\
\ [default: data]\n"
info: null
example:
- "Stringtie"
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--primary_tag"
description: "The primary_tag corresponds to the data type and is stored in 3rd\
\ field of a gff file. Example: gene, mRNA, CDS, etc. [default: gene]\n"
info: null
example:
- "gene"
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean_false"
name: "--inflate_off"
description: "By default we inflate the block fields (blockCount, blockSizes,\
\ blockStarts) to create subfeatures of the main feature (primary_tag). The\
\ type of subfeature created is based on the inflate_type parameter. If you\
\ do not want this inflating behaviour you can deactivate it by using the --inflate_off\
\ option.\n"
info: null
direction: "input"
- type: "string"
name: "--inflate_type"
description: "Feature type (3rd column in gff) created when inflate parameter\
\ activated [default: exon].\n"
info: null
example:
- "exon"
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean_true"
name: "--verbose"
description: "add verbosity"
info: null
direction: "input"
- type: "file"
name: "--config"
alternatives:
- "-c"
description: "Input agat config file. By default AGAT takes as input agat_config.yaml\
\ file from the working directory if any, otherwise it takes the orignal agat_config.yaml\
\ shipped with AGAT. To get the agat_config.yaml locally type: \"agat config\
\ --expose\". The --config option gives you the possibility to use your own\
\ AGAT config file (located elsewhere or named differently).\n"
info: null
example:
- "custom_agat_config.yaml"
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
resources:
- type: "bash_script"
path: "script.sh"
is_executable: true
description: "The script takes a bed file as input, and will translate it in gff format.\
\ The BED format is described here The script converts 0-based, half-open [start-1,\
\ end) bed file to 1-based, closed [start, end] General Feature Format v3 (GFF3).\n"
test_resources:
- type: "bash_script"
path: "test.sh"
is_executable: true
- type: "file"
path: "test_data"
info: null
status: "enabled"
requirements:
commands:
- "ps"
keywords:
- "gene annotations"
- "GFF conversion"
license: "GPL-3.0"
references:
doi:
- "10.5281/zenodo.3552717"
links:
repository: "https://github.com/NBISweden/AGAT"
homepage: "https://github.com/NBISweden/AGAT"
documentation: "https://agat.readthedocs.io/en/latest/tools/agat_convert_bed2gff.html"
issue_tracker: "https://github.com/NBISweden/AGAT/issues"
runners:
- type: "executable"
id: "executable"
docker_setup_strategy: "ifneedbepullelsecachedbuild"
- type: "nextflow"
id: "nextflow"
directives:
tag: "$id"
auto:
simplifyInput: true
simplifyOutput: false
transcript: false
publish: false
config:
labels:
mem1gb: "memory = 1000000000.B"
mem2gb: "memory = 2000000000.B"
mem5gb: "memory = 5000000000.B"
mem10gb: "memory = 10000000000.B"
mem20gb: "memory = 20000000000.B"
mem50gb: "memory = 50000000000.B"
mem100gb: "memory = 100000000000.B"
mem200gb: "memory = 200000000000.B"
mem500gb: "memory = 500000000000.B"
mem1tb: "memory = 1000000000000.B"
mem2tb: "memory = 2000000000000.B"
mem5tb: "memory = 5000000000000.B"
mem10tb: "memory = 10000000000000.B"
mem20tb: "memory = 20000000000000.B"
mem50tb: "memory = 50000000000000.B"
mem100tb: "memory = 100000000000000.B"
mem200tb: "memory = 200000000000000.B"
mem500tb: "memory = 500000000000000.B"
mem1gib: "memory = 1073741824.B"
mem2gib: "memory = 2147483648.B"
mem4gib: "memory = 4294967296.B"
mem8gib: "memory = 8589934592.B"
mem16gib: "memory = 17179869184.B"
mem32gib: "memory = 34359738368.B"
mem64gib: "memory = 68719476736.B"
mem128gib: "memory = 137438953472.B"
mem256gib: "memory = 274877906944.B"
mem512gib: "memory = 549755813888.B"
mem1tib: "memory = 1099511627776.B"
mem2tib: "memory = 2199023255552.B"
mem4tib: "memory = 4398046511104.B"
mem8tib: "memory = 8796093022208.B"
mem16tib: "memory = 17592186044416.B"
mem32tib: "memory = 35184372088832.B"
mem64tib: "memory = 70368744177664.B"
mem128tib: "memory = 140737488355328.B"
mem256tib: "memory = 281474976710656.B"
mem512tib: "memory = 562949953421312.B"
cpu1: "cpus = 1"
cpu2: "cpus = 2"
cpu5: "cpus = 5"
cpu10: "cpus = 10"
cpu20: "cpus = 20"
cpu50: "cpus = 50"
cpu100: "cpus = 100"
cpu200: "cpus = 200"
cpu500: "cpus = 500"
cpu1000: "cpus = 1000"
debug: false
container: "docker"
engines:
- type: "docker"
id: "docker"
image: "quay.io/biocontainers/agat:1.4.0--pl5321hdfd78af_0"
target_registry: "images.viash-hub.com"
target_tag: "v0.2"
namespace_separator: "/"
setup:
- type: "docker"
run:
- "agat --version | sed 's/AGAT\\s\\(.*\\)/agat: \"\\1\"/' > /var/software_versions.txt\n"
entrypoint: []
cmd: null
- type: "native"
id: "native"
build_info:
config: "src/agat/agat_convert_bed2gff/config.vsh.yaml"
runner: "executable"
engine: "docker|native"
output: "target/executable/agat/agat_convert_bed2gff"
executable: "target/executable/agat/agat_convert_bed2gff/agat_convert_bed2gff"
viash_version: "0.9.0-RC7"
git_commit: "f22ab0eab58dcd6bff89d8d73fe951953ff1260f"
git_remote: "https://github.com/viash-hub/biobox"
package_config:
name: "biobox"
version: "v0.2"
description: "A collection of bioinformatics tools for working with sequence data.\n"
info: null
viash_version: "0.9.0-RC7"
source: "src"
target: "target"
config_mods:
- ".requirements.commands := ['ps']\n"
- ".engines += { type: \"native\" }"
- ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
- ".engines[.type == 'docker'].target_tag := 'v0.2'"
keywords:
- "bioinformatics"
- "modules"
- "sequencing"
license: "MIT"
organization: "vsh"
links:
repository: "https://github.com/viash-hub/biobox"
issue_tracker: "https://github.com/viash-hub/biobox/issues"

1260
target/executable/agat/agat_convert_bed2gff/agat_convert_bed2gff Executable file
View File

File diff suppressed because it is too large Load Diff

251
target/executable/agat/agat_convert_embl2gff/.config.vsh.yaml Normal file
View File

@@ -0,0 +1,251 @@
name: "agat_convert_embl2gff"
namespace: "agat"
version: "v0.2"
authors:
- name: "Leïla Paquay"
roles:
- "author"
- "maintainer"
info:
links:
email: "leila@data-intuitive.com"
github: "Leila011"
linkedin: "leilapaquay"
organizations:
- name: "Data Intuitive"
href: "https://www.data-intuitive.com"
role: "Software Developer"
argument_groups:
- name: "Inputs"
arguments:
- type: "file"
name: "--embl"
description: "Input EMBL file that will be read."
info: null
example:
- "input.embl"
must_exist: true
create_parent: true
required: true
direction: "input"
multiple: false
multiple_sep: ";"
- name: "Outputs"
arguments:
- type: "file"
name: "--output"
alternatives:
- "-o"
- "--out"
- "--outfile"
- "--gff"
description: "Output GFF file. If no output file is specified, the output will\
\ be written to STDOUT."
info: null
example:
- "output.gff"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- name: "Arguments"
arguments:
- type: "boolean_true"
name: "--emblmygff3"
description: "Means that the EMBL flat file comes from the EMBLmyGFF3 software.\
\ This is an EMBL format dedicated for submission and contains particularity\
\ to deal with. This parameter is needed to get a proper sequence id in the\
\ GFF3 from an embl made with EMBLmyGFF3.\n"
info: null
direction: "input"
- type: "string"
name: "--primary_tag"
alternatives:
- "--pt"
- "-t"
description: "List of \"primary tag\". Useful to discard or keep specific features.\
\ Multiple tags must be comma-separated.\n"
info: null
example:
- "tag1"
- "tag2"
required: false
direction: "input"
multiple: true
multiple_sep: ";"
- type: "boolean_true"
name: "--discard"
alternatives:
- "-d"
description: "Means that primary tags provided by the option \"primary_tag\" will\
\ be discarded.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--keep"
alternatives:
- "-k"
description: "Means that only primary tags provided by the option \"primary_tag\"\
\ will be kept.\n"
info: null
direction: "input"
- type: "file"
name: "--config"
alternatives:
- "-c"
description: "Input agat config file. By default AGAT takes as input agat_config.yaml\
\ file from the working directory if any, otherwise it takes the original agat_config.yaml\
\ shipped with AGAT. To get the agat_config.yaml locally type: \"agat config\
\ --expose\". The --config option gives you the possibility to use your own\
\ AGAT config file (located elsewhere or named differently).\n"
info: null
example:
- "custom_agat_config.yaml"
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
resources:
- type: "bash_script"
path: "script.sh"
is_executable: true
description: "The script takes an EMBL file as input, and will translate it in gff\
\ format.\n"
test_resources:
- type: "bash_script"
path: "test.sh"
is_executable: true
- type: "file"
path: "test_data"
info: null
status: "enabled"
requirements:
commands:
- "ps"
keywords:
- "gene annotations"
- "GFF conversion"
license: "GPL-3.0"
references:
doi:
- "10.5281/zenodo.3552717"
links:
repository: "https://github.com/NBISweden/AGAT"
homepage: "https://github.com/NBISweden/AGAT"
documentation: "https://agat.readthedocs.io/en/latest/tools/agat_convert_embl2gff.html"
issue_tracker: "https://github.com/NBISweden/AGAT/issues"
runners:
- type: "executable"
id: "executable"
docker_setup_strategy: "ifneedbepullelsecachedbuild"
- type: "nextflow"
id: "nextflow"
directives:
tag: "$id"
auto:
simplifyInput: true
simplifyOutput: false
transcript: false
publish: false
config:
labels:
mem1gb: "memory = 1000000000.B"
mem2gb: "memory = 2000000000.B"
mem5gb: "memory = 5000000000.B"
mem10gb: "memory = 10000000000.B"
mem20gb: "memory = 20000000000.B"
mem50gb: "memory = 50000000000.B"
mem100gb: "memory = 100000000000.B"
mem200gb: "memory = 200000000000.B"
mem500gb: "memory = 500000000000.B"
mem1tb: "memory = 1000000000000.B"
mem2tb: "memory = 2000000000000.B"
mem5tb: "memory = 5000000000000.B"
mem10tb: "memory = 10000000000000.B"
mem20tb: "memory = 20000000000000.B"
mem50tb: "memory = 50000000000000.B"
mem100tb: "memory = 100000000000000.B"
mem200tb: "memory = 200000000000000.B"
mem500tb: "memory = 500000000000000.B"
mem1gib: "memory = 1073741824.B"
mem2gib: "memory = 2147483648.B"
mem4gib: "memory = 4294967296.B"
mem8gib: "memory = 8589934592.B"
mem16gib: "memory = 17179869184.B"
mem32gib: "memory = 34359738368.B"
mem64gib: "memory = 68719476736.B"
mem128gib: "memory = 137438953472.B"
mem256gib: "memory = 274877906944.B"
mem512gib: "memory = 549755813888.B"
mem1tib: "memory = 1099511627776.B"
mem2tib: "memory = 2199023255552.B"
mem4tib: "memory = 4398046511104.B"
mem8tib: "memory = 8796093022208.B"
mem16tib: "memory = 17592186044416.B"
mem32tib: "memory = 35184372088832.B"
mem64tib: "memory = 70368744177664.B"
mem128tib: "memory = 140737488355328.B"
mem256tib: "memory = 281474976710656.B"
mem512tib: "memory = 562949953421312.B"
cpu1: "cpus = 1"
cpu2: "cpus = 2"
cpu5: "cpus = 5"
cpu10: "cpus = 10"
cpu20: "cpus = 20"
cpu50: "cpus = 50"
cpu100: "cpus = 100"
cpu200: "cpus = 200"
cpu500: "cpus = 500"
cpu1000: "cpus = 1000"
debug: false
container: "docker"
engines:
- type: "docker"
id: "docker"
image: "quay.io/biocontainers/agat:1.4.0--pl5321hdfd78af_0"
target_registry: "images.viash-hub.com"
target_tag: "v0.2"
namespace_separator: "/"
setup:
- type: "docker"
run:
- "agat --version | sed 's/AGAT\\s\\(.*\\)/agat: \"\\1\"/' > /var/software_versions.txt\n"
entrypoint: []
cmd: null
- type: "native"
id: "native"
build_info:
config: "src/agat/agat_convert_embl2gff/config.vsh.yaml"
runner: "executable"
engine: "docker|native"
output: "target/executable/agat/agat_convert_embl2gff"
executable: "target/executable/agat/agat_convert_embl2gff/agat_convert_embl2gff"
viash_version: "0.9.0-RC7"
git_commit: "f22ab0eab58dcd6bff89d8d73fe951953ff1260f"
git_remote: "https://github.com/viash-hub/biobox"
package_config:
name: "biobox"
version: "v0.2"
description: "A collection of bioinformatics tools for working with sequence data.\n"
info: null
viash_version: "0.9.0-RC7"
source: "src"
target: "target"
config_mods:
- ".requirements.commands := ['ps']\n"
- ".engines += { type: \"native\" }"
- ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
- ".engines[.type == 'docker'].target_tag := 'v0.2'"
keywords:
- "bioinformatics"
- "modules"
- "sequencing"
license: "MIT"
organization: "vsh"
links:
repository: "https://github.com/viash-hub/biobox"
issue_tracker: "https://github.com/viash-hub/biobox/issues"

1275
target/executable/agat/agat_convert_embl2gff/agat_convert_embl2gff Executable file
View File

File diff suppressed because it is too large Load Diff

254
target/executable/agat/agat_convert_sp_gff2gtf/.config.vsh.yaml Normal file
View File

@@ -0,0 +1,254 @@
name: "agat_convert_sp_gff2gtf"
namespace: "agat"
version: "v0.2"
authors:
- name: "Leïla Paquay"
roles:
- "author"
- "maintainer"
info:
links:
email: "leila@data-intuitive.com"
github: "Leila011"
linkedin: "leilapaquay"
organizations:
- name: "Data Intuitive"
href: "https://www.data-intuitive.com"
role: "Software Developer"
argument_groups:
- name: "Inputs"
arguments:
- type: "file"
name: "--gff"
alternatives:
- "-i"
description: "Input GFF/GTF file that will be read"
info: null
example:
- "input.gff"
must_exist: true
create_parent: true
required: true
direction: "input"
multiple: false
multiple_sep: ";"
- name: "Outputs"
arguments:
- type: "file"
name: "--output"
alternatives:
- "-o"
- "--out"
- "--outfile"
- "--gtf"
description: "Output GTF file. If no output file is specified, the output will\
\ be written to STDOUT."
info: null
example:
- "output.gtf"
must_exist: true
create_parent: true
required: true
direction: "output"
multiple: false
multiple_sep: ";"
- name: "Arguments"
arguments:
- type: "string"
name: "--gtf_version"
description: "Version of the GTF output (1,2,2.1,2.2,2.5,3 or relax). Default\
\ value from AGAT config file (relax for the default config). The script option\
\ has the higher priority. \n\n * relax: all feature types are accepted. \
\ \n * GTF3 (9 feature types accepted): gene, transcript, exon, CDS, Selenocysteine,\
\ start_codon, stop_codon, three_prime_utr and five_prime_utr. \n * GTF2.5\
\ (8 feature types accepted): gene, transcript, exon, CDS, UTR, start_codon,\
\ stop_codon, Selenocysteine. \n * GTF2.2 (9 feature types accepted): CDS,\
\ start_codon, stop_codon, 5UTR, 3UTR, inter, inter_CNS, intron_CNS and exon.\
\ \n * GTF2.1 (6 feature types accepted): CDS, start_codon, stop_codon, exon,\
\ 5UTR, 3UTR. \n * GTF2 (4 feature types accepted): CDS, start_codon, stop_codon,\
\ exon. \n * GTF1 (5 feature types accepted): CDS, start_codon, stop_codon,\
\ exon, intron. \n"
info: null
example:
- "3"
required: false
choices:
- "relax"
- "1"
- "2"
- "2.1"
- "2.2"
- "2.5"
- "3"
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--config"
alternatives:
- "-c"
description: "Input agat config file. By default AGAT takes as input agat_config.yaml\
\ file from the working directory if any, otherwise it takes the orignal agat_config.yaml\
\ shipped with AGAT. To get the agat_config.yaml locally type: \"agat config\
\ --expose\". The --config option gives you the possibility to use your own\
\ AGAT config file (located elsewhere or named differently).\n"
info: null
example:
- "custom_agat_config.yaml"
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
resources:
- type: "bash_script"
path: "script.sh"
is_executable: true
description: "The script aims to convert any GTF/GFF file into a proper GTF file.\
\ Full\ninformation about the format can be found here:\nhttps://agat.readthedocs.io/en/latest/gxf.html\
\ You can choose among 7\ndifferent GTF types (1, 2, 2.1, 2.2, 2.5, 3 or relax).\
\ Depending the\nversion selected the script will filter out the features that are\
\ not\naccepted. For GTF2.5 and 3, every level1 feature (e.g nc_gene\npseudogene)\
\ will be converted into gene feature and every level2 feature\n(e.g mRNA ncRNA)\
\ will be converted into transcript feature. Using the\n\"relax\" option you will\
\ produce a GTF-like output keeping all original\nfeature types (3rd column). No\
\ modification will occur e.g. mRNA to\ntranscript.\n\nTo be fully GTF compliant\
\ all feature have a gene_id and a transcript_id\nattribute. The gene_id is unique\
\ identifier for the genomic source of\nthe transcript, which is used to group transcripts\
\ into genes. The\ntranscript_id is a unique identifier for the predicted transcript,\
\ which\nis used to group features into transcripts.\n"
test_resources:
- type: "bash_script"
path: "test.sh"
is_executable: true
- type: "file"
path: "test_data"
info: null
status: "enabled"
requirements:
commands:
- "ps"
keywords:
- "gene annotations"
- "GTF conversion"
license: "GPL-3.0"
references:
doi:
- "10.5281/zenodo.3552717"
links:
repository: "https://github.com/NBISweden/AGAT"
homepage: "https://github.com/NBISweden/AGAT"
documentation: "https://agat.readthedocs.io/"
issue_tracker: "https://github.com/NBISweden/AGAT/issues"
runners:
- type: "executable"
id: "executable"
docker_setup_strategy: "ifneedbepullelsecachedbuild"
- type: "nextflow"
id: "nextflow"
directives:
tag: "$id"
auto:
simplifyInput: true
simplifyOutput: false
transcript: false
publish: false
config:
labels:
mem1gb: "memory = 1000000000.B"
mem2gb: "memory = 2000000000.B"
mem5gb: "memory = 5000000000.B"
mem10gb: "memory = 10000000000.B"
mem20gb: "memory = 20000000000.B"
mem50gb: "memory = 50000000000.B"
mem100gb: "memory = 100000000000.B"
mem200gb: "memory = 200000000000.B"
mem500gb: "memory = 500000000000.B"
mem1tb: "memory = 1000000000000.B"
mem2tb: "memory = 2000000000000.B"
mem5tb: "memory = 5000000000000.B"
mem10tb: "memory = 10000000000000.B"
mem20tb: "memory = 20000000000000.B"
mem50tb: "memory = 50000000000000.B"
mem100tb: "memory = 100000000000000.B"
mem200tb: "memory = 200000000000000.B"
mem500tb: "memory = 500000000000000.B"
mem1gib: "memory = 1073741824.B"
mem2gib: "memory = 2147483648.B"
mem4gib: "memory = 4294967296.B"
mem8gib: "memory = 8589934592.B"
mem16gib: "memory = 17179869184.B"
mem32gib: "memory = 34359738368.B"
mem64gib: "memory = 68719476736.B"
mem128gib: "memory = 137438953472.B"
mem256gib: "memory = 274877906944.B"
mem512gib: "memory = 549755813888.B"
mem1tib: "memory = 1099511627776.B"
mem2tib: "memory = 2199023255552.B"
mem4tib: "memory = 4398046511104.B"
mem8tib: "memory = 8796093022208.B"
mem16tib: "memory = 17592186044416.B"
mem32tib: "memory = 35184372088832.B"
mem64tib: "memory = 70368744177664.B"
mem128tib: "memory = 140737488355328.B"
mem256tib: "memory = 281474976710656.B"
mem512tib: "memory = 562949953421312.B"
cpu1: "cpus = 1"
cpu2: "cpus = 2"
cpu5: "cpus = 5"
cpu10: "cpus = 10"
cpu20: "cpus = 20"
cpu50: "cpus = 50"
cpu100: "cpus = 100"
cpu200: "cpus = 200"
cpu500: "cpus = 500"
cpu1000: "cpus = 1000"
debug: false
container: "docker"
engines:
- type: "docker"
id: "docker"
image: "quay.io/biocontainers/agat:1.4.0--pl5321hdfd78af_0"
target_registry: "images.viash-hub.com"
target_tag: "v0.2"
namespace_separator: "/"
setup:
- type: "docker"
run:
- "agat --version | sed 's/AGAT\\s\\(.*\\)/agat: \"\\1\"/' > /var/software_versions.txt\n"
entrypoint: []
cmd: null
- type: "native"
id: "native"
build_info:
config: "src/agat/agat_convert_sp_gff2gtf/config.vsh.yaml"
runner: "executable"
engine: "docker|native"
output: "target/executable/agat/agat_convert_sp_gff2gtf"
executable: "target/executable/agat/agat_convert_sp_gff2gtf/agat_convert_sp_gff2gtf"
viash_version: "0.9.0-RC7"
git_commit: "f22ab0eab58dcd6bff89d8d73fe951953ff1260f"
git_remote: "https://github.com/viash-hub/biobox"
package_config:
name: "biobox"
version: "v0.2"
description: "A collection of bioinformatics tools for working with sequence data.\n"
info: null
viash_version: "0.9.0-RC7"
source: "src"
target: "target"
config_mods:
- ".requirements.commands := ['ps']\n"
- ".engines += { type: \"native\" }"
- ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
- ".engines[.type == 'docker'].target_tag := 'v0.2'"
keywords:
- "bioinformatics"
- "modules"
- "sequencing"
license: "MIT"
organization: "vsh"
links:
repository: "https://github.com/viash-hub/biobox"
issue_tracker: "https://github.com/viash-hub/biobox/issues"

1218
target/executable/agat/agat_convert_sp_gff2gtf/agat_convert_sp_gff2gtf Executable file
View File

File diff suppressed because it is too large Load Diff

214
target/executable/agat/agat_convert_sp_gff2tsv/.config.vsh.yaml Normal file
View File

@@ -0,0 +1,214 @@
name: "agat_convert_sp_gff2tsv"
namespace: "agat"
version: "v0.2"
authors:
- name: "Leïla Paquay"
roles:
- "author"
- "maintainer"
info:
links:
email: "leila@data-intuitive.com"
github: "Leila011"
linkedin: "leilapaquay"
organizations:
- name: "Data Intuitive"
href: "https://www.data-intuitive.com"
role: "Software Developer"
argument_groups:
- name: "Inputs"
arguments:
- type: "file"
name: "--gff"
alternatives:
- "-f"
description: "Input GTF/GFF file."
info: null
example:
- "input.gff"
must_exist: true
create_parent: true
required: true
direction: "input"
multiple: false
multiple_sep: ";"
- name: "Outputs"
arguments:
- type: "file"
name: "--output"
alternatives:
- "-o"
- "--out"
- "--outfile"
description: "Output GFF file. If no output file is specified, the output will\
\ be written to STDOUT."
info: null
example:
- "output.gff"
must_exist: true
create_parent: true
required: true
direction: "output"
multiple: false
multiple_sep: ";"
- name: "Arguments"
arguments:
- type: "file"
name: "--config"
alternatives:
- "-c"
description: "String - Input agat config file. By default AGAT takes as input\n\
agat_config.yaml file from the working directory if any,\notherwise it takes\
\ the orignal agat_config.yaml shipped with\nAGAT. To get the agat_config.yaml\
\ locally type: \"agat config\n--expose\". The --config option gives you the\
\ possibility to use\nyour own AGAT config file (located elsewhere or named\n\
differently). \n"
info: null
example:
- "custom_agat_config.yaml"
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
resources:
- type: "bash_script"
path: "script.sh"
is_executable: true
description: "The script aims to convert gtf/gff file into tabulated file. Attribute's\n\
tags from the 9th column become column titles.\n"
test_resources:
- type: "bash_script"
path: "test.sh"
is_executable: true
- type: "file"
path: "test_data"
info: null
status: "enabled"
requirements:
commands:
- "ps"
keywords:
- "gene annotations"
- "GFF conversion"
license: "GPL-3.0"
references:
doi:
- "10.5281/zenodo.3552717"
links:
repository: "https://github.com/NBISweden/AGAT"
homepage: "https://github.com/NBISweden/AGAT"
documentation: "https://agat.readthedocs.io/en/latest/tools/agat_convert_sp_gff2tsv.html"
issue_tracker: "https://github.com/NBISweden/AGAT/issues"
runners:
- type: "executable"
id: "executable"
docker_setup_strategy: "ifneedbepullelsecachedbuild"
- type: "nextflow"
id: "nextflow"
directives:
tag: "$id"
auto:
simplifyInput: true
simplifyOutput: false
transcript: false
publish: false
config:
labels:
mem1gb: "memory = 1000000000.B"
mem2gb: "memory = 2000000000.B"
mem5gb: "memory = 5000000000.B"
mem10gb: "memory = 10000000000.B"
mem20gb: "memory = 20000000000.B"
mem50gb: "memory = 50000000000.B"
mem100gb: "memory = 100000000000.B"
mem200gb: "memory = 200000000000.B"
mem500gb: "memory = 500000000000.B"
mem1tb: "memory = 1000000000000.B"
mem2tb: "memory = 2000000000000.B"
mem5tb: "memory = 5000000000000.B"
mem10tb: "memory = 10000000000000.B"
mem20tb: "memory = 20000000000000.B"
mem50tb: "memory = 50000000000000.B"
mem100tb: "memory = 100000000000000.B"
mem200tb: "memory = 200000000000000.B"
mem500tb: "memory = 500000000000000.B"
mem1gib: "memory = 1073741824.B"
mem2gib: "memory = 2147483648.B"
mem4gib: "memory = 4294967296.B"
mem8gib: "memory = 8589934592.B"
mem16gib: "memory = 17179869184.B"
mem32gib: "memory = 34359738368.B"
mem64gib: "memory = 68719476736.B"
mem128gib: "memory = 137438953472.B"
mem256gib: "memory = 274877906944.B"
mem512gib: "memory = 549755813888.B"
mem1tib: "memory = 1099511627776.B"
mem2tib: "memory = 2199023255552.B"
mem4tib: "memory = 4398046511104.B"
mem8tib: "memory = 8796093022208.B"
mem16tib: "memory = 17592186044416.B"
mem32tib: "memory = 35184372088832.B"
mem64tib: "memory = 70368744177664.B"
mem128tib: "memory = 140737488355328.B"
mem256tib: "memory = 281474976710656.B"
mem512tib: "memory = 562949953421312.B"
cpu1: "cpus = 1"
cpu2: "cpus = 2"
cpu5: "cpus = 5"
cpu10: "cpus = 10"
cpu20: "cpus = 20"
cpu50: "cpus = 50"
cpu100: "cpus = 100"
cpu200: "cpus = 200"
cpu500: "cpus = 500"
cpu1000: "cpus = 1000"
debug: false
container: "docker"
engines:
- type: "docker"
id: "docker"
image: "quay.io/biocontainers/agat:1.4.0--pl5321hdfd78af_0"
target_registry: "images.viash-hub.com"
target_tag: "v0.2"
namespace_separator: "/"
setup:
- type: "docker"
run:
- "agat --version | sed 's/AGAT\\s\\(.*\\)/agat: \"\\1\"/' > /var/software_versions.txt\n"
entrypoint: []
cmd: null
- type: "native"
id: "native"
build_info:
config: "src/agat/agat_convert_sp_gff2tsv/config.vsh.yaml"
runner: "executable"
engine: "docker|native"
output: "target/executable/agat/agat_convert_sp_gff2tsv"
executable: "target/executable/agat/agat_convert_sp_gff2tsv/agat_convert_sp_gff2tsv"
viash_version: "0.9.0-RC7"
git_commit: "f22ab0eab58dcd6bff89d8d73fe951953ff1260f"
git_remote: "https://github.com/viash-hub/biobox"
package_config:
name: "biobox"
version: "v0.2"
description: "A collection of bioinformatics tools for working with sequence data.\n"
info: null
viash_version: "0.9.0-RC7"
source: "src"
target: "target"
config_mods:
- ".requirements.commands := ['ps']\n"
- ".engines += { type: \"native\" }"
- ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
- ".engines[.type == 'docker'].target_tag := 'v0.2'"
keywords:
- "bioinformatics"
- "modules"
- "sequencing"
license: "MIT"
organization: "vsh"
links:
repository: "https://github.com/viash-hub/biobox"
issue_tracker: "https://github.com/viash-hub/biobox/issues"

1151
target/executable/agat/agat_convert_sp_gff2tsv/agat_convert_sp_gff2tsv Executable file
View File

File diff suppressed because it is too large Load Diff

221
target/executable/agat/agat_convert_sp_gxf2gxf/.config.vsh.yaml Normal file
View File

@@ -0,0 +1,221 @@
name: "agat_convert_sp_gxf2gxf"
namespace: "agat"
version: "v0.2"
authors:
- name: "Leïla Paquay"
roles:
- "author"
- "maintainer"
info:
links:
email: "leila@data-intuitive.com"
github: "Leila011"
linkedin: "leilapaquay"
organizations:
- name: "Data Intuitive"
href: "https://www.data-intuitive.com"
role: "Software Developer"
argument_groups:
- name: "Inputs"
arguments:
- type: "file"
name: "--gxf"
alternatives:
- "-g"
- "--gtf"
- "--gff"
description: "String - Input GTF/GFF file. Compressed file with .gz extension\
\ is accepted.\n"
info: null
example:
- "input.gff"
must_exist: true
create_parent: true
required: true
direction: "input"
multiple: false
multiple_sep: ";"
- name: "Outputs"
arguments:
- type: "file"
name: "--output"
alternatives:
- "-o"
description: "String - Output GFF file. If no output file is specified, the output\
\ will be written to STDOUT.\n"
info: null
example:
- "output.gff"
must_exist: true
create_parent: true
required: true
direction: "output"
multiple: false
multiple_sep: ";"
- name: "Arguments"
arguments:
- type: "file"
name: "--config"
alternatives:
- "-c"
description: "String - Input agat config file. By default AGAT takes as input\
\ agat_config.yaml file from the working directory if any, otherwise it takes\
\ the original agat_config.yaml shipped with AGAT. To get the agat_config.yaml\
\ locally type: \"agat config --expose\". The --config option gives you the\
\ possibility to use your own AGAT config file (located elsewhere or named differently).\n"
info: null
example:
- "custom_agat_config.yaml"
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
resources:
- type: "bash_script"
path: "script.sh"
is_executable: true
description: "This script fixes and/or standardizes any GTF/GFF file into full sorted\n\
GTF/GFF file. It AGAT parser removes duplicate features, fixes\nduplicated IDs,\
\ adds missing ID and/or Parent attributes, deflates\nfactorized attributes (attributes\
\ with several parents are duplicated\nwith uniq ID), add missing features when\
\ possible (e.g. add exon if only\nCDS described, add UTR if CDS and exon described),\
\ fix feature locations\n(e.g. check exon is embedded in the parent features mRNA,\
\ gene), etc...\n\nAll AGAT's scripts with the _sp_ prefix use the AGAT parser,\
\ before to\nperform any supplementary task. So, it is not necessary to run this\n\
script prior the use of any other _sp_ script.\n"
test_resources:
- type: "bash_script"
path: "test.sh"
is_executable: true
- type: "file"
path: "test_data"
info: null
status: "enabled"
requirements:
commands:
- "ps"
keywords:
- "gene annotations"
- "GFF conversion"
license: "GPL-3.0"
references:
doi:
- "10.5281/zenodo.3552717"
links:
repository: "https://github.com/NBISweden/AGAT"
homepage: "https://github.com/NBISweden/AGAT"
documentation: "https://agat.readthedocs.io/en/latest/tools/agat_convert_sp_gxf2gxf.html"
issue_tracker: "https://github.com/NBISweden/AGAT/issues"
runners:
- type: "executable"
id: "executable"
docker_setup_strategy: "ifneedbepullelsecachedbuild"
- type: "nextflow"
id: "nextflow"
directives:
tag: "$id"
auto:
simplifyInput: true
simplifyOutput: false
transcript: false
publish: false
config:
labels:
mem1gb: "memory = 1000000000.B"
mem2gb: "memory = 2000000000.B"
mem5gb: "memory = 5000000000.B"
mem10gb: "memory = 10000000000.B"
mem20gb: "memory = 20000000000.B"
mem50gb: "memory = 50000000000.B"
mem100gb: "memory = 100000000000.B"
mem200gb: "memory = 200000000000.B"
mem500gb: "memory = 500000000000.B"
mem1tb: "memory = 1000000000000.B"
mem2tb: "memory = 2000000000000.B"
mem5tb: "memory = 5000000000000.B"
mem10tb: "memory = 10000000000000.B"
mem20tb: "memory = 20000000000000.B"
mem50tb: "memory = 50000000000000.B"
mem100tb: "memory = 100000000000000.B"
mem200tb: "memory = 200000000000000.B"
mem500tb: "memory = 500000000000000.B"
mem1gib: "memory = 1073741824.B"
mem2gib: "memory = 2147483648.B"
mem4gib: "memory = 4294967296.B"
mem8gib: "memory = 8589934592.B"
mem16gib: "memory = 17179869184.B"
mem32gib: "memory = 34359738368.B"
mem64gib: "memory = 68719476736.B"
mem128gib: "memory = 137438953472.B"
mem256gib: "memory = 274877906944.B"
mem512gib: "memory = 549755813888.B"
mem1tib: "memory = 1099511627776.B"
mem2tib: "memory = 2199023255552.B"
mem4tib: "memory = 4398046511104.B"
mem8tib: "memory = 8796093022208.B"
mem16tib: "memory = 17592186044416.B"
mem32tib: "memory = 35184372088832.B"
mem64tib: "memory = 70368744177664.B"
mem128tib: "memory = 140737488355328.B"
mem256tib: "memory = 281474976710656.B"
mem512tib: "memory = 562949953421312.B"
cpu1: "cpus = 1"
cpu2: "cpus = 2"
cpu5: "cpus = 5"
cpu10: "cpus = 10"
cpu20: "cpus = 20"
cpu50: "cpus = 50"
cpu100: "cpus = 100"
cpu200: "cpus = 200"
cpu500: "cpus = 500"
cpu1000: "cpus = 1000"
debug: false
container: "docker"
engines:
- type: "docker"
id: "docker"
image: "quay.io/biocontainers/agat:1.4.0--pl5321hdfd78af_0"
target_registry: "images.viash-hub.com"
target_tag: "v0.2"
namespace_separator: "/"
setup:
- type: "docker"
run:
- "agat --version | sed 's/AGAT\\s\\(.*\\)/agat: \"\\1\"/' > /var/software_versions.txt\n"
entrypoint: []
cmd: null
- type: "native"
id: "native"
build_info:
config: "src/agat/agat_convert_sp_gxf2gxf/config.vsh.yaml"
runner: "executable"
engine: "docker|native"
output: "target/executable/agat/agat_convert_sp_gxf2gxf"
executable: "target/executable/agat/agat_convert_sp_gxf2gxf/agat_convert_sp_gxf2gxf"
viash_version: "0.9.0-RC7"
git_commit: "f22ab0eab58dcd6bff89d8d73fe951953ff1260f"
git_remote: "https://github.com/viash-hub/biobox"
package_config:
name: "biobox"
version: "v0.2"
description: "A collection of bioinformatics tools for working with sequence data.\n"
info: null
viash_version: "0.9.0-RC7"
source: "src"
target: "target"
config_mods:
- ".requirements.commands := ['ps']\n"
- ".engines += { type: \"native\" }"
- ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
- ".engines[.type == 'docker'].target_tag := 'v0.2'"
keywords:
- "bioinformatics"
- "modules"
- "sequencing"
license: "MIT"
organization: "vsh"
links:
repository: "https://github.com/viash-hub/biobox"
issue_tracker: "https://github.com/viash-hub/biobox/issues"

1160
target/executable/agat/agat_convert_sp_gxf2gxf/agat_convert_sp_gxf2gxf Executable file
View File

File diff suppressed because it is too large Load Diff

732
target/executable/arriba/.config.vsh.yaml Normal file
View File

@@ -0,0 +1,732 @@
name: "arriba"
version: "v0.2"
authors:
- name: "Robrecht Cannoodt"
roles:
- "author"
- "maintainer"
info:
links:
email: "robrecht@data-intuitive.com"
github: "rcannood"
orcid: "0000-0003-3641-729X"
linkedin: "robrechtcannoodt"
organizations:
- name: "Data Intuitive"
href: "https://www.data-intuitive.com"
role: "Data Science Engineer"
- name: "Open Problems"
href: "https://openproblems.bio"
role: "Core Member"
argument_groups:
- name: "Inputs"
arguments:
- type: "file"
name: "--bam"
alternatives:
- "-x"
description: "File in SAM/BAM/CRAM format with main alignments as generated by\
\ STAR\n(Aligned.out.sam). Arriba extracts candidate reads from this file.\n"
info: null
example:
- "Aligned.out.bam"
must_exist: true
create_parent: true
required: true
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--genome"
alternatives:
- "-a"
description: "FastA file with genome sequence (assembly). The file may be gzip-compressed.\
\ An \nindex with the file extension .fai must exist only if CRAM files are\
\ processed.\n"
info: null
example:
- "assembly.fa"
must_exist: true
create_parent: true
required: true
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--gene_annotation"
alternatives:
- "-g"
description: "GTF file with gene annotation. The file may be gzip-compressed.\n"
info: null
example:
- "annotation.gtf"
must_exist: true
create_parent: true
required: true
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--known_fusions"
alternatives:
- "-k"
description: "File containing known/recurrent fusions. Some cancer entities are\
\ often \ncharacterized by fusions between the same pair of genes. In order\
\ to boost \nsensitivity, a list of known fusions can be supplied using this\
\ parameter. The list \nmust contain two columns with the names of the fused\
\ genes, separated by tabs.\n"
info: null
example:
- "known_fusions.tsv"
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--blacklist"
alternatives:
- "-b"
description: "File containing blacklisted events (recurrent artifacts and transcripts\
\ \nobserved in healthy tissue).\n"
info: null
example:
- "blacklist.tsv"
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--structural_variants"
alternatives:
- "-d"
description: "Tab-separated file with coordinates of structural variants found\
\ using \nwhole-genome sequencing data. These coordinates serve to increase\
\ sensitivity \ntowards weakly expressed fusions and to eliminate fusions with\
\ low evidence. \n"
info: null
example:
- "structural_variants_from_WGS.tsv"
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--tags"
alternatives:
- "-t"
description: "Tab-separated file containing fusions to annotate with tags in the\
\ 'tags' column. \nThe first two columns specify the genes; the third column\
\ specifies the tag. The \nfile may be gzip-compressed. \n"
info: null
example:
- "tags.tsv"
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--protein_domains"
alternatives:
- "-p"
description: "File in GFF3 format containing coordinates of the protein domains\
\ of genes. The\nprotein domains retained in a fusion are listed in the column\n\
'retained_protein_domains'. The file may be gzip-compressed.\n"
info: null
example:
- "protein_domains.gff3"
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- name: "Outputs"
arguments:
- type: "file"
name: "--fusions"
alternatives:
- "-o"
description: "Output file with fusions that have passed all filters.\n"
info: null
example:
- "fusions.tsv"
must_exist: true
create_parent: true
required: true
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--fusions_discarded"
alternatives:
- "-O"
description: "Output file with fusions that were discarded due to filtering. \n"
info: null
example:
- "fusions.discarded.tsv"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- name: "Arguments"
arguments:
- type: "long"
name: "--max_genomic_breakpoint_distance"
alternatives:
- "-D"
description: "When a file with genomic breakpoints obtained via \nwhole-genome\
\ sequencing is supplied via the --structural_variants\nparameter, this parameter\
\ determines how far a \ngenomic breakpoint may be away from a \ntranscriptomic\
\ breakpoint to consider it as a \nrelated event. For events inside genes, the\
\ \ndistance is added to the end of the gene; for \nintergenic events, the distance\
\ threshold is \napplied as is. Default: 100000.\n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--strandedness"
alternatives:
- "-s"
description: "Whether a strand-specific protocol was used for library preparation,\
\ \nand if so, the type of strandedness (auto/yes/no/reverse). When \nunstranded\
\ data is processed, the strand can sometimes be inferred from \nsplice-patterns.\
\ But in unclear situations, stranded data helps \nresolve ambiguities. Default:\
\ auto\n"
info: null
required: false
choices:
- "auto"
- "yes"
- "no"
- "reverse"
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--interesting_contigs"
alternatives:
- "-i"
description: "List of interesting contigs. Fusions between genes \non other contigs\
\ are ignored. Contigs can be specified with or without the \nprefix \"chr\"\
. Asterisks (*) are treated as wild-cards. \nDefault: 1 2 3 4 5 6 7 8 9 10 11\
\ 12 13 14 15 16 17 18 19 20 21 22 X Y AC_* NC_*\n"
info: null
example:
- "1"
- "2"
- "AC_*"
- "NC_*"
required: false
direction: "input"
multiple: true
multiple_sep: ";"
- type: "string"
name: "--viral_contigs"
alternatives:
- "-v"
description: "List of viral contigs. Asterisks (*) are treated as \nwild-cards.\n\
Default: AC_* NC_*\n"
info: null
example:
- "AC_*"
- "NC_*"
required: false
direction: "input"
multiple: true
multiple_sep: ";"
- type: "string"
name: "--disable_filters"
alternatives:
- "-f"
description: "List of filters to disable. By default all filters are \nenabled.\
\ \n"
info: null
required: false
choices:
- "homologs"
- "low_entropy"
- "isoforms"
- "top_expressed_viral_contigs"
- "viral_contigs"
- "uninteresting_contigs"
- "non_coding_neighbors"
- "mismatches"
- "duplicates"
- "no_genomic_support"
- "genomic_support"
- "intronic"
- "end_to_end"
- "relative_support"
- "low_coverage_viral_contigs"
- "merge_adjacent"
- "mismappers"
- "multimappers"
- "same_gene"
- "long_gap"
- "internal_tandem_duplication"
- "small_insert_size"
- "read_through"
- "inconsistently_clipped"
- "intragenic_exonic"
- "marginal_read_through"
- "spliced"
- "hairpin"
- "blacklist"
- "min_support"
- "select_best"
- "in_vitro"
- "short_anchor"
- "known_fusions"
- "no_coverage"
- "homopolymer"
- "many_spliced"
direction: "input"
multiple: true
multiple_sep: ";"
- type: "double"
name: "--max_e_value"
alternatives:
- "-E"
description: "Arriba estimates the number of fusions with a given number of supporting\
\ \nreads which one would expect to see by random chance. If the expected number\
\ \nof fusions (e-value) is higher than this threshold, the fusion is \ndiscarded\
\ by the 'relative_support' filter. Note: Increasing this \nthreshold can dramatically\
\ increase the number of false positives and may \nincrease the runtime of resource-intensive\
\ steps. Fractional values are \npossible. Default: 0.300000 \n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--min_supporting_reads"
alternatives:
- "-S"
description: "The 'min_support' filter discards all fusions with fewer than \n\
this many supporting reads (split reads and discordant mates \ncombined). Default:\
\ 2 \n"
info: null
example:
- 2
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "double"
name: "--max_mismappers"
alternatives:
- "-m"
description: "When more than this fraction of supporting reads turns out to be\
\ \nmismappers, the 'mismappers' filter discards the fusion. Default: \n0.800000\n"
info: null
example:
- 0.8
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "double"
name: "--max_homolog_identity"
alternatives:
- "-L"
description: "Genes with more than the given fraction of sequence identity are\
\ \nconsidered homologs and removed by the 'homologs' filter. \nDefault: 0.300000\
\ \n"
info: null
example:
- 0.3
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--homopolymer_length"
alternatives:
- "-H"
description: "The 'homopolymer' filter removes breakpoints adjacent to \nhomopolymers\
\ of the given length or more. Default: 6\n"
info: null
example:
- 6
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--read_through_distance"
alternatives:
- "-R"
description: "The 'read_through' filter removes read-through fusions \nwhere the\
\ breakpoints are less than the given distance away \nfrom each other. Default:\
\ 10000 \n"
info: null
example:
- 10000
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--min_anchor_length"
alternatives:
- "-A"
description: "Alignment artifacts are often characterized by split reads coming\
\ \nfrom only one gene and no discordant mates. Moreover, the split \nreads\
\ only align to a short stretch in one of the genes. The \n'short_anchor' filter\
\ removes these fusions. This parameter sets \nthe threshold in bp for what\
\ the filter considers short. Default: 23 \n"
info: null
example:
- 23
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--many_spliced_events"
alternatives:
- "-M"
description: "The 'many_spliced' filter recovers fusions between genes that \n\
have at least this many spliced breakpoints. Default: 4\n"
info: null
example:
- 4
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "double"
name: "--max_kmer_content"
alternatives:
- "-K"
description: "The 'low_entropy' filter removes reads with repetitive 3-mers. If\
\ \nthe 3-mers make up more than the given fraction of the sequence, then \n\
the read is discarded. Default: 0.600000 \n"
info: null
example:
- 0.6
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "double"
name: "--max_mismatch_pvalue"
alternatives:
- "-V"
description: "The 'mismatches' filter uses a binomial model to calculate a \n\
p-value for observing a given number of mismatches in a read. If \nthe number\
\ of mismatches is too high, the read is discarded. \nDefault: 0.010000 \n"
info: null
example:
- 0.05
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--fragment_length"
alternatives:
- "-F"
description: "When paired-end data is given, the fragment length is estimated\
\ \nautomatically and this parameter has no effect. But when single-end \ndata\
\ is given, the mean fragment length should be specified to \neffectively filter\
\ fusions that arise from hairpin structures. \nDefault: 200 \n"
info: null
example:
- 200
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--max_reads"
alternatives:
- "-U"
description: "Subsample fusions with more than the given number of supporting\
\ reads. This \nimproves performance without compromising sensitivity, as long\
\ as the \nthreshold is high. Counting of supporting reads beyond the threshold\
\ is \ninaccurate, obviously. Default: 300 \n"
info: null
example:
- 300
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "double"
name: "--quantile"
alternatives:
- "-Q"
description: "Highly expressed genes are prone to produce artifacts during library\
\ \npreparation. Genes with an expression above the given quantile are eligible\
\ \nfor filtering by the 'in_vitro' filter. Default: 0.998000\n"
info: null
example:
- 0.998
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "double"
name: "--exonic_fraction"
alternatives:
- "-e"
description: "The breakpoints of false-positive predictions of intragenic events\
\ \nare often both in exons. True predictions are more likely to have at \n\
least one breakpoint in an intron, because introns are larger. If the \nfraction\
\ of exonic sequence between two breakpoints is smaller than \nthe given fraction,\
\ the 'intragenic_exonic' filter discards the \nevent. Default: 0.330000 \n"
info: null
example:
- 0.33
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--top_n"
alternatives:
- "-T"
description: "Only report viral integration sites of the top N most highly expressed\
\ viral \ncontigs. Default: 5\n"
info: null
example:
- 5
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "double"
name: "--covered_fraction"
alternatives:
- "-C"
description: "Ignore virally associated events if the virus is not fully \nexpressed,\
\ i.e., less than the given fraction of the viral contig is \ntranscribed. Default:\
\ 0.050000 \n"
info: null
example:
- 0.05
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--max_itd_length"
alternatives:
- "-l"
description: "Maximum length of internal tandem duplications. Note: Increasing\
\ \nthis value beyond the default can impair performance and lead to many \n\
false positives. Default: 100 \n"
info: null
example:
- 100
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "double"
name: "--min_itd_allele_fraction"
alternatives:
- "-z"
description: "Required fraction of supporting reads to report an internal \ntandem\
\ duplication. Default: 0.070000 \n"
info: null
example:
- 0.07
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--min_itd_supporting_reads"
alternatives:
- "-Z"
description: "Required absolute number of supporting reads to report an \ninternal\
\ tandem duplication. Default: 10 \n"
info: null
example:
- 10
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean_true"
name: "--skip_duplicate_marking"
alternatives:
- "-u"
description: "Instead of performing duplicate marking itself, Arriba relies on\
\ duplicate marking by a \npreceding program using the BAM_FDUP flag. This makes\
\ sense when unique molecular \nidentifiers (UMI) are used.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--extra_information"
alternatives:
- "-X"
description: "To reduce the runtime and file size, by default, the columns 'fusion_transcript',\
\ \n'peptide_sequence', and 'read_identifiers' are left empty in the file containing\
\ \ndiscarded fusion candidates (see parameter -O). When this flag is set, this\
\ extra \ninformation is reported in the discarded fusions file.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--fill_gaps"
alternatives:
- "-I"
description: "If assembly of the fusion transcript sequence from the supporting\
\ reads is incomplete \n(denoted as '...'), fill the gaps using the assembly\
\ sequence wherever possible. \n"
info: null
direction: "input"
resources:
- type: "bash_script"
path: "script.sh"
is_executable: true
description: "Detect gene fusions from RNA-Seq data"
test_resources:
- type: "bash_script"
path: "test.sh"
is_executable: true
- type: "file"
path: "test_data"
info: null
status: "enabled"
requirements:
cpus: 1
commands:
- "ps"
keywords:
- "Gene fusion"
- "RNA-Seq"
license: "MIT"
references:
doi:
- "10.1101/gr.257246.119"
links:
repository: "https://github.com/suhrig/arriba"
homepage: "https://arriba.readthedocs.io/en/latest/"
documentation: "https://arriba.readthedocs.io/en/latest/"
runners:
- type: "executable"
id: "executable"
docker_setup_strategy: "ifneedbepullelsecachedbuild"
- type: "nextflow"
id: "nextflow"
directives:
tag: "$id"
auto:
simplifyInput: true
simplifyOutput: false
transcript: false
publish: false
config:
labels:
mem1gb: "memory = 1000000000.B"
mem2gb: "memory = 2000000000.B"
mem5gb: "memory = 5000000000.B"
mem10gb: "memory = 10000000000.B"
mem20gb: "memory = 20000000000.B"
mem50gb: "memory = 50000000000.B"
mem100gb: "memory = 100000000000.B"
mem200gb: "memory = 200000000000.B"
mem500gb: "memory = 500000000000.B"
mem1tb: "memory = 1000000000000.B"
mem2tb: "memory = 2000000000000.B"
mem5tb: "memory = 5000000000000.B"
mem10tb: "memory = 10000000000000.B"
mem20tb: "memory = 20000000000000.B"
mem50tb: "memory = 50000000000000.B"
mem100tb: "memory = 100000000000000.B"
mem200tb: "memory = 200000000000000.B"
mem500tb: "memory = 500000000000000.B"
mem1gib: "memory = 1073741824.B"
mem2gib: "memory = 2147483648.B"
mem4gib: "memory = 4294967296.B"
mem8gib: "memory = 8589934592.B"
mem16gib: "memory = 17179869184.B"
mem32gib: "memory = 34359738368.B"
mem64gib: "memory = 68719476736.B"
mem128gib: "memory = 137438953472.B"
mem256gib: "memory = 274877906944.B"
mem512gib: "memory = 549755813888.B"
mem1tib: "memory = 1099511627776.B"
mem2tib: "memory = 2199023255552.B"
mem4tib: "memory = 4398046511104.B"
mem8tib: "memory = 8796093022208.B"
mem16tib: "memory = 17592186044416.B"
mem32tib: "memory = 35184372088832.B"
mem64tib: "memory = 70368744177664.B"
mem128tib: "memory = 140737488355328.B"
mem256tib: "memory = 281474976710656.B"
mem512tib: "memory = 562949953421312.B"
cpu1: "cpus = 1"
cpu2: "cpus = 2"
cpu5: "cpus = 5"
cpu10: "cpus = 10"
cpu20: "cpus = 20"
cpu50: "cpus = 50"
cpu100: "cpus = 100"
cpu200: "cpus = 200"
cpu500: "cpus = 500"
cpu1000: "cpus = 1000"
debug: false
container: "docker"
engines:
- type: "docker"
id: "docker"
image: "quay.io/biocontainers/arriba:2.4.0--h0033a41_2"
target_registry: "images.viash-hub.com"
target_tag: "v0.2"
namespace_separator: "/"
setup:
- type: "docker"
run:
- "arriba -h | grep 'Version:' 2>&1 | sed 's/Version:\\s\\(.*\\)/arriba: \"\\\
1\"/' > /var/software_versions.txt\n"
entrypoint: []
cmd: null
- type: "native"
id: "native"
build_info:
config: "src/arriba/config.vsh.yaml"
runner: "executable"
engine: "docker|native"
output: "target/executable/arriba"
executable: "target/executable/arriba/arriba"
viash_version: "0.9.0-RC7"
git_commit: "f22ab0eab58dcd6bff89d8d73fe951953ff1260f"
git_remote: "https://github.com/viash-hub/biobox"
package_config:
name: "biobox"
version: "v0.2"
description: "A collection of bioinformatics tools for working with sequence data.\n"
info: null
viash_version: "0.9.0-RC7"
source: "src"
target: "target"
config_mods:
- ".requirements.commands := ['ps']\n"
- ".engines += { type: \"native\" }"
- ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
- ".engines[.type == 'docker'].target_tag := 'v0.2'"
keywords:
- "bioinformatics"
- "modules"
- "sequencing"
license: "MIT"
organization: "vsh"
links:
repository: "https://github.com/viash-hub/biobox"
issue_tracker: "https://github.com/viash-hub/biobox/issues"

2340
target/executable/arriba/arriba Executable file
View File

File diff suppressed because it is too large Load Diff

211
target/executable/bcftools/bcftools_sort/.config.vsh.yaml Normal file
View File

@@ -0,0 +1,211 @@
name: "bcftools_sort"
namespace: "bcftools"
version: "v0.2"
authors:
- name: "Theodoro Gasperin Terra Camargo"
roles:
- "author"
- "maintainer"
info:
links:
email: "theodorogtc@gmail.com"
github: "tgaspe"
linkedin: "theodoro-gasperin-terra-camargo"
organizations:
- name: "Data Intuitive"
href: "https://www.data-intuitive.com"
role: "Bioinformatician"
argument_groups:
- name: "Inputs"
arguments:
- type: "file"
name: "--input"
alternatives:
- "-i"
description: "Input VCF/BCF file."
info: null
must_exist: true
create_parent: true
required: true
direction: "input"
multiple: false
multiple_sep: ";"
- name: "Outputs"
arguments:
- type: "file"
name: "--output"
alternatives:
- "-o"
description: "Output sorted VCF/BCF file."
info: null
must_exist: true
create_parent: true
required: true
direction: "output"
multiple: false
multiple_sep: ";"
- name: "Options"
arguments:
- type: "string"
name: "--output_type"
alternatives:
- "-O"
description: "Compresses or uncompresses the output.\nThe options are:\n b: compressed\
\ BCF, \n u: uncompressed BCF, \n z: compressed VCF, \n v: uncompressed VCF.\
\ \n"
info: null
required: false
choices:
- "b"
- "u"
- "z"
- "v"
direction: "input"
multiple: false
multiple_sep: ";"
resources:
- type: "bash_script"
path: "script.sh"
is_executable: true
description: "Sorts VCF/BCF files.\n"
test_resources:
- type: "bash_script"
path: "test.sh"
is_executable: true
- type: "file"
path: "test_data"
info: null
status: "enabled"
requirements:
commands:
- "ps"
keywords:
- "Sort"
- "VCF"
- "BCF"
license: "MIT/Expat, GNU"
references:
doi:
- "https://doi.org/10.1093/gigascience/giab008"
links:
repository: "https://github.com/samtools/bcftools"
homepage: "https://samtools.github.io/bcftools/"
documentation: "https://samtools.github.io/bcftools/bcftools.html#sort"
issue_tracker: "https://github.com/samtools/bcftools/issues"
runners:
- type: "executable"
id: "executable"
docker_setup_strategy: "ifneedbepullelsecachedbuild"
- type: "nextflow"
id: "nextflow"
directives:
tag: "$id"
auto:
simplifyInput: true
simplifyOutput: false
transcript: false
publish: false
config:
labels:
mem1gb: "memory = 1000000000.B"
mem2gb: "memory = 2000000000.B"
mem5gb: "memory = 5000000000.B"
mem10gb: "memory = 10000000000.B"
mem20gb: "memory = 20000000000.B"
mem50gb: "memory = 50000000000.B"
mem100gb: "memory = 100000000000.B"
mem200gb: "memory = 200000000000.B"
mem500gb: "memory = 500000000000.B"
mem1tb: "memory = 1000000000000.B"
mem2tb: "memory = 2000000000000.B"
mem5tb: "memory = 5000000000000.B"
mem10tb: "memory = 10000000000000.B"
mem20tb: "memory = 20000000000000.B"
mem50tb: "memory = 50000000000000.B"
mem100tb: "memory = 100000000000000.B"
mem200tb: "memory = 200000000000000.B"
mem500tb: "memory = 500000000000000.B"
mem1gib: "memory = 1073741824.B"
mem2gib: "memory = 2147483648.B"
mem4gib: "memory = 4294967296.B"
mem8gib: "memory = 8589934592.B"
mem16gib: "memory = 17179869184.B"
mem32gib: "memory = 34359738368.B"
mem64gib: "memory = 68719476736.B"
mem128gib: "memory = 137438953472.B"
mem256gib: "memory = 274877906944.B"
mem512gib: "memory = 549755813888.B"
mem1tib: "memory = 1099511627776.B"
mem2tib: "memory = 2199023255552.B"
mem4tib: "memory = 4398046511104.B"
mem8tib: "memory = 8796093022208.B"
mem16tib: "memory = 17592186044416.B"
mem32tib: "memory = 35184372088832.B"
mem64tib: "memory = 70368744177664.B"
mem128tib: "memory = 140737488355328.B"
mem256tib: "memory = 281474976710656.B"
mem512tib: "memory = 562949953421312.B"
cpu1: "cpus = 1"
cpu2: "cpus = 2"
cpu5: "cpus = 5"
cpu10: "cpus = 10"
cpu20: "cpus = 20"
cpu50: "cpus = 50"
cpu100: "cpus = 100"
cpu200: "cpus = 200"
cpu500: "cpus = 500"
cpu1000: "cpus = 1000"
debug: false
container: "docker"
engines:
- type: "docker"
id: "docker"
image: "debian:stable-slim"
target_registry: "images.viash-hub.com"
target_tag: "v0.2"
namespace_separator: "/"
setup:
- type: "apt"
packages:
- "bcftools"
- "procps"
interactive: false
- type: "docker"
run:
- "echo \"bcftools: \\\"$(bcftools --version | grep 'bcftools' | sed -n 's/^bcftools\
\ //p')\\\"\" > /var/software_versions.txt\n"
entrypoint: []
cmd: null
- type: "native"
id: "native"
build_info:
config: "src/bcftools/bcftools_sort/config.vsh.yaml"
runner: "executable"
engine: "docker|native"
output: "target/executable/bcftools/bcftools_sort"
executable: "target/executable/bcftools/bcftools_sort/bcftools_sort"
viash_version: "0.9.0-RC7"
git_commit: "f22ab0eab58dcd6bff89d8d73fe951953ff1260f"
git_remote: "https://github.com/viash-hub/biobox"
package_config:
name: "biobox"
version: "v0.2"
description: "A collection of bioinformatics tools for working with sequence data.\n"
info: null
viash_version: "0.9.0-RC7"
source: "src"
target: "target"
config_mods:
- ".requirements.commands := ['ps']\n"
- ".engines += { type: \"native\" }"
- ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
- ".engines[.type == 'docker'].target_tag := 'v0.2'"
keywords:
- "bioinformatics"
- "modules"
- "sequencing"
license: "MIT"
organization: "vsh"
links:
repository: "https://github.com/viash-hub/biobox"
issue_tracker: "https://github.com/viash-hub/biobox/issues"

1146
target/executable/bcftools/bcftools_sort/bcftools_sort Executable file
View File

File diff suppressed because it is too large Load Diff

444
target/executable/bcl_convert/.config.vsh.yaml Normal file
View File

@@ -0,0 +1,444 @@
name: "bcl_convert"
version: "v0.2"
authors:
- name: "Toni Verbeiren"
roles:
- "author"
- "maintainer"
info:
links:
github: "tverbeiren"
linkedin: "verbeiren"
organizations:
- name: "Data Intuitive"
href: "https://www.data-intuitive.com"
role: "Data Scientist and CEO"
- name: "Dorien Roosen"
roles:
- "author"
info:
links:
email: "dorien@data-intuitive.com"
github: "dorien-er"
linkedin: "dorien-roosen"
organizations:
- name: "Data Intuitive"
href: "https://www.data-intuitive.com"
role: "Data Scientist"
argument_groups:
- name: "Input arguments"
arguments:
- type: "file"
name: "--bcl_input_directory"
alternatives:
- "-i"
description: "Input run directory"
info: null
example:
- "bcl_dir"
must_exist: true
create_parent: true
required: true
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--sample_sheet"
alternatives:
- "-s"
description: "Path to SampleSheet.csv file (default searched for in --bcl_input_directory)"
info: null
example:
- "bcl_dir/sample_sheet.csv"
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--run_info"
description: "Path to RunInfo.xml file (default root of BCL input directory)"
info: null
example:
- "bcl_dir/RunInfo.xml"
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- name: "Lane and tile settings"
arguments:
- type: "integer"
name: "--bcl_only_lane"
description: "Convert only specified lane number (default all lanes)"
info: null
example:
- 1
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean"
name: "--first_tile_only"
description: "Only convert first tile of input (for testing & debugging)"
info: null
example:
- true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--tiles"
description: "Process only a subset of tiles by a regular expression"
info: null
example:
- "s_[0-9]+_1"
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--exclude_tiles"
description: "Exclude set of tiles by a regular expression"
info: null
example:
- "s_[0-9]+_1"
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- name: "Resource arguments"
arguments:
- type: "boolean"
name: "--shared_thread_odirect_output"
description: "Use linux native asynchronous io (io_submit) for file output (Default=false)"
info: null
example:
- true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--bcl_num_parallel_tiles"
description: "\\# of tiles to process in parallel (default 1)"
info: null
example:
- 1
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--bcl_num_conversion_threads"
description: "\\# of threads for conversion (per tile, default # cpu threads)"
info: null
example:
- 1
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--bcl_num_compression_threads"
description: "\\# of threads for fastq.gz output compression (per tile, default\
\ # cpu threads, or HW+12)"
info: null
example:
- 1
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--bcl_num_decompression_threads"
description: "\\# of threads for bcl/cbcl input decompression (per tile, default\
\ half # cpu threads, or HW+8). Only applies when preloading files"
info: null
example:
- 1
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- name: "Run arguments"
arguments:
- type: "boolean"
name: "--bcl_only_matched_reads"
description: "For pure BCL conversion, do not output files for 'Undetermined'\
\ [unmatched] reads (output by default)"
info: null
example:
- true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean"
name: "--no_lane_splitting"
description: "Do not split FASTQ file by lane (false by default)"
info: null
example:
- true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--num_unknown_barcodes_reported"
description: "\\# of Top Unknown Barcodes to output (1000 by default)"
info: null
example:
- 1000
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean"
name: "--bcl_validate_sample_sheet_only"
description: "Only validate RunInfo.xml & SampleSheet files (produce no FASTQ\
\ files)"
info: null
example:
- true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean"
name: "--strict_mode"
description: "Abort if any files are missing (false by default)"
info: null
example:
- true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean"
name: "--sample_name_column_enabled"
description: "Use sample sheet 'Sample_Name' column when naming fastq files &\
\ subdirectories"
info: null
example:
- true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- name: "Output arguments"
arguments:
- type: "file"
name: "--output_directory"
alternatives:
- "-o"
description: "Output directory containig fastq files"
info: null
example:
- "fastq_dir"
must_exist: true
create_parent: true
required: true
direction: "output"
multiple: false
multiple_sep: ";"
- type: "boolean"
name: "--bcl_sampleproject_subdirectories"
description: "Output to subdirectories based upon sample sheet 'Sample_Project'\
\ column"
info: null
example:
- true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--fastq_gzip_compression_level"
description: "Set fastq output compression level 0-9 (default 1)"
info: null
example:
- 1
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--reports"
description: "Reports directory"
info: null
example:
- "reports_dir"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--logs"
description: "Reports directory"
info: null
example:
- "logs_dir"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
resources:
- type: "bash_script"
path: "script.sh"
is_executable: true
description: "Convert bcl files to fastq files using bcl-convert.\nInformation about\
\ upgrading from bcl2fastq via\n[Upgrading from bcl2fastq to BCL Convert](https://emea.support.illumina.com/bulletins/2020/10/upgrading-from-bcl2fastq-to-bcl-convert.html)\n\
and [BCL Convert Compatible Products](https://support.illumina.com/sequencing/sequencing_software/bcl-convert/compatibility.html)\n"
test_resources:
- type: "bash_script"
path: "test.sh"
is_executable: true
info: null
status: "enabled"
requirements:
commands:
- "ps"
keywords:
- "demultiplex"
- "fastq"
- "bcl"
- "illumina"
license: "Proprietary"
links:
repository: "https://github.com/viash-hub/biobox"
homepage: "https://support.illumina.com/sequencing/sequencing_software/bcl-convert.html"
documentation: "https://support.illumina.com/downloads/bcl-convert-user-guide.html"
runners:
- type: "executable"
id: "executable"
docker_setup_strategy: "ifneedbepullelsecachedbuild"
- type: "nextflow"
id: "nextflow"
directives:
tag: "$id"
auto:
simplifyInput: true
simplifyOutput: false
transcript: false
publish: false
config:
labels:
mem1gb: "memory = 1000000000.B"
mem2gb: "memory = 2000000000.B"
mem5gb: "memory = 5000000000.B"
mem10gb: "memory = 10000000000.B"
mem20gb: "memory = 20000000000.B"
mem50gb: "memory = 50000000000.B"
mem100gb: "memory = 100000000000.B"
mem200gb: "memory = 200000000000.B"
mem500gb: "memory = 500000000000.B"
mem1tb: "memory = 1000000000000.B"
mem2tb: "memory = 2000000000000.B"
mem5tb: "memory = 5000000000000.B"
mem10tb: "memory = 10000000000000.B"
mem20tb: "memory = 20000000000000.B"
mem50tb: "memory = 50000000000000.B"
mem100tb: "memory = 100000000000000.B"
mem200tb: "memory = 200000000000000.B"
mem500tb: "memory = 500000000000000.B"
mem1gib: "memory = 1073741824.B"
mem2gib: "memory = 2147483648.B"
mem4gib: "memory = 4294967296.B"
mem8gib: "memory = 8589934592.B"
mem16gib: "memory = 17179869184.B"
mem32gib: "memory = 34359738368.B"
mem64gib: "memory = 68719476736.B"
mem128gib: "memory = 137438953472.B"
mem256gib: "memory = 274877906944.B"
mem512gib: "memory = 549755813888.B"
mem1tib: "memory = 1099511627776.B"
mem2tib: "memory = 2199023255552.B"
mem4tib: "memory = 4398046511104.B"
mem8tib: "memory = 8796093022208.B"
mem16tib: "memory = 17592186044416.B"
mem32tib: "memory = 35184372088832.B"
mem64tib: "memory = 70368744177664.B"
mem128tib: "memory = 140737488355328.B"
mem256tib: "memory = 281474976710656.B"
mem512tib: "memory = 562949953421312.B"
cpu1: "cpus = 1"
cpu2: "cpus = 2"
cpu5: "cpus = 5"
cpu10: "cpus = 10"
cpu20: "cpus = 20"
cpu50: "cpus = 50"
cpu100: "cpus = 100"
cpu200: "cpus = 200"
cpu500: "cpus = 500"
cpu1000: "cpus = 1000"
debug: false
container: "docker"
engines:
- type: "docker"
id: "docker"
image: "debian:trixie-slim"
target_registry: "images.viash-hub.com"
target_tag: "v0.2"
namespace_separator: "/"
setup:
- type: "apt"
packages:
- "wget"
- "gdb"
- "which"
- "hostname"
- "alien"
- "procps"
interactive: false
- type: "docker"
run:
- "wget https://s3.amazonaws.com/webdata.illumina.com/downloads/software/bcl-convert/bcl-convert-4.2.7-2.el8.x86_64.rpm\
\ -O /tmp/bcl-convert.rpm && \\\nalien -i /tmp/bcl-convert.rpm && \\\nrm -rf\
\ /var/lib/apt/lists/* && \\\nrm /tmp/bcl-convert.rpm\n"
- type: "docker"
run:
- "echo \"bcl-convert: \\\"$(bcl-convert -V 2>&1 >/dev/null | sed -n '/Version/\
\ s/^bcl-convert\\ Version //p')\\\"\" > /var/software_versions.txt\n"
entrypoint: []
cmd: null
- type: "native"
id: "native"
build_info:
config: "src/bcl_convert/config.vsh.yaml"
runner: "executable"
engine: "docker|native"
output: "target/executable/bcl_convert"
executable: "target/executable/bcl_convert/bcl_convert"
viash_version: "0.9.0-RC7"
git_commit: "f22ab0eab58dcd6bff89d8d73fe951953ff1260f"
git_remote: "https://github.com/viash-hub/biobox"
package_config:
name: "biobox"
version: "v0.2"
description: "A collection of bioinformatics tools for working with sequence data.\n"
info: null
viash_version: "0.9.0-RC7"
source: "src"
target: "target"
config_mods:
- ".requirements.commands := ['ps']\n"
- ".engines += { type: \"native\" }"
- ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
- ".engines[.type == 'docker'].target_tag := 'v0.2'"
keywords:
- "bioinformatics"
- "modules"
- "sequencing"
license: "MIT"
organization: "vsh"
links:
repository: "https://github.com/viash-hub/biobox"
issue_tracker: "https://github.com/viash-hub/biobox/issues"

1658
target/executable/bcl_convert/bcl_convert Executable file
View File

File diff suppressed because it is too large Load Diff

296
target/executable/bd_rhapsody/bd_rhapsody_make_reference/.config.vsh.yaml Normal file
View File

@@ -0,0 +1,296 @@
name: "bd_rhapsody_make_reference"
namespace: "bd_rhapsody"
version: "v0.2"
authors:
- name: "Robrecht Cannoodt"
roles:
- "author"
- "maintainer"
info:
links:
email: "robrecht@data-intuitive.com"
github: "rcannood"
orcid: "0000-0003-3641-729X"
linkedin: "robrechtcannoodt"
organizations:
- name: "Data Intuitive"
href: "https://www.data-intuitive.com"
role: "Data Science Engineer"
- name: "Open Problems"
href: "https://openproblems.bio"
role: "Core Member"
- name: "Weiwei Schultz"
roles:
- "contributor"
info:
organizations:
- name: "Janssen R&D US"
role: "Associate Director Data Sciences"
argument_groups:
- name: "Inputs"
arguments:
- type: "file"
name: "--genome_fasta"
description: "Reference genome file in FASTA or FASTA.GZ format. The BD Rhapsody\
\ Sequencing Analysis Pipeline uses GRCh38 for Human and GRCm39 for Mouse."
info:
config_key: "Genome_fasta"
example:
- "genome_sequence.fa.gz"
must_exist: true
create_parent: true
required: true
direction: "input"
multiple: true
multiple_sep: ";"
- type: "file"
name: "--gtf"
description: "File path to the transcript annotation files in GTF or GTF.GZ format.\
\ The Sequence Analysis Pipeline requires the 'gene_name' or \n'gene_id' attribute\
\ to be set on each gene and exon feature. Gene and exon feature lines must\
\ have the same attribute, and exons\nmust have a corresponding gene with the\
\ same value. For TCR/BCR assays, the TCR or BCR gene segments must have the\
\ 'gene_type' or\n'gene_biotype' attribute set, and the value should begin with\
\ 'TR' or 'IG', respectively.\n"
info:
config_key: "Gtf"
example:
- "transcriptome_annotation.gtf.gz"
must_exist: true
create_parent: true
required: true
direction: "input"
multiple: true
multiple_sep: ";"
- type: "file"
name: "--extra_sequences"
description: "File path to additional sequences in FASTA format to use when building\
\ the STAR index. (e.g. transgenes or CRISPR guide barcodes).\nGTF lines for\
\ these sequences will be automatically generated and combined with the main\
\ GTF.\n"
info:
config_key: "Extra_sequences"
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: true
multiple_sep: ";"
- name: "Outputs"
arguments:
- type: "file"
name: "--reference_archive"
description: "A Compressed archive containing the Reference Genome Index and annotation\
\ GTF files. This archive is meant to be used as an\ninput in the BD Rhapsody\
\ Sequencing Analysis Pipeline.\n"
info: null
example:
- "star_index.tar.gz"
must_exist: true
create_parent: true
required: true
direction: "output"
multiple: false
multiple_sep: ";"
- name: "Arguments"
arguments:
- type: "string"
name: "--mitochondrial_contigs"
description: "Names of the Mitochondrial contigs in the provided Reference Genome.\
\ Fragments originating from contigs other than these are\nidentified as 'nuclear\
\ fragments' in the ATACseq analysis pipeline.\n"
info:
config_key: "Mitochondrial_contigs"
default:
- "chrM"
- "chrMT"
- "M"
- "MT"
required: false
direction: "input"
multiple: true
multiple_sep: ";"
- type: "boolean_true"
name: "--filtering_off"
description: "By default the input Transcript Annotation files are filtered based\
\ on the gene_type/gene_biotype attribute. Only features \nhaving the following\
\ attribute values are kept:\n\n - protein_coding\n - lncRNA (lincRNA and\
\ antisense for Gencode < v31/M22/Ensembl97)\n - IG_LV_gene\n - IG_V_gene\n\
\ - IG_V_pseudogene\n - IG_D_gene\n - IG_J_gene\n - IG_J_pseudogene\n -\
\ IG_C_gene\n - IG_C_pseudogene\n - TR_V_gene\n - TR_V_pseudogene\n - TR_D_gene\n\
\ - TR_J_gene\n - TR_J_pseudogene\n - TR_C_gene\n\n If you have already\
\ pre-filtered the input Annotation files and/or wish to turn-off the filtering,\
\ please set this option to True.\n"
info:
config_key: "Filtering_off"
direction: "input"
- type: "boolean_true"
name: "--wta_only_index"
description: "Build a WTA only index, otherwise builds a WTA + ATAC index."
info:
config_key: "Wta_Only"
direction: "input"
- type: "string"
name: "--extra_star_params"
description: "Additional parameters to pass to STAR when building the genome index.\
\ Specify exactly like how you would on the command line."
info:
config_key: "Extra_STAR_params"
example:
- "--limitGenomeGenerateRAM 48000 --genomeSAindexNbases 11"
required: false
direction: "input"
multiple: false
multiple_sep: ";"
resources:
- type: "python_script"
path: "script.py"
is_executable: true
- type: "file"
path: "make_rhap_reference_2.2.1_nodocker.cwl"
description: "The Reference Files Generator creates an archive containing Genome Index\n\
and Transcriptome annotation files needed for the BD Rhapsody Sequencing\nAnalysis\
\ Pipeline. The app takes as input one or more FASTA and GTF files\nand produces\
\ a compressed archive in the form of a tar.gz file. The \narchive contains:\n\n\
- STAR index\n- Filtered GTF file\n"
test_resources:
- type: "bash_script"
path: "test.sh"
is_executable: true
- type: "file"
path: "test_data"
info: null
status: "enabled"
requirements:
commands:
- "ps"
keywords:
- "genome"
- "reference"
- "index"
- "align"
license: "Unknown"
links:
repository: "https://bitbucket.org/CRSwDev/cwl/src/master/v2.2.1/Extra_Utilities/"
documentation: "https://bd-rhapsody-bioinfo-docs.genomics.bd.com/resources/extra_utilities.html#make-rhapsody-reference"
runners:
- type: "executable"
id: "executable"
docker_setup_strategy: "ifneedbepullelsecachedbuild"
- type: "nextflow"
id: "nextflow"
directives:
tag: "$id"
auto:
simplifyInput: true
simplifyOutput: false
transcript: false
publish: false
config:
labels:
mem1gb: "memory = 1000000000.B"
mem2gb: "memory = 2000000000.B"
mem5gb: "memory = 5000000000.B"
mem10gb: "memory = 10000000000.B"
mem20gb: "memory = 20000000000.B"
mem50gb: "memory = 50000000000.B"
mem100gb: "memory = 100000000000.B"
mem200gb: "memory = 200000000000.B"
mem500gb: "memory = 500000000000.B"
mem1tb: "memory = 1000000000000.B"
mem2tb: "memory = 2000000000000.B"
mem5tb: "memory = 5000000000000.B"
mem10tb: "memory = 10000000000000.B"
mem20tb: "memory = 20000000000000.B"
mem50tb: "memory = 50000000000000.B"
mem100tb: "memory = 100000000000000.B"
mem200tb: "memory = 200000000000000.B"
mem500tb: "memory = 500000000000000.B"
mem1gib: "memory = 1073741824.B"
mem2gib: "memory = 2147483648.B"
mem4gib: "memory = 4294967296.B"
mem8gib: "memory = 8589934592.B"
mem16gib: "memory = 17179869184.B"
mem32gib: "memory = 34359738368.B"
mem64gib: "memory = 68719476736.B"
mem128gib: "memory = 137438953472.B"
mem256gib: "memory = 274877906944.B"
mem512gib: "memory = 549755813888.B"
mem1tib: "memory = 1099511627776.B"
mem2tib: "memory = 2199023255552.B"
mem4tib: "memory = 4398046511104.B"
mem8tib: "memory = 8796093022208.B"
mem16tib: "memory = 17592186044416.B"
mem32tib: "memory = 35184372088832.B"
mem64tib: "memory = 70368744177664.B"
mem128tib: "memory = 140737488355328.B"
mem256tib: "memory = 281474976710656.B"
mem512tib: "memory = 562949953421312.B"
cpu1: "cpus = 1"
cpu2: "cpus = 2"
cpu5: "cpus = 5"
cpu10: "cpus = 10"
cpu20: "cpus = 20"
cpu50: "cpus = 50"
cpu100: "cpus = 100"
cpu200: "cpus = 200"
cpu500: "cpus = 500"
cpu1000: "cpus = 1000"
debug: false
container: "docker"
engines:
- type: "docker"
id: "docker"
image: "bdgenomics/rhapsody:2.2.1"
target_registry: "images.viash-hub.com"
target_tag: "v0.2"
namespace_separator: "/"
setup:
- type: "apt"
packages:
- "procps"
interactive: false
- type: "python"
user: false
packages:
- "cwlref-runner"
- "cwl-runner"
upgrade: true
- type: "docker"
run:
- "echo \"bdgenomics/rhapsody: 2.2.1\" > /var/software_versions.txt\n"
entrypoint: []
cmd: null
- type: "native"
id: "native"
build_info:
config: "src/bd_rhapsody/bd_rhapsody_make_reference/config.vsh.yaml"
runner: "executable"
engine: "docker|native"
output: "target/executable/bd_rhapsody/bd_rhapsody_make_reference"
executable: "target/executable/bd_rhapsody/bd_rhapsody_make_reference/bd_rhapsody_make_reference"
viash_version: "0.9.0-RC7"
git_commit: "f22ab0eab58dcd6bff89d8d73fe951953ff1260f"
git_remote: "https://github.com/viash-hub/biobox"
package_config:
name: "biobox"
version: "v0.2"
description: "A collection of bioinformatics tools for working with sequence data.\n"
info: null
viash_version: "0.9.0-RC7"
source: "src"
target: "target"
config_mods:
- ".requirements.commands := ['ps']\n"
- ".engines += { type: \"native\" }"
- ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
- ".engines[.type == 'docker'].target_tag := 'v0.2'"
keywords:
- "bioinformatics"
- "modules"
- "sequencing"
license: "MIT"
organization: "vsh"
links:
repository: "https://github.com/viash-hub/biobox"
issue_tracker: "https://github.com/viash-hub/biobox/issues"

1513
target/executable/bd_rhapsody/bd_rhapsody_make_reference/bd_rhapsody_make_reference Executable file
View File

File diff suppressed because it is too large Load Diff

115
target/executable/bd_rhapsody/bd_rhapsody_make_reference/make_rhap_reference_2.2.1_nodocker.cwl Normal file
View File

@@ -0,0 +1,115 @@
requirements:
InlineJavascriptRequirement: {}
class: CommandLineTool
label: Reference Files Generator for BD Rhapsodyâ„¢ Sequencing Analysis Pipeline
cwlVersion: v1.2
doc: >-
The Reference Files Generator creates an archive containing Genome Index and Transcriptome annotation files needed for the BD Rhapsodyâ„¢ Sequencing Analysis Pipeline. The app takes as input one or more FASTA and GTF files and produces a compressed archive in the form of a tar.gz file. The archive contains:\n - STAR index\n - Filtered GTF file
baseCommand: run_reference_generator.sh
inputs:
Genome_fasta:
type: File[]
label: Reference Genome
doc: |-
Reference genome file in FASTA format. The BD Rhapsodyâ„¢ Sequencing Analysis Pipeline uses GRCh38 for Human and GRCm39 for Mouse.
inputBinding:
prefix: --reference-genome
shellQuote: false
Gtf:
type: File[]
label: Transcript Annotations
doc: |-
Transcript annotation files in GTF format. The BD Rhapsodyâ„¢ Sequencing Analysis Pipeline uses Gencode v42 for Human and M31 for Mouse.
inputBinding:
prefix: --gtf
shellQuote: false
Extra_sequences:
type: File[]?
label: Extra Sequences
doc: |-
Additional sequences in FASTA format to use when building the STAR index. (E.g. phiX genome)
inputBinding:
prefix: --extra-sequences
shellQuote: false
Mitochondrial_Contigs:
type: string[]?
default: ["chrM", "chrMT", "M", "MT"]
label: Mitochondrial Contig Names
doc: |-
Names of the Mitochondrial contigs in the provided Reference Genome. Fragments originating from contigs other than these are identified as 'nuclear fragments' in the ATACseq analysis pipeline.
inputBinding:
prefix: --mitochondrial-contigs
shellQuote: false
Filtering_off:
type: boolean?
label: Turn off filtering
doc: |-
By default the input Transcript Annotation files are filtered based on the gene_type/gene_biotype attribute. Only features having the following attribute values are are kept:
- protein_coding
- lncRNA (lincRNA and antisense for Gencode < v31/M22/Ensembl97)
- IG_LV_gene
- IG_V_gene
- IG_V_pseudogene
- IG_D_gene
- IG_J_gene
- IG_J_pseudogene
- IG_C_gene
- IG_C_pseudogene
- TR_V_gene
- TR_V_pseudogene
- TR_D_gene
- TR_J_gene
- TR_J_pseudogene
- TR_C_gene
If you have already pre-filtered the input Annotation files and/or wish to turn-off the filtering, please set this option to True.
inputBinding:
prefix: --filtering-off
shellQuote: false
WTA_Only:
type: boolean?
label: WTA only index
doc: Build a WTA only index, otherwise builds a WTA + ATAC index.
inputBinding:
prefix: --wta-only-index
shellQuote: false
Archive_prefix:
type: string?
label: Archive Prefix
doc: |-
A prefix for naming the compressed archive file containing the Reference genome index and annotation files. The default value is constructed based on the input Reference files.
inputBinding:
prefix: --archive-prefix
shellQuote: false
Extra_STAR_params:
type: string?
label: Extra STAR Params
doc: |-
Additional parameters to pass to STAR when building the genome index. Specify exactly like how you would on the command line.
Example:
--limitGenomeGenerateRAM 48000 --genomeSAindexNbases 11
inputBinding:
prefix: --extra-star-params
shellQuote: true
Maximum_threads:
type: int?
label: Maximum Number of Threads
doc: |-
The maximum number of threads to use in the pipeline. By default, all available cores are used.
inputBinding:
prefix: --maximum-threads
shellQuote: false
outputs:
Archive:
type: File
doc: |-
A Compressed archive containing the Reference Genome Index and annotation GTF files. This archive is meant to be used as an input in the BD Rhapsodyâ„¢ Sequencing Analysis Pipeline.
id: Reference_Archive
label: Reference Files Archive
outputBinding:
glob: '*.tar.gz'

213
target/executable/bedtools/bedtools_bamtofastq/.config.vsh.yaml Normal file
View File

@@ -0,0 +1,213 @@
name: "bedtools_bamtofastq"
namespace: "bedtools"
version: "v0.2"
authors:
- name: "Theodoro Gasperin Terra Camargo"
roles:
- "author"
- "maintainer"
info:
links:
email: "theodorogtc@gmail.com"
github: "tgaspe"
linkedin: "theodoro-gasperin-terra-camargo"
organizations:
- name: "Data Intuitive"
href: "https://www.data-intuitive.com"
role: "Bioinformatician"
argument_groups:
- name: "Inputs"
arguments:
- type: "file"
name: "--input"
alternatives:
- "-i"
description: "Input BAM file to be converted to FASTQ."
info: null
must_exist: true
create_parent: true
required: true
direction: "input"
multiple: false
multiple_sep: ";"
- name: "Outputs"
arguments:
- type: "file"
name: "--fastq"
alternatives:
- "-fq"
description: "Output FASTQ file."
info: null
must_exist: true
create_parent: true
required: true
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--fastq2"
alternatives:
- "-fq2"
description: "FASTQ for second end. Used if BAM contains paired-end data.\nBAM\
\ should be sorted by query name is creating paired FASTQ.\n"
info: null
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- name: "Options"
arguments:
- type: "boolean_true"
name: "--tags"
description: "Create FASTQ based on the mate info in the BAM R2 and Q2 tags.\n"
info: null
direction: "input"
resources:
- type: "bash_script"
path: "script.sh"
is_executable: true
description: "Conversion tool for extracting FASTQ records from sequence alignments\
\ in BAM format.\n"
test_resources:
- type: "bash_script"
path: "test.sh"
is_executable: true
- type: "file"
path: "test_data"
info: null
status: "enabled"
requirements:
commands:
- "ps"
keywords:
- "Conversion"
- "BAM"
- "FASTQ"
license: "MIT"
references:
doi:
- "10.1093/bioinformatics/btq033"
links:
repository: "https://github.com/arq5x/bedtools2"
homepage: "https://bedtools.readthedocs.io/en/latest/#"
documentation: "https://bedtools.readthedocs.io/en/latest/content/tools/bamtofastq.html"
issue_tracker: "https://github.com/arq5x/bedtools2/issues"
runners:
- type: "executable"
id: "executable"
docker_setup_strategy: "ifneedbepullelsecachedbuild"
- type: "nextflow"
id: "nextflow"
directives:
tag: "$id"
auto:
simplifyInput: true
simplifyOutput: false
transcript: false
publish: false
config:
labels:
mem1gb: "memory = 1000000000.B"
mem2gb: "memory = 2000000000.B"
mem5gb: "memory = 5000000000.B"
mem10gb: "memory = 10000000000.B"
mem20gb: "memory = 20000000000.B"
mem50gb: "memory = 50000000000.B"
mem100gb: "memory = 100000000000.B"
mem200gb: "memory = 200000000000.B"
mem500gb: "memory = 500000000000.B"
mem1tb: "memory = 1000000000000.B"
mem2tb: "memory = 2000000000000.B"
mem5tb: "memory = 5000000000000.B"
mem10tb: "memory = 10000000000000.B"
mem20tb: "memory = 20000000000000.B"
mem50tb: "memory = 50000000000000.B"
mem100tb: "memory = 100000000000000.B"
mem200tb: "memory = 200000000000000.B"
mem500tb: "memory = 500000000000000.B"
mem1gib: "memory = 1073741824.B"
mem2gib: "memory = 2147483648.B"
mem4gib: "memory = 4294967296.B"
mem8gib: "memory = 8589934592.B"
mem16gib: "memory = 17179869184.B"
mem32gib: "memory = 34359738368.B"
mem64gib: "memory = 68719476736.B"
mem128gib: "memory = 137438953472.B"
mem256gib: "memory = 274877906944.B"
mem512gib: "memory = 549755813888.B"
mem1tib: "memory = 1099511627776.B"
mem2tib: "memory = 2199023255552.B"
mem4tib: "memory = 4398046511104.B"
mem8tib: "memory = 8796093022208.B"
mem16tib: "memory = 17592186044416.B"
mem32tib: "memory = 35184372088832.B"
mem64tib: "memory = 70368744177664.B"
mem128tib: "memory = 140737488355328.B"
mem256tib: "memory = 281474976710656.B"
mem512tib: "memory = 562949953421312.B"
cpu1: "cpus = 1"
cpu2: "cpus = 2"
cpu5: "cpus = 5"
cpu10: "cpus = 10"
cpu20: "cpus = 20"
cpu50: "cpus = 50"
cpu100: "cpus = 100"
cpu200: "cpus = 200"
cpu500: "cpus = 500"
cpu1000: "cpus = 1000"
debug: false
container: "docker"
engines:
- type: "docker"
id: "docker"
image: "debian:stable-slim"
target_registry: "images.viash-hub.com"
target_tag: "v0.2"
namespace_separator: "/"
setup:
- type: "apt"
packages:
- "bedtools"
- "procps"
interactive: false
- type: "docker"
run:
- "echo \"bedtools: \\\"$(bedtools --version | sed -n 's/^bedtools //p')\\\"\"\
\ > /var/software_versions.txt\n"
entrypoint: []
cmd: null
- type: "native"
id: "native"
build_info:
config: "src/bedtools/bedtools_bamtofastq/config.vsh.yaml"
runner: "executable"
engine: "docker|native"
output: "target/executable/bedtools/bedtools_bamtofastq"
executable: "target/executable/bedtools/bedtools_bamtofastq/bedtools_bamtofastq"
viash_version: "0.9.0-RC7"
git_commit: "f22ab0eab58dcd6bff89d8d73fe951953ff1260f"
git_remote: "https://github.com/viash-hub/biobox"
package_config:
name: "biobox"
version: "v0.2"
description: "A collection of bioinformatics tools for working with sequence data.\n"
info: null
viash_version: "0.9.0-RC7"
source: "src"
target: "target"
config_mods:
- ".requirements.commands := ['ps']\n"
- ".engines += { type: \"native\" }"
- ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
- ".engines[.type == 'docker'].target_tag := 'v0.2'"
keywords:
- "bioinformatics"
- "modules"
- "sequencing"
license: "MIT"
organization: "vsh"
links:
repository: "https://github.com/viash-hub/biobox"
issue_tracker: "https://github.com/viash-hub/biobox/issues"

1168
target/executable/bedtools/bedtools_bamtofastq/bedtools_bamtofastq Executable file
View File

File diff suppressed because it is too large Load Diff

202
target/executable/bedtools/bedtools_bed12tobed6/.config.vsh.yaml Normal file
View File

@@ -0,0 +1,202 @@
name: "bedtools_bed12tobed6"
namespace: "bedtools"
version: "v0.2"
authors:
- name: "Theodoro Gasperin Terra Camargo"
roles:
- "author"
- "maintainer"
info:
links:
email: "theodorogtc@gmail.com"
github: "tgaspe"
linkedin: "theodoro-gasperin-terra-camargo"
organizations:
- name: "Data Intuitive"
href: "https://www.data-intuitive.com"
role: "Bioinformatician"
argument_groups:
- name: "Inputs"
arguments:
- type: "file"
name: "--input"
alternatives:
- "-i"
description: "Input BED12 file."
info: null
must_exist: true
create_parent: true
required: true
direction: "input"
multiple: false
multiple_sep: ";"
- name: "Outputs"
arguments:
- type: "file"
name: "--output"
alternatives:
- "-o"
description: "Output BED6 file to be written."
info: null
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- name: "Options"
arguments:
- type: "boolean_true"
name: "--n_score"
alternatives:
- "-n"
description: "Force the score to be the (1-based) block number from the BED12.\n"
info: null
direction: "input"
resources:
- type: "bash_script"
path: "script.sh"
is_executable: true
description: "Converts BED features in BED12 (a.k.a. “blocked” BED features such as\
\ genes) to discrete BED6 features.\nFor example, in the case of a gene with six\
\ exons, bed12ToBed6 would create six separate BED6 features (i.e., one for each\
\ exon).\n"
test_resources:
- type: "bash_script"
path: "test.sh"
is_executable: true
info: null
status: "enabled"
requirements:
commands:
- "ps"
keywords:
- "Converts"
- "BED12"
- "BED6"
license: "MIT"
references:
doi:
- "10.1093/bioinformatics/btq033"
links:
repository: "https://github.com/arq5x/bedtools2"
homepage: "https://bedtools.readthedocs.io/en/latest/#"
documentation: "https://bedtools.readthedocs.io/en/latest/content/tools/bed12tobed6.html"
issue_tracker: "https://github.com/arq5x/bedtools2/issues"
runners:
- type: "executable"
id: "executable"
docker_setup_strategy: "ifneedbepullelsecachedbuild"
- type: "nextflow"
id: "nextflow"
directives:
tag: "$id"
auto:
simplifyInput: true
simplifyOutput: false
transcript: false
publish: false
config:
labels:
mem1gb: "memory = 1000000000.B"
mem2gb: "memory = 2000000000.B"
mem5gb: "memory = 5000000000.B"
mem10gb: "memory = 10000000000.B"
mem20gb: "memory = 20000000000.B"
mem50gb: "memory = 50000000000.B"
mem100gb: "memory = 100000000000.B"
mem200gb: "memory = 200000000000.B"
mem500gb: "memory = 500000000000.B"
mem1tb: "memory = 1000000000000.B"
mem2tb: "memory = 2000000000000.B"
mem5tb: "memory = 5000000000000.B"
mem10tb: "memory = 10000000000000.B"
mem20tb: "memory = 20000000000000.B"
mem50tb: "memory = 50000000000000.B"
mem100tb: "memory = 100000000000000.B"
mem200tb: "memory = 200000000000000.B"
mem500tb: "memory = 500000000000000.B"
mem1gib: "memory = 1073741824.B"
mem2gib: "memory = 2147483648.B"
mem4gib: "memory = 4294967296.B"
mem8gib: "memory = 8589934592.B"
mem16gib: "memory = 17179869184.B"
mem32gib: "memory = 34359738368.B"
mem64gib: "memory = 68719476736.B"
mem128gib: "memory = 137438953472.B"
mem256gib: "memory = 274877906944.B"
mem512gib: "memory = 549755813888.B"
mem1tib: "memory = 1099511627776.B"
mem2tib: "memory = 2199023255552.B"
mem4tib: "memory = 4398046511104.B"
mem8tib: "memory = 8796093022208.B"
mem16tib: "memory = 17592186044416.B"
mem32tib: "memory = 35184372088832.B"
mem64tib: "memory = 70368744177664.B"
mem128tib: "memory = 140737488355328.B"
mem256tib: "memory = 281474976710656.B"
mem512tib: "memory = 562949953421312.B"
cpu1: "cpus = 1"
cpu2: "cpus = 2"
cpu5: "cpus = 5"
cpu10: "cpus = 10"
cpu20: "cpus = 20"
cpu50: "cpus = 50"
cpu100: "cpus = 100"
cpu200: "cpus = 200"
cpu500: "cpus = 500"
cpu1000: "cpus = 1000"
debug: false
container: "docker"
engines:
- type: "docker"
id: "docker"
image: "debian:stable-slim"
target_registry: "images.viash-hub.com"
target_tag: "v0.2"
namespace_separator: "/"
setup:
- type: "apt"
packages:
- "bedtools"
- "procps"
interactive: false
- type: "docker"
run:
- "echo \"bedtools: \\\"$(bedtools --version | sed -n 's/^bedtools //p')\\\"\"\
\ > /var/software_versions.txt\n"
entrypoint: []
cmd: null
- type: "native"
id: "native"
build_info:
config: "src/bedtools/bedtools_bed12tobed6/config.vsh.yaml"
runner: "executable"
engine: "docker|native"
output: "target/executable/bedtools/bedtools_bed12tobed6"
executable: "target/executable/bedtools/bedtools_bed12tobed6/bedtools_bed12tobed6"
viash_version: "0.9.0-RC7"
git_commit: "f22ab0eab58dcd6bff89d8d73fe951953ff1260f"
git_remote: "https://github.com/viash-hub/biobox"
package_config:
name: "biobox"
version: "v0.2"
description: "A collection of bioinformatics tools for working with sequence data.\n"
info: null
viash_version: "0.9.0-RC7"
source: "src"
target: "target"
config_mods:
- ".requirements.commands := ['ps']\n"
- ".engines += { type: \"native\" }"
- ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
- ".engines[.type == 'docker'].target_tag := 'v0.2'"
keywords:
- "bioinformatics"
- "modules"
- "sequencing"
license: "MIT"
organization: "vsh"
links:
repository: "https://github.com/viash-hub/biobox"
issue_tracker: "https://github.com/viash-hub/biobox/issues"

1130
target/executable/bedtools/bedtools_bed12tobed6/bedtools_bed12tobed6 Executable file
View File

File diff suppressed because it is too large Load Diff

240
target/executable/bedtools/bedtools_bedtobam/.config.vsh.yaml Normal file
View File

@@ -0,0 +1,240 @@
name: "bedtools_bedtobam"
namespace: "bedtools"
version: "v0.2"
authors:
- name: "Theodoro Gasperin Terra Camargo"
roles:
- "author"
- "maintainer"
info:
links:
email: "theodorogtc@gmail.com"
github: "tgaspe"
linkedin: "theodoro-gasperin-terra-camargo"
organizations:
- name: "Data Intuitive"
href: "https://www.data-intuitive.com"
role: "Bioinformatician"
argument_groups:
- name: "Inputs"
arguments:
- type: "file"
name: "--input"
alternatives:
- "-i"
description: "Input file (bed/gff/vcf)."
info: null
must_exist: true
create_parent: true
required: true
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--genome"
alternatives:
- "-g"
description: "Input genome file.\nNOTE: This is not a fasta file. This is a two-column\
\ tab-delimited file\nwhere the first column is the chromosome name and the\
\ second their sizes.\n"
info: null
must_exist: true
create_parent: true
required: true
direction: "input"
multiple: false
multiple_sep: ";"
- name: "Outputs"
arguments:
- type: "file"
name: "--output"
alternatives:
- "-o"
description: "Output BAM file to be written."
info: null
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- name: "Options"
arguments:
- type: "integer"
name: "--map_quality"
alternatives:
- "-mapq"
description: "Set the mappinq quality for the BAM records.\n"
info: null
default:
- 255
required: false
min: 0
max: 255
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean_true"
name: "--bed12"
description: "The BED file is in BED12 format. The BAM CIGAR\nstring will reflect\
\ BED \"blocks\".\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--uncompress_bam"
alternatives:
- "-ubam"
description: "Write uncompressed BAM output. Default writes compressed BAM.\n"
info: null
direction: "input"
resources:
- type: "bash_script"
path: "script.sh"
is_executable: true
description: "Converts feature records (bed/gff/vcf) to BAM format."
test_resources:
- type: "bash_script"
path: "test.sh"
is_executable: true
info: null
status: "enabled"
requirements:
commands:
- "ps"
keywords:
- "Converts"
- "BED"
- "GFF"
- "VCF"
- "BAM"
license: "MIT"
references:
doi:
- "10.1093/bioinformatics/btq033"
links:
repository: "https://github.com/arq5x/bedtools2"
homepage: "https://bedtools.readthedocs.io/en/latest/#"
documentation: "https://bedtools.readthedocs.io/en/latest/content/tools/bedtobam.html"
issue_tracker: "https://github.com/arq5x/bedtools2/issues"
runners:
- type: "executable"
id: "executable"
docker_setup_strategy: "ifneedbepullelsecachedbuild"
- type: "nextflow"
id: "nextflow"
directives:
tag: "$id"
auto:
simplifyInput: true
simplifyOutput: false
transcript: false
publish: false
config:
labels:
mem1gb: "memory = 1000000000.B"
mem2gb: "memory = 2000000000.B"
mem5gb: "memory = 5000000000.B"
mem10gb: "memory = 10000000000.B"
mem20gb: "memory = 20000000000.B"
mem50gb: "memory = 50000000000.B"
mem100gb: "memory = 100000000000.B"
mem200gb: "memory = 200000000000.B"
mem500gb: "memory = 500000000000.B"
mem1tb: "memory = 1000000000000.B"
mem2tb: "memory = 2000000000000.B"
mem5tb: "memory = 5000000000000.B"
mem10tb: "memory = 10000000000000.B"
mem20tb: "memory = 20000000000000.B"
mem50tb: "memory = 50000000000000.B"
mem100tb: "memory = 100000000000000.B"
mem200tb: "memory = 200000000000000.B"
mem500tb: "memory = 500000000000000.B"
mem1gib: "memory = 1073741824.B"
mem2gib: "memory = 2147483648.B"
mem4gib: "memory = 4294967296.B"
mem8gib: "memory = 8589934592.B"
mem16gib: "memory = 17179869184.B"
mem32gib: "memory = 34359738368.B"
mem64gib: "memory = 68719476736.B"
mem128gib: "memory = 137438953472.B"
mem256gib: "memory = 274877906944.B"
mem512gib: "memory = 549755813888.B"
mem1tib: "memory = 1099511627776.B"
mem2tib: "memory = 2199023255552.B"
mem4tib: "memory = 4398046511104.B"
mem8tib: "memory = 8796093022208.B"
mem16tib: "memory = 17592186044416.B"
mem32tib: "memory = 35184372088832.B"
mem64tib: "memory = 70368744177664.B"
mem128tib: "memory = 140737488355328.B"
mem256tib: "memory = 281474976710656.B"
mem512tib: "memory = 562949953421312.B"
cpu1: "cpus = 1"
cpu2: "cpus = 2"
cpu5: "cpus = 5"
cpu10: "cpus = 10"
cpu20: "cpus = 20"
cpu50: "cpus = 50"
cpu100: "cpus = 100"
cpu200: "cpus = 200"
cpu500: "cpus = 500"
cpu1000: "cpus = 1000"
debug: false
container: "docker"
engines:
- type: "docker"
id: "docker"
image: "debian:stable-slim"
target_registry: "images.viash-hub.com"
target_tag: "v0.2"
namespace_separator: "/"
setup:
- type: "apt"
packages:
- "bedtools"
- "procps"
interactive: false
- type: "docker"
run:
- "echo \"bedtools: \\\"$(bedtools --version | sed -n 's/^bedtools //p')\\\"\"\
\ > /var/software_versions.txt\n"
test_setup:
- type: "apt"
packages:
- "samtools"
interactive: false
entrypoint: []
cmd: null
- type: "native"
id: "native"
build_info:
config: "src/bedtools/bedtools_bedtobam/config.vsh.yaml"
runner: "executable"
engine: "docker|native"
output: "target/executable/bedtools/bedtools_bedtobam"
executable: "target/executable/bedtools/bedtools_bedtobam/bedtools_bedtobam"
viash_version: "0.9.0-RC7"
git_commit: "f22ab0eab58dcd6bff89d8d73fe951953ff1260f"
git_remote: "https://github.com/viash-hub/biobox"
package_config:
name: "biobox"
version: "v0.2"
description: "A collection of bioinformatics tools for working with sequence data.\n"
info: null
viash_version: "0.9.0-RC7"
source: "src"
target: "target"
config_mods:
- ".requirements.commands := ['ps']\n"
- ".engines += { type: \"native\" }"
- ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
- ".engines[.type == 'docker'].target_tag := 'v0.2'"
keywords:
- "bioinformatics"
- "modules"
- "sequencing"
license: "MIT"
organization: "vsh"
links:
repository: "https://github.com/viash-hub/biobox"
issue_tracker: "https://github.com/viash-hub/biobox/issues"

1233
target/executable/bedtools/bedtools_bedtobam/bedtools_bedtobam Executable file
View File

File diff suppressed because it is too large Load Diff

258
target/executable/bedtools/bedtools_getfasta/.config.vsh.yaml Normal file
View File

@@ -0,0 +1,258 @@
name: "bedtools_getfasta"
namespace: "bedtools"
version: "v0.2"
authors:
- name: "Dries Schaumont"
roles:
- "author"
- "maintainer"
info:
links:
email: "dries@data-intuitive.com"
github: "DriesSchaumont"
orcid: "0000-0002-4389-0440"
linkedin: "dries-schaumont"
organizations:
- name: "Data Intuitive"
href: "https://www.data-intuitive.com"
role: "Data Scientist"
argument_groups:
- name: "Input arguments"
arguments:
- type: "file"
name: "--input_fasta"
description: "FASTA file containing sequences for each interval specified in the\
\ input BED file.\nThe headers in the input FASTA file must exactly match the\
\ chromosome column in the BED file.\n"
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--input_bed"
description: "BED file containing intervals to extract from the FASTA file.\n\
BED files containing a single region require a newline character\nat the end\
\ of the line, otherwise a blank output file is produced.\n"
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean_true"
name: "--rna"
description: "The FASTA is RNA not DNA. Reverse complementation handled accordingly.\n"
info: null
direction: "input"
- name: "Run arguments"
arguments:
- type: "boolean_true"
name: "--strandedness"
alternatives:
- "-s"
description: "Force strandedness. If the feature occupies the antisense strand,\
\ the output sequence will\nbe reverse complemented. By default strandedness\
\ is not taken into account.\n"
info: null
direction: "input"
- name: "Output arguments"
arguments:
- type: "file"
name: "--output"
alternatives:
- "-o"
description: "Output file where the output from the 'bedtools getfasta' commend\
\ will\nbe written to.\n"
info: null
must_exist: true
create_parent: true
required: true
direction: "output"
multiple: false
multiple_sep: ";"
- type: "boolean_true"
name: "--tab"
description: "Report extract sequences in a tab-delimited format instead of in\
\ FASTA format.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--bed_out"
description: "Report extract sequences in a tab-delimited BED format instead of\
\ in FASTA format.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--name"
description: "Set the FASTA header for each extracted sequence to be the \"name\"\
\ and coordinate columns from the BED feature.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--name_only"
description: "Set the FASTA header for each extracted sequence to be the \"name\"\
\ columns from the BED feature.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--split"
description: "When --input is in BED12 format, create a separate fasta entry for\
\ each block in a BED12 record,\nblocks being described in the 11th and 12th\
\ column of the BED.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--full_header"
description: "Use full fasta header. By default, only the word before the first\
\ space or tab is used.\n"
info: null
direction: "input"
resources:
- type: "bash_script"
path: "script.sh"
is_executable: true
description: "Extract sequences from a FASTA file for each of the intervals defined\
\ in a BED/GFF/VCF file."
test_resources:
- type: "bash_script"
path: "test.sh"
is_executable: true
info: null
status: "enabled"
requirements:
commands:
- "ps"
keywords:
- "sequencing"
- "fasta"
- "BED"
- "GFF"
- "VCF"
license: "GPL-2.0"
references:
doi:
- "10.1093/bioinformatics/btq033"
links:
repository: "https://github.com/arq5x/bedtools2"
documentation: "https://bedtools.readthedocs.io/en/latest/content/tools/getfasta.html"
runners:
- type: "executable"
id: "executable"
docker_setup_strategy: "ifneedbepullelsecachedbuild"
- type: "nextflow"
id: "nextflow"
directives:
tag: "$id"
auto:
simplifyInput: true
simplifyOutput: false
transcript: false
publish: false
config:
labels:
mem1gb: "memory = 1000000000.B"
mem2gb: "memory = 2000000000.B"
mem5gb: "memory = 5000000000.B"
mem10gb: "memory = 10000000000.B"
mem20gb: "memory = 20000000000.B"
mem50gb: "memory = 50000000000.B"
mem100gb: "memory = 100000000000.B"
mem200gb: "memory = 200000000000.B"
mem500gb: "memory = 500000000000.B"
mem1tb: "memory = 1000000000000.B"
mem2tb: "memory = 2000000000000.B"
mem5tb: "memory = 5000000000000.B"
mem10tb: "memory = 10000000000000.B"
mem20tb: "memory = 20000000000000.B"
mem50tb: "memory = 50000000000000.B"
mem100tb: "memory = 100000000000000.B"
mem200tb: "memory = 200000000000000.B"
mem500tb: "memory = 500000000000000.B"
mem1gib: "memory = 1073741824.B"
mem2gib: "memory = 2147483648.B"
mem4gib: "memory = 4294967296.B"
mem8gib: "memory = 8589934592.B"
mem16gib: "memory = 17179869184.B"
mem32gib: "memory = 34359738368.B"
mem64gib: "memory = 68719476736.B"
mem128gib: "memory = 137438953472.B"
mem256gib: "memory = 274877906944.B"
mem512gib: "memory = 549755813888.B"
mem1tib: "memory = 1099511627776.B"
mem2tib: "memory = 2199023255552.B"
mem4tib: "memory = 4398046511104.B"
mem8tib: "memory = 8796093022208.B"
mem16tib: "memory = 17592186044416.B"
mem32tib: "memory = 35184372088832.B"
mem64tib: "memory = 70368744177664.B"
mem128tib: "memory = 140737488355328.B"
mem256tib: "memory = 281474976710656.B"
mem512tib: "memory = 562949953421312.B"
cpu1: "cpus = 1"
cpu2: "cpus = 2"
cpu5: "cpus = 5"
cpu10: "cpus = 10"
cpu20: "cpus = 20"
cpu50: "cpus = 50"
cpu100: "cpus = 100"
cpu200: "cpus = 200"
cpu500: "cpus = 500"
cpu1000: "cpus = 1000"
debug: false
container: "docker"
engines:
- type: "docker"
id: "docker"
image: "debian:stable-slim"
target_registry: "images.viash-hub.com"
target_tag: "v0.2"
namespace_separator: "/"
setup:
- type: "apt"
packages:
- "bedtools"
- "procps"
interactive: false
- type: "docker"
run:
- "echo \"bedtools: \\\"$(bedtools --version | sed -n 's/^bedtools //p')\\\"\"\
\ > /var/software_versions.txt\n"
entrypoint: []
cmd: null
- type: "native"
id: "native"
build_info:
config: "src/bedtools/bedtools_getfasta/config.vsh.yaml"
runner: "executable"
engine: "docker|native"
output: "target/executable/bedtools/bedtools_getfasta"
executable: "target/executable/bedtools/bedtools_getfasta/bedtools_getfasta"
viash_version: "0.9.0-RC7"
git_commit: "f22ab0eab58dcd6bff89d8d73fe951953ff1260f"
git_remote: "https://github.com/viash-hub/biobox"
package_config:
name: "biobox"
version: "v0.2"
description: "A collection of bioinformatics tools for working with sequence data.\n"
info: null
viash_version: "0.9.0-RC7"
source: "src"
target: "target"
config_mods:
- ".requirements.commands := ['ps']\n"
- ".engines += { type: \"native\" }"
- ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
- ".engines[.type == 'docker'].target_tag := 'v0.2'"
keywords:
- "bioinformatics"
- "modules"
- "sequencing"
license: "MIT"
organization: "vsh"
links:
repository: "https://github.com/viash-hub/biobox"
issue_tracker: "https://github.com/viash-hub/biobox/issues"

1306
target/executable/bedtools/bedtools_getfasta/bedtools_getfasta Executable file
View File

File diff suppressed because it is too large Load Diff

299
target/executable/bedtools/bedtools_groupby/.config.vsh.yaml Normal file
View File

@@ -0,0 +1,299 @@
name: "bedtools_groupby"
namespace: "bedtools"
version: "v0.2"
authors:
- name: "Theodoro Gasperin Terra Camargo"
roles:
- "author"
- "maintainer"
info:
links:
email: "theodorogtc@gmail.com"
github: "tgaspe"
linkedin: "theodoro-gasperin-terra-camargo"
organizations:
- name: "Data Intuitive"
href: "https://www.data-intuitive.com"
role: "Bioinformatician"
argument_groups:
- name: "Inputs"
arguments:
- type: "file"
name: "--input"
alternatives:
- "-i"
description: "The input BED file to be used.\n"
info: null
example:
- "input_a.bed"
must_exist: true
create_parent: true
required: true
direction: "input"
multiple: false
multiple_sep: ";"
- name: "Outputs"
arguments:
- type: "file"
name: "--output"
description: "The output groupby BED file. \n"
info: null
example:
- "output.bed"
must_exist: true
create_parent: true
required: true
direction: "output"
multiple: false
multiple_sep: ";"
- name: "Options"
arguments:
- type: "string"
name: "--groupby"
alternatives:
- "-g"
- "-grp"
description: "Specify the columns (1-based) for the grouping.\nThe columns must\
\ be comma separated.\n- Default: 1,2,3 \n"
info: null
required: true
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--column"
alternatives:
- "-c"
- "-opCols"
description: "Specify the column (1-based) that should be summarized.\n"
info: null
required: true
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--operation"
alternatives:
- "-o"
- "-ops"
description: "Specify the operation that should be applied to opCol.\nValid operations:\n\
\ sum, count, count_distinct, min, max,\n mean, median, mode, antimode,\n\
\ stdev, sstdev (sample standard dev.),\n collapse (i.e., print a comma\
\ separated list (duplicates allowed)), \n distinct (i.e., print a comma\
\ separated list (NO duplicates allowed)), \n distinct_sort_num (as distinct,\
\ but sorted numerically, ascending), \n distinct_sort_num_desc (as distinct,\
\ but sorted numerically, descending), \n concat (i.e., merge values into\
\ a single, non-delimited string), \n freqdesc (i.e., print desc. list of\
\ values:freq)\n freqasc (i.e., print asc. list of values:freq)\n first\
\ (i.e., print first value)\n last (i.e., print last value)\n\nDefault value:\
\ sum \n\nIf there is only column, but multiple operations, all operations\
\ will be\napplied on that column. Likewise, if there is only one operation,\
\ but\nmultiple columns, that operation will be applied to all columns.\nOtherwise,\
\ the number of columns must match the the number of operations,\nand will be\
\ applied in respective order.\nE.g., \"-c 5,4,6 -o sum,mean,count\" will give\
\ the sum of column 5,\nthe mean of column 4, and the count of column 6.\nThe\
\ order of output columns will match the ordering given in the command.\n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean_true"
name: "--full"
description: "Print all columns from input file. The first line in the group is\
\ used.\nDefault: print only grouped columns.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--inheader"
description: "Input file has a header line - the first line will be ignored.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--outheader"
description: "Print header line in the output, detailing the column names. \n\
If the input file has headers (-inheader), the output file\nwill use the input's\
\ column names.\nIf the input file has no headers, the output file\nwill use\
\ \"col_1\", \"col_2\", etc. as the column names.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--header"
description: "same as '-inheader -outheader'."
info: null
direction: "input"
- type: "boolean_true"
name: "--ignorecase"
description: "Group values regardless of upper/lower case.\n"
info: null
direction: "input"
- type: "integer"
name: "--precision"
alternatives:
- "-prec"
description: "Sets the decimal precision for output. \n"
info: null
default:
- 5
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--delimiter"
alternatives:
- "-delim"
description: "Specify a custom delimiter for the collapse operations.\n"
info: null
example:
- "|"
default:
- ","
required: false
direction: "input"
multiple: false
multiple_sep: ";"
resources:
- type: "bash_script"
path: "script.sh"
is_executable: true
description: "Summarizes a dataset column based upon common column groupings. \nAkin\
\ to the SQL \"group by\" command.\n"
test_resources:
- type: "bash_script"
path: "test.sh"
is_executable: true
info: null
status: "enabled"
requirements:
commands:
- "ps"
keywords:
- "groupby"
- "BED"
license: "MIT"
references:
doi:
- "10.1093/bioinformatics/btq033"
links:
repository: "https://github.com/arq5x/bedtools2"
homepage: "https://bedtools.readthedocs.io/en/latest/#"
documentation: "https://bedtools.readthedocs.io/en/latest/content/tools/groupby.html"
issue_tracker: "https://github.com/arq5x/bedtools2/issues"
runners:
- type: "executable"
id: "executable"
docker_setup_strategy: "ifneedbepullelsecachedbuild"
- type: "nextflow"
id: "nextflow"
directives:
tag: "$id"
auto:
simplifyInput: true
simplifyOutput: false
transcript: false
publish: false
config:
labels:
mem1gb: "memory = 1000000000.B"
mem2gb: "memory = 2000000000.B"
mem5gb: "memory = 5000000000.B"
mem10gb: "memory = 10000000000.B"
mem20gb: "memory = 20000000000.B"
mem50gb: "memory = 50000000000.B"
mem100gb: "memory = 100000000000.B"
mem200gb: "memory = 200000000000.B"
mem500gb: "memory = 500000000000.B"
mem1tb: "memory = 1000000000000.B"
mem2tb: "memory = 2000000000000.B"
mem5tb: "memory = 5000000000000.B"
mem10tb: "memory = 10000000000000.B"
mem20tb: "memory = 20000000000000.B"
mem50tb: "memory = 50000000000000.B"
mem100tb: "memory = 100000000000000.B"
mem200tb: "memory = 200000000000000.B"
mem500tb: "memory = 500000000000000.B"
mem1gib: "memory = 1073741824.B"
mem2gib: "memory = 2147483648.B"
mem4gib: "memory = 4294967296.B"
mem8gib: "memory = 8589934592.B"
mem16gib: "memory = 17179869184.B"
mem32gib: "memory = 34359738368.B"
mem64gib: "memory = 68719476736.B"
mem128gib: "memory = 137438953472.B"
mem256gib: "memory = 274877906944.B"
mem512gib: "memory = 549755813888.B"
mem1tib: "memory = 1099511627776.B"
mem2tib: "memory = 2199023255552.B"
mem4tib: "memory = 4398046511104.B"
mem8tib: "memory = 8796093022208.B"
mem16tib: "memory = 17592186044416.B"
mem32tib: "memory = 35184372088832.B"
mem64tib: "memory = 70368744177664.B"
mem128tib: "memory = 140737488355328.B"
mem256tib: "memory = 281474976710656.B"
mem512tib: "memory = 562949953421312.B"
cpu1: "cpus = 1"
cpu2: "cpus = 2"
cpu5: "cpus = 5"
cpu10: "cpus = 10"
cpu20: "cpus = 20"
cpu50: "cpus = 50"
cpu100: "cpus = 100"
cpu200: "cpus = 200"
cpu500: "cpus = 500"
cpu1000: "cpus = 1000"
debug: false
container: "docker"
engines:
- type: "docker"
id: "docker"
image: "debian:stable-slim"
target_registry: "images.viash-hub.com"
target_tag: "v0.2"
namespace_separator: "/"
setup:
- type: "apt"
packages:
- "bedtools"
- "procps"
interactive: false
- type: "docker"
run:
- "echo \"bedtools: \\\"$(bedtools --version | sed -n 's/^bedtools //p')\\\"\"\
\ > /var/software_versions.txt\n"
entrypoint: []
cmd: null
- type: "native"
id: "native"
build_info:
config: "src/bedtools/bedtools_groupby/config.vsh.yaml"
runner: "executable"
engine: "docker|native"
output: "target/executable/bedtools/bedtools_groupby"
executable: "target/executable/bedtools/bedtools_groupby/bedtools_groupby"
viash_version: "0.9.0-RC7"
git_commit: "f22ab0eab58dcd6bff89d8d73fe951953ff1260f"
git_remote: "https://github.com/viash-hub/biobox"
package_config:
name: "biobox"
version: "v0.2"
description: "A collection of bioinformatics tools for working with sequence data.\n"
info: null
viash_version: "0.9.0-RC7"
source: "src"
target: "target"
config_mods:
- ".requirements.commands := ['ps']\n"
- ".engines += { type: \"native\" }"
- ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
- ".engines[.type == 'docker'].target_tag := 'v0.2'"
keywords:
- "bioinformatics"
- "modules"
- "sequencing"
license: "MIT"
organization: "vsh"
links:
repository: "https://github.com/viash-hub/biobox"
issue_tracker: "https://github.com/viash-hub/biobox/issues"

1410
target/executable/bedtools/bedtools_groupby/bedtools_groupby Executable file
View File

File diff suppressed because it is too large Load Diff

436
target/executable/bedtools/bedtools_intersect/.config.vsh.yaml Normal file
View File

@@ -0,0 +1,436 @@
name: "bedtools_intersect"
namespace: "bedtools"
version: "v0.2"
authors:
- name: "Theodoro Gasperin Terra Camargo"
roles:
- "author"
- "maintainer"
info:
links:
email: "theodorogtc@gmail.com"
github: "tgaspe"
linkedin: "theodoro-gasperin-terra-camargo"
organizations:
- name: "Data Intuitive"
href: "https://www.data-intuitive.com"
role: "Bioinformatician"
argument_groups:
- name: "Inputs"
arguments:
- type: "file"
name: "--input_a"
alternatives:
- "-a"
description: "The input file (BED/GFF/VCF/BAM) to be used as the -a file.\n"
info: null
example:
- "input_a.bed"
must_exist: true
create_parent: true
required: true
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--input_b"
alternatives:
- "-b"
description: "The input file(s) (BED/GFF/VCF/BAM) to be used as the -b file(s).\n"
info: null
example:
- "input_b.bed"
must_exist: true
create_parent: true
required: true
direction: "input"
multiple: true
multiple_sep: ";"
- name: "Outputs"
arguments:
- type: "file"
name: "--output"
description: "The output BED file. \n"
info: null
example:
- "output.bed"
must_exist: true
create_parent: true
required: true
direction: "output"
multiple: false
multiple_sep: ";"
- name: "Options"
arguments:
- type: "boolean_true"
name: "--write_a"
alternatives:
- "-wa"
description: "Write the original A entry for each overlap."
info: null
direction: "input"
- type: "boolean_true"
name: "--write_b"
alternatives:
- "-wb"
description: "Write the original B entry for each overlap. \nUseful for knowing\
\ _what_ A overlaps. Restricted by -f and -r.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--left_outer_join"
alternatives:
- "-loj"
description: "Perform a \"left outer join\". That is, for each feature in A report\
\ each overlap with B. \nIf no overlaps are found, report a NULL feature for\
\ B.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--write_overlap"
alternatives:
- "-wo"
description: "Write the original A and B entries plus the number of base pairs\
\ of overlap between the two features.\n- Overlaps restricted by -f and -r.\
\ \n Only A features with overlap are reported.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--write_overlap_plus"
alternatives:
- "-wao"
description: "Write the original A and B entries plus the number of base pairs\
\ of overlap between the two features.\n- Overlaps restricted by -f and -r.\
\ \n However, A features w/o overlap are also reported with a NULL B feature\
\ and overlap = 0.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--report_A_if_no_overlap"
alternatives:
- "-u"
description: "Write the original A entry _if_ no overlap is found. \n- In other\
\ words, just report the fact >=1 hit was found.\n- Overlaps restricted by -f\
\ and -r. \n"
info: null
direction: "input"
- type: "boolean_true"
name: "--number_of_overlaps_A"
alternatives:
- "-c"
description: "For each entry in A, report the number of overlaps with B.\n- Reports\
\ 0 for A entries that have no overlap with B.\n- Overlaps restricted by -f\
\ and -r.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--report_no_overlaps_A"
alternatives:
- "-v"
description: "Only report those entries in A that have _no overlaps_ with B.\n\
- Similar to \"grep -v\" (an homage).\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--uncompressed_bam"
alternatives:
- "-ubam"
description: "Write uncompressed BAM output. Default writes compressed BAM."
info: null
direction: "input"
- type: "boolean_true"
name: "--same_strand"
alternatives:
- "-s"
description: "Require same strandedness. That is, only report hits in B.\nthat\
\ overlap A on the _same_ strand.\n- By default, overlaps are reported without\
\ respect to strand.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--opposite_strand"
alternatives:
- "-S"
description: "Require different strandedness. That is, only report hits in B\n\
that overlap A on the _opposite_ strand.\n- By default, overlaps are reported\
\ without respect to strand.\n"
info: null
direction: "input"
- type: "double"
name: "--min_overlap_A"
alternatives:
- "-f"
description: "Minimum overlap required as a fraction of A.\n- Default is 1E-9\
\ (i.e., 1bp).\n- FLOAT (e.g. 0.50)\n"
info: null
example:
- 0.5
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "double"
name: "--min_overlap_B"
alternatives:
- "-F"
description: "Minimum overlap required as a fraction of B.\n- Default is 1E-9\
\ (i.e., 1bp).\n- FLOAT (e.g. 0.50)\n"
info: null
example:
- 0.5
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean_true"
name: "--reciprocal_overlap"
alternatives:
- "-r"
description: "Require that the fraction overlap be reciprocal for A AND B.\n-\
\ In other words, if -f is 0.90 and -r is used, this requires\nthat B overlap\
\ 90% of A and A _also_ overlaps 90% of B.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--either_overlap"
alternatives:
- "-e"
description: "Require that the minimum fraction be satisfied for A OR B.\n- In\
\ other words, if -e is used with -f 0.90 and -F 0.10 this requires\nthat either\
\ 90% of A is covered OR 10% of B is covered.\nWithout -e, both fractions would\
\ have to be satisfied.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--split"
description: "Treat \"split\" BAM or BED12 entries as distinct BED intervals."
info: null
direction: "input"
- type: "file"
name: "--genome"
alternatives:
- "-g"
description: "Provide a genome file to enforce consistent chromosome \nsort order\
\ across input files. Only applies when used \nwith -sorted option.\n"
info: null
example:
- "genome.txt"
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean_true"
name: "--nonamecheck"
description: "For sorted data, don't throw an error if the file \nhas different\
\ naming conventions for the same chromosome \n(e.g., \"chr1\" vs \"chr01\"\
).\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--sorted"
description: "Use the \"chromsweep\" algorithm for sorted (-k1,1 -k2,2n) input.\n"
info: null
direction: "input"
- type: "string"
name: "--names"
description: "When using multiple databases, provide an alias \nfor each that\
\ will appear instead of a fileId when \nalso printing the DB record.\n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean_true"
name: "--filenames"
description: "When using multiple databases, show each complete filename instead\
\ of a fileId when also printing the DB record."
info: null
direction: "input"
- type: "boolean_true"
name: "--sortout"
description: "When using multiple databases, sort the output DB hits for each\
\ record."
info: null
direction: "input"
- type: "boolean_true"
name: "--bed"
description: "If using BAM input, write output as BED."
info: null
direction: "input"
- type: "boolean_true"
name: "--header"
description: "Print the header from the A file prior to results."
info: null
direction: "input"
- type: "boolean_true"
name: "--no_buffer_output"
alternatives:
- "--nobuf"
description: "Disable buffered output. Using this option will cause each line\n\
of output to be printed as it is generated, rather than saved\nin a buffer.\
\ This will make printing large output files \nnoticeably slower, but can be\
\ useful in conjunction with\nother software tools and scripts that need to\
\ process one\nline of bedtools output at a time.\n"
info: null
direction: "input"
- type: "integer"
name: "--io_buffer_size"
alternatives:
- "--iobuf"
description: "Specify amount of memory to use for input buffer.\nTakes an integer\
\ argument. Optional suffixes K/M/G supported.\nNote: currently has no effect\
\ with compressed files. \n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
resources:
- type: "bash_script"
path: "script.sh"
is_executable: true
description: "bedtools intersect allows one to screen for overlaps between two sets\
\ of genomic features. \nMoreover, it allows one to have fine control as to how\
\ the intersections are reported. \nbedtools intersect works with both BED/GFF/VCF\
\ and BAM files as input.\n"
test_resources:
- type: "bash_script"
path: "test.sh"
is_executable: true
info: null
status: "enabled"
requirements:
commands:
- "ps"
keywords:
- "feature intersection"
- "BAM"
- "BED"
- "GFF"
- "VCF"
license: "GPL-2.0, MIT"
references:
doi:
- "10.1093/bioinformatics/btq033"
links:
repository: "https://github.com/arq5x/bedtools2"
documentation: "https://bedtools.readthedocs.io/en/latest/content/tools/intersect.html"
runners:
- type: "executable"
id: "executable"
docker_setup_strategy: "ifneedbepullelsecachedbuild"
- type: "nextflow"
id: "nextflow"
directives:
tag: "$id"
auto:
simplifyInput: true
simplifyOutput: false
transcript: false
publish: false
config:
labels:
mem1gb: "memory = 1000000000.B"
mem2gb: "memory = 2000000000.B"
mem5gb: "memory = 5000000000.B"
mem10gb: "memory = 10000000000.B"
mem20gb: "memory = 20000000000.B"
mem50gb: "memory = 50000000000.B"
mem100gb: "memory = 100000000000.B"
mem200gb: "memory = 200000000000.B"
mem500gb: "memory = 500000000000.B"
mem1tb: "memory = 1000000000000.B"
mem2tb: "memory = 2000000000000.B"
mem5tb: "memory = 5000000000000.B"
mem10tb: "memory = 10000000000000.B"
mem20tb: "memory = 20000000000000.B"
mem50tb: "memory = 50000000000000.B"
mem100tb: "memory = 100000000000000.B"
mem200tb: "memory = 200000000000000.B"
mem500tb: "memory = 500000000000000.B"
mem1gib: "memory = 1073741824.B"
mem2gib: "memory = 2147483648.B"
mem4gib: "memory = 4294967296.B"
mem8gib: "memory = 8589934592.B"
mem16gib: "memory = 17179869184.B"
mem32gib: "memory = 34359738368.B"
mem64gib: "memory = 68719476736.B"
mem128gib: "memory = 137438953472.B"
mem256gib: "memory = 274877906944.B"
mem512gib: "memory = 549755813888.B"
mem1tib: "memory = 1099511627776.B"
mem2tib: "memory = 2199023255552.B"
mem4tib: "memory = 4398046511104.B"
mem8tib: "memory = 8796093022208.B"
mem16tib: "memory = 17592186044416.B"
mem32tib: "memory = 35184372088832.B"
mem64tib: "memory = 70368744177664.B"
mem128tib: "memory = 140737488355328.B"
mem256tib: "memory = 281474976710656.B"
mem512tib: "memory = 562949953421312.B"
cpu1: "cpus = 1"
cpu2: "cpus = 2"
cpu5: "cpus = 5"
cpu10: "cpus = 10"
cpu20: "cpus = 20"
cpu50: "cpus = 50"
cpu100: "cpus = 100"
cpu200: "cpus = 200"
cpu500: "cpus = 500"
cpu1000: "cpus = 1000"
debug: false
container: "docker"
engines:
- type: "docker"
id: "docker"
image: "debian:stable-slim"
target_registry: "images.viash-hub.com"
target_tag: "v0.2"
namespace_separator: "/"
setup:
- type: "apt"
packages:
- "bedtools"
- "procps"
interactive: false
- type: "docker"
run:
- "echo \"bedtools: \\\"$(bedtools --version | sed -n 's/^bedtools //p')\\\"\"\
\ > /var/software_versions.txt\n"
entrypoint: []
cmd: null
- type: "native"
id: "native"
build_info:
config: "src/bedtools/bedtools_intersect/config.vsh.yaml"
runner: "executable"
engine: "docker|native"
output: "target/executable/bedtools/bedtools_intersect"
executable: "target/executable/bedtools/bedtools_intersect/bedtools_intersect"
viash_version: "0.9.0-RC7"
git_commit: "f22ab0eab58dcd6bff89d8d73fe951953ff1260f"
git_remote: "https://github.com/viash-hub/biobox"
package_config:
name: "biobox"
version: "v0.2"
description: "A collection of bioinformatics tools for working with sequence data.\n"
info: null
viash_version: "0.9.0-RC7"
source: "src"
target: "target"
config_mods:
- ".requirements.commands := ['ps']\n"
- ".engines += { type: \"native\" }"
- ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
- ".engines[.type == 'docker'].target_tag := 'v0.2'"
keywords:
- "bioinformatics"
- "modules"
- "sequencing"
license: "MIT"
organization: "vsh"
links:
repository: "https://github.com/viash-hub/biobox"
issue_tracker: "https://github.com/viash-hub/biobox/issues"

1880
target/executable/bedtools/bedtools_intersect/bedtools_intersect Executable file
View File

File diff suppressed because it is too large Load Diff

236
target/executable/bedtools/bedtools_links/.config.vsh.yaml Normal file
View File

@@ -0,0 +1,236 @@
name: "bedtools_links"
namespace: "bedtools"
version: "v0.2"
authors:
- name: "Theodoro Gasperin Terra Camargo"
roles:
- "author"
- "maintainer"
info:
links:
email: "theodorogtc@gmail.com"
github: "tgaspe"
linkedin: "theodoro-gasperin-terra-camargo"
organizations:
- name: "Data Intuitive"
href: "https://www.data-intuitive.com"
role: "Bioinformatician"
argument_groups:
- name: "Inputs"
arguments:
- type: "file"
name: "--input"
alternatives:
- "-i"
description: "Input file (bed/gff/vcf)."
info: null
must_exist: true
create_parent: true
required: true
direction: "input"
multiple: false
multiple_sep: ";"
- name: "Outputs"
arguments:
- type: "file"
name: "--output"
alternatives:
- "-o"
description: "Output HTML file to be written."
info: null
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- name: "Options"
description: "By default, the links created will point to human (hg18) UCSC browser.\n\
If you have a local mirror, you can override this behavior by supplying\nthe -base,\
\ -org, and -db options.\n\nFor example, if the URL of your local mirror for mouse\
\ MM9 is called: \nhttp://mymirror.myuniversity.edu, then you would use the following:\n\
--base_url http://mymirror.myuniversity.edu\n--organism mouse\n--database mm9\n"
arguments:
- type: "string"
name: "--base_url"
alternatives:
- "-base"
description: "The “basename” for the UCSC browser.\n"
info: null
default:
- "http://genome.ucsc.edu"
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--organism"
alternatives:
- "-org"
description: "The organism (e.g. mouse, human). \n"
info: null
default:
- "human"
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--database"
alternatives:
- "-db"
description: "The genome build. \n"
info: null
default:
- "hg18"
required: false
direction: "input"
multiple: false
multiple_sep: ";"
resources:
- type: "bash_script"
path: "script.sh"
is_executable: true
description: "Creates an HTML file with links to an instance of the UCSC Genome Browser\
\ for all features / intervals in a file. \nThis is useful for cases when one wants\
\ to manually inspect through a large set of annotations or features.\n"
test_resources:
- type: "bash_script"
path: "test.sh"
is_executable: true
info: null
status: "enabled"
requirements:
commands:
- "ps"
keywords:
- "Links"
- "BED"
- "GFF"
- "VCF"
license: "MIT"
references:
doi:
- "10.1093/bioinformatics/btq033"
links:
repository: "https://github.com/arq5x/bedtools2"
homepage: "https://bedtools.readthedocs.io/en/latest/#"
documentation: "https://bedtools.readthedocs.io/en/latest/content/tools/links.html"
issue_tracker: "https://github.com/arq5x/bedtools2/issues"
runners:
- type: "executable"
id: "executable"
docker_setup_strategy: "ifneedbepullelsecachedbuild"
- type: "nextflow"
id: "nextflow"
directives:
tag: "$id"
auto:
simplifyInput: true
simplifyOutput: false
transcript: false
publish: false
config:
labels:
mem1gb: "memory = 1000000000.B"
mem2gb: "memory = 2000000000.B"
mem5gb: "memory = 5000000000.B"
mem10gb: "memory = 10000000000.B"
mem20gb: "memory = 20000000000.B"
mem50gb: "memory = 50000000000.B"
mem100gb: "memory = 100000000000.B"
mem200gb: "memory = 200000000000.B"
mem500gb: "memory = 500000000000.B"
mem1tb: "memory = 1000000000000.B"
mem2tb: "memory = 2000000000000.B"
mem5tb: "memory = 5000000000000.B"
mem10tb: "memory = 10000000000000.B"
mem20tb: "memory = 20000000000000.B"
mem50tb: "memory = 50000000000000.B"
mem100tb: "memory = 100000000000000.B"
mem200tb: "memory = 200000000000000.B"
mem500tb: "memory = 500000000000000.B"
mem1gib: "memory = 1073741824.B"
mem2gib: "memory = 2147483648.B"
mem4gib: "memory = 4294967296.B"
mem8gib: "memory = 8589934592.B"
mem16gib: "memory = 17179869184.B"
mem32gib: "memory = 34359738368.B"
mem64gib: "memory = 68719476736.B"
mem128gib: "memory = 137438953472.B"
mem256gib: "memory = 274877906944.B"
mem512gib: "memory = 549755813888.B"
mem1tib: "memory = 1099511627776.B"
mem2tib: "memory = 2199023255552.B"
mem4tib: "memory = 4398046511104.B"
mem8tib: "memory = 8796093022208.B"
mem16tib: "memory = 17592186044416.B"
mem32tib: "memory = 35184372088832.B"
mem64tib: "memory = 70368744177664.B"
mem128tib: "memory = 140737488355328.B"
mem256tib: "memory = 281474976710656.B"
mem512tib: "memory = 562949953421312.B"
cpu1: "cpus = 1"
cpu2: "cpus = 2"
cpu5: "cpus = 5"
cpu10: "cpus = 10"
cpu20: "cpus = 20"
cpu50: "cpus = 50"
cpu100: "cpus = 100"
cpu200: "cpus = 200"
cpu500: "cpus = 500"
cpu1000: "cpus = 1000"
debug: false
container: "docker"
engines:
- type: "docker"
id: "docker"
image: "debian:stable-slim"
target_registry: "images.viash-hub.com"
target_tag: "v0.2"
namespace_separator: "/"
setup:
- type: "apt"
packages:
- "bedtools"
- "procps"
interactive: false
- type: "docker"
run:
- "echo \"bedtools: \\\"$(bedtools --version | sed -n 's/^bedtools //p')\\\"\"\
\ > /var/software_versions.txt\n"
entrypoint: []
cmd: null
- type: "native"
id: "native"
build_info:
config: "src/bedtools/bedtools_links/config.vsh.yaml"
runner: "executable"
engine: "docker|native"
output: "target/executable/bedtools/bedtools_links"
executable: "target/executable/bedtools/bedtools_links/bedtools_links"
viash_version: "0.9.0-RC7"
git_commit: "f22ab0eab58dcd6bff89d8d73fe951953ff1260f"
git_remote: "https://github.com/viash-hub/biobox"
package_config:
name: "biobox"
version: "v0.2"
description: "A collection of bioinformatics tools for working with sequence data.\n"
info: null
viash_version: "0.9.0-RC7"
source: "src"
target: "target"
config_mods:
- ".requirements.commands := ['ps']\n"
- ".engines += { type: \"native\" }"
- ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
- ".engines[.type == 'docker'].target_tag := 'v0.2'"
keywords:
- "bioinformatics"
- "modules"
- "sequencing"
license: "MIT"
organization: "vsh"
links:
repository: "https://github.com/viash-hub/biobox"
issue_tracker: "https://github.com/viash-hub/biobox/issues"

1192
target/executable/bedtools/bedtools_links/bedtools_links Executable file
View File

File diff suppressed because it is too large Load Diff

305
target/executable/bedtools/bedtools_merge/.config.vsh.yaml Normal file
View File

@@ -0,0 +1,305 @@
name: "bedtools_merge"
namespace: "bedtools"
version: "v0.2"
authors:
- name: "Theodoro Gasperin Terra Camargo"
roles:
- "author"
- "maintainer"
info:
links:
email: "theodorogtc@gmail.com"
github: "tgaspe"
linkedin: "theodoro-gasperin-terra-camargo"
organizations:
- name: "Data Intuitive"
href: "https://www.data-intuitive.com"
role: "Bioinformatician"
argument_groups:
- name: "Inputs"
arguments:
- type: "file"
name: "--input"
alternatives:
- "-i"
description: "Input file (BED/GFF/VCF) to be merged."
info: null
must_exist: true
create_parent: true
required: true
direction: "input"
multiple: false
multiple_sep: ";"
- name: "Outputs"
arguments:
- type: "file"
name: "--output"
description: "Output merged file BED to be written."
info: null
must_exist: true
create_parent: true
required: true
direction: "output"
multiple: false
multiple_sep: ";"
- name: "Options"
arguments:
- type: "boolean_true"
name: "--strand"
alternatives:
- "-s"
description: "Force strandedness. That is, only merge features\nthat are on the\
\ same strand.\n- By default, merging is done without respect to strand.\n"
info: null
direction: "input"
- type: "string"
name: "--specific_strand"
alternatives:
- "-S"
description: "Force merge for one specific strand only.\nFollow with + or - to\
\ force merge from only\nthe forward or reverse strand, respectively.\n- By\
\ default, merging is done without respect to strand.\n"
info: null
required: false
choices:
- "+"
- "-"
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--distance"
alternatives:
- "-d"
description: "Maximum distance between features allowed for features\nto be merged.\n\
- Def. 0. That is, overlapping & book-ended features are merged.\n- (INTEGER)\n\
- Note: negative values enforce the number of b.p. required for overlap.\n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--columns"
alternatives:
- "-c"
description: "Specify columns from the B file to map onto intervals in A.\nDefault:\
\ 5.\nMultiple columns can be specified in a comma-delimited list.\n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--operation"
alternatives:
- "-o"
description: "Specify the operation that should be applied to -c.\nValid operations:\n\
\ sum, min, max, absmin, absmax,\n mean, median, mode, antimode\n stdev,\
\ sstdev\n collapse (i.e., print a delimited list (duplicates allowed)),\
\ \n distinct (i.e., print a delimited list (NO duplicates allowed)), \n\
\ distinct_sort_num (as distinct, sorted numerically, ascending),\n distinct_sort_num_desc\
\ (as distinct, sorted numerically, desscending),\n distinct_only (delimited\
\ list of only unique values),\n count\n count_distinct (i.e., a count\
\ of the unique values in the column), \n first (i.e., just the first value\
\ in the column), \n last (i.e., just the last value in the column), \nDefault:\
\ sum\nMultiple operations can be specified in a comma-delimited list.\n\nIf\
\ there is only column, but multiple operations, all operations will be\napplied\
\ on that column. Likewise, if there is only one operation, but\nmultiple columns,\
\ that operation will be applied to all columns.\nOtherwise, the number of columns\
\ must match the the number of operations,\nand will be applied in respective\
\ order.\nE.g., \"-c 5,4,6 -o sum,mean,count\" will give the sum of column 5,\n\
the mean of column 4, and the count of column 6.\nThe order of output columns\
\ will match the ordering given in the command.\n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--delimiter"
alternatives:
- "-delim"
description: "Specify a custom delimiter for the collapse operations.\n"
info: null
example:
- "|"
default:
- ","
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--precision"
alternatives:
- "-prec"
description: "Sets the decimal precision for output (Default: 5).\n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean_true"
name: "--bed"
description: "If using BAM input, write output as BED.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--header"
description: "Print the header from the A file prior to results.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--no_buffer"
alternatives:
- "-nobuf"
description: "Disable buffered output. Using this option will cause each line\n\
of output to be printed as it is generated, rather than saved\nin a buffer.\
\ This will make printing large output files \nnoticeably slower, but can be\
\ useful in conjunction with\nother software tools and scripts that need to\
\ process one\nline of bedtools output at a time.\n"
info: null
direction: "input"
resources:
- type: "bash_script"
path: "script.sh"
is_executable: true
description: "Merges overlapping BED/GFF/VCF entries into a single interval.\n"
test_resources:
- type: "bash_script"
path: "test.sh"
is_executable: true
- type: "file"
path: "test_data"
info: null
status: "enabled"
requirements:
commands:
- "ps"
license: "MIT"
references:
doi:
- "10.1093/bioinformatics/btq033"
links:
repository: "https://github.com/arq5x/bedtools2"
homepage: "https://bedtools.readthedocs.io/en/latest/#"
documentation: "https://bedtools.readthedocs.io/en/latest/content/tools/merge.html"
issue_tracker: "https://github.com/arq5x/bedtools2/issues"
runners:
- type: "executable"
id: "executable"
docker_setup_strategy: "ifneedbepullelsecachedbuild"
- type: "nextflow"
id: "nextflow"
directives:
tag: "$id"
auto:
simplifyInput: true
simplifyOutput: false
transcript: false
publish: false
config:
labels:
mem1gb: "memory = 1000000000.B"
mem2gb: "memory = 2000000000.B"
mem5gb: "memory = 5000000000.B"
mem10gb: "memory = 10000000000.B"
mem20gb: "memory = 20000000000.B"
mem50gb: "memory = 50000000000.B"
mem100gb: "memory = 100000000000.B"
mem200gb: "memory = 200000000000.B"
mem500gb: "memory = 500000000000.B"
mem1tb: "memory = 1000000000000.B"
mem2tb: "memory = 2000000000000.B"
mem5tb: "memory = 5000000000000.B"
mem10tb: "memory = 10000000000000.B"
mem20tb: "memory = 20000000000000.B"
mem50tb: "memory = 50000000000000.B"
mem100tb: "memory = 100000000000000.B"
mem200tb: "memory = 200000000000000.B"
mem500tb: "memory = 500000000000000.B"
mem1gib: "memory = 1073741824.B"
mem2gib: "memory = 2147483648.B"
mem4gib: "memory = 4294967296.B"
mem8gib: "memory = 8589934592.B"
mem16gib: "memory = 17179869184.B"
mem32gib: "memory = 34359738368.B"
mem64gib: "memory = 68719476736.B"
mem128gib: "memory = 137438953472.B"
mem256gib: "memory = 274877906944.B"
mem512gib: "memory = 549755813888.B"
mem1tib: "memory = 1099511627776.B"
mem2tib: "memory = 2199023255552.B"
mem4tib: "memory = 4398046511104.B"
mem8tib: "memory = 8796093022208.B"
mem16tib: "memory = 17592186044416.B"
mem32tib: "memory = 35184372088832.B"
mem64tib: "memory = 70368744177664.B"
mem128tib: "memory = 140737488355328.B"
mem256tib: "memory = 281474976710656.B"
mem512tib: "memory = 562949953421312.B"
cpu1: "cpus = 1"
cpu2: "cpus = 2"
cpu5: "cpus = 5"
cpu10: "cpus = 10"
cpu20: "cpus = 20"
cpu50: "cpus = 50"
cpu100: "cpus = 100"
cpu200: "cpus = 200"
cpu500: "cpus = 500"
cpu1000: "cpus = 1000"
debug: false
container: "docker"
engines:
- type: "docker"
id: "docker"
image: "debian:stable-slim"
target_registry: "images.viash-hub.com"
target_tag: "v0.2"
namespace_separator: "/"
setup:
- type: "apt"
packages:
- "bedtools"
- "procps"
interactive: false
- type: "docker"
run:
- "echo \"bedtools: \\\"$(bedtools --version | sed -n 's/^bedtools //p')\\\"\"\
\ > /var/software_versions.txt\n"
entrypoint: []
cmd: null
- type: "native"
id: "native"
build_info:
config: "src/bedtools/bedtools_merge/config.vsh.yaml"
runner: "executable"
engine: "docker|native"
output: "target/executable/bedtools/bedtools_merge"
executable: "target/executable/bedtools/bedtools_merge/bedtools_merge"
viash_version: "0.9.0-RC7"
git_commit: "f22ab0eab58dcd6bff89d8d73fe951953ff1260f"
git_remote: "https://github.com/viash-hub/biobox"
package_config:
name: "biobox"
version: "v0.2"
description: "A collection of bioinformatics tools for working with sequence data.\n"
info: null
viash_version: "0.9.0-RC7"
source: "src"
target: "target"
config_mods:
- ".requirements.commands := ['ps']\n"
- ".engines += { type: \"native\" }"
- ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
- ".engines[.type == 'docker'].target_tag := 'v0.2'"
keywords:
- "bioinformatics"
- "modules"
- "sequencing"
license: "MIT"
organization: "vsh"
links:
repository: "https://github.com/viash-hub/biobox"
issue_tracker: "https://github.com/viash-hub/biobox/issues"

1418
target/executable/bedtools/bedtools_merge/bedtools_merge Executable file
View File

File diff suppressed because it is too large Load Diff

248
target/executable/bedtools/bedtools_sort/.config.vsh.yaml Normal file
View File

@@ -0,0 +1,248 @@
name: "bedtools_sort"
namespace: "bedtools"
version: "v0.2"
authors:
- name: "Theodoro Gasperin Terra Camargo"
roles:
- "author"
- "maintainer"
info:
links:
email: "theodorogtc@gmail.com"
github: "tgaspe"
linkedin: "theodoro-gasperin-terra-camargo"
organizations:
- name: "Data Intuitive"
href: "https://www.data-intuitive.com"
role: "Bioinformatician"
argument_groups:
- name: "Inputs"
arguments:
- type: "file"
name: "--input"
alternatives:
- "-i"
description: "Input file (bed/gff/vcf) to be sorted."
info: null
must_exist: true
create_parent: true
required: true
direction: "input"
multiple: false
multiple_sep: ";"
- name: "Outputs"
arguments:
- type: "file"
name: "--output"
alternatives:
- "-o"
description: "Output sorted file (bed/gff/vcf) to be written."
info: null
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- name: "Options"
arguments:
- type: "boolean_true"
name: "--sizeA"
description: "Sort by feature size in ascending order."
info: null
direction: "input"
- type: "boolean_true"
name: "--sizeD"
description: "Sort by feature size in descending order."
info: null
direction: "input"
- type: "boolean_true"
name: "--chrThenSizeA"
description: "Sort by chrom (asc), then feature size (asc)."
info: null
direction: "input"
- type: "boolean_true"
name: "--chrThenSizeD"
description: "Sort by chrom (asc), then feature size (desc)."
info: null
direction: "input"
- type: "boolean_true"
name: "--chrThenScoreA"
description: "Sort by chrom (asc), then score (asc)."
info: null
direction: "input"
- type: "boolean_true"
name: "--chrThenScoreD"
description: "Sort by chrom (asc), then score (desc)."
info: null
direction: "input"
- type: "file"
name: "--genome"
alternatives:
- "-g"
description: "Sort according to the chromosomes declared in \"genome.txt\""
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--faidx"
description: "Sort according to the chromosomes declared in \"names.txt\""
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean_true"
name: "--header"
description: "Print the header from the A file prior to results."
info: null
direction: "input"
resources:
- type: "bash_script"
path: "script.sh"
is_executable: true
description: "Sorts a feature file (bed/gff/vcf) by chromosome and other criteria."
test_resources:
- type: "bash_script"
path: "test.sh"
is_executable: true
info: null
status: "enabled"
requirements:
commands:
- "ps"
keywords:
- "sort"
- "BED"
- "GFF"
- "VCF"
license: "GPL-2.0, MIT"
references:
doi:
- "10.1093/bioinformatics/btq033"
links:
repository: "https://github.com/arq5x/bedtools2"
documentation: "https://bedtools.readthedocs.io/en/latest/content/tools/sort.html"
runners:
- type: "executable"
id: "executable"
docker_setup_strategy: "ifneedbepullelsecachedbuild"
- type: "nextflow"
id: "nextflow"
directives:
tag: "$id"
auto:
simplifyInput: true
simplifyOutput: false
transcript: false
publish: false
config:
labels:
mem1gb: "memory = 1000000000.B"
mem2gb: "memory = 2000000000.B"
mem5gb: "memory = 5000000000.B"
mem10gb: "memory = 10000000000.B"
mem20gb: "memory = 20000000000.B"
mem50gb: "memory = 50000000000.B"
mem100gb: "memory = 100000000000.B"
mem200gb: "memory = 200000000000.B"
mem500gb: "memory = 500000000000.B"
mem1tb: "memory = 1000000000000.B"
mem2tb: "memory = 2000000000000.B"
mem5tb: "memory = 5000000000000.B"
mem10tb: "memory = 10000000000000.B"
mem20tb: "memory = 20000000000000.B"
mem50tb: "memory = 50000000000000.B"
mem100tb: "memory = 100000000000000.B"
mem200tb: "memory = 200000000000000.B"
mem500tb: "memory = 500000000000000.B"
mem1gib: "memory = 1073741824.B"
mem2gib: "memory = 2147483648.B"
mem4gib: "memory = 4294967296.B"
mem8gib: "memory = 8589934592.B"
mem16gib: "memory = 17179869184.B"
mem32gib: "memory = 34359738368.B"
mem64gib: "memory = 68719476736.B"
mem128gib: "memory = 137438953472.B"
mem256gib: "memory = 274877906944.B"
mem512gib: "memory = 549755813888.B"
mem1tib: "memory = 1099511627776.B"
mem2tib: "memory = 2199023255552.B"
mem4tib: "memory = 4398046511104.B"
mem8tib: "memory = 8796093022208.B"
mem16tib: "memory = 17592186044416.B"
mem32tib: "memory = 35184372088832.B"
mem64tib: "memory = 70368744177664.B"
mem128tib: "memory = 140737488355328.B"
mem256tib: "memory = 281474976710656.B"
mem512tib: "memory = 562949953421312.B"
cpu1: "cpus = 1"
cpu2: "cpus = 2"
cpu5: "cpus = 5"
cpu10: "cpus = 10"
cpu20: "cpus = 20"
cpu50: "cpus = 50"
cpu100: "cpus = 100"
cpu200: "cpus = 200"
cpu500: "cpus = 500"
cpu1000: "cpus = 1000"
debug: false
container: "docker"
engines:
- type: "docker"
id: "docker"
image: "debian:stable-slim"
target_registry: "images.viash-hub.com"
target_tag: "v0.2"
namespace_separator: "/"
setup:
- type: "apt"
packages:
- "bedtools"
- "procps"
interactive: false
- type: "docker"
run:
- "echo \"bedtools: \\\"$(bedtools --version | sed -n 's/^bedtools //p')\\\"\"\
\ > /var/software_versions.txt\n"
entrypoint: []
cmd: null
- type: "native"
id: "native"
build_info:
config: "src/bedtools/bedtools_sort/config.vsh.yaml"
runner: "executable"
engine: "docker|native"
output: "target/executable/bedtools/bedtools_sort"
executable: "target/executable/bedtools/bedtools_sort/bedtools_sort"
viash_version: "0.9.0-RC7"
git_commit: "f22ab0eab58dcd6bff89d8d73fe951953ff1260f"
git_remote: "https://github.com/viash-hub/biobox"
package_config:
name: "biobox"
version: "v0.2"
description: "A collection of bioinformatics tools for working with sequence data.\n"
info: null
viash_version: "0.9.0-RC7"
source: "src"
target: "target"
config_mods:
- ".requirements.commands := ['ps']\n"
- ".engines += { type: \"native\" }"
- ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
- ".engines[.type == 'docker'].target_tag := 'v0.2'"
keywords:
- "bioinformatics"
- "modules"
- "sequencing"
license: "MIT"
organization: "vsh"
links:
repository: "https://github.com/viash-hub/biobox"
issue_tracker: "https://github.com/viash-hub/biobox/issues"

1315
target/executable/bedtools/bedtools_sort/bedtools_sort Executable file
View File

File diff suppressed because it is too large Load Diff

184
target/executable/busco/busco_download_datasets/.config.vsh.yaml Normal file
View File

@@ -0,0 +1,184 @@
name: "busco_download_datasets"
namespace: "busco"
version: "v0.2"
authors:
- name: "Dorien Roosen"
roles:
- "author"
- "maintainer"
info:
links:
email: "dorien@data-intuitive.com"
github: "dorien-er"
linkedin: "dorien-roosen"
organizations:
- name: "Data Intuitive"
href: "https://www.data-intuitive.com"
role: "Data Scientist"
argument_groups:
- name: "Inputs"
arguments:
- type: "string"
name: "--download"
description: "Download dataset. Possible values are a specific dataset name, \"\
all\", \"prokaryota\", \"eukaryota\", or \"virus\".\nThe full list of available\
\ datasets can be viewed [here](https://busco-data.ezlab.org/v5/data/lineages/)\
\ or by running the busco/busco_list_datasets component.\n"
info: null
example:
- "stramenopiles_odb10"
required: true
direction: "input"
multiple: false
multiple_sep: ";"
- name: "Outputs"
arguments:
- type: "file"
name: "--download_path"
description: "Local filepath for storing BUSCO dataset downloads\n"
info: null
example:
- "busco_downloads"
default:
- "busco_downloads"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
resources:
- type: "bash_script"
path: "script.sh"
is_executable: true
description: "Downloads available busco datasets"
test_resources:
- type: "bash_script"
path: "test.sh"
is_executable: true
info: null
status: "enabled"
requirements:
commands:
- "ps"
keywords:
- "lineage datasets"
license: "MIT"
references:
doi:
- "10.1007/978-1-4939-9173-0_14"
links:
repository: "https://gitlab.com/ezlab/busco"
homepage: "https://busco.ezlab.org/"
documentation: "https://busco.ezlab.org/busco_userguide.html"
runners:
- type: "executable"
id: "executable"
docker_setup_strategy: "ifneedbepullelsecachedbuild"
- type: "nextflow"
id: "nextflow"
directives:
tag: "$id"
auto:
simplifyInput: true
simplifyOutput: false
transcript: false
publish: false
config:
labels:
mem1gb: "memory = 1000000000.B"
mem2gb: "memory = 2000000000.B"
mem5gb: "memory = 5000000000.B"
mem10gb: "memory = 10000000000.B"
mem20gb: "memory = 20000000000.B"
mem50gb: "memory = 50000000000.B"
mem100gb: "memory = 100000000000.B"
mem200gb: "memory = 200000000000.B"
mem500gb: "memory = 500000000000.B"
mem1tb: "memory = 1000000000000.B"
mem2tb: "memory = 2000000000000.B"
mem5tb: "memory = 5000000000000.B"
mem10tb: "memory = 10000000000000.B"
mem20tb: "memory = 20000000000000.B"
mem50tb: "memory = 50000000000000.B"
mem100tb: "memory = 100000000000000.B"
mem200tb: "memory = 200000000000000.B"
mem500tb: "memory = 500000000000000.B"
mem1gib: "memory = 1073741824.B"
mem2gib: "memory = 2147483648.B"
mem4gib: "memory = 4294967296.B"
mem8gib: "memory = 8589934592.B"
mem16gib: "memory = 17179869184.B"
mem32gib: "memory = 34359738368.B"
mem64gib: "memory = 68719476736.B"
mem128gib: "memory = 137438953472.B"
mem256gib: "memory = 274877906944.B"
mem512gib: "memory = 549755813888.B"
mem1tib: "memory = 1099511627776.B"
mem2tib: "memory = 2199023255552.B"
mem4tib: "memory = 4398046511104.B"
mem8tib: "memory = 8796093022208.B"
mem16tib: "memory = 17592186044416.B"
mem32tib: "memory = 35184372088832.B"
mem64tib: "memory = 70368744177664.B"
mem128tib: "memory = 140737488355328.B"
mem256tib: "memory = 281474976710656.B"
mem512tib: "memory = 562949953421312.B"
cpu1: "cpus = 1"
cpu2: "cpus = 2"
cpu5: "cpus = 5"
cpu10: "cpus = 10"
cpu20: "cpus = 20"
cpu50: "cpus = 50"
cpu100: "cpus = 100"
cpu200: "cpus = 200"
cpu500: "cpus = 500"
cpu1000: "cpus = 1000"
debug: false
container: "docker"
engines:
- type: "docker"
id: "docker"
image: "quay.io/biocontainers/busco:5.7.1--pyhdfd78af_0"
target_registry: "images.viash-hub.com"
target_tag: "v0.2"
namespace_separator: "/"
setup:
- type: "docker"
run:
- "busco --version | sed 's/BUSCO\\s\\(.*\\)/busco: \"\\1\"/' > /var/software_versions.txt\n"
entrypoint: []
cmd: null
- type: "native"
id: "native"
build_info:
config: "src/busco/busco_download_datasets/config.vsh.yaml"
runner: "executable"
engine: "docker|native"
output: "target/executable/busco/busco_download_datasets"
executable: "target/executable/busco/busco_download_datasets/busco_download_datasets"
viash_version: "0.9.0-RC7"
git_commit: "f22ab0eab58dcd6bff89d8d73fe951953ff1260f"
git_remote: "https://github.com/viash-hub/biobox"
package_config:
name: "biobox"
version: "v0.2"
description: "A collection of bioinformatics tools for working with sequence data.\n"
info: null
viash_version: "0.9.0-RC7"
source: "src"
target: "target"
config_mods:
- ".requirements.commands := ['ps']\n"
- ".engines += { type: \"native\" }"
- ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
- ".engines[.type == 'docker'].target_tag := 'v0.2'"
keywords:
- "bioinformatics"
- "modules"
- "sequencing"
license: "MIT"
organization: "vsh"
links:
repository: "https://github.com/viash-hub/biobox"
issue_tracker: "https://github.com/viash-hub/biobox/issues"

1082
target/executable/busco/busco_download_datasets/busco_download_datasets Executable file
View File

File diff suppressed because it is too large Load Diff

171
target/executable/busco/busco_list_datasets/.config.vsh.yaml Normal file
View File

@@ -0,0 +1,171 @@
name: "busco_list_datasets"
namespace: "busco"
version: "v0.2"
authors:
- name: "Dorien Roosen"
roles:
- "author"
- "maintainer"
info:
links:
email: "dorien@data-intuitive.com"
github: "dorien-er"
linkedin: "dorien-roosen"
organizations:
- name: "Data Intuitive"
href: "https://www.data-intuitive.com"
role: "Data Scientist"
argument_groups:
- name: "Outputs"
arguments:
- type: "file"
name: "--output"
alternatives:
- "-o"
description: "Output file of the available busco datasets\n"
info: null
example:
- "file.txt"
default:
- "busco_dataset_list.txt"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
resources:
- type: "bash_script"
path: "script.sh"
is_executable: true
description: "Lists the available busco datasets"
test_resources:
- type: "bash_script"
path: "test.sh"
is_executable: true
info: null
status: "enabled"
requirements:
commands:
- "ps"
keywords:
- "lineage datasets"
license: "MIT"
references:
doi:
- "10.1007/978-1-4939-9173-0_14"
links:
repository: "https://gitlab.com/ezlab/busco"
homepage: "https://busco.ezlab.org/"
documentation: "https://busco.ezlab.org/busco_userguide.html"
runners:
- type: "executable"
id: "executable"
docker_setup_strategy: "ifneedbepullelsecachedbuild"
- type: "nextflow"
id: "nextflow"
directives:
tag: "$id"
auto:
simplifyInput: true
simplifyOutput: false
transcript: false
publish: false
config:
labels:
mem1gb: "memory = 1000000000.B"
mem2gb: "memory = 2000000000.B"
mem5gb: "memory = 5000000000.B"
mem10gb: "memory = 10000000000.B"
mem20gb: "memory = 20000000000.B"
mem50gb: "memory = 50000000000.B"
mem100gb: "memory = 100000000000.B"
mem200gb: "memory = 200000000000.B"
mem500gb: "memory = 500000000000.B"
mem1tb: "memory = 1000000000000.B"
mem2tb: "memory = 2000000000000.B"
mem5tb: "memory = 5000000000000.B"
mem10tb: "memory = 10000000000000.B"
mem20tb: "memory = 20000000000000.B"
mem50tb: "memory = 50000000000000.B"
mem100tb: "memory = 100000000000000.B"
mem200tb: "memory = 200000000000000.B"
mem500tb: "memory = 500000000000000.B"
mem1gib: "memory = 1073741824.B"
mem2gib: "memory = 2147483648.B"
mem4gib: "memory = 4294967296.B"
mem8gib: "memory = 8589934592.B"
mem16gib: "memory = 17179869184.B"
mem32gib: "memory = 34359738368.B"
mem64gib: "memory = 68719476736.B"
mem128gib: "memory = 137438953472.B"
mem256gib: "memory = 274877906944.B"
mem512gib: "memory = 549755813888.B"
mem1tib: "memory = 1099511627776.B"
mem2tib: "memory = 2199023255552.B"
mem4tib: "memory = 4398046511104.B"
mem8tib: "memory = 8796093022208.B"
mem16tib: "memory = 17592186044416.B"
mem32tib: "memory = 35184372088832.B"
mem64tib: "memory = 70368744177664.B"
mem128tib: "memory = 140737488355328.B"
mem256tib: "memory = 281474976710656.B"
mem512tib: "memory = 562949953421312.B"
cpu1: "cpus = 1"
cpu2: "cpus = 2"
cpu5: "cpus = 5"
cpu10: "cpus = 10"
cpu20: "cpus = 20"
cpu50: "cpus = 50"
cpu100: "cpus = 100"
cpu200: "cpus = 200"
cpu500: "cpus = 500"
cpu1000: "cpus = 1000"
debug: false
container: "docker"
engines:
- type: "docker"
id: "docker"
image: "quay.io/biocontainers/busco:5.7.1--pyhdfd78af_0"
target_registry: "images.viash-hub.com"
target_tag: "v0.2"
namespace_separator: "/"
setup:
- type: "docker"
run:
- "busco --version | sed 's/BUSCO\\s\\(.*\\)/busco: \"\\1\"/' > /var/software_versions.txt\n"
entrypoint: []
cmd: null
- type: "native"
id: "native"
build_info:
config: "src/busco/busco_list_datasets/config.vsh.yaml"
runner: "executable"
engine: "docker|native"
output: "target/executable/busco/busco_list_datasets"
executable: "target/executable/busco/busco_list_datasets/busco_list_datasets"
viash_version: "0.9.0-RC7"
git_commit: "f22ab0eab58dcd6bff89d8d73fe951953ff1260f"
git_remote: "https://github.com/viash-hub/biobox"
package_config:
name: "biobox"
version: "v0.2"
description: "A collection of bioinformatics tools for working with sequence data.\n"
info: null
viash_version: "0.9.0-RC7"
source: "src"
target: "target"
config_mods:
- ".requirements.commands := ['ps']\n"
- ".engines += { type: \"native\" }"
- ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
- ".engines[.type == 'docker'].target_tag := 'v0.2'"
keywords:
- "bioinformatics"
- "modules"
- "sequencing"
license: "MIT"
organization: "vsh"
links:
repository: "https://github.com/viash-hub/biobox"
issue_tracker: "https://github.com/viash-hub/biobox/issues"

1054
target/executable/busco/busco_list_datasets/busco_list_datasets Executable file
View File

File diff suppressed because it is too large Load Diff

449
target/executable/busco/busco_run/.config.vsh.yaml Normal file
View File

@@ -0,0 +1,449 @@
name: "busco_run"
namespace: "busco"
version: "v0.2"
authors:
- name: "Dorien Roosen"
roles:
- "author"
- "maintainer"
info:
links:
email: "dorien@data-intuitive.com"
github: "dorien-er"
linkedin: "dorien-roosen"
organizations:
- name: "Data Intuitive"
href: "https://www.data-intuitive.com"
role: "Data Scientist"
argument_groups:
- name: "Inputs"
arguments:
- type: "file"
name: "--input"
alternatives:
- "-i"
description: "Input sequence file in FASTA format. Can be an assembled genome\
\ or transcriptome (DNA), or protein sequences from an annotated gene set. Also\
\ possible to use a path to a directory containing multiple input files.\n"
info: null
example:
- "file.fasta"
must_exist: true
create_parent: true
required: true
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--mode"
alternatives:
- "-m"
description: "Specify which BUSCO analysis mode to run. There are three valid\
\ modes:\n - geno or genome, for genome assemblies (DNA)\n - tran or transcriptome,\
\ for transcriptome assemblies (DNA)\n - prot or proteins, for annotated gene\
\ sets (protein)\n"
info: null
example:
- "proteins"
required: true
choices:
- "genome"
- "geno"
- "transcriptome"
- "tran"
- "proteins"
- "prot"
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--lineage_dataset"
alternatives:
- "-l"
description: "Specify a BUSCO lineage dataset that is most closely related to\
\ the assembly or gene set being assessed. \nThe full list of available datasets\
\ can be viewed [here](https://busco-data.ezlab.org/v5/data/lineages/) or by\
\ running the busco/busco_list_datasets component.\nWhen unsure, the \"--auto_lineage\"\
\ flag can be set to automatically find the optimal lineage path.\nBUSCO will\
\ automatically download the requested dataset if it is not already present\
\ in the download folder. \nYou can optionally provide a path to a local dataset\
\ instead of a name, e.g. path/to/dataset.\nDatasets can be downloaded using\
\ the busco/busco_download_dataset component.\n"
info: null
example:
- "stramenopiles_odb10"
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- name: "Outputs"
arguments:
- type: "file"
name: "--short_summary_json"
description: "Output file for short summary in JSON format.\n"
info: null
example:
- "short_summary.json"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--short_summary_txt"
description: "Output file for short summary in TXT format.\n"
info: null
example:
- "short_summary.txt"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--full_table"
description: "Full table output in TSV format.\n"
info: null
example:
- "full_table.tsv"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--missing_busco_list"
description: "Missing list output in TSV format.\n"
info: null
example:
- "missing_busco_list.tsv"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--output_dir"
description: "The full output directory, if so desired.\n"
info: null
example:
- "output_dir"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- name: "Resource and Run Settings"
arguments:
- type: "boolean_true"
name: "--force"
description: "Force rewriting of existing files. Must be used when output files\
\ with the provided name already exist.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--quiet"
alternatives:
- "-q"
description: "Disable the info logs, displays only errors.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--restart"
alternatives:
- "-r"
description: "Continue a run that had already partially completed. Restarting\
\ skips calls to tools that have completed but performs all pre- and post-processing\
\ steps.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--tar"
description: "Compress some subdirectories with many files to save space.\n"
info: null
direction: "input"
- name: "Lineage Dataset Settings"
arguments:
- type: "boolean_true"
name: "--auto_lineage"
description: "Run auto-lineage pipelilne to automatically determine BUSCO lineage\
\ dataset that is most closely related to the assembly or gene set being assessed.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--auto_lineage_euk"
description: "Run auto-placement just on eukaryota tree to find optimal lineage\
\ path.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--auto_lineage_prok"
description: "Run auto_lineage just on prokaryota trees to find optimum lineage\
\ path.\n"
info: null
direction: "input"
- type: "string"
name: "--datasets_version"
description: "Specify the version of BUSCO datasets\n"
info: null
example:
- "odb10"
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- name: "Augustus Settings"
arguments:
- type: "boolean_true"
name: "--augustus"
description: "Use augustus gene predictor for eukaryote runs.\n"
info: null
direction: "input"
- type: "string"
name: "--augustus_parameters"
description: "Additional parameters to be passed to Augustus (see Augustus documentation:\
\ https://github.com/Gaius-Augustus/Augustus/blob/master/docs/RUNNING-AUGUSTUS.md).\n\
Parameters should be contained within a single string, without whitespace and\
\ seperated by commas.\n"
info: null
example:
- "--PARAM1=VALUE1,--PARAM2=VALUE2"
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--augustus_species"
description: "Specify the augustus species\n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean_true"
name: "--long"
description: "Optimize Augustus self-training mode. This adds considerably to\
\ the run time, but can improve results for some non-model organisms.\n"
info: null
direction: "input"
- name: "BBTools Settings"
arguments:
- type: "integer"
name: "--contig_break"
description: "Number of contiguous Ns to signify a break between contigs in BBTools\
\ analysis.\n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--limit"
description: "Number of candidate regions (contig or transcript) from the BLAST\
\ output to consider per BUSCO.\nThis option is only effective in pipelines\
\ using BLAST, i.e. the genome pipeline (see --augustus) or the prokaryota transcriptome\
\ pipeline.\n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean_true"
name: "--scaffold_composition"
description: "Writes ACGTN content per scaffold to a file scaffold_composition.txt.\n"
info: null
direction: "input"
- name: "BLAST Settings"
arguments:
- type: "double"
name: "--e_value"
description: "E-value cutoff for BLAST searches.\n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- name: "Protein Gene Prediction settings"
arguments:
- type: "boolean_true"
name: "--miniprot"
description: "Use Miniprot gene predictor.\n"
info: null
direction: "input"
- name: "MetaEuk Settings"
arguments:
- type: "boolean_true"
name: "--metaeuk"
description: "Use Metaeuk gene predictor.\n"
info: null
direction: "input"
- type: "string"
name: "--metaeuk_parameters"
description: "Pass additional arguments to Metaeuk for the first run (see Metaeuk\
\ documentation https://github.com/soedinglab/metaeuk).\nAll parameters should\
\ be contained within a single string with no white space, with each parameter\
\ separated by a comma.\n"
info: null
example:
- "--max-overlap=15,--min-exon-aa=15"
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--metaeuk_rerun_parameters"
description: "Pass additional arguments to Metaeuk for the second run (see Metaeuk\
\ documentation https://github.com/soedinglab/metaeuk).\nAll parameters should\
\ be contained within a single string with no white space, with each parameter\
\ separated by a comma.\n"
info: null
example:
- "--max-overlap=15,--min-exon-aa=15"
required: false
direction: "input"
multiple: false
multiple_sep: ";"
resources:
- type: "bash_script"
path: "script.sh"
is_executable: true
description: "Assessment of genome assembly and annotation completeness with single\
\ copy orthologs"
test_resources:
- type: "bash_script"
path: "test.sh"
is_executable: true
- type: "file"
path: "test_data"
info: null
status: "enabled"
requirements:
commands:
- "ps"
keywords:
- "Genome assembly"
- "quality control"
license: "MIT"
references:
doi:
- "10.1007/978-1-4939-9173-0_14"
links:
repository: "https://gitlab.com/ezlab/busco"
homepage: "https://busco.ezlab.org/"
documentation: "https://busco.ezlab.org/busco_userguide.html"
runners:
- type: "executable"
id: "executable"
docker_setup_strategy: "ifneedbepullelsecachedbuild"
- type: "nextflow"
id: "nextflow"
directives:
tag: "$id"
auto:
simplifyInput: true
simplifyOutput: false
transcript: false
publish: false
config:
labels:
mem1gb: "memory = 1000000000.B"
mem2gb: "memory = 2000000000.B"
mem5gb: "memory = 5000000000.B"
mem10gb: "memory = 10000000000.B"
mem20gb: "memory = 20000000000.B"
mem50gb: "memory = 50000000000.B"
mem100gb: "memory = 100000000000.B"
mem200gb: "memory = 200000000000.B"
mem500gb: "memory = 500000000000.B"
mem1tb: "memory = 1000000000000.B"
mem2tb: "memory = 2000000000000.B"
mem5tb: "memory = 5000000000000.B"
mem10tb: "memory = 10000000000000.B"
mem20tb: "memory = 20000000000000.B"
mem50tb: "memory = 50000000000000.B"
mem100tb: "memory = 100000000000000.B"
mem200tb: "memory = 200000000000000.B"
mem500tb: "memory = 500000000000000.B"
mem1gib: "memory = 1073741824.B"
mem2gib: "memory = 2147483648.B"
mem4gib: "memory = 4294967296.B"
mem8gib: "memory = 8589934592.B"
mem16gib: "memory = 17179869184.B"
mem32gib: "memory = 34359738368.B"
mem64gib: "memory = 68719476736.B"
mem128gib: "memory = 137438953472.B"
mem256gib: "memory = 274877906944.B"
mem512gib: "memory = 549755813888.B"
mem1tib: "memory = 1099511627776.B"
mem2tib: "memory = 2199023255552.B"
mem4tib: "memory = 4398046511104.B"
mem8tib: "memory = 8796093022208.B"
mem16tib: "memory = 17592186044416.B"
mem32tib: "memory = 35184372088832.B"
mem64tib: "memory = 70368744177664.B"
mem128tib: "memory = 140737488355328.B"
mem256tib: "memory = 281474976710656.B"
mem512tib: "memory = 562949953421312.B"
cpu1: "cpus = 1"
cpu2: "cpus = 2"
cpu5: "cpus = 5"
cpu10: "cpus = 10"
cpu20: "cpus = 20"
cpu50: "cpus = 50"
cpu100: "cpus = 100"
cpu200: "cpus = 200"
cpu500: "cpus = 500"
cpu1000: "cpus = 1000"
debug: false
container: "docker"
engines:
- type: "docker"
id: "docker"
image: "quay.io/biocontainers/busco:5.7.1--pyhdfd78af_0"
target_registry: "images.viash-hub.com"
target_tag: "v0.2"
namespace_separator: "/"
setup:
- type: "docker"
run:
- "busco --version | sed 's/BUSCO\\s\\(.*\\)/busco: \"\\1\"/' > /var/software_versions.txt\n"
entrypoint: []
cmd: null
- type: "native"
id: "native"
build_info:
config: "src/busco/busco_run/config.vsh.yaml"
runner: "executable"
engine: "docker|native"
output: "target/executable/busco/busco_run"
executable: "target/executable/busco/busco_run/busco_run"
viash_version: "0.9.0-RC7"
git_commit: "f22ab0eab58dcd6bff89d8d73fe951953ff1260f"
git_remote: "https://github.com/viash-hub/biobox"
package_config:
name: "biobox"
version: "v0.2"
description: "A collection of bioinformatics tools for working with sequence data.\n"
info: null
viash_version: "0.9.0-RC7"
source: "src"
target: "target"
config_mods:
- ".requirements.commands := ['ps']\n"
- ".engines += { type: \"native\" }"
- ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
- ".engines[.type == 'docker'].target_tag := 'v0.2'"
keywords:
- "bioinformatics"
- "modules"
- "sequencing"
license: "MIT"
organization: "vsh"
links:
repository: "https://github.com/viash-hub/biobox"
issue_tracker: "https://github.com/viash-hub/biobox/issues"

1783
target/executable/busco/busco_run/busco_run Executable file
View File

File diff suppressed because it is too large Load Diff

766
target/executable/cutadapt/.config.vsh.yaml Normal file
View File

@@ -0,0 +1,766 @@
name: "cutadapt"
version: "v0.2"
authors:
- name: "Toni Verbeiren"
roles:
- "author"
- "maintainer"
info:
links:
github: "tverbeiren"
linkedin: "verbeiren"
organizations:
- name: "Data Intuitive"
href: "https://www.data-intuitive.com"
role: "Data Scientist and CEO"
argument_groups:
- name: "Specify Adapters for R1"
arguments:
- type: "string"
name: "--adapter"
alternatives:
- "-a"
description: "Sequence of an adapter ligated to the 3' end (paired data:\nof the\
\ first read). The adapter and subsequent bases are\ntrimmed. If a '$' character\
\ is appended ('anchoring'), the\nadapter is only found if it is a suffix of\
\ the read.\n"
info: null
required: false
direction: "input"
multiple: true
multiple_sep: ";"
- type: "string"
name: "--front"
alternatives:
- "-g"
description: "Sequence of an adapter ligated to the 5' end (paired data:\nof the\
\ first read). The adapter and any preceding bases\nare trimmed. Partial matches\
\ at the 5' end are allowed. If\na '^' character is prepended ('anchoring'),\
\ the adapter is\nonly found if it is a prefix of the read.\n"
info: null
required: false
direction: "input"
multiple: true
multiple_sep: ";"
- type: "string"
name: "--anywhere"
alternatives:
- "-b"
description: "Sequence of an adapter that may be ligated to the 5' or 3'\nend\
\ (paired data: of the first read). Both types of\nmatches as described under\
\ -a and -g are allowed. If the\nfirst base of the read is part of the match,\
\ the behavior\nis as with -g, otherwise as with -a. This option is mostly\n\
for rescuing failed library preparations - do not use if\nyou know which end\
\ your adapter was ligated to!\n"
info: null
required: false
direction: "input"
multiple: true
multiple_sep: ";"
- name: "Specify Adapters using Fasta files for R1"
arguments:
- type: "file"
name: "--adapter_fasta"
description: "Fasta file containing sequences of an adapter ligated to the 3'\
\ end (paired data:\nof the first read). The adapter and subsequent bases are\n\
trimmed. If a '$' character is appended ('anchoring'), the\nadapter is only\
\ found if it is a suffix of the read.\n"
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: true
multiple_sep: ";"
- type: "file"
name: "--front_fasta"
description: "Fasta file containing sequences of an adapter ligated to the 5'\
\ end (paired data:\nof the first read). The adapter and any preceding bases\n\
are trimmed. Partial matches at the 5' end are allowed. If\na '^' character\
\ is prepended ('anchoring'), the adapter is\nonly found if it is a prefix of\
\ the read.\n"
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--anywhere_fasta"
description: "Fasta file containing sequences of an adapter that may be ligated\
\ to the 5' or 3'\nend (paired data: of the first read). Both types of\nmatches\
\ as described under -a and -g are allowed. If the\nfirst base of the read is\
\ part of the match, the behavior\nis as with -g, otherwise as with -a. This\
\ option is mostly\nfor rescuing failed library preparations - do not use if\n\
you know which end your adapter was ligated to!\n"
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- name: "Specify Adapters for R2"
arguments:
- type: "string"
name: "--adapter_r2"
alternatives:
- "-A"
description: "Sequence of an adapter ligated to the 3' end (paired data:\nof the\
\ first read). The adapter and subsequent bases are\ntrimmed. If a '$' character\
\ is appended ('anchoring'), the\nadapter is only found if it is a suffix of\
\ the read.\n"
info: null
required: false
direction: "input"
multiple: true
multiple_sep: ";"
- type: "string"
name: "--front_r2"
alternatives:
- "-G"
description: "Sequence of an adapter ligated to the 5' end (paired data:\nof the\
\ first read). The adapter and any preceding bases\nare trimmed. Partial matches\
\ at the 5' end are allowed. If\na '^' character is prepended ('anchoring'),\
\ the adapter is\nonly found if it is a prefix of the read.\n"
info: null
required: false
direction: "input"
multiple: true
multiple_sep: ";"
- type: "string"
name: "--anywhere_r2"
alternatives:
- "-B"
description: "Sequence of an adapter that may be ligated to the 5' or 3'\nend\
\ (paired data: of the first read). Both types of\nmatches as described under\
\ -a and -g are allowed. If the\nfirst base of the read is part of the match,\
\ the behavior\nis as with -g, otherwise as with -a. This option is mostly\n\
for rescuing failed library preparations - do not use if\nyou know which end\
\ your adapter was ligated to!\n"
info: null
required: false
direction: "input"
multiple: true
multiple_sep: ";"
- name: "Specify Adapters using Fasta files for R2"
arguments:
- type: "file"
name: "--adapter_r2_fasta"
description: "Fasta file containing sequences of an adapter ligated to the 3'\
\ end (paired data:\nof the first read). The adapter and subsequent bases are\n\
trimmed. If a '$' character is appended ('anchoring'), the\nadapter is only\
\ found if it is a suffix of the read.\n"
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--front_r2_fasta"
description: "Fasta file containing sequences of an adapter ligated to the 5'\
\ end (paired data:\nof the first read). The adapter and any preceding bases\n\
are trimmed. Partial matches at the 5' end are allowed. If\na '^' character\
\ is prepended ('anchoring'), the adapter is\nonly found if it is a prefix of\
\ the read.\n"
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--anywhere_r2_fasta"
description: "Fasta file containing sequences of an adapter that may be ligated\
\ to the 5' or 3'\nend (paired data: of the first read). Both types of\nmatches\
\ as described under -a and -g are allowed. If the\nfirst base of the read is\
\ part of the match, the behavior\nis as with -g, otherwise as with -a. This\
\ option is mostly\nfor rescuing failed library preparations - do not use if\n\
you know which end your adapter was ligated to!\n"
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- name: "Paired-end options"
arguments:
- type: "boolean_true"
name: "--pair_adapters"
description: "Treat adapters given with -a/-A etc. as pairs. Either both\nor none\
\ are removed from each read pair.\n"
info: null
direction: "input"
- type: "string"
name: "--pair_filter"
description: "Which of the reads in a paired-end read have to match the\nfiltering\
\ criterion in order for the pair to be filtered.\n"
info: null
required: false
choices:
- "any"
- "both"
- "first"
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean_true"
name: "--interleaved"
description: "Read and/or write interleaved paired-end reads.\n"
info: null
direction: "input"
- name: "Input parameters"
arguments:
- type: "file"
name: "--input"
description: "Input fastq file for single-end reads or R1 for paired-end reads.\n"
info: null
must_exist: true
create_parent: true
required: true
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--input_r2"
description: "Input fastq file for R2 in the case of paired-end reads.\n"
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "double"
name: "--error_rate"
alternatives:
- "-E"
- "--errors"
description: "Maximum allowed error rate (if 0 <= E < 1), or absolute\nnumber\
\ of errors for full-length adapter match (if E is an\ninteger >= 1). Error\
\ rate = no. of errors divided by\nlength of matching region. Default: 0.1 (10%).\n"
info: null
example:
- 0.1
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean_false"
name: "--no_indels"
description: "Allow only mismatches in alignments.\n"
info: null
direction: "input"
- type: "integer"
name: "--times"
alternatives:
- "-n"
description: "Remove up to COUNT adapters from each read. Default: 1.\n"
info: null
example:
- 1
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--overlap"
alternatives:
- "-O"
description: "Require MINLENGTH overlap between read and adapter for an\nadapter\
\ to be found. The default is 3.\n"
info: null
example:
- 3
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean_true"
name: "--match_read_wildcards"
description: "Interpret IUPAC wildcards in reads.\n"
info: null
direction: "input"
- type: "boolean_false"
name: "--no_match_adapter_wildcards"
description: "Do not interpret IUPAC wildcards in adapters.\n"
info: null
direction: "input"
- type: "string"
name: "--action"
description: "What to do if a match was found. trim: trim adapter and\nup- or\
\ downstream sequence; retain: trim, but retain\nadapter; mask: replace with\
\ 'N' characters; lowercase:\nconvert to lowercase; none: leave unchanged.\n\
The default is trim.\n"
info: null
example:
- "trim"
required: false
choices:
- "trim"
- "retain"
- "mask"
- "lowercase"
- "none"
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean_true"
name: "--revcomp"
alternatives:
- "--rc"
description: "Check both the read and its reverse complement for adapter\nmatches.\
\ If match is on reverse-complemented version,\noutput that one.\n"
info: null
direction: "input"
- name: "Demultiplexing options"
arguments:
- type: "string"
name: "--demultiplex_mode"
description: "Enable demultiplexing and set the mode for it.\nWith mode 'unique_dual',\
\ adapters from the first and second read are used,\nand the indexes from the\
\ reads are only used in pairs. This implies\n--pair_adapters.\nEnabling mode\
\ 'combinatorial_dual' allows all combinations of the sets of indexes\non R1\
\ and R2. It is necessary to write each read pair to an output\nfile depending\
\ on the adapters found on both R1 and R2.\nMode 'single', uses indexes or barcodes\
\ located at the 5'\nend of the R1 read (single). \n"
info: null
required: false
choices:
- "single"
- "unique_dual"
- "combinatorial_dual"
direction: "input"
multiple: false
multiple_sep: ";"
- name: "Read modifications"
arguments:
- type: "integer"
name: "--cut"
alternatives:
- "-u"
description: "Remove LEN bases from each read (or R1 if paired; use --cut_r2\n\
option for R2). If LEN is positive, remove bases from the\nbeginning. If LEN\
\ is negative, remove bases from the end.\nCan be used twice if LENs have different\
\ signs. Applied\n*before* adapter trimming.\n"
info: null
required: false
direction: "input"
multiple: true
multiple_sep: ";"
- type: "integer"
name: "--cut_r2"
description: "Remove LEN bases from each read (for R2). If LEN is positive, remove\
\ bases from the\nbeginning. If LEN is negative, remove bases from the end.\n\
Can be used twice if LENs have different signs. Applied\n*before* adapter trimming.\n"
info: null
required: false
direction: "input"
multiple: true
multiple_sep: ";"
- type: "string"
name: "--nextseq_trim"
description: "NextSeq-specific quality trimming (each read). Trims also\ndark\
\ cycles appearing as high-quality G bases.\n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--quality_cutoff"
alternatives:
- "-q"
description: "Trim low-quality bases from 5' and/or 3' ends of each read\nbefore\
\ adapter removal. Applied to both reads if data is\npaired. If one value is\
\ given, only the 3' end is trimmed.\nIf two comma-separated cutoffs are given,\
\ the 5' end is\ntrimmed with the first cutoff, the 3' end with the second.\n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--quality_cutoff_r2"
alternatives:
- "-Q"
description: "Quality-trimming cutoff for R2. Default: same as for R1\n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--quality_base"
description: "Assume that quality values in FASTQ are encoded as\nascii(quality\
\ + N). This needs to be set to 64 for some\nold Illumina FASTQ files. The default\
\ is 33.\n"
info: null
example:
- 33
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean_true"
name: "--poly_a"
description: "Trim poly-A tails"
info: null
direction: "input"
- type: "integer"
name: "--length"
alternatives:
- "-l"
description: "Shorten reads to LENGTH. Positive values remove bases at\nthe end\
\ while negative ones remove bases at the beginning.\nThis and the following\
\ modifications are applied after\nadapter trimming.\n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean_true"
name: "--trim_n"
description: "Trim N's on ends of reads."
info: null
direction: "input"
- type: "string"
name: "--length_tag"
description: "Search for TAG followed by a decimal number in the\ndescription\
\ field of the read. Replace the decimal number\nwith the correct length of\
\ the trimmed read. For example,\nuse --length-tag 'length=' to correct fields\
\ like\n'length=123'.\n"
info: null
example:
- "length="
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--strip_suffix"
description: "Remove this suffix from read names if present. Can be\ngiven multiple\
\ times.\n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--prefix"
alternatives:
- "-x"
description: "Add this prefix to read names. Use {name} to insert the\nname of\
\ the matching adapter.\n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--suffix"
alternatives:
- "-y"
description: "Add this suffix to read names; can also include {name}\n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--rename"
description: "Rename reads using TEMPLATE containing variables such as\n{id},\
\ {adapter_name} etc. (see documentation)\n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean_true"
name: "--zero_cap"
alternatives:
- "-z"
description: "Change negative quality values to zero."
info: null
direction: "input"
- name: "Filtering of processed reads"
description: "Filters are applied after above read modifications. Paired-end reads\
\ are\nalways discarded pairwise (see also --pair_filter).\n"
arguments:
- type: "string"
name: "--minimum_length"
alternatives:
- "-m"
description: "Discard reads shorter than LEN. Default is 0.\nWhen trimming paired-end\
\ reads, the minimum lengths for R1 and R2 can be specified separately by separating\
\ them with a colon (:).\nIf the colon syntax is not used, the same minimum\
\ length applies to both reads, as discussed above.\nAlso, one of the values\
\ can be omitted to impose no restrictions.\nFor example, with -m 17:, the length\
\ of R1 must be at least 17, but the length of R2 is ignored.\n"
info: null
example:
- "0"
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--maximum_length"
alternatives:
- "-M"
description: "Discard reads longer than LEN. Default: no limit.\nFor paired reads,\
\ see the remark for --minimum_length\n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--max_n"
description: "Discard reads with more than COUNT 'N' bases. If COUNT is\na number\
\ between 0 and 1, it is interpreted as a fraction\nof the read length.\n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "long"
name: "--max_expected_errors"
alternatives:
- "--max_ee"
description: "Discard reads whose expected number of errors (computed\nfrom quality\
\ values) exceeds ERRORS.\n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "long"
name: "--max_average_error_rate"
alternatives:
- "--max_aer"
description: "as --max_expected_errors (see above), but divided by\nlength to\
\ account for reads of varying length.\n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean_true"
name: "--discard_trimmed"
alternatives:
- "--discard"
description: "Discard reads that contain an adapter. Use also -O to\navoid discarding\
\ too many randomly matching reads.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--discard_untrimmed"
alternatives:
- "--trimmed_only"
description: "Discard reads that do not contain an adapter.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--discard_casava"
description: "Discard reads that did not pass CASAVA filtering (header\nhas :Y:).\n"
info: null
direction: "input"
- name: "Output parameters"
arguments:
- type: "string"
name: "--report"
description: "Which type of report to print: 'full' (default) or 'minimal'.\n"
info: null
example:
- "full"
required: false
choices:
- "full"
- "minimal"
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean_true"
name: "--json"
description: "Write report in JSON format to this file.\n"
info: null
direction: "input"
- type: "file"
name: "--output"
description: "Glob pattern for matching the expected output files.\nShould include\
\ `$output_dir`.\n"
info: null
example:
- "fastq/*_001.fast[a,q]"
must_exist: true
create_parent: true
required: true
direction: "output"
multiple: true
multiple_sep: ";"
- type: "boolean_true"
name: "--fasta"
description: "Output FASTA to standard output even on FASTQ input.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--info_file"
description: "Write information about each read and its adapter matches\ninto\
\ info.txt in the output directory.\nSee the documentation for the file format.\n"
info: null
direction: "input"
- name: "Debug"
arguments:
- type: "boolean_true"
name: "--debug"
description: "Print debug information"
info: null
direction: "input"
resources:
- type: "bash_script"
path: "script.sh"
is_executable: true
description: "Cutadapt removes adapter sequences from high-throughput sequencing reads.\n"
test_resources:
- type: "bash_script"
path: "test.sh"
is_executable: true
info: null
status: "enabled"
requirements:
commands:
- "ps"
keywords:
- "RNA-seq"
- "scRNA-seq"
- "high-throughput"
license: "MIT"
references:
doi:
- "10.14806/ej.17.1.200"
links:
repository: "https://github.com/marcelm/cutadapt"
homepage: "https://cutadapt.readthedocs.io"
documentation: "https://cutadapt.readthedocs.io"
runners:
- type: "executable"
id: "executable"
docker_setup_strategy: "ifneedbepullelsecachedbuild"
- type: "nextflow"
id: "nextflow"
directives:
tag: "$id"
auto:
simplifyInput: true
simplifyOutput: false
transcript: false
publish: false
config:
labels:
mem1gb: "memory = 1000000000.B"
mem2gb: "memory = 2000000000.B"
mem5gb: "memory = 5000000000.B"
mem10gb: "memory = 10000000000.B"
mem20gb: "memory = 20000000000.B"
mem50gb: "memory = 50000000000.B"
mem100gb: "memory = 100000000000.B"
mem200gb: "memory = 200000000000.B"
mem500gb: "memory = 500000000000.B"
mem1tb: "memory = 1000000000000.B"
mem2tb: "memory = 2000000000000.B"
mem5tb: "memory = 5000000000000.B"
mem10tb: "memory = 10000000000000.B"
mem20tb: "memory = 20000000000000.B"
mem50tb: "memory = 50000000000000.B"
mem100tb: "memory = 100000000000000.B"
mem200tb: "memory = 200000000000000.B"
mem500tb: "memory = 500000000000000.B"
mem1gib: "memory = 1073741824.B"
mem2gib: "memory = 2147483648.B"
mem4gib: "memory = 4294967296.B"
mem8gib: "memory = 8589934592.B"
mem16gib: "memory = 17179869184.B"
mem32gib: "memory = 34359738368.B"
mem64gib: "memory = 68719476736.B"
mem128gib: "memory = 137438953472.B"
mem256gib: "memory = 274877906944.B"
mem512gib: "memory = 549755813888.B"
mem1tib: "memory = 1099511627776.B"
mem2tib: "memory = 2199023255552.B"
mem4tib: "memory = 4398046511104.B"
mem8tib: "memory = 8796093022208.B"
mem16tib: "memory = 17592186044416.B"
mem32tib: "memory = 35184372088832.B"
mem64tib: "memory = 70368744177664.B"
mem128tib: "memory = 140737488355328.B"
mem256tib: "memory = 281474976710656.B"
mem512tib: "memory = 562949953421312.B"
cpu1: "cpus = 1"
cpu2: "cpus = 2"
cpu5: "cpus = 5"
cpu10: "cpus = 10"
cpu20: "cpus = 20"
cpu50: "cpus = 50"
cpu100: "cpus = 100"
cpu200: "cpus = 200"
cpu500: "cpus = 500"
cpu1000: "cpus = 1000"
debug: false
container: "docker"
engines:
- type: "docker"
id: "docker"
image: "python:3.12"
target_registry: "images.viash-hub.com"
target_tag: "v0.2"
namespace_separator: "/"
setup:
- type: "python"
user: false
pip:
- "cutadapt"
upgrade: true
- type: "docker"
run:
- "cutadapt --version | sed 's/\\(.*\\)/cutadapt: \"\\1\"/' > /var/software_versions.txt\n"
entrypoint: []
cmd: null
- type: "native"
id: "native"
build_info:
config: "src/cutadapt/config.vsh.yaml"
runner: "executable"
engine: "docker|native"
output: "target/executable/cutadapt"
executable: "target/executable/cutadapt/cutadapt"
viash_version: "0.9.0-RC7"
git_commit: "f22ab0eab58dcd6bff89d8d73fe951953ff1260f"
git_remote: "https://github.com/viash-hub/biobox"
package_config:
name: "biobox"
version: "v0.2"
description: "A collection of bioinformatics tools for working with sequence data.\n"
info: null
viash_version: "0.9.0-RC7"
source: "src"
target: "target"
config_mods:
- ".requirements.commands := ['ps']\n"
- ".engines += { type: \"native\" }"
- ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
- ".engines[.type == 'docker'].target_tag := 'v0.2'"
keywords:
- "bioinformatics"
- "modules"
- "sequencing"
license: "MIT"
organization: "vsh"
links:
repository: "https://github.com/viash-hub/biobox"
issue_tracker: "https://github.com/viash-hub/biobox/issues"

2820
target/executable/cutadapt/cutadapt Executable file
View File

File diff suppressed because it is too large Load Diff

343
target/executable/falco/.config.vsh.yaml Normal file
View File

@@ -0,0 +1,343 @@
name: "falco"
version: "v0.2"
authors:
- name: "Toni Verbeiren"
roles:
- "author"
- "maintainer"
info:
links:
github: "tverbeiren"
linkedin: "verbeiren"
organizations:
- name: "Data Intuitive"
href: "https://www.data-intuitive.com"
role: "Data Scientist and CEO"
argument_groups:
- name: "Input arguments"
arguments:
- type: "file"
name: "--input"
description: "input fastq files"
info: null
example:
- "input1.fastq;input2.fastq"
must_exist: true
create_parent: true
required: true
direction: "input"
multiple: true
multiple_sep: ";"
- name: "Run arguments"
arguments:
- type: "boolean_true"
name: "--nogroup"
description: "Disable grouping of bases for reads >50bp. \nAll reports will show\
\ data for every base in \nthe read. WARNING: When using this option, \nyour\
\ plots may end up a ridiculous size. You \nhave been warned!\n"
info: null
direction: "input"
- type: "file"
name: "--contaminents"
description: "Specifies a non-default file which contains \nthe list of contaminants\
\ to screen \noverrepresented sequences against. The file \nmust contain sets\
\ of named contaminants in \nthe form name[tab]sequence. Lines prefixed \nwith\
\ a hash will be ignored. Default: \nhttps://github.com/smithlabcode/falco/blob/v1.2.2/Configuration/contaminant_list.txt\n"
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--adapters"
description: "Specifies a non-default file which contains \nthe list of adapter\
\ sequences which will be \nexplicity searched against the library. The \nfile\
\ must contain sets of named adapters in \nthe form name[tab]sequence. Lines\
\ prefixed \nwith a hash will be ignored. Default:\nhttps://github.com/smithlabcode/falco/blob/v1.2.2/Configuration/adapter_list.txt\n"
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--limits"
description: "Specifies a non-default file which contains \na set of criteria\
\ which will be used to \ndetermine the warn/error limits for the \nvarious\
\ modules. This file can also be used \nto selectively remove some modules from\
\ the \noutput all together. The format needs to \nmirror the default limits.txt\
\ file found in \nthe Configuration folder. Default: \nhttps://github.com/smithlabcode/falco/blob/v1.2.2/Configuration/limits.txt\n"
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--subsample"
alternatives:
- "-s"
description: "[Falco only] makes falco faster (but \npossibly less accurate) by\
\ only processing \nreads that are a multiple of this value (using \n0-based\
\ indexing to number reads).\n"
info: null
example:
- 10
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean_true"
name: "--bisulfite"
alternatives:
- "-b"
description: "[Falco only] reads are whole genome \nbisulfite sequencing, and\
\ more Ts and fewer \nCs are therefore expected and will be \naccounted for\
\ in base content.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--reverse_complliment"
alternatives:
- "-r"
description: "[Falco only] The input is a \nreverse-complement. All modules will\
\ be \ntested by swapping A/T and C/G\n"
info: null
direction: "input"
- name: "Output arguments"
arguments:
- type: "file"
name: "--outdir"
alternatives:
- "-o"
description: "Create all output files in the specified \noutput directory. FALCO-SPECIFIC:\
\ If the \ndirectory does not exists, the program will \ncreate it.\n"
info: null
example:
- "output"
must_exist: true
create_parent: true
required: true
direction: "output"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--format"
alternatives:
- "-f"
description: "Bypasses the normal sequence file format \ndetection and forces\
\ the program to use the \nspecified format. Validformats are bam, sam, \nbam_mapped,\
\ sam_mapped, fastq, fq, fastq.gz \nor fq.gz.\n"
info: null
required: false
choices:
- "bam"
- "sam"
- "bam_mapped"
- "sam_mapped"
- "fastq"
- "fq"
- "fastq.gz"
- "fq.gz"
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--data_filename"
alternatives:
- "-D"
description: "[Falco only] Specify filename for FastQC \ndata output (TXT). If\
\ not specified, it will \nbe called fastq_data.txt in either the input \nfile's\
\ directory or the one specified in the \n--output flag. Only available when\
\ running \nfalco with a single input.\n"
info: null
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--report_filename"
alternatives:
- "-R"
description: "[Falco only] Specify filename for FastQC \nreport output (HTML).\
\ If not specified, it \nwill be called fastq_report.html in either \nthe input\
\ file's directory or the one \nspecified in the --output flag. Only \navailable\
\ when running falco with a single \ninput.\n"
info: null
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--summary_filename"
alternatives:
- "-S"
description: "[Falco only] Specify filename for the short \nsummary output (TXT).\
\ If not specified, it \nwill be called fastq_report.html in either \nthe input\
\ file's directory or the one \nspecified in the --output flag. Only \navailable\
\ when running falco with a single \ninput.\n"
info: null
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
resources:
- type: "bash_script"
path: "script.sh"
is_executable: true
description: "A C++ drop-in replacement of FastQC to assess the quality of sequence\
\ read data"
test_resources:
- type: "bash_script"
path: "test.sh"
is_executable: true
info: null
status: "enabled"
requirements:
commands:
- "ps"
keywords:
- "qc"
- "fastqc"
- "sequencing"
license: "GPL-3.0"
references:
doi:
- "10.12688/f1000research.21142.2"
links:
repository: "https://github.com/smithlabcode/falco"
documentation: "https://falco.readthedocs.io/en/latest/"
runners:
- type: "executable"
id: "executable"
docker_setup_strategy: "ifneedbepullelsecachedbuild"
- type: "nextflow"
id: "nextflow"
directives:
tag: "$id"
auto:
simplifyInput: true
simplifyOutput: false
transcript: false
publish: false
config:
labels:
mem1gb: "memory = 1000000000.B"
mem2gb: "memory = 2000000000.B"
mem5gb: "memory = 5000000000.B"
mem10gb: "memory = 10000000000.B"
mem20gb: "memory = 20000000000.B"
mem50gb: "memory = 50000000000.B"
mem100gb: "memory = 100000000000.B"
mem200gb: "memory = 200000000000.B"
mem500gb: "memory = 500000000000.B"
mem1tb: "memory = 1000000000000.B"
mem2tb: "memory = 2000000000000.B"
mem5tb: "memory = 5000000000000.B"
mem10tb: "memory = 10000000000000.B"
mem20tb: "memory = 20000000000000.B"
mem50tb: "memory = 50000000000000.B"
mem100tb: "memory = 100000000000000.B"
mem200tb: "memory = 200000000000000.B"
mem500tb: "memory = 500000000000000.B"
mem1gib: "memory = 1073741824.B"
mem2gib: "memory = 2147483648.B"
mem4gib: "memory = 4294967296.B"
mem8gib: "memory = 8589934592.B"
mem16gib: "memory = 17179869184.B"
mem32gib: "memory = 34359738368.B"
mem64gib: "memory = 68719476736.B"
mem128gib: "memory = 137438953472.B"
mem256gib: "memory = 274877906944.B"
mem512gib: "memory = 549755813888.B"
mem1tib: "memory = 1099511627776.B"
mem2tib: "memory = 2199023255552.B"
mem4tib: "memory = 4398046511104.B"
mem8tib: "memory = 8796093022208.B"
mem16tib: "memory = 17592186044416.B"
mem32tib: "memory = 35184372088832.B"
mem64tib: "memory = 70368744177664.B"
mem128tib: "memory = 140737488355328.B"
mem256tib: "memory = 281474976710656.B"
mem512tib: "memory = 562949953421312.B"
cpu1: "cpus = 1"
cpu2: "cpus = 2"
cpu5: "cpus = 5"
cpu10: "cpus = 10"
cpu20: "cpus = 20"
cpu50: "cpus = 50"
cpu100: "cpus = 100"
cpu200: "cpus = 200"
cpu500: "cpus = 500"
cpu1000: "cpus = 1000"
debug: false
container: "docker"
engines:
- type: "docker"
id: "docker"
image: "debian:trixie-slim"
target_registry: "images.viash-hub.com"
target_tag: "v0.2"
namespace_separator: "/"
setup:
- type: "apt"
packages:
- "wget"
- "build-essential"
- "g++"
- "zlib1g-dev"
- "procps"
interactive: false
- type: "docker"
run:
- "wget https://github.com/smithlabcode/falco/releases/download/v1.2.2/falco-1.2.2.tar.gz\
\ -O /tmp/falco.tar.gz && \\\ncd /tmp && \\\ntar xvf falco.tar.gz && \\\ncd\
\ falco-1.2.2 && \\\n./configure && \\\nmake all && \\\nmake install\n"
- type: "docker"
run:
- "echo \"falco: \\\"$(falco -v | sed -n 's/^falco //p')\\\"\" > /var/software_versions.txt\n"
entrypoint: []
cmd: null
- type: "native"
id: "native"
build_info:
config: "src/falco/config.vsh.yaml"
runner: "executable"
engine: "docker|native"
output: "target/executable/falco"
executable: "target/executable/falco/falco"
viash_version: "0.9.0-RC7"
git_commit: "f22ab0eab58dcd6bff89d8d73fe951953ff1260f"
git_remote: "https://github.com/viash-hub/biobox"
package_config:
name: "biobox"
version: "v0.2"
description: "A collection of bioinformatics tools for working with sequence data.\n"
info: null
viash_version: "0.9.0-RC7"
source: "src"
target: "target"
config_mods:
- ".requirements.commands := ['ps']\n"
- ".engines += { type: \"native\" }"
- ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
- ".engines[.type == 'docker'].target_tag := 'v0.2'"
keywords:
- "bioinformatics"
- "modules"
- "sequencing"
license: "MIT"
organization: "vsh"
links:
repository: "https://github.com/viash-hub/biobox"
issue_tracker: "https://github.com/viash-hub/biobox/issues"

1537
target/executable/falco/falco Executable file
View File

File diff suppressed because it is too large Load Diff

1109
target/executable/fastp/.config.vsh.yaml Normal file
View File

File diff suppressed because it is too large Load Diff

3429
target/executable/fastp/fastp Executable file
View File

File diff suppressed because it is too large Load Diff

366
target/executable/fastqc/.config.vsh.yaml Normal file
View File

@@ -0,0 +1,366 @@
name: "fastqc"
version: "v0.2"
authors:
- name: "Theodoro Gasperin Terra Camargo"
roles:
- "author"
- "maintainer"
info:
links:
email: "theodorogtc@gmail.com"
github: "tgaspe"
linkedin: "theodoro-gasperin-terra-camargo"
organizations:
- name: "Data Intuitive"
href: "https://www.data-intuitive.com"
role: "Bioinformatician"
argument_groups:
- name: "Inputs"
arguments:
- type: "file"
name: "--input"
description: "FASTQ file(s) to be analyzed.\n"
info: null
example:
- "input.fq"
must_exist: true
create_parent: true
required: true
direction: "input"
multiple: true
multiple_sep: ";"
- name: "Outputs"
description: "At least one of the output options (--html, --zip, --summary, --data)\
\ must be used.\n"
arguments:
- type: "file"
name: "--html"
description: "Create the HTML report of the results. \n'*' wild card must be provided\
\ in the output file name. \nWild card will be replaced by the input file basename.\n\
e.g. \n --input \"sample_1.fq\"\n --html \"*.html\"\n would create an output\
\ html file named sample_1.html\n"
info: null
example:
- "*.html"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: true
multiple_sep: ";"
- type: "file"
name: "--zip"
description: "Create the zip file(s) containing: html report, data, images, icons,\
\ summary, etc.\n'*' wild card must be provided in the output file name.\nWild\
\ card will be replaced by the input basename.\ne.g. \n --input \"sample_1.fq\"\
\n --html \"*.zip\"\n would create an output zip file named sample_1.zip\n"
info: null
example:
- "*.zip"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: true
multiple_sep: ";"
- type: "file"
name: "--summary"
description: "Create the summary file(s).\n'*' wild card must be provided in the\
\ output file name.\nWild card will be replaced by the input basename.\ne.g.\
\ \n --input \"sample_1.fq\"\n --summary \"*_summary.txt\"\n would create\
\ an output summary.txt file named sample_1_summary.txt\n"
info: null
example:
- "*_summary.txt"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: true
multiple_sep: ";"
- type: "file"
name: "--data"
description: "Create the data file(s).\n'*' wild card must be provided in the\
\ output file name.\nWild card will be replaced by the input basename.\ne.g.\
\ \n --input \"sample_1.fq\"\n --summary \"*_data.txt\"\n would create an\
\ output data.txt file named sample_1_data.txt\n"
info: null
example:
- "*_data.txt"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: true
multiple_sep: ";"
- name: "Options"
arguments:
- type: "boolean_true"
name: "--casava"
description: "Files come from raw casava output. Files in the same sample\ngroup\
\ (differing only by the group number) will be analysed\nas a set rather than\
\ individually. Sequences with the filter\nflag set in the header will be excluded\
\ from the analysis.\nFiles must have the same names given to them by casava\n\
(including being gzipped and ending with .gz) otherwise they\nwon't be grouped\
\ together correctly.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--nano"
description: "Files come from nanopore sequences and are in fast5 format. In\n\
this mode you can pass in directories to process and the program\nwill take\
\ in all fast5 files within those directories and produce\na single output file\
\ from the sequences found in all files.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--nofilter"
description: "If running with --casava then don't remove read flagged by\ncasava\
\ as poor quality when performing the QC analysis.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--nogroup"
description: "Disable grouping of bases for reads >50bp. \nAll reports will show\
\ data for every base in the read. \nWARNING: Using this option will cause fastqc\
\ to crash \nand burn if you use it on really long reads, and your \nplots may\
\ end up a ridiculous size. You have been warned!\n"
info: null
direction: "input"
- type: "integer"
name: "--min_length"
description: "Sets an artificial lower limit on the length of the \nsequence to\
\ be shown in the report. As long as you \nset this to a value greater or equal\
\ to your longest \nread length then this will be the sequence length used \n\
to create your read groups. This can be useful for making\ndirectly comparable\
\ statistics from datasets with somewhat \nvariable read lengths.\n"
info: null
example:
- 0
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--format"
alternatives:
- "-f"
description: "Bypasses the normal sequence file format detection and \nforces\
\ the program to use the specified format. \nValid formats are bam, sam, bam_mapped,\
\ sam_mapped, and fastq.\n"
info: null
example:
- "bam"
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--contaminants"
alternatives:
- "-c"
description: "Specifies a non-default file which contains the list \nof contaminants\
\ to screen overrepresented sequences against. \nThe file must contain sets\
\ of named contaminants in the form\nname[tab]sequence. Lines prefixed with\
\ a hash will be ignored.\n"
info: null
example:
- "contaminants.txt"
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--adapters"
alternatives:
- "-a"
description: "Specifies a non-default file which contains the list of \nadapter\
\ sequences which will be explicitly searched against \nthe library. The file\
\ must contain sets of named adapters \nin the form name[tab]sequence. Lines\
\ prefixed with a hash will be ignored.\n"
info: null
example:
- "adapters.txt"
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--limits"
alternatives:
- "-l"
description: "Specifies a non-default file which contains \na set of criteria\
\ which will be used to determine \nthe warn/error limits for the various modules.\
\ \nThis file can also be used to selectively remove \nsome modules from the\
\ output altogether. The format \nneeds to mirror the default limits.txt file\
\ found in \nthe Configuration folder.\n"
info: null
example:
- "limits.txt"
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--kmers"
alternatives:
- "-k"
description: "Specifies the length of Kmer to look for in the Kmer \ncontent module.\
\ Specified Kmer length must be between \n2 and 10. Default length is 7 if not\
\ specified.\n"
info: null
example:
- 7
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean_true"
name: "--quiet"
alternatives:
- "-q"
description: "Suppress all progress messages on stdout and only report errors.\n"
info: null
direction: "input"
resources:
- type: "bash_script"
path: "script.sh"
is_executable: true
description: "FastQC - A high throughput sequence QC analysis tool."
test_resources:
- type: "bash_script"
path: "test.sh"
is_executable: true
info: null
status: "enabled"
requirements:
commands:
- "ps"
keywords:
- "Quality control"
- "BAM"
- "SAM"
- "FASTQ"
license: "GPL-3.0, Apache-2.0"
links:
repository: "https://github.com/s-andrews/FastQC"
homepage: "https://www.bioinformatics.babraham.ac.uk/projects/fastqc/"
documentation: "https://www.bioinformatics.babraham.ac.uk/projects/fastqc/Help/"
issue_tracker: "https://github.com/s-andrews/FastQC/issues"
runners:
- type: "executable"
id: "executable"
docker_setup_strategy: "ifneedbepullelsecachedbuild"
- type: "nextflow"
id: "nextflow"
directives:
tag: "$id"
auto:
simplifyInput: true
simplifyOutput: false
transcript: false
publish: false
config:
labels:
mem1gb: "memory = 1000000000.B"
mem2gb: "memory = 2000000000.B"
mem5gb: "memory = 5000000000.B"
mem10gb: "memory = 10000000000.B"
mem20gb: "memory = 20000000000.B"
mem50gb: "memory = 50000000000.B"
mem100gb: "memory = 100000000000.B"
mem200gb: "memory = 200000000000.B"
mem500gb: "memory = 500000000000.B"
mem1tb: "memory = 1000000000000.B"
mem2tb: "memory = 2000000000000.B"
mem5tb: "memory = 5000000000000.B"
mem10tb: "memory = 10000000000000.B"
mem20tb: "memory = 20000000000000.B"
mem50tb: "memory = 50000000000000.B"
mem100tb: "memory = 100000000000000.B"
mem200tb: "memory = 200000000000000.B"
mem500tb: "memory = 500000000000000.B"
mem1gib: "memory = 1073741824.B"
mem2gib: "memory = 2147483648.B"
mem4gib: "memory = 4294967296.B"
mem8gib: "memory = 8589934592.B"
mem16gib: "memory = 17179869184.B"
mem32gib: "memory = 34359738368.B"
mem64gib: "memory = 68719476736.B"
mem128gib: "memory = 137438953472.B"
mem256gib: "memory = 274877906944.B"
mem512gib: "memory = 549755813888.B"
mem1tib: "memory = 1099511627776.B"
mem2tib: "memory = 2199023255552.B"
mem4tib: "memory = 4398046511104.B"
mem8tib: "memory = 8796093022208.B"
mem16tib: "memory = 17592186044416.B"
mem32tib: "memory = 35184372088832.B"
mem64tib: "memory = 70368744177664.B"
mem128tib: "memory = 140737488355328.B"
mem256tib: "memory = 281474976710656.B"
mem512tib: "memory = 562949953421312.B"
cpu1: "cpus = 1"
cpu2: "cpus = 2"
cpu5: "cpus = 5"
cpu10: "cpus = 10"
cpu20: "cpus = 20"
cpu50: "cpus = 50"
cpu100: "cpus = 100"
cpu200: "cpus = 200"
cpu500: "cpus = 500"
cpu1000: "cpus = 1000"
debug: false
container: "docker"
engines:
- type: "docker"
id: "docker"
image: "biocontainers/fastqc:v0.11.9_cv8"
target_registry: "images.viash-hub.com"
target_tag: "v0.2"
namespace_separator: "/"
setup:
- type: "docker"
run:
- "echo \"fastqc: $(fastqc --version | sed -n 's/^FastQC //p')\" > /var/software_versions.txt\n"
entrypoint: []
cmd: null
- type: "native"
id: "native"
build_info:
config: "src/fastqc/config.vsh.yaml"
runner: "executable"
engine: "docker|native"
output: "target/executable/fastqc"
executable: "target/executable/fastqc/fastqc"
viash_version: "0.9.0-RC7"
git_commit: "f22ab0eab58dcd6bff89d8d73fe951953ff1260f"
git_remote: "https://github.com/viash-hub/biobox"
package_config:
name: "biobox"
version: "v0.2"
description: "A collection of bioinformatics tools for working with sequence data.\n"
info: null
viash_version: "0.9.0-RC7"
source: "src"
target: "target"
config_mods:
- ".requirements.commands := ['ps']\n"
- ".engines += { type: \"native\" }"
- ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
- ".engines[.type == 'docker'].target_tag := 'v0.2'"
keywords:
- "bioinformatics"
- "modules"
- "sequencing"
license: "MIT"
organization: "vsh"
links:
repository: "https://github.com/viash-hub/biobox"
issue_tracker: "https://github.com/viash-hub/biobox/issues"

1680
target/executable/fastqc/fastqc Executable file
View File

File diff suppressed because it is too large Load Diff

671
target/executable/featurecounts/.config.vsh.yaml Normal file
View File

@@ -0,0 +1,671 @@
name: "featurecounts"
version: "v0.2"
authors:
- name: "Sai Nirmayi Yasa"
roles:
- "author"
- "maintainer"
info:
links:
email: "nirmayi@data-intuitive.com"
github: "sainirmayi"
linkedin: "sai-nirmayi-yasa"
organizations:
- name: "Data Intuitive"
href: "https://www.data-intuitive.com"
role: "Junior Bioinformatics Researcher"
argument_groups:
- name: "Inputs"
arguments:
- type: "file"
name: "--annotation"
alternatives:
- "-a"
description: "Name of an annotation file. GTF/GFF format by default. See '--format'\
\ option for more format information.\n"
info: null
example:
- "annotation.gtf"
must_exist: true
create_parent: true
required: true
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--input"
alternatives:
- "-i"
description: "A list of SAM or BAM format files separated by semi-colon (;). They\
\ can be either name or location sorted. Location-sorted paired-end reads are\
\ automatically sorted by read names.\n"
info: null
example:
- "input_file1.bam"
must_exist: true
create_parent: true
required: true
direction: "input"
multiple: true
multiple_sep: ";"
- name: "Outputs"
arguments:
- type: "file"
name: "--counts"
alternatives:
- "-o"
description: "Name of output file including read counts in tab delimited format.\n"
info: null
example:
- "features.tsv"
must_exist: true
create_parent: true
required: true
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--summary"
description: "Summary statistics of counting results in tab delimited format.\n"
info: null
example:
- "summary.tsv"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--junctions"
description: "Count number of reads supporting each exon-exon junction. Junctions\
\ were identified from those exon-spanning reads in the input (containing 'N'\
\ in CIGAR string).\n"
info: null
example:
- "junctions.txt"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- name: "Annotation"
arguments:
- type: "string"
name: "--format"
alternatives:
- "-F"
description: "Specify format of the provided annotation file. Acceptable formats\
\ include 'GTF' (or compatible GFF format) and 'SAF'. 'GTF' by default. \n"
info: null
example:
- "GTF"
required: false
choices:
- "GTF"
- "GFF"
- "SAF"
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--feature_type"
alternatives:
- "-t"
description: "Specify feature type(s) in a GTF annotation. If multiple types are\
\ provided, they should be separated by ';' with no space in between. 'exon'\
\ by default. Rows in the annotation with a matched feature will be extracted\
\ and used for read mapping.\n"
info: null
example:
- "exon"
required: false
direction: "input"
multiple: true
multiple_sep: ";"
- type: "string"
name: "--attribute_type"
alternatives:
- "-g"
description: "Specify attribute type in GTF annotation. 'gene_id' by default.\
\ Meta-features used for read counting will be extracted from annotation using\
\ the provided value.\n"
info: null
example:
- "gene_id"
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--extra_attributes"
description: "Extract extra attribute types from the provided GTF annotation and\
\ include them in the counting output. These attribute types will not be used\
\ to group features. If more than one attribute type is provided they should\
\ be separated by semicolon (;).\n"
info: null
required: false
direction: "input"
multiple: true
multiple_sep: ";"
- type: "file"
name: "--chrom_alias"
alternatives:
- "-A"
description: "Provide a chromosome name alias file to match chr names in annotation\
\ with those in the reads. This should be a two-column comma-delimited text\
\ file. Its first column should include chr names in the annotation and its\
\ second column should include chr names in the reads. Chr names are case sensitive.\
\ No column header should be included in the file.\n"
info: null
example:
- "chrom_alias.csv"
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- name: "Level of summarization"
arguments:
- type: "boolean_true"
name: "--feature_level"
alternatives:
- "-f"
description: "Perform read counting at feature level (eg. counting reads for exons\
\ rather than genes).\n"
info: null
direction: "input"
- name: "Overlap between reads and features"
arguments:
- type: "boolean_true"
name: "--overlapping"
alternatives:
- "-O"
description: "Assign reads to all their overlapping meta-features (or features\
\ if '--feature_level' is specified).\n"
info: null
direction: "input"
- type: "integer"
name: "--min_overlap"
description: "Minimum number of overlapping bases in a read that is required for\
\ read assignment. 1 by default. Number of overlapping bases is counted from\
\ both reads if paired end. If a negative value is provided, then a gap of up\
\ to specified size will be allowed between read and the feature that the read\
\ is assigned to.\n"
info: null
example:
- 1
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "double"
name: "--frac_overlap"
description: "Minimum fraction of overlapping bases in a read that is required\
\ for read assignment. Value should be within range [0,1]. 0 by default. Number\
\ of overlapping bases is counted from both reads if paired end. Both this option\
\ and '--min_overlap' option need to be satisfied for read assignment.\n"
info: null
example:
- 0.0
required: false
min: 0.0
max: 1.0
direction: "input"
multiple: false
multiple_sep: ";"
- type: "double"
name: "--frac_overlap_feature"
description: "Minimum fraction of overlapping bases in a feature that is required\
\ for read assignment. Value should be within range [0,1]. 0 by default.\n"
info: null
example:
- 0.0
required: false
min: 0.0
max: 1.0
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean_true"
name: "--largest_overlap"
description: "Assign reads to a meta-feature/feature that has the largest number\
\ of overlapping bases.\n"
info: null
direction: "input"
- type: "integer"
name: "--non_overlap"
description: "Maximum number of non-overlapping bases in a read (or a read pair)\
\ that is allowed when being assigned to a feature. No limit is set by default.\n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--non_overlap_feature"
description: "Maximum number of non-overlapping bases in a feature that is allowed\
\ in read assignment. No limit is set by default.\n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--read_extension5"
description: "Reads are extended upstream by <int> bases from their 5' end.\n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--read_extension3"
description: "Reads are extended upstream by <int> bases from their 3' end.\n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--read2pos"
description: "Reduce reads to their 5' most base or 3' most base. Read counting\
\ is then performed based on the single base the read is reduced to.\n"
info: null
required: false
choices:
- 3
- 5
direction: "input"
multiple: false
multiple_sep: ";"
- name: "Multi-mapping reads"
arguments:
- type: "boolean_true"
name: "--multi_mapping"
alternatives:
- "-M"
description: "Multi-mapping reads will also be counted. For a multi-mapping read,\
\ all its reported alignments will be counted. The 'NH' tag in BAM/SAM input\
\ is used to detect multi-mapping reads.\n"
info: null
direction: "input"
- name: "Fractional counting"
arguments:
- type: "boolean_true"
name: "--fraction"
description: "Assign fractional counts to features. This option must be used together\
\ with '--multi_mapping' or '--overlapping' or both. When '--multi_mapping'\
\ is specified, each reported alignment from a multi-mapping read (identified\
\ via 'NH' tag) will carry a fractional count of 1/x, instead of 1 (one), where\
\ x is the total number of alignments reported for the same read. When '--overlapping'\
\ is specified, each overlapping feature will receive a fractional count of\
\ 1/y, where y is the total number of features overlapping with the read. When\
\ both '--multi_mapping' and '--overlapping' are specified, each alignment will\
\ carry a fractional count of 1/(x*y).\n"
info: null
direction: "input"
- name: "Read filtering"
arguments:
- type: "integer"
name: "--min_map_quality"
alternatives:
- "-Q"
description: "The minimum mapping quality score a read must satisfy in order to\
\ be counted. For paired-end reads, at least one end should satisfy this criteria.\
\ 0 by default.\n"
info: null
example:
- 0
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean_true"
name: "--split_only"
description: "Count split alignments only (ie. alignments with CIGAR string containing\
\ 'N'). An example of split alignments is exon-spanning reads in RNA-seq data.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--non_split_only"
description: "If specified, only non-split alignments (CIGAR strings do not contain\
\ letter 'N') will be counted. All the other alignments will be ignored.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--primary"
description: "Count primary alignments only. Primary alignments are identified\
\ using bit 0x100 in SAM/BAM FLAG field.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--ignore_dup"
description: "Ignore duplicate reads in read counting. Duplicate reads are identified\
\ using bit Ox400 in BAM/SAM FLAG field. The whole read pair is ignored if one\
\ of the reads is a duplicate read for paired end data.\n"
info: null
direction: "input"
- name: "Strandedness"
arguments:
- type: "integer"
name: "--strand"
alternatives:
- "-s"
description: "Perform strand-specific read counting. A single integer value (applied\
\ to all input files) should be provided. Possible values include: 0 (unstranded),\
\ 1 (stranded) and 2 (reversely stranded). Default value is 0 (ie. unstranded\
\ read counting carried out for all input files).\n"
info: null
example:
- 0
required: false
choices:
- 0
- 1
- 2
direction: "input"
multiple: false
multiple_sep: ";"
- name: "Exon-exon junctions"
arguments:
- type: "file"
name: "--ref_fasta"
alternatives:
- "-G"
description: "Provide the name of a FASTA-format file that contains the reference\
\ sequences used in read mapping that produced the provided SAM/BAM files.\n"
info: null
example:
- "reference.fasta"
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- name: "Parameters specific to paired end reads"
arguments:
- type: "boolean_true"
name: "--paired"
alternatives:
- "-p"
description: "Specify that input data contain paired-end reads. To perform fragment\
\ counting (ie. counting read pairs), the '--countReadPairs' parameter should\
\ also be specified in addition to this parameter.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--count_read_pairs"
description: "Count read pairs (fragments) instead of reads. This option is only\
\ applicable for paired-end reads.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--both_aligned"
alternatives:
- "-B"
description: "Count read pairs (fragments) instead of reads. This option is only\
\ applicable for paired-end reads.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--check_pe_dist"
alternatives:
- "-P"
description: "Check validity of paired-end distance when counting read pairs.\
\ Use '--min_length' and '--max_length' to set thresholds.\n"
info: null
direction: "input"
- type: "integer"
name: "--min_length"
alternatives:
- "-d"
description: "Minimum fragment/template length, 50 by default.\n"
info: null
example:
- 50
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--max_length"
alternatives:
- "-D"
description: "Maximum fragment/template length, 600 by default.\n"
info: null
example:
- 600
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean_true"
name: "--same_strand"
alternatives:
- "-C"
description: "Do not count read pairs that have their two ends mapping to different\
\ chromosomes or mapping to same chromosome but on different strands.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--donotsort"
description: "Do not sort reads in BAM/SAM input. Note that reads from the same\
\ pair are required to be located next to each other in the input.\n"
info: null
direction: "input"
- name: "Read groups"
arguments:
- type: "boolean_true"
name: "--by_read_group"
description: "Assign reads by read group. \"RG\" tag is required to be present\
\ in the input BAM/SAM files.\n"
info: null
direction: "input"
- name: "Long reads"
arguments:
- type: "boolean_true"
name: "--long_reads"
description: "Count long reads such as Nanopore and PacBio reads. Long read counting\
\ can only run in one thread and only reads (not read-pairs) can be counted.\
\ There is no limitation on the number of 'M' operations allowed in a CIGAR\
\ string in long read counting.\n"
info: null
direction: "input"
- name: "Assignment results for each read"
arguments:
- type: "file"
name: "--detailed_results"
description: "Directory to save the detailed assignment results. Use `--detailed_results_format`\
\ to determine the format of the detailed results.\n"
info: null
example:
- "detailed_results"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--detailed_results_format"
alternatives:
- "-R"
description: "Output detailed assignment results for each read or read-pair. Results\
\ are saved to a file that is in one of the following formats: CORE, SAM and\
\ BAM. See documentaiton for more info about these formats.\n"
info: null
required: false
choices:
- "CORE"
- "SAM"
- "BAM"
direction: "input"
multiple: false
multiple_sep: ";"
- name: "Miscellaneous"
arguments:
- type: "integer"
name: "--max_M_op"
description: "Maximum number of 'M' operations allowed in a CIGAR string. 10 by\
\ default. Both 'X' and '=' are treated as 'M' and adjacent 'M' operations are\
\ merged in the CIGAR string.\n"
info: null
example:
- 10
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean_true"
name: "--verbose"
description: "Output verbose information for debugging, such as un-matched chromosome/contig\
\ names.\n"
info: null
direction: "input"
resources:
- type: "bash_script"
path: "script.sh"
is_executable: true
description: "featureCounts is a read summarization program for counting reads generated\
\ from either RNA or genomic DNA sequencing experiments by implementing highly efficient\
\ chromosome hashing and feature blocking techniques. It works with either single\
\ or paired-end reads and provides a wide range of options appropriate for different\
\ sequencing applications.\n"
test_resources:
- type: "bash_script"
path: "test.sh"
is_executable: true
- type: "file"
path: "test_data"
info: null
status: "enabled"
requirements:
commands:
- "ps"
keywords:
- "Read counting"
- "Genomic features"
license: "GPL-3.0"
references:
doi:
- "10.1093/bioinformatics/btt656"
links:
repository: "https://github.com/ShiLab-Bioinformatics/subread"
homepage: "https://subread.sourceforge.net/"
documentation: "https://subread.sourceforge.net/SubreadUsersGuide.pdf"
runners:
- type: "executable"
id: "executable"
docker_setup_strategy: "ifneedbepullelsecachedbuild"
- type: "nextflow"
id: "nextflow"
directives:
tag: "$id"
auto:
simplifyInput: true
simplifyOutput: false
transcript: false
publish: false
config:
labels:
mem1gb: "memory = 1000000000.B"
mem2gb: "memory = 2000000000.B"
mem5gb: "memory = 5000000000.B"
mem10gb: "memory = 10000000000.B"
mem20gb: "memory = 20000000000.B"
mem50gb: "memory = 50000000000.B"
mem100gb: "memory = 100000000000.B"
mem200gb: "memory = 200000000000.B"
mem500gb: "memory = 500000000000.B"
mem1tb: "memory = 1000000000000.B"
mem2tb: "memory = 2000000000000.B"
mem5tb: "memory = 5000000000000.B"
mem10tb: "memory = 10000000000000.B"
mem20tb: "memory = 20000000000000.B"
mem50tb: "memory = 50000000000000.B"
mem100tb: "memory = 100000000000000.B"
mem200tb: "memory = 200000000000000.B"
mem500tb: "memory = 500000000000000.B"
mem1gib: "memory = 1073741824.B"
mem2gib: "memory = 2147483648.B"
mem4gib: "memory = 4294967296.B"
mem8gib: "memory = 8589934592.B"
mem16gib: "memory = 17179869184.B"
mem32gib: "memory = 34359738368.B"
mem64gib: "memory = 68719476736.B"
mem128gib: "memory = 137438953472.B"
mem256gib: "memory = 274877906944.B"
mem512gib: "memory = 549755813888.B"
mem1tib: "memory = 1099511627776.B"
mem2tib: "memory = 2199023255552.B"
mem4tib: "memory = 4398046511104.B"
mem8tib: "memory = 8796093022208.B"
mem16tib: "memory = 17592186044416.B"
mem32tib: "memory = 35184372088832.B"
mem64tib: "memory = 70368744177664.B"
mem128tib: "memory = 140737488355328.B"
mem256tib: "memory = 281474976710656.B"
mem512tib: "memory = 562949953421312.B"
cpu1: "cpus = 1"
cpu2: "cpus = 2"
cpu5: "cpus = 5"
cpu10: "cpus = 10"
cpu20: "cpus = 20"
cpu50: "cpus = 50"
cpu100: "cpus = 100"
cpu200: "cpus = 200"
cpu500: "cpus = 500"
cpu1000: "cpus = 1000"
debug: false
container: "docker"
engines:
- type: "docker"
id: "docker"
image: "quay.io/biocontainers/subread:2.0.6--he4a0461_0"
target_registry: "images.viash-hub.com"
target_tag: "v0.2"
namespace_separator: "/"
setup:
- type: "docker"
run:
- "featureCounts -v 2>&1 | sed 's/featureCounts v\\([0-9.]*\\)/featureCounts:\
\ \\1/' > /var/software_versions.txt\n"
entrypoint: []
cmd: null
- type: "native"
id: "native"
build_info:
config: "src/featurecounts/config.vsh.yaml"
runner: "executable"
engine: "docker|native"
output: "target/executable/featurecounts"
executable: "target/executable/featurecounts/featurecounts"
viash_version: "0.9.0-RC7"
git_commit: "f22ab0eab58dcd6bff89d8d73fe951953ff1260f"
git_remote: "https://github.com/viash-hub/biobox"
package_config:
name: "biobox"
version: "v0.2"
description: "A collection of bioinformatics tools for working with sequence data.\n"
info: null
viash_version: "0.9.0-RC7"
source: "src"
target: "target"
config_mods:
- ".requirements.commands := ['ps']\n"
- ".engines += { type: \"native\" }"
- ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
- ".engines[.type == 'docker'].target_tag := 'v0.2'"
keywords:
- "bioinformatics"
- "modules"
- "sequencing"
license: "MIT"
organization: "vsh"
links:
repository: "https://github.com/viash-hub/biobox"
issue_tracker: "https://github.com/viash-hub/biobox/issues"

2443
target/executable/featurecounts/featurecounts Executable file
View File

File diff suppressed because it is too large Load Diff

711
target/executable/gffread/.config.vsh.yaml Normal file
View File

@@ -0,0 +1,711 @@
name: "gffread"
version: "v0.2"
authors:
- name: "Emma Rousseau"
roles:
- "author"
- "maintainer"
info:
links:
email: "emma@data-intuitive.com"
github: "emmarousseau"
linkedin: "emmarousseau1"
organizations:
- name: "Data Intuitive"
href: "https://www.data-intuitive.com"
role: "Bioinformatician"
argument_groups:
- name: "Inputs"
arguments:
- type: "file"
name: "--input"
description: "A reference file in either the GFF3, GFF2 or GTF format.\n"
info: null
example:
- "annotation.gff"
must_exist: true
create_parent: true
required: true
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--chr_mapping"
alternatives:
- "-m"
description: "<chr_replace> is a name mapping table for converting reference sequence\
\ names, \nhaving this 2-column format: <original_ref_ID> <new_ref_ID>.\n"
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--seq_info"
alternatives:
- "-s"
description: "<seq_info.fsize> is a tab-delimited file providing this info for\
\ each of the mapped \nsequences: <seq-name> <seq-length> <seq-description>\
\ (useful for --description option with \nmRNA/EST/protein mappings).\n"
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--genome"
alternatives:
- "-g"
description: "Full path to a multi-fasta file with the genomic sequences for all\
\ input mappings, \nOR a directory with single-fasta files (one per genomic\
\ sequence, with file names \nmatching sequence names).\n"
info: null
example:
- "genome.fa"
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- name: "Outputs"
arguments:
- type: "file"
name: "--outfile"
alternatives:
- "-o"
description: "Write the output records into <outfile>.\n"
info: null
example:
- "output.gff"
must_exist: true
create_parent: true
required: true
direction: "output"
multiple: false
multiple_sep: ";"
- type: "boolean_true"
name: "--force_exons"
description: "Make sure that the lowest level GFF features are considered \"exon\"\
\ features.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--gene2exon"
description: "For single-line genes not parenting any transcripts, add an exon\
\ feature spanning \nthe entire gene (treat it as a transcript).\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--t_adopt"
description: "Try to find a parent gene overlapping/containing a transcript that\
\ does not have \nany explicit gene Parent.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--decode"
alternatives:
- "-D"
description: "Decode url encoded characters within attributes.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--merge_exons"
alternatives:
- "-Z"
description: "Merge very close exons into a single exon (when intron size<4).\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--junctions"
alternatives:
- "-j"
description: "Output the junctions and the corresponding transcripts.\n"
info: null
direction: "input"
- type: "file"
name: "--spliced_exons"
alternatives:
- "-w"
description: "Write a fasta file with spliced exons for each transcript.\n"
info: null
example:
- "exons.fa"
must_exist: false
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--w_add"
description: "For the --spliced_exons option, extract additional <N> bases both\
\ upstream and \ndownstream of the transcript boundaries.\n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean_true"
name: "--w_nocds"
description: "For --spliced_exons, disable the output of CDS info in the FASTA\
\ file.\n"
info: null
direction: "input"
- type: "file"
name: "--spliced_cds"
alternatives:
- "-x"
description: "Write a fasta file with spliced CDS for each GFF transcript.\n"
info: null
example:
- "cds.fa"
must_exist: false
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--tr_cds"
alternatives:
- "-y"
description: "Write a protein fasta file with the translation of CDS for each\
\ record.\n"
info: null
example:
- "tr_cds.fa"
must_exist: false
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean_true"
name: "--w_coords"
alternatives:
- "-W"
description: "For --spliced_exons, --spliced_cds and -tr_cds options, write in\
\ the FASTA defline \nall the exon coordinates projected onto the spliced sequence.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--stop_dot"
alternatives:
- "-S"
description: "For --tr_cds option, use '*' instead of '.' as stop codon translation.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--id_version"
alternatives:
- "-L"
description: "Ensembl GTF to GFF3 conversion, adds version to IDs.\n"
info: null
direction: "input"
- type: "string"
name: "--trackname"
alternatives:
- "-t"
description: "Use <trackname> in the 2nd column of each GFF/GTF output line.\n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean_true"
name: "--gtf_output"
alternatives:
- "-T"
description: "Main output will be GTF instead of GFF3.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--bed"
description: "Output records in BED format instead of default GFF3.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--tlf"
description: "Output \"transcript line format\" which is like GFF but with exons\
\ and CDS related \nfeatures stored as GFF attributes in the transcript feature\
\ line, like this:\n exoncount=N;exons=<exons>;CDSphase=<N>;CDS=<CDScoords>\n\
<exons> is a comma-delimited list of exon_start-exon_end coordinates;\n<CDScoords>\
\ is CDS_start:CDS_end coordinates or a list like <exons>.\n"
info: null
direction: "input"
- type: "string"
name: "--table"
description: "Output a simple tab delimited format instead of GFF, with columns\
\ having the values \nof GFF attributes given in <attrlist>; special pseudo-attributes\
\ (prefixed by @) are \nrecognized:\n @id, @geneid, @chr, @start, @end, @strand,\
\ @numexons, @exons, @cds, @covlen, @cdslen\nIf any of --spliced_exons/--tr_cds/--spliced_cds\
\ FASTA output files are enabled, the \nsame fields (excluding @id) are appended\
\ to the definition line of corresponding FASTA\nrecords.\n"
info: null
required: false
direction: "input"
multiple: true
multiple_sep: ";"
- type: "boolean_true"
name: "--expose_dups"
alternatives:
- "-E"
- "-v"
description: "Expose (warn about) duplicate transcript IDs and other potential\
\ problems with the \ngiven GFF/GTF records.\n"
info: null
direction: "input"
- name: "Options"
arguments:
- type: "file"
name: "--ids"
description: "Discard records/transcripts if their IDs are not listed in <IDs.lst>.\n"
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--nids"
description: "Discard records/transcripts if their IDs are listed in <IDs.lst>.\n"
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--maxintron"
alternatives:
- "-i"
description: "Discard transcripts having an intron larger than <maxintron>.\n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--minlen"
alternatives:
- "-l"
description: "Discard transcripts shorter than <minlen> bases.\n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--range"
alternatives:
- "-r"
description: "Only show transcripts overlapping coordinate range <start>..<end>\
\ (on chromosome/contig \n<chr>, strand <strand> if provided).\n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean_true"
name: "--strict_range"
alternatives:
- "-R"
description: "For --range option, discard all transcripts that are not fully contained\
\ within the given \nrange.\n"
info: null
direction: "input"
- type: "string"
name: "--jmatch"
description: "Only output transcripts matching the given junction.\n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean_true"
name: "--no_single_exon"
alternatives:
- "-U"
description: "Discard single-exon transcripts.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--coding"
alternatives:
- "-C"
description: "Coding only: discard mRNAs that have no CDS features.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--nc"
description: "Non-coding only: discard mRNAs that have CDS features.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--ignore_locus"
description: "Discard locus features and attributes found in the input.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--description"
alternatives:
- "-A"
description: "Use the description field from <seq_info.fsize> and add it as the\
\ value for a 'descr' \nattribute to the GFF record.\n"
info: null
direction: "input"
- name: "Sorting"
arguments:
- type: "boolean_true"
name: "--sort_alpha"
description: "Chromosomes (reference sequences) are sorted alphabetically.\n"
info: null
direction: "input"
- type: "file"
name: "--sort_by"
description: "Sort the reference sequences by the order in which their names are\
\ given in the \n<refseq.lst> file.\n"
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- name: "Misc options"
arguments:
- type: "boolean_true"
name: "--keep_attrs"
alternatives:
- "-F"
description: "Keep all GFF attributes (for non-exon features).\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--keep_exon_attrs"
description: "For -F option, do not attempt to reduce redundant exon/CDS attributes.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--no_exon_attrs"
alternatives:
- "-G"
description: "Do not keep exon attributes, move them to the transcript feature\
\ (for GFF3 output).\n"
info: null
direction: "input"
- type: "string"
name: "--attrs"
description: "Only output the GTF/GFF attributes listed in <attr-list> which is\
\ a comma delimited \nlist of attribute names to.\n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean_true"
name: "--keep_genes"
description: "In transcript-only mode (default), also preserve gene records.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--keep_comments"
description: "For GFF3 input/output, try to preserve comments.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--process_other"
alternatives:
- "-O"
description: "process other non-transcript GFF records (by default non-transcript\
\ records are ignored).\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--rm_stop_codons"
alternatives:
- "-V"
description: "Discard any mRNAs with CDS having in-frame stop codons (requires\
\ --genome).\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--adj_cds_start"
alternatives:
- "-H"
description: "For --rm_stop_codons option, check and adjust the starting CDS phase\
\ if the original phase\nleads to a translation with an in-frame stop codon.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--opposite_strand"
alternatives:
- "-B"
description: "For -V option, single-exon transcripts are also checked on the opposite\
\ strand (requires \n--genome). \n"
info: null
direction: "input"
- type: "boolean_true"
name: "--coding_status"
alternatives:
- "-P"
description: "Add transcript level GFF attributes about the coding status of each\
\ transcript, including \npartialness or in-frame stop codons (requires --genome).\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--add_hasCDS"
description: "Add a \"hasCDS\" attribute with value \"true\" for transcripts that\
\ have CDS features. \n"
info: null
direction: "input"
- type: "boolean_true"
name: "--adj_stop"
description: "Stop codon adjustment: enables --coding_status and performs automatic\
\ adjustment of the CDS stop \ncoordinate if premature or downstream.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--rm_noncanon"
alternatives:
- "-N"
description: "Discard multi-exon mRNAs that have any intron with a non-canonical\
\ splice site consensus \n(i.e. not GT-AG, GC-AG or AT-AC).\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--complete_cds"
alternatives:
- "-J"
description: "Discard any mRNAs that either lack initial START codon or the terminal\
\ STOP codon, or \nhave an in-frame stop codon (i.e. only print mRNAs with a\
\ complete CDS).\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--no_pseudo"
description: "Filter out records matching the 'pseudo' keyword.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--in_bed"
description: "Input should be parsed as BED format (automatic if the input filename\
\ ends with .bed*).\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--in_tlf"
description: "Input GFF-like one-line-per-transcript format without exon/CDS features\
\ (see --tlf option \nbelow); automatic if the input filename ends with .tlf).\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--stream"
description: "Fast processing of input GFF/BED transcripts as they are received\
\ (no sorting, exons must \nbe grouped by transcript in the input data).\n"
info: null
direction: "input"
- name: "Clustering"
arguments:
- type: "boolean_true"
name: "--merge"
alternatives:
- "-M"
description: "Cluster the input transcripts into loci, discarding \"redundant\"\
\ transcripts (those with \nthe same exact introns and fully contained or equal\
\ boundaries).\n"
info: null
direction: "input"
- type: "file"
name: "--dupinfo"
alternatives:
- "-d"
description: "For --merge option, write duplication info to file <dupinfo>.\n"
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean_true"
name: "--cluster_only"
description: "Same as --merge but without discarding any of the \"duplicate\"\
\ transcripts, only create \n\"locus\" features.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--rm_redundant"
alternatives:
- "-K"
description: "For --merge option: also discard as redundant the shorter, fully\
\ contained transcripts (intron \nchains matching a part of the container).\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--no_boundary"
alternatives:
- "-Q"
description: "For --merge option, no longer require boundary containment when\
\ assessing redundancy (can be \ncombined with --rm_redundant); only introns\
\ have to match for multi-exon transcripts, and >=80%\noverlap for single-exon\
\ transcripts.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--no_overlap"
alternatives:
- "-Y"
description: "For --merge option, enforce --no_boundary but also discard overlapping\
\ single-exon transcripts,\neven on the opposite strand (can be combined with\
\ --rm_redudant).\n"
info: null
direction: "input"
resources:
- type: "bash_script"
path: "script.sh"
is_executable: true
description: "Validate, filter, convert and perform various other operations on GFF\
\ files."
test_resources:
- type: "bash_script"
path: "test.sh"
is_executable: true
- type: "file"
path: "test_data"
info: null
status: "enabled"
requirements:
commands:
- "ps"
keywords:
- "gff"
- "conversion"
- "validation"
- "filtering"
license: "MIT"
references:
doi:
- "10.12688/f1000research.23297.2"
links:
repository: "https://github.com/gpertea/gffread"
homepage: "https://ccb.jhu.edu/software/stringtie/gff.shtml#gffread"
documentation: "https://ccb.jhu.edu/software/stringtie/gff.shtml#gffread"
runners:
- type: "executable"
id: "executable"
docker_setup_strategy: "ifneedbepullelsecachedbuild"
- type: "nextflow"
id: "nextflow"
directives:
tag: "$id"
auto:
simplifyInput: true
simplifyOutput: false
transcript: false
publish: false
config:
labels:
mem1gb: "memory = 1000000000.B"
mem2gb: "memory = 2000000000.B"
mem5gb: "memory = 5000000000.B"
mem10gb: "memory = 10000000000.B"
mem20gb: "memory = 20000000000.B"
mem50gb: "memory = 50000000000.B"
mem100gb: "memory = 100000000000.B"
mem200gb: "memory = 200000000000.B"
mem500gb: "memory = 500000000000.B"
mem1tb: "memory = 1000000000000.B"
mem2tb: "memory = 2000000000000.B"
mem5tb: "memory = 5000000000000.B"
mem10tb: "memory = 10000000000000.B"
mem20tb: "memory = 20000000000000.B"
mem50tb: "memory = 50000000000000.B"
mem100tb: "memory = 100000000000000.B"
mem200tb: "memory = 200000000000000.B"
mem500tb: "memory = 500000000000000.B"
mem1gib: "memory = 1073741824.B"
mem2gib: "memory = 2147483648.B"
mem4gib: "memory = 4294967296.B"
mem8gib: "memory = 8589934592.B"
mem16gib: "memory = 17179869184.B"
mem32gib: "memory = 34359738368.B"
mem64gib: "memory = 68719476736.B"
mem128gib: "memory = 137438953472.B"
mem256gib: "memory = 274877906944.B"
mem512gib: "memory = 549755813888.B"
mem1tib: "memory = 1099511627776.B"
mem2tib: "memory = 2199023255552.B"
mem4tib: "memory = 4398046511104.B"
mem8tib: "memory = 8796093022208.B"
mem16tib: "memory = 17592186044416.B"
mem32tib: "memory = 35184372088832.B"
mem64tib: "memory = 70368744177664.B"
mem128tib: "memory = 140737488355328.B"
mem256tib: "memory = 281474976710656.B"
mem512tib: "memory = 562949953421312.B"
cpu1: "cpus = 1"
cpu2: "cpus = 2"
cpu5: "cpus = 5"
cpu10: "cpus = 10"
cpu20: "cpus = 20"
cpu50: "cpus = 50"
cpu100: "cpus = 100"
cpu200: "cpus = 200"
cpu500: "cpus = 500"
cpu1000: "cpus = 1000"
debug: false
container: "docker"
engines:
- type: "docker"
id: "docker"
image: "quay.io/biocontainers/gffread:0.12.7--hdcf5f25_3"
target_registry: "images.viash-hub.com"
target_tag: "v0.2"
namespace_separator: "/"
setup:
- type: "docker"
run:
- "echo \"gffread: \\\"$(gffread --version 2>&1)\\\"\" > /var/software_versions.txt\n"
entrypoint: []
cmd: null
- type: "native"
id: "native"
build_info:
config: "src/gffread/config.vsh.yaml"
runner: "executable"
engine: "docker|native"
output: "target/executable/gffread"
executable: "target/executable/gffread/gffread"
viash_version: "0.9.0-RC7"
git_commit: "f22ab0eab58dcd6bff89d8d73fe951953ff1260f"
git_remote: "https://github.com/viash-hub/biobox"
package_config:
name: "biobox"
version: "v0.2"
description: "A collection of bioinformatics tools for working with sequence data.\n"
info: null
viash_version: "0.9.0-RC7"
source: "src"
target: "target"
config_mods:
- ".requirements.commands := ['ps']\n"
- ".engines += { type: \"native\" }"
- ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
- ".engines[.type == 'docker'].target_tag := 'v0.2'"
keywords:
- "bioinformatics"
- "modules"
- "sequencing"
license: "MIT"
organization: "vsh"
links:
repository: "https://github.com/viash-hub/biobox"
issue_tracker: "https://github.com/viash-hub/biobox/issues"

2745
target/executable/gffread/gffread Executable file
View File

File diff suppressed because it is too large Load Diff

533
target/executable/lofreq/lofreq_call/.config.vsh.yaml Normal file
View File

@@ -0,0 +1,533 @@
name: "lofreq_call"
namespace: "lofreq"
version: "v0.2"
authors:
- name: "Kai Waldrant"
roles:
- "author"
- "maintainer"
info:
links:
email: "kai@data-intuitive.com"
github: "KaiWaldrant"
orcid: "0009-0003-8555-1361"
linkedin: "kaiwaldrant"
organizations:
- name: "Data Intuitive"
href: "https://www.data-intuitive.com"
role: "Bioinformatician"
- name: "Open Problems"
href: "https://openproblems.bio"
role: "Contributor"
argument_groups:
- name: "Inputs"
arguments:
- type: "file"
name: "--input"
description: "Input BAM file.\n"
info: null
example:
- "normal.bam"
must_exist: true
create_parent: true
required: true
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--input_bai"
description: "Index file for the input BAM file.\n"
info: null
example:
- "normal.bai"
must_exist: true
create_parent: true
required: true
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--ref"
alternatives:
- "-f"
description: "Indexed reference fasta file (gzip supported). Default: none.\n"
info: null
example:
- "reference.fasta"
must_exist: true
create_parent: true
required: true
direction: "input"
multiple: false
multiple_sep: ";"
- name: "Outputs"
arguments:
- type: "file"
name: "--out"
alternatives:
- "-o"
description: "Vcf output file. Default: stdout.\n"
info: null
example:
- "output.vcf"
must_exist: true
create_parent: true
required: true
direction: "output"
multiple: false
multiple_sep: ";"
- name: "Arguments"
arguments:
- type: "string"
name: "--region"
alternatives:
- "-r"
description: "Limit calls to this region (chrom:start-end). Default: none.\n"
info: null
example:
- "chr1:1000-2000"
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--bed"
alternatives:
- "-l"
description: "List of positions (chr pos) or regions (BED). Default: none.\n"
info: null
example:
- "regions.bed"
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--min_bq"
alternatives:
- "-q"
description: "Skip any base with baseQ smaller than INT. Default: 6.\n"
info: null
example:
- 6
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--min_alt_bq"
alternatives:
- "-Q"
description: "Skip alternate bases with baseQ smaller than INT. Default: 6.\n"
info: null
example:
- 6
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--def_alt_bq"
alternatives:
- "-R"
description: "Overwrite baseQs of alternate bases (that passed bq filter) with\
\ this value (-1: use median ref-bq; 0: keep). Default: 0.\n"
info: null
example:
- 0
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--min_jq"
alternatives:
- "-j"
description: "Skip any base with joinedQ smaller than INT. Default: 0.\n"
info: null
example:
- 0
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--min_alt_jq"
alternatives:
- "-J"
description: "Skip alternate bases with joinedQ smaller than INT. Default: 0.\n"
info: null
example:
- 0
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--def_alt_jq"
alternatives:
- "-K"
description: "Overwrite joinedQs of alternate bases (that passed jq filter) with\
\ this value (-1: use median ref-bq; 0: keep). Default: 0.\n"
info: null
example:
- 0
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean_true"
name: "--no_baq"
alternatives:
- "-B"
description: "Disable use of base-alignment quality (BAQ).\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--no_idaq"
alternatives:
- "-A"
description: "Don't use IDAQ values (NOT recommended under ANY circumstances other\
\ than debugging).\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--del_baq"
alternatives:
- "-D"
description: "Delete pre-existing BAQ values, i.e. compute even if already present\
\ in BAM.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--no_ext_baq"
alternatives:
- "-e"
description: "Use 'normal' BAQ (samtools default) instead of extended BAQ (both\
\ computed on the fly if not already present in lb tag).\n"
info: null
direction: "input"
- type: "integer"
name: "--min_mq"
alternatives:
- "-m"
description: "Skip reads with mapping quality smaller than INT. Default: 0.\n"
info: null
example:
- 0
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--max_mq"
alternatives:
- "-M"
description: "Cap mapping quality at INT. Default: 255.\n"
info: null
example:
- 255
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean_true"
name: "--no_mq"
alternatives:
- "-N"
description: "Don't merge mapping quality in LoFreq's model.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--call_indels"
description: "Enable indel calls (note: preprocess your file to include indel\
\ alignment qualities!).\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--only_indels"
description: "Only call indels; no SNVs.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--src_qual"
alternatives:
- "-s"
description: "Enable computation of source quality.\n"
info: null
direction: "input"
- type: "file"
name: "--ign_vcf"
alternatives:
- "-S"
description: "Ignore variants in this vcf file for source quality computation.\
\ Multiple files can be given separated by commas.\n"
info: null
example:
- "variants.vcf"
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--def_nm_q"
alternatives:
- "-T"
description: "If >= 0, then replace non-match base qualities with this default\
\ value. Default: -1.\n"
info: null
example:
- -1
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "double"
name: "--sig"
alternatives:
- "-a"
description: "P-Value cutoff / significance level. Default: 0.010000.\n"
info: null
example:
- 0.01
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--bonf"
alternatives:
- "-b"
description: "Bonferroni factor. 'dynamic' (increase per actually performed test)\
\ or INT. Default: Dynamic.\n"
info: null
example:
- "dynamic"
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--min_cov"
alternatives:
- "-C"
description: "Test only positions having at least this coverage. Default: 1.\n\
(note: without --no-default-filter default filters (incl. coverage) kick in\
\ after predictions are done).\n"
info: null
example:
- 1
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--max_depth"
alternatives:
- "-d"
description: "Cap coverage at this depth. Default: 1000000.\n"
info: null
example:
- 1000000
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean_true"
name: "--illumina_13"
description: "Assume the quality is Illumina-1.3-1.7/ASCII+64 encoded.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--use_orphan"
description: "Count anomalous read pairs (i.e. where mate is not aligned properly).\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--plp_summary_only"
description: "No variant calling. Just output pileup summary per column.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--no_default_filter"
description: "Don't run default 'lofreq filter' automatically after calling variants.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--force_overwrite"
description: "Overwrite any existing output.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--verbose"
description: "Be verbose.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--debug"
description: "Enable debugging.\n"
info: null
direction: "input"
resources:
- type: "bash_script"
path: "script.sh"
is_executable: true
description: "Call variants from a BAM file.\n\nLoFreq* (i.e. LoFreq version 2) is\
\ a fast and sensitive variant-caller for inferring SNVs and indels from next-generation\
\ sequencing data. It makes full use of base-call qualities and other sources of\
\ errors inherent in sequencing (e.g. mapping or base/indel alignment uncertainty),\
\ which are usually ignored by other methods or only used for filtering.\n\nLoFreq*\
\ can run on almost any type of aligned sequencing data (e.g. Illumina, IonTorrent\
\ or Pacbio) since no machine- or sequencing-technology dependent thresholds are\
\ used. It automatically adapts to changes in coverage and sequencing quality and\
\ can therefore be applied to a variety of data-sets e.g. viral/quasispecies, bacterial,\
\ metagenomics or somatic data.\n\nLoFreq* is very sensitive; most notably, it is\
\ able to predict variants below the average base-call quality (i.e. sequencing\
\ error rate). Each variant call is assigned a p-value which allows for rigorous\
\ false positive control. Even though it uses no approximations or heuristics, it\
\ is very efficient due to several runtime optimizations and also provides a (pseudo-)parallel\
\ implementation. LoFreq* is generic and fast enough to be applied to high-coverage\
\ data and large genomes. On a single processor it takes a minute to analyze Dengue\
\ genome sequencing data with nearly 4000X coverage, roughly one hour to call SNVs\
\ on a 600X coverage E.coli genome and also roughly an hour to run on a 100X coverage\
\ human exome dataset.\n"
test_resources:
- type: "bash_script"
path: "test.sh"
is_executable: true
- type: "file"
path: "test_data"
info: null
status: "enabled"
requirements:
commands:
- "ps"
keywords:
- "variant calling"
- "low frequancy variant calling"
- "lofreq"
- "lofreq/call"
license: "MIT"
references:
doi:
- "10.1093/nar/gks918"
links:
repository: "https://github.com/viash-hub/biobox"
homepage: "https://csb5.github.io/lofreq/"
documentation: "https://csb5.github.io/lofreq/commands/"
runners:
- type: "executable"
id: "executable"
docker_setup_strategy: "ifneedbepullelsecachedbuild"
- type: "nextflow"
id: "nextflow"
directives:
tag: "$id"
auto:
simplifyInput: true
simplifyOutput: false
transcript: false
publish: false
config:
labels:
mem1gb: "memory = 1000000000.B"
mem2gb: "memory = 2000000000.B"
mem5gb: "memory = 5000000000.B"
mem10gb: "memory = 10000000000.B"
mem20gb: "memory = 20000000000.B"
mem50gb: "memory = 50000000000.B"
mem100gb: "memory = 100000000000.B"
mem200gb: "memory = 200000000000.B"
mem500gb: "memory = 500000000000.B"
mem1tb: "memory = 1000000000000.B"
mem2tb: "memory = 2000000000000.B"
mem5tb: "memory = 5000000000000.B"
mem10tb: "memory = 10000000000000.B"
mem20tb: "memory = 20000000000000.B"
mem50tb: "memory = 50000000000000.B"
mem100tb: "memory = 100000000000000.B"
mem200tb: "memory = 200000000000000.B"
mem500tb: "memory = 500000000000000.B"
mem1gib: "memory = 1073741824.B"
mem2gib: "memory = 2147483648.B"
mem4gib: "memory = 4294967296.B"
mem8gib: "memory = 8589934592.B"
mem16gib: "memory = 17179869184.B"
mem32gib: "memory = 34359738368.B"
mem64gib: "memory = 68719476736.B"
mem128gib: "memory = 137438953472.B"
mem256gib: "memory = 274877906944.B"
mem512gib: "memory = 549755813888.B"
mem1tib: "memory = 1099511627776.B"
mem2tib: "memory = 2199023255552.B"
mem4tib: "memory = 4398046511104.B"
mem8tib: "memory = 8796093022208.B"
mem16tib: "memory = 17592186044416.B"
mem32tib: "memory = 35184372088832.B"
mem64tib: "memory = 70368744177664.B"
mem128tib: "memory = 140737488355328.B"
mem256tib: "memory = 281474976710656.B"
mem512tib: "memory = 562949953421312.B"
cpu1: "cpus = 1"
cpu2: "cpus = 2"
cpu5: "cpus = 5"
cpu10: "cpus = 10"
cpu20: "cpus = 20"
cpu50: "cpus = 50"
cpu100: "cpus = 100"
cpu200: "cpus = 200"
cpu500: "cpus = 500"
cpu1000: "cpus = 1000"
debug: false
container: "docker"
engines:
- type: "docker"
id: "docker"
image: "quay.io/biocontainers/lofreq:2.1.5--py38h794fc9e_10"
target_registry: "images.viash-hub.com"
target_tag: "v0.2"
namespace_separator: "/"
setup:
- type: "docker"
run:
- "version=$(lofreq version | grep 'version' | sed 's/version: //') && \\\necho\
\ \"lofreq: $version\" > /var/software_versions.txt\n"
entrypoint: []
cmd: null
- type: "native"
id: "native"
build_info:
config: "src/lofreq/call/config.vsh.yaml"
runner: "executable"
engine: "docker|native"
output: "target/executable/lofreq/lofreq_call"
executable: "target/executable/lofreq/lofreq_call/lofreq_call"
viash_version: "0.9.0-RC7"
git_commit: "f22ab0eab58dcd6bff89d8d73fe951953ff1260f"
git_remote: "https://github.com/viash-hub/biobox"
package_config:
name: "biobox"
version: "v0.2"
description: "A collection of bioinformatics tools for working with sequence data.\n"
info: null
viash_version: "0.9.0-RC7"
source: "src"
target: "target"
config_mods:
- ".requirements.commands := ['ps']\n"
- ".engines += { type: \"native\" }"
- ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
- ".engines[.type == 'docker'].target_tag := 'v0.2'"
keywords:
- "bioinformatics"
- "modules"
- "sequencing"
license: "MIT"
organization: "vsh"
links:
repository: "https://github.com/viash-hub/biobox"
issue_tracker: "https://github.com/viash-hub/biobox/issues"

2030
target/executable/lofreq/lofreq_call/lofreq_call Executable file
View File

File diff suppressed because it is too large Load Diff

241
target/executable/lofreq/lofreq_indelqual/.config.vsh.yaml Normal file
View File

@@ -0,0 +1,241 @@
name: "lofreq_indelqual"
namespace: "lofreq"
version: "v0.2"
authors:
- name: "Kai Waldrant"
roles:
- "author"
- "maintainer"
info:
links:
email: "kai@data-intuitive.com"
github: "KaiWaldrant"
orcid: "0009-0003-8555-1361"
linkedin: "kaiwaldrant"
organizations:
- name: "Data Intuitive"
href: "https://www.data-intuitive.com"
role: "Bioinformatician"
- name: "Open Problems"
href: "https://openproblems.bio"
role: "Contributor"
argument_groups:
- name: "Inputs"
arguments:
- type: "file"
name: "--input"
description: "Input BAM file.\n"
info: null
example:
- "normal.bam"
must_exist: true
create_parent: true
required: true
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--ref"
alternatives:
- "-f"
description: "Reference sequence used for mapping (Only required for --dindel).\n"
info: null
example:
- "reference.fasta"
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- name: "Outputs"
arguments:
- type: "file"
name: "--out"
alternatives:
- "-o"
description: "Output BAM file.\n"
info: null
example:
- "output.bam"
must_exist: true
create_parent: true
required: true
direction: "output"
multiple: false
multiple_sep: ";"
- name: "Arguments"
arguments:
- type: "string"
name: "--uniform"
alternatives:
- "-u"
description: "Add this indel quality uniformly to all bases. Use two comma separated\
\ values to specify insertion and deletion quality separately. (clashes with\
\ --dindel).\n"
info: null
example:
- "50,50"
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean_true"
name: "--dindel"
description: "Add Dindel's indel qualities (Illumina specific) (clashes with -u;\
\ needs --ref).\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--verbose"
description: "Be verbose.\n"
info: null
direction: "input"
resources:
- type: "bash_script"
path: "script.sh"
is_executable: true
description: "Insert indel qualities into BAM file (required for indel predictions).\n\
\nThe preferred way of inserting indel qualities should be via GATK's BQSR (>=2)\
\ If that's not possible, use this subcommand.\nThe command has two modes: 'uniform'\
\ and 'dindel':\n- 'uniform' will assign a given value uniformly, whereas\n- 'dindel'\
\ will insert indel qualities based on Dindel (PMID 20980555).\nBoth will overwrite\
\ any existing values.\nDo not realign your BAM file afterwards!\n"
test_resources:
- type: "bash_script"
path: "test.sh"
is_executable: true
- type: "file"
path: "test_data"
info: null
status: "enabled"
requirements:
commands:
- "ps"
keywords:
- "bam"
- "indel"
- "qualities"
- "indelqual"
- "lofreq"
- "lofreq/indelqual"
license: "MIT"
references:
doi:
- "10.1093/nar/gks918"
links:
repository: "https://github.com/viash-hub/biobox"
homepage: "https://csb5.github.io/lofreq/"
documentation: "https://csb5.github.io/lofreq/commands/"
runners:
- type: "executable"
id: "executable"
docker_setup_strategy: "ifneedbepullelsecachedbuild"
- type: "nextflow"
id: "nextflow"
directives:
tag: "$id"
auto:
simplifyInput: true
simplifyOutput: false
transcript: false
publish: false
config:
labels:
mem1gb: "memory = 1000000000.B"
mem2gb: "memory = 2000000000.B"
mem5gb: "memory = 5000000000.B"
mem10gb: "memory = 10000000000.B"
mem20gb: "memory = 20000000000.B"
mem50gb: "memory = 50000000000.B"
mem100gb: "memory = 100000000000.B"
mem200gb: "memory = 200000000000.B"
mem500gb: "memory = 500000000000.B"
mem1tb: "memory = 1000000000000.B"
mem2tb: "memory = 2000000000000.B"
mem5tb: "memory = 5000000000000.B"
mem10tb: "memory = 10000000000000.B"
mem20tb: "memory = 20000000000000.B"
mem50tb: "memory = 50000000000000.B"
mem100tb: "memory = 100000000000000.B"
mem200tb: "memory = 200000000000000.B"
mem500tb: "memory = 500000000000000.B"
mem1gib: "memory = 1073741824.B"
mem2gib: "memory = 2147483648.B"
mem4gib: "memory = 4294967296.B"
mem8gib: "memory = 8589934592.B"
mem16gib: "memory = 17179869184.B"
mem32gib: "memory = 34359738368.B"
mem64gib: "memory = 68719476736.B"
mem128gib: "memory = 137438953472.B"
mem256gib: "memory = 274877906944.B"
mem512gib: "memory = 549755813888.B"
mem1tib: "memory = 1099511627776.B"
mem2tib: "memory = 2199023255552.B"
mem4tib: "memory = 4398046511104.B"
mem8tib: "memory = 8796093022208.B"
mem16tib: "memory = 17592186044416.B"
mem32tib: "memory = 35184372088832.B"
mem64tib: "memory = 70368744177664.B"
mem128tib: "memory = 140737488355328.B"
mem256tib: "memory = 281474976710656.B"
mem512tib: "memory = 562949953421312.B"
cpu1: "cpus = 1"
cpu2: "cpus = 2"
cpu5: "cpus = 5"
cpu10: "cpus = 10"
cpu20: "cpus = 20"
cpu50: "cpus = 50"
cpu100: "cpus = 100"
cpu200: "cpus = 200"
cpu500: "cpus = 500"
cpu1000: "cpus = 1000"
debug: false
container: "docker"
engines:
- type: "docker"
id: "docker"
image: "quay.io/biocontainers/lofreq:2.1.5--py38h794fc9e_10"
target_registry: "images.viash-hub.com"
target_tag: "v0.2"
namespace_separator: "/"
setup:
- type: "docker"
run:
- "version=$(lofreq version | grep 'version' | sed 's/version: //') && \\\necho\
\ \"lofreq: $version\" > /var/software_versions.txt\n"
entrypoint: []
cmd: null
- type: "native"
id: "native"
build_info:
config: "src/lofreq/indelqual/config.vsh.yaml"
runner: "executable"
engine: "docker|native"
output: "target/executable/lofreq/lofreq_indelqual"
executable: "target/executable/lofreq/lofreq_indelqual/lofreq_indelqual"
viash_version: "0.9.0-RC7"
git_commit: "f22ab0eab58dcd6bff89d8d73fe951953ff1260f"
git_remote: "https://github.com/viash-hub/biobox"
package_config:
name: "biobox"
version: "v0.2"
description: "A collection of bioinformatics tools for working with sequence data.\n"
info: null
viash_version: "0.9.0-RC7"
source: "src"
target: "target"
config_mods:
- ".requirements.commands := ['ps']\n"
- ".engines += { type: \"native\" }"
- ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
- ".engines[.type == 'docker'].target_tag := 'v0.2'"
keywords:
- "bioinformatics"
- "modules"
- "sequencing"
license: "MIT"
organization: "vsh"
links:
repository: "https://github.com/viash-hub/biobox"
issue_tracker: "https://github.com/viash-hub/biobox/issues"

1208
target/executable/lofreq/lofreq_indelqual/lofreq_indelqual Executable file
View File

File diff suppressed because it is too large Load Diff

482
target/executable/multiqc/.config.vsh.yaml Normal file
View File

@@ -0,0 +1,482 @@
name: "multiqc"
version: "v0.2"
authors:
- name: "Dorien Roosen"
roles:
- "author"
- "maintainer"
info:
links:
email: "dorien@data-intuitive.com"
github: "dorien-er"
linkedin: "dorien-roosen"
organizations:
- name: "Data Intuitive"
href: "https://www.data-intuitive.com"
role: "Data Scientist"
argument_groups:
- name: "Input"
arguments:
- type: "file"
name: "--input"
description: "File paths to be searched for analysis results to be included in\
\ the report.\n"
info: null
example:
- "data/results"
must_exist: true
create_parent: true
required: true
direction: "input"
multiple: true
multiple_sep: ";"
- name: "Ouput"
arguments:
- type: "file"
name: "--output_report"
description: "Filepath of the generated report.\n"
info: null
example:
- "multiqc_report.html"
must_exist: false
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--output_data"
description: "Output directory for parsed data files. If not provided, parsed\
\ data will not be published.\n"
info: null
example:
- "multiqc_data"
must_exist: false
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--output_plots"
description: "Output directory for generated plots. If not provided, plots will\
\ not be published.\n"
info: null
example:
- "multiqc_plots"
must_exist: false
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- name: "Modules and analyses to run"
arguments:
- type: "string"
name: "--include_modules"
description: "Use only these module"
info: null
example:
- "fastqc"
- "cutadapt"
required: false
direction: "input"
multiple: true
multiple_sep: ";"
- type: "string"
name: "--exclude_modules"
description: "Do not use only these modules"
info: null
example:
- "fastqc"
- "cutadapt"
required: false
direction: "input"
multiple: true
multiple_sep: ";"
- type: "string"
name: "--ignore_analysis"
info: null
example:
- "run_one/*"
- "run_two/*"
required: false
direction: "input"
multiple: true
multiple_sep: ";"
- type: "string"
name: "--ignore_samples"
info: null
example:
- "sample_1*"
- "sample_3*"
required: false
direction: "input"
multiple: true
multiple_sep: ";"
- type: "boolean_true"
name: "--ignore_symlinks"
description: "Ignore symlinked directories and files"
info: null
direction: "input"
- name: "Sample name handling"
arguments:
- type: "boolean_true"
name: "--dirs"
description: "Prepend directory to sample names to avoid clashing filenames"
info: null
direction: "input"
- type: "integer"
name: "--dirs_depth"
description: "Prepend n directories to sample names. Negative number to take from\
\ start of path."
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean_true"
name: "--full_names"
description: "Do not clean the sample names (leave as full file name)"
info: null
direction: "input"
- type: "boolean_true"
name: "--fn_as_s_name"
description: "Use the log filename as the sample name"
info: null
direction: "input"
- type: "file"
name: "--replace_names"
description: "TSV file to rename sample names during report generation"
info: null
example:
- "replace_names.tsv"
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- name: "Report Customisation"
arguments:
- type: "string"
name: "--title"
description: "Report title. Printed as page header, used for filename if not otherwise\
\ specified.\n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--comment"
description: "Custom comment, will be printed at the top of the report.\n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--template"
description: "Report template to use.\n"
info: null
required: false
choices:
- "default"
- "gathered"
- "geo"
- "highcharts"
- "sections"
- "simple"
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--sample_names"
description: "TSV file containing alternative sample names for renaming buttons\
\ in the report.\n"
info: null
example:
- "sample_names.tsv"
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--sample_filters"
description: "TSV file containing show/hide patterns for the report\n"
info: null
example:
- "sample_filters.tsv"
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--custom_css_file"
description: "Custom CSS file to add to the final report\n"
info: null
example:
- "custom_style_sheet.css"
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean_true"
name: "--profile_runtime"
description: "Add analysis of how long MultiQC takes to run to the report\n"
info: null
direction: "input"
- name: "MultiQC behaviour"
arguments:
- type: "boolean_true"
name: "--verbose"
description: "Increase output verbosity.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--quiet"
description: "Only show log warnings\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--strict"
description: "Don't catch exceptions, run additional code checks to help development.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--development"
description: "Development mode. Do not compress and minimise JS, export uncompressed\
\ plot data.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--require_logs"
description: "Require all explicitly requested modules to have log files. If not,\
\ MultiQC will exit with an error.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--no_megaqc_upload"
description: "Don't upload generated report to MegaQC, even if MegaQC options\
\ are found.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--no_ansi"
description: "Disable coloured log output.\n"
info: null
direction: "input"
- type: "string"
name: "--cl_config"
description: "YAML formatted string that allows to customize MultiQC behaviour\
\ like input file detection.\n"
info: null
example:
- "qualimap_config: { general_stats_coverage: [20,40,200] }"
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- name: "Output format"
arguments:
- type: "boolean_true"
name: "--flat"
description: "Use only flat plots (static images).\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--interactive"
description: "Use only interactive plots (in-browser Javascript).\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--data_dir"
description: "Force the parsed data directory to be created.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--no_data_dir"
description: "Prevent the parsed data directory from being created.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--zip_data_dir"
description: "Compress the data directory.\n"
info: null
direction: "input"
- type: "string"
name: "--data_format"
description: "Output parsed data in a different format than the default 'txt'.\n"
info: null
required: false
choices:
- "tsv"
- "csv"
- "json"
- "yaml"
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean_true"
name: "--pdf"
description: "Creates PDF report with the 'simple' template. Requires Pandoc to\
\ be installed.\n"
info: null
direction: "input"
resources:
- type: "bash_script"
path: "script.sh"
is_executable: true
description: "MultiQC aggregates results from bioinformatics analyses across many\
\ samples into a single report.\nIt searches a given directory for analysis logs\
\ and compiles a HTML report. It's a general use tool, perfect for summarising the\
\ output from numerous bioinformatics tools.\n"
test_resources:
- type: "bash_script"
path: "test.sh"
is_executable: true
- type: "file"
path: "test_data"
info:
keywords:
- "QC"
- "html report"
- "aggregate analysis"
links:
homepage: "https://multiqc.info/"
documentation: "https://multiqc.info/docs/"
repository: "https://github.com/MultiQC/MultiQC"
references:
doi: "10.1093/bioinformatics/btw354"
licence: "GPL v3 or later"
status: "enabled"
requirements:
commands:
- "ps"
license: "MIT"
links:
repository: "https://github.com/viash-hub/biobox"
runners:
- type: "executable"
id: "executable"
docker_setup_strategy: "ifneedbepullelsecachedbuild"
- type: "nextflow"
id: "nextflow"
directives:
tag: "$id"
auto:
simplifyInput: true
simplifyOutput: false
transcript: false
publish: false
config:
labels:
mem1gb: "memory = 1000000000.B"
mem2gb: "memory = 2000000000.B"
mem5gb: "memory = 5000000000.B"
mem10gb: "memory = 10000000000.B"
mem20gb: "memory = 20000000000.B"
mem50gb: "memory = 50000000000.B"
mem100gb: "memory = 100000000000.B"
mem200gb: "memory = 200000000000.B"
mem500gb: "memory = 500000000000.B"
mem1tb: "memory = 1000000000000.B"
mem2tb: "memory = 2000000000000.B"
mem5tb: "memory = 5000000000000.B"
mem10tb: "memory = 10000000000000.B"
mem20tb: "memory = 20000000000000.B"
mem50tb: "memory = 50000000000000.B"
mem100tb: "memory = 100000000000000.B"
mem200tb: "memory = 200000000000000.B"
mem500tb: "memory = 500000000000000.B"
mem1gib: "memory = 1073741824.B"
mem2gib: "memory = 2147483648.B"
mem4gib: "memory = 4294967296.B"
mem8gib: "memory = 8589934592.B"
mem16gib: "memory = 17179869184.B"
mem32gib: "memory = 34359738368.B"
mem64gib: "memory = 68719476736.B"
mem128gib: "memory = 137438953472.B"
mem256gib: "memory = 274877906944.B"
mem512gib: "memory = 549755813888.B"
mem1tib: "memory = 1099511627776.B"
mem2tib: "memory = 2199023255552.B"
mem4tib: "memory = 4398046511104.B"
mem8tib: "memory = 8796093022208.B"
mem16tib: "memory = 17592186044416.B"
mem32tib: "memory = 35184372088832.B"
mem64tib: "memory = 70368744177664.B"
mem128tib: "memory = 140737488355328.B"
mem256tib: "memory = 281474976710656.B"
mem512tib: "memory = 562949953421312.B"
cpu1: "cpus = 1"
cpu2: "cpus = 2"
cpu5: "cpus = 5"
cpu10: "cpus = 10"
cpu20: "cpus = 20"
cpu50: "cpus = 50"
cpu100: "cpus = 100"
cpu200: "cpus = 200"
cpu500: "cpus = 500"
cpu1000: "cpus = 1000"
debug: false
container: "docker"
engines:
- type: "docker"
id: "docker"
image: "quay.io/biocontainers/multiqc:1.21--pyhdfd78af_0"
target_registry: "images.viash-hub.com"
target_tag: "v0.2"
namespace_separator: "/"
setup:
- type: "docker"
run:
- "multiqc --version | sed 's/multiqc, version\\s\\(.*\\)/multiqc: \"\\1\"/' >\
\ /var/software_versions.txt\n"
test_setup:
- type: "apt"
packages:
- "jq"
interactive: false
entrypoint: []
cmd: null
- type: "native"
id: "native"
build_info:
config: "src/multiqc/config.vsh.yaml"
runner: "executable"
engine: "docker|native"
output: "target/executable/multiqc"
executable: "target/executable/multiqc/multiqc"
viash_version: "0.9.0-RC7"
git_commit: "f22ab0eab58dcd6bff89d8d73fe951953ff1260f"
git_remote: "https://github.com/viash-hub/biobox"
package_config:
name: "biobox"
version: "v0.2"
description: "A collection of bioinformatics tools for working with sequence data.\n"
info: null
viash_version: "0.9.0-RC7"
source: "src"
target: "target"
config_mods:
- ".requirements.commands := ['ps']\n"
- ".engines += { type: \"native\" }"
- ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
- ".engines[.type == 'docker'].target_tag := 'v0.2'"
keywords:
- "bioinformatics"
- "modules"
- "sequencing"
license: "MIT"
organization: "vsh"
links:
repository: "https://github.com/viash-hub/biobox"
issue_tracker: "https://github.com/viash-hub/biobox/issues"

1985
target/executable/multiqc/multiqc Executable file
View File

File diff suppressed because it is too large Load Diff

424
target/executable/pear/.config.vsh.yaml Normal file
View File

@@ -0,0 +1,424 @@
name: "pear"
version: "v0.2"
authors:
- name: "Kai Waldrant"
roles:
- "author"
- "maintainer"
info:
links:
email: "kai@data-intuitive.com"
github: "KaiWaldrant"
orcid: "0009-0003-8555-1361"
linkedin: "kaiwaldrant"
organizations:
- name: "Data Intuitive"
href: "https://www.data-intuitive.com"
role: "Bioinformatician"
- name: "Open Problems"
href: "https://openproblems.bio"
role: "Contributor"
argument_groups:
- name: "Inputs"
arguments:
- type: "file"
name: "--forward_fastq"
alternatives:
- "-f"
description: "Forward paired-end FASTQ file"
info: null
example:
- "forward.fastq"
must_exist: true
create_parent: true
required: true
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--reverse_fastq"
alternatives:
- "-r"
description: "Reverse paired-end FASTQ file"
info: null
example:
- "reverse.fastq"
must_exist: true
create_parent: true
required: true
direction: "input"
multiple: false
multiple_sep: ";"
- name: "Outputs"
arguments:
- type: "file"
name: "--assembled"
description: "The output file containing assembled reads. Can be compressed with\
\ gzip."
info: null
must_exist: true
create_parent: true
required: true
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--unassembled_forward"
description: "The output file containing forward reads that could not be assembled.\
\ Can be compressed with gzip."
info: null
must_exist: true
create_parent: true
required: true
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--unassembled_reverse"
description: "The output file containing reverse reads that could not be assembled.\
\ Can be compressed with gzip."
info: null
must_exist: true
create_parent: true
required: true
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--discarded"
description: "The output file containing reads that were discarded due to too\
\ low quality or too many uncalled bases. Can be compressed with gzip."
info: null
must_exist: true
create_parent: true
required: true
direction: "output"
multiple: false
multiple_sep: ";"
- name: "Arguments"
arguments:
- type: "double"
name: "--p_value"
alternatives:
- "-p"
description: "Specify a p-value for the statistical test. If the computed p-value\
\ of a possible assembly exceeds the specified p-value then paired-end read\
\ will not be assembled. Valid options are: 0.0001, 0.001, 0.01, 0.05 and 1.0.\
\ Setting 1.0 disables the test.\n"
info: null
example:
- 0.01
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--min_overlap"
alternatives:
- "-v"
description: "Specify the minimum overlap size. The minimum overlap may be set\
\ to 1 when the statistical test is used. However, further restricting the minimum\
\ overlap size to a proper value may reduce false-positive assembles.\n"
info: null
example:
- 10
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--max_assembly_length"
alternatives:
- "-m"
description: "Specify the maximum possible length of the assembled sequences.\
\ Setting this value to 0 disables the restriction and assembled sequences may\
\ be arbitrary long.\n"
info: null
example:
- 0
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--min_assembly_length"
alternatives:
- "-n"
description: "Specify the minimum possible length of the assembled sequences.\
\ Setting this value to 0 disables the restriction and assembled sequences may\
\ be arbitrary short.\n"
info: null
example:
- 0
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--min_trim_length"
alternatives:
- "-t"
description: "Specify the minimum length of reads after trimming the low quality\
\ part (see option -q)\n"
info: null
example:
- 1
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--quality_threshold"
alternatives:
- "-q"
description: "Specify the quality threshold for trimming the low quality part\
\ of a read. If the quality scores of two consecutive bases are strictly less\
\ than the specified threshold, the rest of the read will be trimmed.\n"
info: null
example:
- 0
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "double"
name: "--max_uncalled_base"
alternatives:
- "-u"
description: "Specify the maximal proportion of uncalled bases in a read. Setting\
\ this value to 0 will cause PEAR to discard all reads containing uncalled bases.\
\ The other extreme setting is 1 which causes PEAR to process all reads independent\
\ on the number of uncalled bases.\n"
info: null
example:
- 1.0
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--test_method"
alternatives:
- "-g"
description: "Specify the type of statistical test. Two options are available.\
\ 1: Given the minimum allowed overlap, test using the highest OES. Note that\
\ due to its discrete nature, this test usually yields a lower p-value for the\
\ assembled read than the cut- off (specified by -p). For example, setting the\
\ cut-off to 0.05 using this test, the assembled reads might have an actual\
\ p-value of 0.02.\n2. Use the acceptance probability (m.a.p). This test methods\
\ computes the same probability as test method 1. However, it assumes that the\
\ minimal overlap is the observed overlap with the highest OES, instead of the\
\ one specified by -v. Therefore, this is not a valid statistical test and the\
\ 'p-value' is in fact the maximal probability for accepting the assembly. Nevertheless,\
\ we observed in practice that for the case the actual overlap sizes are relatively\
\ small, test 2 can correctly assemble more reads with only slightly higher\
\ false-positive rate.\n"
info: null
example:
- 1
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean_true"
name: "--emperical_freqs"
alternatives:
- "-e"
description: "Disable empirical base frequencies.\n"
info: null
direction: "input"
- type: "integer"
name: "--score_method"
alternatives:
- "-s"
description: "Specify the scoring method. 1. OES with +1 for match and -1 for\
\ mismatch. 2: Assembly score (AS). Use +1 for match and -1 for mismatch multiplied\
\ by base quality scores. 3: Ignore quality scores and use +1 for a match and\
\ -1 for a mismatch.\n"
info: null
example:
- 2
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--phred_base"
alternatives:
- "-b"
description: "Base PHRED quality score.\n"
info: null
example:
- 33
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--cap"
alternatives:
- "-c"
description: "Specify the upper bound for the resulting quality score. If set\
\ to zero, capping is disabled.\n"
info: null
example:
- 40
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean_true"
name: "--nbase"
alternatives:
- "-z"
description: "When merging a base-pair that consists of two non-equal bases out\
\ of which none is degenerate, set the merged base to N and use the highest\
\ quality score of the two bases\n"
info: null
direction: "input"
resources:
- type: "bash_script"
path: "script.sh"
is_executable: true
description: "PEAR is an ultrafast, memory-efficient and highly accurate pair-end\
\ read merger. It is fully parallelized and can run with as low as just a few kilobytes\
\ of memory.\n\nPEAR evaluates all possible paired-end read overlaps and without\
\ requiring the target fragment size as input. In addition, it implements a statistical\
\ test for minimizing false-positive results. Together with a highly optimized implementation,\
\ it can merge millions of paired end reads within a couple of minutes on a standard\
\ desktop computer.\n"
test_resources:
- type: "bash_script"
path: "test.sh"
is_executable: true
- type: "file"
path: "test_data"
info: null
status: "enabled"
requirements:
commands:
- "ps"
keywords:
- "pair-end"
- "read"
- "merge"
license: "CC-BY-NC-SA-3.0"
references:
doi:
- "10.1093/bioinformatics/btt593"
links:
repository: "https://github.com/tseemann/PEAR"
homepage: "https://cme.h-its.org/exelixis/web/software/pear"
documentation: "https://cme.h-its.org/exelixis/web/software/pear/doc.html"
runners:
- type: "executable"
id: "executable"
docker_setup_strategy: "ifneedbepullelsecachedbuild"
- type: "nextflow"
id: "nextflow"
directives:
tag: "$id"
auto:
simplifyInput: true
simplifyOutput: false
transcript: false
publish: false
config:
labels:
mem1gb: "memory = 1000000000.B"
mem2gb: "memory = 2000000000.B"
mem5gb: "memory = 5000000000.B"
mem10gb: "memory = 10000000000.B"
mem20gb: "memory = 20000000000.B"
mem50gb: "memory = 50000000000.B"
mem100gb: "memory = 100000000000.B"
mem200gb: "memory = 200000000000.B"
mem500gb: "memory = 500000000000.B"
mem1tb: "memory = 1000000000000.B"
mem2tb: "memory = 2000000000000.B"
mem5tb: "memory = 5000000000000.B"
mem10tb: "memory = 10000000000000.B"
mem20tb: "memory = 20000000000000.B"
mem50tb: "memory = 50000000000000.B"
mem100tb: "memory = 100000000000000.B"
mem200tb: "memory = 200000000000000.B"
mem500tb: "memory = 500000000000000.B"
mem1gib: "memory = 1073741824.B"
mem2gib: "memory = 2147483648.B"
mem4gib: "memory = 4294967296.B"
mem8gib: "memory = 8589934592.B"
mem16gib: "memory = 17179869184.B"
mem32gib: "memory = 34359738368.B"
mem64gib: "memory = 68719476736.B"
mem128gib: "memory = 137438953472.B"
mem256gib: "memory = 274877906944.B"
mem512gib: "memory = 549755813888.B"
mem1tib: "memory = 1099511627776.B"
mem2tib: "memory = 2199023255552.B"
mem4tib: "memory = 4398046511104.B"
mem8tib: "memory = 8796093022208.B"
mem16tib: "memory = 17592186044416.B"
mem32tib: "memory = 35184372088832.B"
mem64tib: "memory = 70368744177664.B"
mem128tib: "memory = 140737488355328.B"
mem256tib: "memory = 281474976710656.B"
mem512tib: "memory = 562949953421312.B"
cpu1: "cpus = 1"
cpu2: "cpus = 2"
cpu5: "cpus = 5"
cpu10: "cpus = 10"
cpu20: "cpus = 20"
cpu50: "cpus = 50"
cpu100: "cpus = 100"
cpu200: "cpus = 200"
cpu500: "cpus = 500"
cpu1000: "cpus = 1000"
debug: false
container: "docker"
engines:
- type: "docker"
id: "docker"
image: "quay.io/biocontainers/pear:0.9.6--h9d449c0_10"
target_registry: "images.viash-hub.com"
target_tag: "v0.2"
namespace_separator: "/"
setup:
- type: "docker"
run:
- "version=$(pear -h | grep 'PEAR v' | sed 's/PEAR v//' | sed 's/ .*//') && \\\
\necho \"pear: $version\" > /var/software_versions.txt\n"
entrypoint: []
cmd: null
- type: "native"
id: "native"
build_info:
config: "src/pear/config.vsh.yaml"
runner: "executable"
engine: "docker|native"
output: "target/executable/pear"
executable: "target/executable/pear/pear"
viash_version: "0.9.0-RC7"
git_commit: "f22ab0eab58dcd6bff89d8d73fe951953ff1260f"
git_remote: "https://github.com/viash-hub/biobox"
package_config:
name: "biobox"
version: "v0.2"
description: "A collection of bioinformatics tools for working with sequence data.\n"
info: null
viash_version: "0.9.0-RC7"
source: "src"
target: "target"
config_mods:
- ".requirements.commands := ['ps']\n"
- ".engines += { type: \"native\" }"
- ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
- ".engines[.type == 'docker'].target_tag := 'v0.2'"
keywords:
- "bioinformatics"
- "modules"
- "sequencing"
license: "MIT"
organization: "vsh"
links:
repository: "https://github.com/viash-hub/biobox"
issue_tracker: "https://github.com/viash-hub/biobox/issues"

1705
target/executable/pear/pear Executable file
View File

File diff suppressed because it is too large Load Diff

290
target/executable/qualimap/qualimap_rnaseq/.config.vsh.yaml Normal file
View File

@@ -0,0 +1,290 @@
name: "qualimap_rnaseq"
namespace: "qualimap"
version: "v0.2"
authors:
- name: "Dorien Roosen"
roles:
- "author"
- "maintainer"
info:
links:
email: "dorien@data-intuitive.com"
github: "dorien-er"
linkedin: "dorien-roosen"
organizations:
- name: "Data Intuitive"
href: "https://www.data-intuitive.com"
role: "Data Scientist"
argument_groups:
- name: "Input"
arguments:
- type: "file"
name: "--bam"
description: "Path to the sequence alignment file in BAM format, produced by a\
\ splicing-aware aligner."
info: null
example:
- "alignment.bam"
must_exist: true
create_parent: true
required: true
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--gtf"
description: "Path to genomic annotations in Ensembl GTF format."
info: null
example:
- "annotations.gtf"
must_exist: true
create_parent: true
required: true
direction: "input"
multiple: false
multiple_sep: ";"
- name: "Output"
arguments:
- type: "file"
name: "--qc_results"
description: "Text file containing the RNAseq QC results."
info: null
example:
- "rnaseq_qc_results.txt"
must_exist: true
create_parent: true
required: true
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--counts"
description: "Output file for computed counts."
info: null
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--report"
description: "Report output file. Supported formats are PDF or HTML."
info: null
example:
- "report.html"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- name: "Optional"
arguments:
- type: "integer"
name: "--num_pr_bases"
description: "Number of upstream/downstream nucleotide bases to compute 5'-3'\
\ bias (default = 100)."
info: null
required: false
min: 1
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--num_tr_bias"
description: "Number of top highly expressed transcripts to compute 5'-3' bias\
\ (default = 1000)."
info: null
required: false
min: 1
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--algorithm"
description: "Counting algorithm (uniquely-mapped-reads (default) or proportional)."
info: null
required: false
choices:
- "uniquely-mapped-reads"
- "proportional"
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--sequencing_protocol"
description: "Sequencing library protocol (strand-specific-forward, strand-specific-reverse\
\ or non-strand-specific (default))."
info: null
required: false
choices:
- "non-strand-specific"
- "strand-specific-reverse"
- "strand-specific-forward"
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean_true"
name: "--paired"
description: "Setting this flag for paired-end experiments will result in counting\
\ fragments instead of reads."
info: null
direction: "input"
- type: "boolean_true"
name: "--sorted"
description: "Setting this flag indicates that the input file is already sorted\
\ by name. If flag is not set, additional sorting by name will be performed.\
\ Only requiredfor paired-end analysis."
info: null
direction: "input"
- type: "string"
name: "--java_memory_size"
description: "maximum Java heap memory size, default = 4G."
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
resources:
- type: "bash_script"
path: "script.sh"
is_executable: true
description: "Qualimap RNA-seq QC reports quality control metrics and bias estimations\
\ \nwhich are specific for whole transcriptome sequencing, including reads genomic\
\ \norigin, junction analysis, transcript coverage and 5’-3’ bias computation.\n"
test_resources:
- type: "bash_script"
path: "test.sh"
is_executable: true
- type: "file"
path: "test_data"
info: null
status: "enabled"
requirements:
commands:
- "ps"
keywords:
- "RNA-seq"
- "quality control"
- "QC Report"
license: "GPL-2.0"
references:
doi:
- "10.1093/bioinformatics/btv566"
links:
repository: "https://bitbucket.org/kokonech/qualimap/commits/branch/master"
homepage: "http://qualimap.conesalab.org/"
documentation: "http://qualimap.conesalab.org/doc_html/analysis.html#rna-seq-qc"
issue_tracker: "https://bitbucket.org/kokonech/qualimap/issues?status=new&status=open"
runners:
- type: "executable"
id: "executable"
docker_setup_strategy: "ifneedbepullelsecachedbuild"
- type: "nextflow"
id: "nextflow"
directives:
tag: "$id"
auto:
simplifyInput: true
simplifyOutput: false
transcript: false
publish: false
config:
labels:
mem1gb: "memory = 1000000000.B"
mem2gb: "memory = 2000000000.B"
mem5gb: "memory = 5000000000.B"
mem10gb: "memory = 10000000000.B"
mem20gb: "memory = 20000000000.B"
mem50gb: "memory = 50000000000.B"
mem100gb: "memory = 100000000000.B"
mem200gb: "memory = 200000000000.B"
mem500gb: "memory = 500000000000.B"
mem1tb: "memory = 1000000000000.B"
mem2tb: "memory = 2000000000000.B"
mem5tb: "memory = 5000000000000.B"
mem10tb: "memory = 10000000000000.B"
mem20tb: "memory = 20000000000000.B"
mem50tb: "memory = 50000000000000.B"
mem100tb: "memory = 100000000000000.B"
mem200tb: "memory = 200000000000000.B"
mem500tb: "memory = 500000000000000.B"
mem1gib: "memory = 1073741824.B"
mem2gib: "memory = 2147483648.B"
mem4gib: "memory = 4294967296.B"
mem8gib: "memory = 8589934592.B"
mem16gib: "memory = 17179869184.B"
mem32gib: "memory = 34359738368.B"
mem64gib: "memory = 68719476736.B"
mem128gib: "memory = 137438953472.B"
mem256gib: "memory = 274877906944.B"
mem512gib: "memory = 549755813888.B"
mem1tib: "memory = 1099511627776.B"
mem2tib: "memory = 2199023255552.B"
mem4tib: "memory = 4398046511104.B"
mem8tib: "memory = 8796093022208.B"
mem16tib: "memory = 17592186044416.B"
mem32tib: "memory = 35184372088832.B"
mem64tib: "memory = 70368744177664.B"
mem128tib: "memory = 140737488355328.B"
mem256tib: "memory = 281474976710656.B"
mem512tib: "memory = 562949953421312.B"
cpu1: "cpus = 1"
cpu2: "cpus = 2"
cpu5: "cpus = 5"
cpu10: "cpus = 10"
cpu20: "cpus = 20"
cpu50: "cpus = 50"
cpu100: "cpus = 100"
cpu200: "cpus = 200"
cpu500: "cpus = 500"
cpu1000: "cpus = 1000"
debug: false
container: "docker"
engines:
- type: "docker"
id: "docker"
image: "quay.io/biocontainers/qualimap:2.3--hdfd78af_0"
target_registry: "images.viash-hub.com"
target_tag: "v0.2"
namespace_separator: "/"
setup:
- type: "docker"
run:
- "echo QualiMap: $(qualimap 2>&1 | grep QualiMap | sed 's/^.*QualiMap//') > /var/software_versions.txt\n"
entrypoint: []
cmd: null
- type: "native"
id: "native"
build_info:
config: "src/qualimap/qualimap_rnaseq/config.vsh.yaml"
runner: "executable"
engine: "docker|native"
output: "target/executable/qualimap/qualimap_rnaseq"
executable: "target/executable/qualimap/qualimap_rnaseq/qualimap_rnaseq"
viash_version: "0.9.0-RC7"
git_commit: "f22ab0eab58dcd6bff89d8d73fe951953ff1260f"
git_remote: "https://github.com/viash-hub/biobox"
package_config:
name: "biobox"
version: "v0.2"
description: "A collection of bioinformatics tools for working with sequence data.\n"
info: null
viash_version: "0.9.0-RC7"
source: "src"
target: "target"
config_mods:
- ".requirements.commands := ['ps']\n"
- ".engines += { type: \"native\" }"
- ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
- ".engines[.type == 'docker'].target_tag := 'v0.2'"
keywords:
- "bioinformatics"
- "modules"
- "sequencing"
license: "MIT"
organization: "vsh"
links:
repository: "https://github.com/viash-hub/biobox"
issue_tracker: "https://github.com/viash-hub/biobox/issues"

1402
target/executable/qualimap/qualimap_rnaseq/qualimap_rnaseq Executable file
View File

File diff suppressed because it is too large Load Diff

442
target/executable/rsem/rsem_prepare_reference/.config.vsh.yaml Normal file
View File

@@ -0,0 +1,442 @@
name: "rsem_prepare_reference"
namespace: "rsem"
version: "v0.2"
authors:
- name: "Sai Nirmayi Yasa"
roles:
- "author"
- "maintainer"
info:
links:
email: "nirmayi@data-intuitive.com"
github: "sainirmayi"
linkedin: "sai-nirmayi-yasa"
organizations:
- name: "Data Intuitive"
href: "https://www.data-intuitive.com"
role: "Junior Bioinformatics Researcher"
argument_groups:
- name: "Inputs"
arguments:
- type: "file"
name: "--reference_fasta_files"
description: "Semi-colon separated list of Multi-FASTA formatted files OR a directory\
\ name. If a directory name is specified, RSEM will read all files with suffix\
\ \".fa\" or \".fasta\" in this directory. The files should contain either the\
\ sequences of transcripts or an entire genome, depending on whether the '--gtf'\
\ option is used.\n"
info: null
example:
- "read1.fasta"
must_exist: true
create_parent: true
required: true
direction: "input"
multiple: true
multiple_sep: ";"
- type: "string"
name: "--reference_name"
description: "The name of the reference used. RSEM will generate several reference-related\
\ files that are prefixed by this name. This name can contain path information\
\ (e.g. '/ref/mm9').\n"
info: null
example:
- "/ref/mm9"
required: true
direction: "input"
multiple: false
multiple_sep: ";"
- name: "Outputs"
arguments:
- type: "file"
name: "--output"
description: "Directory containing reference files generated by RSEM."
info: null
must_exist: true
create_parent: true
required: true
direction: "output"
multiple: false
multiple_sep: ";"
- name: "Other options"
arguments:
- type: "file"
name: "--gtf"
description: "Assume that 'reference_fasta_files' contains the sequence of a genome,\
\ and extract transcript reference sequences using the gene annotations specified\
\ in the GTF file. If this and '--gff3' options are not provided, RSEM will\
\ assume 'reference_fasta_files' contains the reference transcripts. In this\
\ case, RSEM assumes that name of each sequence in the Multi-FASTA files is\
\ its transcript_id."
info: null
example:
- "annotations.gtf"
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--gff3"
description: "GFF3 annotation file. Converted to GTF format with the file name\
\ 'reference_name.gtf'. Please make sure that 'reference_name.gtf' does not\
\ exist."
info: null
example:
- "annotations.gff"
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--gff3_rna_patterns"
description: "List of transcript categories (separated by semi-colon). Only transcripts\
\ that match the string will be extracted."
info: null
example:
- "mRNA;rRNA"
required: false
direction: "input"
multiple: true
multiple_sep: ";"
- type: "boolean_true"
name: "--gff3_genes_as_transcripts"
description: "This option is designed for untypical organisms, such as viruses,\
\ whose GFF3 files only contain genes. RSEM will assume each gene as a unique\
\ transcript when it converts the GFF3 file into GTF format."
info: null
direction: "input"
- type: "string"
name: "--trusted_sources"
description: "List of trusted sources (separated by semi-colon). Only transcripts\
\ coming from these sources will be extracted. If this option is off, all sources\
\ are accepted."
info: null
example:
- "ENSEMBL;HAVANA"
required: false
direction: "input"
multiple: true
multiple_sep: ";"
- type: "file"
name: "--transcript_to_gene_map"
description: "Use information from this file to map from transcript (isoform)\
\ ids to gene ids. Each line of this file should be of the form: \n gene_id\
\ transcript_id\nwith the two fields separated by a tab character.\nIf you are\
\ using a GTF file for the \"UCSC Genes\" gene set from the UCSC Genome Browser,\
\ then the \"knownIsoforms.txt\" file (obtained from the \"Downloads\" section\
\ of the UCSC Genome Browser site) is of this format. \nIf this option is off,\
\ then the mapping of isoforms to genes depends on whether the '--gtf' option\
\ is specified. If '--gtf' is specified, then RSEM uses the \"gene_id\" and\
\ \"transcript_id\" attributes in the GTF file. Otherwise, RSEM assumes that\
\ each sequence in the reference sequence files is a separate gene.\n"
info: null
example:
- "isoforms.txt"
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--allele_to_gene_map"
description: "Use information from <file> to provide gene_id and transcript_id\
\ information for each allele-specific transcript. Each line of <file> should\
\ be of the form:\n gene_id transcript_id allele_id\nwith the fields separated\
\ by a tab character.\nThis option is designed for quantifying allele-specific\
\ expression. It is only valid if '--gtf' option is not specified. allele_id\
\ should be the sequence names presented in the Multi-FASTA-formatted files.\n"
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean_true"
name: "--polyA"
description: "Add poly(A) tails to the end of all reference isoforms. The length\
\ of poly(A) tail added is specified by '--polyA-length' option. STAR aligner\
\ users may not want to use this option."
info: null
direction: "input"
- type: "integer"
name: "--polyA_length"
description: "The length of the poly(A) tails to be added."
info: null
example:
- 125
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--no_polyA_subset"
description: "Only meaningful if '--polyA' is specified. Do not add poly(A) tails\
\ to those transcripts listed in this file containing a list of transcript_ids."
info: null
example:
- "transcript_ids.txt"
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean_true"
name: "--bowtie"
description: "Build Bowtie indices."
info: null
direction: "input"
- type: "boolean_true"
name: "--bowtie2"
description: "Build Bowtie 2 indices."
info: null
direction: "input"
- type: "boolean_true"
name: "--star"
description: "Build STAR indices."
info: null
direction: "input"
- type: "integer"
name: "--star_sjdboverhang"
description: "Length of the genomic sequence around annotated junction. It is\
\ only used for STAR to build splice junctions database and not needed for Bowtie\
\ or Bowtie2. It will be passed as the --sjdbOverhang option to STAR. According\
\ to STAR's manual, its ideal value is max(ReadLength)-1, e.g. for 2x101 paired-end\
\ reads, the ideal value is 101-1=100. In most cases, the default value of 100\
\ will work as well as the ideal value. (Default is 100)"
info: null
example:
- 100
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean_true"
name: "--hisat2_hca"
description: "Build HISAT2 indices on the transcriptome according to Human Cell\
\ Atlas (HCA) SMART-Seq2 pipeline."
info: null
direction: "input"
- type: "boolean_true"
name: "--quiet"
alternatives:
- "-q"
description: "Suppress the output of logging information."
info: null
direction: "input"
- name: "Prior-enhanced RSEM options"
arguments:
- type: "boolean_true"
name: "--prep_pRSEM"
description: "A Boolean indicating whether to prepare reference files for pRSEM,\
\ including building Bowtie indices for a genome and selecting training set\
\ isoforms. The index files will be used for aligning ChIP-seq reads in prior-enhanced\
\ RSEM and the training set isoforms will be used for learning prior. A path\
\ to Bowtie executables and a mappability file in bigWig format are required\
\ when this option is on. Currently, Bowtie2 is not supported for prior-enhanced\
\ RSEM."
info: null
direction: "input"
- type: "file"
name: "--mappability_bigwig_file"
description: "Full path to a whole-genome mappability file in bigWig format. This\
\ file is required for running prior-enhanced RSEM. It is used for selecting\
\ a training set of isoforms for prior-learning. This file can be either downloaded\
\ from UCSC Genome Browser or generated by GEM (Derrien et al., 2012, PLoS One)."
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
resources:
- type: "bash_script"
path: "script.sh"
is_executable: true
description: "RSEM is a software package for estimating gene and isoform expression\
\ levels from RNA-Seq data. This component prepares transcript references for RSEM.\n"
test_resources:
- type: "bash_script"
path: "test.sh"
is_executable: true
info: null
status: "enabled"
requirements:
commands:
- "ps"
keywords:
- "Transcriptome"
- "Index"
license: "GPL-3.0"
references:
doi:
- "10.1186/1471-2105-12-323"
links:
repository: "https://github.com/deweylab/RSEM"
homepage: "http://deweylab.github.io/RSEM"
documentation: "https://deweylab.github.io/RSEM/rsem-prepare-reference.html"
runners:
- type: "executable"
id: "executable"
docker_setup_strategy: "ifneedbepullelsecachedbuild"
- type: "nextflow"
id: "nextflow"
directives:
tag: "$id"
auto:
simplifyInput: true
simplifyOutput: false
transcript: false
publish: false
config:
labels:
mem1gb: "memory = 1000000000.B"
mem2gb: "memory = 2000000000.B"
mem5gb: "memory = 5000000000.B"
mem10gb: "memory = 10000000000.B"
mem20gb: "memory = 20000000000.B"
mem50gb: "memory = 50000000000.B"
mem100gb: "memory = 100000000000.B"
mem200gb: "memory = 200000000000.B"
mem500gb: "memory = 500000000000.B"
mem1tb: "memory = 1000000000000.B"
mem2tb: "memory = 2000000000000.B"
mem5tb: "memory = 5000000000000.B"
mem10tb: "memory = 10000000000000.B"
mem20tb: "memory = 20000000000000.B"
mem50tb: "memory = 50000000000000.B"
mem100tb: "memory = 100000000000000.B"
mem200tb: "memory = 200000000000000.B"
mem500tb: "memory = 500000000000000.B"
mem1gib: "memory = 1073741824.B"
mem2gib: "memory = 2147483648.B"
mem4gib: "memory = 4294967296.B"
mem8gib: "memory = 8589934592.B"
mem16gib: "memory = 17179869184.B"
mem32gib: "memory = 34359738368.B"
mem64gib: "memory = 68719476736.B"
mem128gib: "memory = 137438953472.B"
mem256gib: "memory = 274877906944.B"
mem512gib: "memory = 549755813888.B"
mem1tib: "memory = 1099511627776.B"
mem2tib: "memory = 2199023255552.B"
mem4tib: "memory = 4398046511104.B"
mem8tib: "memory = 8796093022208.B"
mem16tib: "memory = 17592186044416.B"
mem32tib: "memory = 35184372088832.B"
mem64tib: "memory = 70368744177664.B"
mem128tib: "memory = 140737488355328.B"
mem256tib: "memory = 281474976710656.B"
mem512tib: "memory = 562949953421312.B"
cpu1: "cpus = 1"
cpu2: "cpus = 2"
cpu5: "cpus = 5"
cpu10: "cpus = 10"
cpu20: "cpus = 20"
cpu50: "cpus = 50"
cpu100: "cpus = 100"
cpu200: "cpus = 200"
cpu500: "cpus = 500"
cpu1000: "cpus = 1000"
debug: false
container: "docker"
engines:
- type: "docker"
id: "docker"
image: "ubuntu:22.04"
target_registry: "images.viash-hub.com"
target_tag: "v0.2"
namespace_separator: "/"
setup:
- type: "apt"
packages:
- "build-essential"
- "gcc"
- "g++"
- "make"
- "wget"
- "zlib1g-dev"
- "unzip xxd"
- "perl"
- "r-base"
- "bowtie2"
- "pip"
- "git"
interactive: false
- type: "python"
user: false
packages:
- "bowtie"
upgrade: true
- type: "docker"
run:
- "ln -snf /usr/share/zoneinfo/$TZ /etc/localtime && echo $TZ > /etc/timezone\
\ && \\\ncd /tmp && \\\nwget --no-check-certificate https://github.com/alexdobin/STAR/archive/refs/tags/${STAR_VERSION}.zip\
\ && \\\nunzip ${STAR_VERSION}.zip && \\\ncd STAR-${STAR_VERSION}/source &&\
\ \\\nmake STARstatic CXXFLAGS_SIMD=-std=c++11 && \\\ncp STAR /usr/local/bin\
\ && \\\ncd /tmp && \\\nwget --no-check-certificate https://github.com/deweylab/RSEM/archive/refs/tags/v${RSEM_VERSION}.zip\
\ && \\\nunzip v${RSEM_VERSION}.zip && \\\ncd RSEM-${RSEM_VERSION} && \\\nmake\
\ && \\\nmake install && \\\ncd /tmp && \\\nwget --no-check-certificate -O bowtie-${BOWTIE_VERSION}-linux-x86_64.zip\
\ https://sourceforge.net/projects/bowtie-bio/files/bowtie/${BOWTIE_VERSION}/bowtie-${BOWTIE_VERSION}-linux-x86_64.zip/download\
\ && \\\nunzip bowtie-${BOWTIE_VERSION}-linux-x86_64.zip && \\\ncp bowtie-${BOWTIE_VERSION}-linux-x86_64/bowtie*\
\ /usr/local/bin && \\\ncd /tmp && \\\ngit clone https://github.com/DaehwanKimLab/hisat2.git\
\ /tmp/hisat2 && \\\ncd /tmp/hisat2 && \\\nmake && \\\ncp -r hisat2* /usr/local/bin\
\ && \\\ncd && \\\nrm -rf /tmp/STAR-${STAR_VERSION} /tmp/${STAR_VERSION}.zip\
\ /tmp/bowtie-${BOWTIE_VERSION}-linux-x86_64 /tmp/hisat2 && \\\napt-get --purge\
\ autoremove -y ${PACKAGES} && \\\napt-get clean \n"
env:
- "STAR_VERSION=2.7.11b"
- "RSEM_VERSION=1.3.3"
- "BOWTIE_VERSION=1.3.1"
- "TZ=Europe/Brussels"
- type: "docker"
run:
- "echo \"RSEM: `rsem-calculate-expression --version | sed -e 's/Current version:\
\ RSEM v//g'`\" > /var/software_versions.txt && \\\necho \"STAR: `STAR --version`\"\
\ >> /var/software_versions.txt && \\\necho \"bowtie2: `bowtie2 --version |\
\ grep -oP '\\d+\\.\\d+\\.\\d+'`\" >> /var/software_versions.txt && \\\necho\
\ \"bowtie: `bowtie --version | grep -oP 'bowtie-align-s version \\K\\d+\\.\\\
d+\\.\\d+'`\" >> /var/software_versions.txt && \\\necho \"HISAT2: `hisat2 --version\
\ | grep -oP 'hisat2-align-s version \\K\\d+\\.\\d+\\.\\d+'`\" >> /var/software_versions.txt\n"
entrypoint: []
cmd: null
- type: "native"
id: "native"
build_info:
config: "src/rsem/rsem_prepare_reference/config.vsh.yaml"
runner: "executable"
engine: "docker|native"
output: "target/executable/rsem/rsem_prepare_reference"
executable: "target/executable/rsem/rsem_prepare_reference/rsem_prepare_reference"
viash_version: "0.9.0-RC7"
git_commit: "f22ab0eab58dcd6bff89d8d73fe951953ff1260f"
git_remote: "https://github.com/viash-hub/biobox"
package_config:
name: "biobox"
version: "v0.2"
description: "A collection of bioinformatics tools for working with sequence data.\n"
info: null
viash_version: "0.9.0-RC7"
source: "src"
target: "target"
config_mods:
- ".requirements.commands := ['ps']\n"
- ".engines += { type: \"native\" }"
- ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
- ".engines[.type == 'docker'].target_tag := 'v0.2'"
keywords:
- "bioinformatics"
- "modules"
- "sequencing"
license: "MIT"
organization: "vsh"
links:
repository: "https://github.com/viash-hub/biobox"
issue_tracker: "https://github.com/viash-hub/biobox/issues"

1689
target/executable/rsem/rsem_prepare_reference/rsem_prepare_reference Executable file
View File

File diff suppressed because it is too large Load Diff

303
target/executable/salmon/salmon_index/.config.vsh.yaml Normal file
View File

@@ -0,0 +1,303 @@
name: "salmon_index"
namespace: "salmon"
version: "v0.2"
authors:
- name: "Sai Nirmayi Yasa"
roles:
- "author"
- "maintainer"
info:
links:
email: "nirmayi@data-intuitive.com"
github: "sainirmayi"
linkedin: "sai-nirmayi-yasa"
organizations:
- name: "Data Intuitive"
href: "https://www.data-intuitive.com"
role: "Junior Bioinformatics Researcher"
argument_groups:
- name: "Inputs"
arguments:
- type: "file"
name: "--genome"
description: "Genome of the organism to prepare the set of decoy sequences. Required\
\ to build decoy-aware transcriptome.\n"
info: null
example:
- "genome.fasta"
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--transcripts"
alternatives:
- "-t"
description: "Transcript fasta file.\n"
info: null
example:
- "transcriptome.fasta"
must_exist: true
create_parent: true
required: true
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--kmer_len"
alternatives:
- "-k"
description: "The size of k-mers that should be used for the quasi index.\n"
info: null
example:
- 31
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean_true"
name: "--gencode"
description: "This flag will expect the input transcript fasta to be in GENCODE\
\ format, and will split the transcript name at the first '|' character. These\
\ reduced names will be used in the output and when looking for these transcripts\
\ in a gene to transcript GTF.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--features"
description: "This flag will expect the input reference to be in the tsv file\
\ format, and will split the feature name at the first 'tab' character. These\
\ reduced names will be used in the output and when looking for the sequence\
\ of the features.GTF.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--keep_duplicates"
description: "This flag will disable the default indexing behavior of discarding\
\ sequence-identical duplicate transcripts. If this flag is passed, then duplicate\
\ transcripts that appear in the input will be retained and quantified separately.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--keep_fixed_fasta"
description: "Retain the fixed fasta file (without short transcripts and duplicates,\
\ clipped, etc.) generated during indexing.\n"
info: null
direction: "input"
- type: "integer"
name: "--filter_size"
alternatives:
- "-f"
description: "The size of the Bloom filter that will be used by TwoPaCo during\
\ indexing. The filter will be of size 2^{filter_size}. The default value of\
\ -1 means that the filter size will be automatically set based on the number\
\ of distinct k-mers in the input, as estimated by nthll.\n"
info: null
example:
- -1
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean_true"
name: "--sparse"
description: "Build the index using a sparse sampling of k-mer positions This\
\ will require less memory (especially during quantification), but will take\
\ longer to construct and can slow down mapping / alignment.\n"
info: null
direction: "input"
- type: "file"
name: "--decoys"
alternatives:
- "-d"
description: "Treat these sequences ids from the reference as the decoys that\
\ may have sequence homologous to some known transcript. For example in case\
\ of the genome, provide a list of chromosome names (one per line).\n"
info: null
example:
- "decoys.txt"
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean_true"
name: "--no_clip"
description: "Don't clip poly-A tails from the ends of target sequences.\n"
info: null
direction: "input"
- type: "string"
name: "--type"
alternatives:
- "-n"
description: "The type of index to build; the only option is \"puff\" in this\
\ version of salmon.\n"
info: null
example:
- "puff"
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- name: "Output"
arguments:
- type: "file"
name: "--index"
alternatives:
- "-i"
description: "Salmon index\n"
info: null
example:
- "Salmon_index"
must_exist: true
create_parent: true
required: true
direction: "output"
multiple: false
multiple_sep: ";"
resources:
- type: "bash_script"
path: "script.sh"
is_executable: true
description: "Salmon is a tool for wicked-fast transcript quantification from RNA-seq\
\ data. It can either make use of pre-computed alignments (in the form of a SAM/BAM\
\ file) to the transcripts rather than the raw reads, or can be run in the mapping-based\
\ mode. This component creates a salmon index for the transcriptome to use Salmon\
\ in the mapping-based mode. It is generally recommend that you build a decoy-aware\
\ transcriptome file. This is done using the entire genome of the organism as the\
\ decoy sequence by concatenating the genome to the end of the transcriptome to\
\ be indexed and populating the decoys.txt file with the chromosome names.\n"
test_resources:
- type: "bash_script"
path: "test.sh"
is_executable: true
info: null
status: "enabled"
requirements:
commands:
- "ps"
keywords:
- "Transcriptome"
- "Index"
license: "GPL-3.0"
references:
doi:
- "10.1038/nmeth.4197"
links:
repository: "https://github.com/COMBINE-lab/salmon"
homepage: "https://salmon.readthedocs.io/en/latest/salmon.html"
documentation: "https://salmon.readthedocs.io/en/latest/salmon.html"
runners:
- type: "executable"
id: "executable"
docker_setup_strategy: "ifneedbepullelsecachedbuild"
- type: "nextflow"
id: "nextflow"
directives:
tag: "$id"
auto:
simplifyInput: true
simplifyOutput: false
transcript: false
publish: false
config:
labels:
mem1gb: "memory = 1000000000.B"
mem2gb: "memory = 2000000000.B"
mem5gb: "memory = 5000000000.B"
mem10gb: "memory = 10000000000.B"
mem20gb: "memory = 20000000000.B"
mem50gb: "memory = 50000000000.B"
mem100gb: "memory = 100000000000.B"
mem200gb: "memory = 200000000000.B"
mem500gb: "memory = 500000000000.B"
mem1tb: "memory = 1000000000000.B"
mem2tb: "memory = 2000000000000.B"
mem5tb: "memory = 5000000000000.B"
mem10tb: "memory = 10000000000000.B"
mem20tb: "memory = 20000000000000.B"
mem50tb: "memory = 50000000000000.B"
mem100tb: "memory = 100000000000000.B"
mem200tb: "memory = 200000000000000.B"
mem500tb: "memory = 500000000000000.B"
mem1gib: "memory = 1073741824.B"
mem2gib: "memory = 2147483648.B"
mem4gib: "memory = 4294967296.B"
mem8gib: "memory = 8589934592.B"
mem16gib: "memory = 17179869184.B"
mem32gib: "memory = 34359738368.B"
mem64gib: "memory = 68719476736.B"
mem128gib: "memory = 137438953472.B"
mem256gib: "memory = 274877906944.B"
mem512gib: "memory = 549755813888.B"
mem1tib: "memory = 1099511627776.B"
mem2tib: "memory = 2199023255552.B"
mem4tib: "memory = 4398046511104.B"
mem8tib: "memory = 8796093022208.B"
mem16tib: "memory = 17592186044416.B"
mem32tib: "memory = 35184372088832.B"
mem64tib: "memory = 70368744177664.B"
mem128tib: "memory = 140737488355328.B"
mem256tib: "memory = 281474976710656.B"
mem512tib: "memory = 562949953421312.B"
cpu1: "cpus = 1"
cpu2: "cpus = 2"
cpu5: "cpus = 5"
cpu10: "cpus = 10"
cpu20: "cpus = 20"
cpu50: "cpus = 50"
cpu100: "cpus = 100"
cpu200: "cpus = 200"
cpu500: "cpus = 500"
cpu1000: "cpus = 1000"
debug: false
container: "docker"
engines:
- type: "docker"
id: "docker"
image: "quay.io/biocontainers/salmon:1.10.2--hecfa306_0"
target_registry: "images.viash-hub.com"
target_tag: "v0.2"
namespace_separator: "/"
setup:
- type: "docker"
run:
- "salmon index -v 2>&1 | sed 's/salmon \\([0-9.]*\\)/salmon: \\1/' > /var/software_versions.txt\n"
entrypoint: []
cmd: null
- type: "native"
id: "native"
build_info:
config: "src/salmon/salmon_index/config.vsh.yaml"
runner: "executable"
engine: "docker|native"
output: "target/executable/salmon/salmon_index"
executable: "target/executable/salmon/salmon_index/salmon_index"
viash_version: "0.9.0-RC7"
git_commit: "f22ab0eab58dcd6bff89d8d73fe951953ff1260f"
git_remote: "https://github.com/viash-hub/biobox"
package_config:
name: "biobox"
version: "v0.2"
description: "A collection of bioinformatics tools for working with sequence data.\n"
info: null
viash_version: "0.9.0-RC7"
source: "src"
target: "target"
config_mods:
- ".requirements.commands := ['ps']\n"
- ".engines += { type: \"native\" }"
- ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
- ".engines[.type == 'docker'].target_tag := 'v0.2'"
keywords:
- "bioinformatics"
- "modules"
- "sequencing"
license: "MIT"
organization: "vsh"
links:
repository: "https://github.com/viash-hub/biobox"
issue_tracker: "https://github.com/viash-hub/biobox/issues"

1429
target/executable/salmon/salmon_index/salmon_index Executable file
View File

File diff suppressed because it is too large Load Diff

1199
target/executable/salmon/salmon_quant/.config.vsh.yaml Normal file
View File

File diff suppressed because it is too large Load Diff

3927
target/executable/salmon/salmon_quant/salmon_quant Executable file
View File

File diff suppressed because it is too large Load Diff

290
target/executable/samtools/samtools_collate/.config.vsh.yaml Normal file
View File

@@ -0,0 +1,290 @@
name: "samtools_collate"
namespace: "samtools"
version: "v0.2"
authors:
- name: "Emma Rousseau"
roles:
- "author"
- "maintainer"
info:
links:
email: "emma@data-intuitive.com"
github: "emmarousseau"
linkedin: "emmarousseau1"
organizations:
- name: "Data Intuitive"
href: "https://www.data-intuitive.com"
role: "Bioinformatician"
argument_groups:
- name: "Inputs"
arguments:
- type: "file"
name: "--input"
description: "The input BAM file."
info: null
must_exist: true
create_parent: true
required: true
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--reference"
description: "Reference sequence FASTA FILE."
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- name: "Outputs"
arguments:
- type: "file"
name: "--output"
alternatives:
- "-o"
description: "The output filename."
info: null
must_exist: true
create_parent: true
required: true
direction: "output"
multiple: false
multiple_sep: ";"
- name: "Options"
arguments:
- type: "boolean_true"
name: "--uncompressed"
alternatives:
- "-u"
description: "Output uncompressed BAM."
info: null
direction: "input"
- type: "boolean_true"
name: "--fast"
alternatives:
- "-f"
description: "Fast mode, only primary alignments."
info: null
direction: "input"
- type: "integer"
name: "--working_reads"
alternatives:
- "-r"
description: "Working reads stored (for use with -f)."
info: null
default:
- 10000
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--compression"
alternatives:
- "-l"
description: "Compression level."
info: null
default:
- 1
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--nb_tmp_files"
alternatives:
- "-n"
description: "Number of temporary files."
info: null
default:
- 64
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--tmp_prefix"
alternatives:
- "-T"
description: "Write temporary files to PREFIX.nnnn.bam."
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean_true"
name: "--no_pg"
description: "Do not add a PG line."
info: null
direction: "input"
- type: "string"
name: "--input_fmt_option"
description: "Specify a single input file format option in the form of OPTION\
\ or OPTION=VALUE."
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--output_fmt"
description: "Specify output format (SAM, BAM, CRAM)."
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--output_fmt_option"
description: "Specify a single output file format option in the form of OPTION\
\ or OPTION=VALUE."
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
resources:
- type: "bash_script"
path: "script.sh"
is_executable: true
description: "Shuffles and groups reads in SAM/BAM/CRAM files together by their names."
test_resources:
- type: "bash_script"
path: "test.sh"
is_executable: true
- type: "file"
path: "test_data"
info: null
status: "enabled"
requirements:
commands:
- "ps"
keywords:
- "collate"
- "counts"
- "bam"
- "sam"
- "cram"
license: "MIT/Expat"
references:
doi:
- "10.1093/bioinformatics/btp352"
- "10.1093/gigascience/giab008"
links:
repository: "https://github.com/samtools/samtools"
homepage: "https://www.htslib.org/"
documentation: "https://www.htslib.org/doc/samtools-icollate.html"
runners:
- type: "executable"
id: "executable"
docker_setup_strategy: "ifneedbepullelsecachedbuild"
- type: "nextflow"
id: "nextflow"
directives:
tag: "$id"
auto:
simplifyInput: true
simplifyOutput: false
transcript: false
publish: false
config:
labels:
mem1gb: "memory = 1000000000.B"
mem2gb: "memory = 2000000000.B"
mem5gb: "memory = 5000000000.B"
mem10gb: "memory = 10000000000.B"
mem20gb: "memory = 20000000000.B"
mem50gb: "memory = 50000000000.B"
mem100gb: "memory = 100000000000.B"
mem200gb: "memory = 200000000000.B"
mem500gb: "memory = 500000000000.B"
mem1tb: "memory = 1000000000000.B"
mem2tb: "memory = 2000000000000.B"
mem5tb: "memory = 5000000000000.B"
mem10tb: "memory = 10000000000000.B"
mem20tb: "memory = 20000000000000.B"
mem50tb: "memory = 50000000000000.B"
mem100tb: "memory = 100000000000000.B"
mem200tb: "memory = 200000000000000.B"
mem500tb: "memory = 500000000000000.B"
mem1gib: "memory = 1073741824.B"
mem2gib: "memory = 2147483648.B"
mem4gib: "memory = 4294967296.B"
mem8gib: "memory = 8589934592.B"
mem16gib: "memory = 17179869184.B"
mem32gib: "memory = 34359738368.B"
mem64gib: "memory = 68719476736.B"
mem128gib: "memory = 137438953472.B"
mem256gib: "memory = 274877906944.B"
mem512gib: "memory = 549755813888.B"
mem1tib: "memory = 1099511627776.B"
mem2tib: "memory = 2199023255552.B"
mem4tib: "memory = 4398046511104.B"
mem8tib: "memory = 8796093022208.B"
mem16tib: "memory = 17592186044416.B"
mem32tib: "memory = 35184372088832.B"
mem64tib: "memory = 70368744177664.B"
mem128tib: "memory = 140737488355328.B"
mem256tib: "memory = 281474976710656.B"
mem512tib: "memory = 562949953421312.B"
cpu1: "cpus = 1"
cpu2: "cpus = 2"
cpu5: "cpus = 5"
cpu10: "cpus = 10"
cpu20: "cpus = 20"
cpu50: "cpus = 50"
cpu100: "cpus = 100"
cpu200: "cpus = 200"
cpu500: "cpus = 500"
cpu1000: "cpus = 1000"
debug: false
container: "docker"
engines:
- type: "docker"
id: "docker"
image: "quay.io/biocontainers/samtools:1.19.2--h50ea8bc_1"
target_registry: "images.viash-hub.com"
target_tag: "v0.2"
namespace_separator: "/"
setup:
- type: "docker"
run:
- "samtools --version 2>&1 | grep -E '^(samtools|Using htslib)' | \\\nsed 's#Using\
\ ##;s# \\([0-9\\.]*\\)$#: \\1#' > /var/software_versions.txt\n"
entrypoint: []
cmd: null
- type: "native"
id: "native"
build_info:
config: "src/samtools/samtools_collate/config.vsh.yaml"
runner: "executable"
engine: "docker|native"
output: "target/executable/samtools/samtools_collate"
executable: "target/executable/samtools/samtools_collate/samtools_collate"
viash_version: "0.9.0-RC7"
git_commit: "f22ab0eab58dcd6bff89d8d73fe951953ff1260f"
git_remote: "https://github.com/viash-hub/biobox"
package_config:
name: "biobox"
version: "v0.2"
description: "A collection of bioinformatics tools for working with sequence data.\n"
info: null
viash_version: "0.9.0-RC7"
source: "src"
target: "target"
config_mods:
- ".requirements.commands := ['ps']\n"
- ".engines += { type: \"native\" }"
- ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
- ".engines[.type == 'docker'].target_tag := 'v0.2'"
keywords:
- "bioinformatics"
- "modules"
- "sequencing"
license: "MIT"
organization: "vsh"
links:
repository: "https://github.com/viash-hub/biobox"
issue_tracker: "https://github.com/viash-hub/biobox/issues"

1372
target/executable/samtools/samtools_collate/samtools_collate Executable file
View File

File diff suppressed because it is too large Load Diff

269
target/executable/samtools/samtools_faidx/.config.vsh.yaml Normal file
View File

@@ -0,0 +1,269 @@
name: "samtools_faidx"
namespace: "samtools"
version: "v0.2"
authors:
- name: "Emma Rousseau"
roles:
- "author"
- "maintainer"
info:
links:
email: "emma@data-intuitive.com"
github: "emmarousseau"
linkedin: "emmarousseau1"
organizations:
- name: "Data Intuitive"
href: "https://www.data-intuitive.com"
role: "Bioinformatician"
argument_groups:
- name: "Inputs"
arguments:
- type: "file"
name: "--input"
description: "FASTA input file.\n"
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--length"
alternatives:
- "-n"
description: "Length for FASTA sequence line wrapping. If zero, this means do\
\ not\nline wrap. Defaults to the line length in the input file.\n"
info: null
default:
- 60
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--region_file"
alternatives:
- "-r"
description: "File of regions. Format is chr:from-to. One per line.\nMust be used\
\ with --output to avoid sending output to stdout.\n"
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- name: "Options"
arguments:
- type: "boolean_true"
name: "--continue"
description: "Continue working if a non-existent region is requested.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--reverse_complement"
alternatives:
- "-i"
description: "Reverse complement sequences.\n"
info: null
direction: "input"
- name: "Outputs"
arguments:
- type: "file"
name: "--output"
alternatives:
- "-o"
description: "Write output to file.\n"
info: null
example:
- "output.fasta"
must_exist: true
create_parent: true
required: true
direction: "output"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--mark_strand"
description: "Add strand indicator to sequence name. Options are:\n[ rc, no, sign,\
\ custom,<pos>,<neg> ]\n"
info: null
default:
- "rc"
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--fai_idx"
description: "Read/Write to specified index file (default file.fa.fai).\n"
info: null
example:
- "file.fa.fai"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--gzi_idx"
description: "Read/Write to specified compressed file index (used with .gz files,\
\ default file.fa.gz.gzi).\n"
info: null
example:
- "file.fa.gz.gzi"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "boolean_true"
name: "--fastq"
description: "Read FASTQ files and output extracted sequences in FASTQ format.\
\ Same as using samtools fqidx.\n"
info: null
direction: "input"
resources:
- type: "bash_script"
path: "script.sh"
is_executable: true
description: "Indexes FASTA files to enable random access to fasta and fastq files."
test_resources:
- type: "bash_script"
path: "test.sh"
is_executable: true
- type: "file"
path: "test_data"
info: null
status: "enabled"
requirements:
commands:
- "ps"
keywords:
- "idex"
- "fasta"
- "faidx"
license: "MIT/Expat"
references:
doi:
- "10.1093/bioinformatics/btp352"
- "10.1093/gigascience/giab008"
links:
repository: "https://github.com/samtools/samtools"
homepage: "https://www.htslib.org/"
documentation: "https://www.htslib.org/doc/samtools-faidx.html"
runners:
- type: "executable"
id: "executable"
docker_setup_strategy: "ifneedbepullelsecachedbuild"
- type: "nextflow"
id: "nextflow"
directives:
tag: "$id"
auto:
simplifyInput: true
simplifyOutput: false
transcript: false
publish: false
config:
labels:
mem1gb: "memory = 1000000000.B"
mem2gb: "memory = 2000000000.B"
mem5gb: "memory = 5000000000.B"
mem10gb: "memory = 10000000000.B"
mem20gb: "memory = 20000000000.B"
mem50gb: "memory = 50000000000.B"
mem100gb: "memory = 100000000000.B"
mem200gb: "memory = 200000000000.B"
mem500gb: "memory = 500000000000.B"
mem1tb: "memory = 1000000000000.B"
mem2tb: "memory = 2000000000000.B"
mem5tb: "memory = 5000000000000.B"
mem10tb: "memory = 10000000000000.B"
mem20tb: "memory = 20000000000000.B"
mem50tb: "memory = 50000000000000.B"
mem100tb: "memory = 100000000000000.B"
mem200tb: "memory = 200000000000000.B"
mem500tb: "memory = 500000000000000.B"
mem1gib: "memory = 1073741824.B"
mem2gib: "memory = 2147483648.B"
mem4gib: "memory = 4294967296.B"
mem8gib: "memory = 8589934592.B"
mem16gib: "memory = 17179869184.B"
mem32gib: "memory = 34359738368.B"
mem64gib: "memory = 68719476736.B"
mem128gib: "memory = 137438953472.B"
mem256gib: "memory = 274877906944.B"
mem512gib: "memory = 549755813888.B"
mem1tib: "memory = 1099511627776.B"
mem2tib: "memory = 2199023255552.B"
mem4tib: "memory = 4398046511104.B"
mem8tib: "memory = 8796093022208.B"
mem16tib: "memory = 17592186044416.B"
mem32tib: "memory = 35184372088832.B"
mem64tib: "memory = 70368744177664.B"
mem128tib: "memory = 140737488355328.B"
mem256tib: "memory = 281474976710656.B"
mem512tib: "memory = 562949953421312.B"
cpu1: "cpus = 1"
cpu2: "cpus = 2"
cpu5: "cpus = 5"
cpu10: "cpus = 10"
cpu20: "cpus = 20"
cpu50: "cpus = 50"
cpu100: "cpus = 100"
cpu200: "cpus = 200"
cpu500: "cpus = 500"
cpu1000: "cpus = 1000"
debug: false
container: "docker"
engines:
- type: "docker"
id: "docker"
image: "quay.io/biocontainers/samtools:1.19.2--h50ea8bc_1"
target_registry: "images.viash-hub.com"
target_tag: "v0.2"
namespace_separator: "/"
setup:
- type: "docker"
run:
- "samtools --version 2>&1 | grep -E '^(samtools|Using htslib)' | \\\nsed 's#Using\
\ ##;s# \\([0-9\\.]*\\)$#: \\1#' > /var/software_versions.txt\n"
entrypoint: []
cmd: null
- type: "native"
id: "native"
build_info:
config: "src/samtools/samtools_faidx/config.vsh.yaml"
runner: "executable"
engine: "docker|native"
output: "target/executable/samtools/samtools_faidx"
executable: "target/executable/samtools/samtools_faidx/samtools_faidx"
viash_version: "0.9.0-RC7"
git_commit: "f22ab0eab58dcd6bff89d8d73fe951953ff1260f"
git_remote: "https://github.com/viash-hub/biobox"
package_config:
name: "biobox"
version: "v0.2"
description: "A collection of bioinformatics tools for working with sequence data.\n"
info: null
viash_version: "0.9.0-RC7"
source: "src"
target: "target"
config_mods:
- ".requirements.commands := ['ps']\n"
- ".engines += { type: \"native\" }"
- ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
- ".engines[.type == 'docker'].target_tag := 'v0.2'"
keywords:
- "bioinformatics"
- "modules"
- "sequencing"
license: "MIT"
organization: "vsh"
links:
repository: "https://github.com/viash-hub/biobox"
issue_tracker: "https://github.com/viash-hub/biobox/issues"

1320
target/executable/samtools/samtools_faidx/samtools_faidx Executable file
View File

File diff suppressed because it is too large Load Diff

459
target/executable/samtools/samtools_fasta/.config.vsh.yaml Normal file
View File

@@ -0,0 +1,459 @@
name: "samtools_fasta"
namespace: "samtools"
version: "v0.2"
authors:
- name: "Emma Rousseau"
roles:
- "author"
- "maintainer"
info:
links:
email: "emma@data-intuitive.com"
github: "emmarousseau"
linkedin: "emmarousseau1"
organizations:
- name: "Data Intuitive"
href: "https://www.data-intuitive.com"
role: "Bioinformatician"
argument_groups:
- name: "Inputs"
arguments:
- type: "file"
name: "--input"
description: "input SAM/BAM/CRAM file"
info: null
must_exist: true
create_parent: true
required: true
direction: "input"
multiple: false
multiple_sep: ";"
- name: "Outputs"
arguments:
- type: "file"
name: "--output"
description: "output FASTA file"
info: null
must_exist: true
create_parent: true
required: true
direction: "output"
multiple: false
multiple_sep: ";"
- name: "Options"
arguments:
- type: "boolean_true"
name: "--no_suffix"
alternatives:
- "-n"
description: "By default, either '/1' or '/2' is added to the end of read names\
\ where the corresponding \nREAD1 or READ2 FLAG bit is set. Using -n causes\
\ read names to be left as they are.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--suffix"
alternatives:
- "-N"
description: "Always add either '/1' or '/2' to the end of read names even when\
\ put into different files.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--use_oq"
alternatives:
- "-O"
description: "Use quality values from OQ tags in preference to standard quality\
\ string if available.\n"
info: null
direction: "input"
- type: "file"
name: "--singleton"
alternatives:
- "-s"
description: "write singleton reads to FILE."
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean_true"
name: "--copy_tags"
alternatives:
- "-t"
description: "Copy RG, BC and QT tags to the FASTA header line, if they exist.\n"
info: null
direction: "input"
- type: "string"
name: "--copy_tags_list"
alternatives:
- "-T"
description: "Specify a comma-separated list of tags to copy to the FASTA header\
\ line, if they exist. \nTAGLIST can be blank or `*` to indicate all tags should\
\ be copied to the output. If using `*`, \nbe careful to quote it to avoid unwanted\
\ shell expansion.\n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--read1"
alternatives:
- "-1"
description: "Write reads with the READ1 FLAG set (and READ2 not set) to FILE\
\ instead of outputting them. \nIf the -s option is used, only paired reads\
\ will be written to this file.\n"
info: null
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--read2"
alternatives:
- "-2"
description: "Write reads with the READ2 FLAG set (and READ1 not set) to FILE\
\ instead of outputting them. \nIf the -s option is used, only paired reads\
\ will be written to this file.\n"
info: null
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--output_reads"
alternatives:
- "-o"
description: "Write reads with either READ1 FLAG or READ2 flag set to FILE instead\
\ of outputting them to stdout. \nThis is equivalent to -1 FILE -2 FILE.\n"
info: null
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--output_reads_both"
alternatives:
- "0"
description: "Write reads where the READ1 and READ2 FLAG bits set are either both\
\ set or both unset to FILE \ninstead of outputting them.\n"
info: null
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--filter_flags"
alternatives:
- "-f"
description: "Only output alignments with all bits set in INT present in the FLAG\
\ field. INT can be specified \nin hex by beginning with '0x' (i.e. /^0x[0-9A-F]+/)\
\ or in octal by beginning with '0' \n(i.e. /^0[0-7]+/). Default: `0`.\n"
info: null
example:
- 0
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--excl_flags"
alternatives:
- "-F"
description: "Do not output alignments with any bits set in INT present in the\
\ FLAG field. INT can be specified \nin hex by beginning with '0x' (i.e. /^0x[0-9A-F]+/)\
\ or in octal by beginning with '0'\n(i.e. /^0[0-7]+/). This defaults to 0x900\
\ representing filtering of secondary and \nsupplementary alignments. Default:\
\ `0x900`.\n"
info: null
example:
- "0x900"
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--incl_flags"
alternatives:
- "--rf"
description: "Only output alignments with any bits set in INT present in the FLAG\
\ field. INT can be specified \nin hex by beginning with '0x' (i.e. /^0x[0-9A-F]+/),\
\ in octal by beginning with '0'\n(i.e. /^0[0-7]+/), as a decimal number not\
\ beginning with '0' or as a comma-separated list of \nflag names. Default:\
\ `0`.\n"
info: null
example:
- "0"
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--excl_flags_all"
alternatives:
- "-G"
description: "Only EXCLUDE reads with all of the bits set in INT present in the\
\ FLAG field. INT can be specified \nin hex by beginning with '0x' (i.e. /^0x[0-9A-F]+/)\
\ or in octal by beginning with '0' (i.e. /^0[0-7]+/).\nDefault: `0`.\n"
info: null
example:
- 0
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--aux_tag"
alternatives:
- "-d"
description: "Only output alignments containing an auxiliary tag matching both\
\ TAG and VAL. If VAL is omitted \nthen any value is accepted. The tag types\
\ supported are i, f, Z, A and H. \"B\" arrays are not \nsupported. This is\
\ comparable to the method used in samtools view --tag. The option may be specified\
\ \nmultiple times and is equivalent to using the --aux_tag_file option.\n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--aux_tag_file"
alternatives:
- "-D"
description: "Only output alignments containing an auxiliary tag matching TAG\
\ and having a value listed in FILE. \nThe format of the file is one line per\
\ value. This is equivalent to specifying --aux_tag multiple times.\n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean_true"
name: "--casava"
alternatives:
- "-i"
description: "add Illumina Casava 1.8 format entry to header (eg 1:N:0:ATCACG)"
info: null
direction: "input"
- type: "integer"
name: "--compression"
alternatives:
- "-c"
description: "set compression level when writing gz or bgzf fasta files."
info: null
example:
- 0
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--index1"
alternatives:
- "--i1"
description: "write first index reads to FILE."
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--index2"
alternatives:
- "--i2"
description: "write second index reads to FILE."
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--barcode_tag"
description: "Auxiliary tag to find index reads in. Default: `BC`.\n"
info: null
example:
- "BC"
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--quality_tag"
description: "Auxiliary tag to find index quality in. Default: `QT`.\n"
info: null
example:
- "QT"
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--index_format"
description: "string to describe how to parse the barcode and quality tags. For\
\ example:\n* `i14i8`: the first 14 characters are index 1, the next 8 characters\
\ are index 2.\n* `n8i14`: ignore the first 8 characters, and use the next 14\
\ characters for index 1.\nIf the tag contains a separator, then the numeric\
\ part can be replaced with`*` to mean \n'read until the separator or end of\
\ tag', for example: `n*i*`.\n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
resources:
- type: "bash_script"
path: "script.sh"
is_executable: true
description: "Converts a SAM, BAM or CRAM to FASTA format."
test_resources:
- type: "bash_script"
path: "test.sh"
is_executable: true
- type: "file"
path: "test_data"
info: null
status: "enabled"
requirements:
commands:
- "ps"
keywords:
- "fasta"
- "bam"
- "sam"
- "cram"
license: "MIT/Expat"
references:
doi:
- "10.1093/bioinformatics/btp352"
- "10.1093/gigascience/giab008"
links:
repository: "https://github.com/samtools/samtools"
homepage: "https://www.htslib.org/"
documentation: "https://www.htslib.org/doc/samtools-fasta.html"
runners:
- type: "executable"
id: "executable"
docker_setup_strategy: "ifneedbepullelsecachedbuild"
- type: "nextflow"
id: "nextflow"
directives:
tag: "$id"
auto:
simplifyInput: true
simplifyOutput: false
transcript: false
publish: false
config:
labels:
mem1gb: "memory = 1000000000.B"
mem2gb: "memory = 2000000000.B"
mem5gb: "memory = 5000000000.B"
mem10gb: "memory = 10000000000.B"
mem20gb: "memory = 20000000000.B"
mem50gb: "memory = 50000000000.B"
mem100gb: "memory = 100000000000.B"
mem200gb: "memory = 200000000000.B"
mem500gb: "memory = 500000000000.B"
mem1tb: "memory = 1000000000000.B"
mem2tb: "memory = 2000000000000.B"
mem5tb: "memory = 5000000000000.B"
mem10tb: "memory = 10000000000000.B"
mem20tb: "memory = 20000000000000.B"
mem50tb: "memory = 50000000000000.B"
mem100tb: "memory = 100000000000000.B"
mem200tb: "memory = 200000000000000.B"
mem500tb: "memory = 500000000000000.B"
mem1gib: "memory = 1073741824.B"
mem2gib: "memory = 2147483648.B"
mem4gib: "memory = 4294967296.B"
mem8gib: "memory = 8589934592.B"
mem16gib: "memory = 17179869184.B"
mem32gib: "memory = 34359738368.B"
mem64gib: "memory = 68719476736.B"
mem128gib: "memory = 137438953472.B"
mem256gib: "memory = 274877906944.B"
mem512gib: "memory = 549755813888.B"
mem1tib: "memory = 1099511627776.B"
mem2tib: "memory = 2199023255552.B"
mem4tib: "memory = 4398046511104.B"
mem8tib: "memory = 8796093022208.B"
mem16tib: "memory = 17592186044416.B"
mem32tib: "memory = 35184372088832.B"
mem64tib: "memory = 70368744177664.B"
mem128tib: "memory = 140737488355328.B"
mem256tib: "memory = 281474976710656.B"
mem512tib: "memory = 562949953421312.B"
cpu1: "cpus = 1"
cpu2: "cpus = 2"
cpu5: "cpus = 5"
cpu10: "cpus = 10"
cpu20: "cpus = 20"
cpu50: "cpus = 50"
cpu100: "cpus = 100"
cpu200: "cpus = 200"
cpu500: "cpus = 500"
cpu1000: "cpus = 1000"
debug: false
container: "docker"
engines:
- type: "docker"
id: "docker"
image: "quay.io/biocontainers/samtools:1.19.2--h50ea8bc_1"
target_registry: "images.viash-hub.com"
target_tag: "v0.2"
namespace_separator: "/"
setup:
- type: "docker"
run:
- "samtools --version 2>&1 | grep -E '^(samtools|Using htslib)' | \\\nsed 's#Using\
\ ##;s# \\([0-9\\.]*\\)$#: \\1#' > /var/software_versions.txt\n"
entrypoint: []
cmd: null
- type: "native"
id: "native"
build_info:
config: "src/samtools/samtools_fasta/config.vsh.yaml"
runner: "executable"
engine: "docker|native"
output: "target/executable/samtools/samtools_fasta"
executable: "target/executable/samtools/samtools_fasta/samtools_fasta"
viash_version: "0.9.0-RC7"
git_commit: "f22ab0eab58dcd6bff89d8d73fe951953ff1260f"
git_remote: "https://github.com/viash-hub/biobox"
package_config:
name: "biobox"
version: "v0.2"
description: "A collection of bioinformatics tools for working with sequence data.\n"
info: null
viash_version: "0.9.0-RC7"
source: "src"
target: "target"
config_mods:
- ".requirements.commands := ['ps']\n"
- ".engines += { type: \"native\" }"
- ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
- ".engines[.type == 'docker'].target_tag := 'v0.2'"
keywords:
- "bioinformatics"
- "modules"
- "sequencing"
license: "MIT"
organization: "vsh"
links:
repository: "https://github.com/viash-hub/biobox"
issue_tracker: "https://github.com/viash-hub/biobox/issues"

1802
target/executable/samtools/samtools_fasta/samtools_fasta Executable file
View File

File diff suppressed because it is too large Load Diff

459
target/executable/samtools/samtools_fastq/.config.vsh.yaml Normal file
View File

@@ -0,0 +1,459 @@
name: "samtools_fastq"
namespace: "samtools"
version: "v0.2"
authors:
- name: "Emma Rousseau"
roles:
- "author"
- "maintainer"
info:
links:
email: "emma@data-intuitive.com"
github: "emmarousseau"
linkedin: "emmarousseau1"
organizations:
- name: "Data Intuitive"
href: "https://www.data-intuitive.com"
role: "Bioinformatician"
argument_groups:
- name: "Inputs"
arguments:
- type: "file"
name: "--input"
description: "input SAM/BAM/CRAM file"
info: null
must_exist: true
create_parent: true
required: true
direction: "input"
multiple: false
multiple_sep: ";"
- name: "Outputs"
arguments:
- type: "file"
name: "--output"
description: "output FASTQ file"
info: null
must_exist: true
create_parent: true
required: true
direction: "output"
multiple: false
multiple_sep: ";"
- name: "Options"
arguments:
- type: "boolean_true"
name: "--no_suffix"
alternatives:
- "-n"
description: "By default, either '/1' or '/2' is added to the end of read names\
\ where the corresponding \nREAD1 or READ2 FLAG bit is set. Using -n causes\
\ read names to be left as they are.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--suffix"
alternatives:
- "-N"
description: "Always add either '/1' or '/2' to the end of read names even when\
\ put into different files.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--use_oq"
alternatives:
- "-O"
description: "Use quality values from OQ tags in preference to standard quality\
\ string if available.\n"
info: null
direction: "input"
- type: "file"
name: "--singleton"
alternatives:
- "-s"
description: "write singleton reads to FILE."
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean_true"
name: "--copy_tags"
alternatives:
- "-t"
description: "Copy RG, BC and QT tags to the FASTQ header line, if they exist.\n"
info: null
direction: "input"
- type: "string"
name: "--copy_tags_list"
alternatives:
- "-T"
description: "Specify a comma-separated list of tags to copy to the FASTQ header\
\ line, if they exist. \nTAGLIST can be blank or `*` to indicate all tags should\
\ be copied to the output. If using `*`, \nbe careful to quote it to avoid unwanted\
\ shell expansion.\n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--read1"
alternatives:
- "-1"
description: "Write reads with the READ1 FLAG set (and READ2 not set) to FILE\
\ instead of outputting them. \nIf the -s option is used, only paired reads\
\ will be written to this file.\n"
info: null
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--read2"
alternatives:
- "-2"
description: "Write reads with the READ2 FLAG set (and READ1 not set) to FILE\
\ instead of outputting them. \nIf the -s option is used, only paired reads\
\ will be written to this file.\n"
info: null
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--output_reads"
alternatives:
- "-o"
description: "Write reads with either READ1 FLAG or READ2 flag set to FILE instead\
\ of outputting them to stdout. \nThis is equivalent to -1 FILE -2 FILE.\n"
info: null
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--output_reads_both"
alternatives:
- "0"
description: "Write reads where the READ1 and READ2 FLAG bits set are either both\
\ set or both unset to FILE \ninstead of outputting them.\n"
info: null
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--filter_flags"
alternatives:
- "-f"
description: "Only output alignments with all bits set in INT present in the FLAG\
\ field. INT can be specified \nin hex by beginning with '0x' (i.e. /^0x[0-9A-F]+/)\
\ or in octal by beginning with '0'\n(i.e. /^0[0-7]+/). Default: `0`.\n"
info: null
example:
- 0
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--excl_flags"
alternatives:
- "-F"
description: "Do not output alignments with any bits set in INT present in the\
\ FLAG field. INT can be specified \nin hex by beginning with '0x' (i.e. /^0x[0-9A-F]+/)\
\ or in octal by beginning with '0' \n(i.e. /^0[0-7]+/). This defaults to 0x900\
\ representing filtering of secondary and \nsupplementary alignments. Default:\
\ `0x900`.\n"
info: null
example:
- "0x900"
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--incl_flags"
alternatives:
- "--rf"
description: "Only output alignments with any bits set in INT present in the FLAG\
\ field. INT can be specified \nin hex by beginning with '0x' (i.e. /^0x[0-9A-F]+/),\
\ in octal by beginning with '0'\n(i.e. /^0[0-7]+/), as a decimal number not\
\ beginning with '0' or as a comma-separated list of \nflag names. Default:\
\ `0`.\n"
info: null
example:
- "0"
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--excl_flags_all"
alternatives:
- "-G"
description: "Only EXCLUDE reads with all of the bits set in INT present in the\
\ FLAG field. INT can be specified \nin hex by beginning with '0x' (i.e. /^0x[0-9A-F]+/)\
\ or in octal by beginning with '0' (i.e. /^0[0-7]+/).\nDefault: `0`.\n"
info: null
example:
- 0
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--aux_tag"
alternatives:
- "-d"
description: "Only output alignments containing an auxiliary tag matching both\
\ TAG and VAL. If VAL is omitted \nthen any value is accepted. The tag types\
\ supported are i, f, Z, A and H. \"B\" arrays are not \nsupported. This is\
\ comparable to the method used in samtools view --tag. The option may be specified\
\ \nmultiple times and is equivalent to using the --aux_tag_file option.\n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--aux_tag_file"
alternatives:
- "-D"
description: "Only output alignments containing an auxiliary tag matching TAG\
\ and having a value listed in FILE. \nThe format of the file is one line per\
\ value. This is equivalent to specifying --aux_tag multiple times.\n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean_true"
name: "--casava"
alternatives:
- "-i"
description: "Add Illumina Casava 1.8 format entry to header, for example: `1:N:0:ATCACG`.\n"
info: null
direction: "input"
- type: "integer"
name: "--compression"
alternatives:
- "-c"
description: "set compression level when writing gz or bgzf fastq files."
info: null
example:
- 0
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--index1"
alternatives:
- "--i1"
description: "write first index reads to FILE."
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--index2"
alternatives:
- "--i2"
description: "write second index reads to FILE."
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--barcode_tag"
description: "Auxiliary tag to find index reads in. Default: `BC`.\n"
info: null
example:
- "BC"
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--quality_tag"
description: "Auxiliary tag to find index quality in. Default: `QT`.\n"
info: null
example:
- "QT"
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--index_format"
description: "string to describe how to parse the barcode and quality tags. For\
\ example:\n* `i14i8`: the first 14 characters are index 1, the next 8 characters\
\ are index 2.\n* `n8i14`: ignore the first 8 characters, and use the next 14\
\ characters for index 1.\nIf the tag contains a separator, then the numeric\
\ part can be replaced with '*' to mean \n'read until the separator or end of\
\ tag', for example: `n*i*`.\n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
resources:
- type: "bash_script"
path: "script.sh"
is_executable: true
description: "Converts a SAM, BAM or CRAM to FASTQ format."
test_resources:
- type: "bash_script"
path: "test.sh"
is_executable: true
- type: "file"
path: "test_data"
info: null
status: "enabled"
requirements:
commands:
- "ps"
keywords:
- "fastq"
- "bam"
- "sam"
- "cram"
license: "MIT/Expat"
references:
doi:
- "10.1093/bioinformatics/btp352"
- "10.1093/gigascience/giab008"
links:
repository: "https://github.com/samtools/samtools"
homepage: "https://www.htslib.org/"
documentation: "https://www.htslib.org/doc/samtools-fastq.html"
runners:
- type: "executable"
id: "executable"
docker_setup_strategy: "ifneedbepullelsecachedbuild"
- type: "nextflow"
id: "nextflow"
directives:
tag: "$id"
auto:
simplifyInput: true
simplifyOutput: false
transcript: false
publish: false
config:
labels:
mem1gb: "memory = 1000000000.B"
mem2gb: "memory = 2000000000.B"
mem5gb: "memory = 5000000000.B"
mem10gb: "memory = 10000000000.B"
mem20gb: "memory = 20000000000.B"
mem50gb: "memory = 50000000000.B"
mem100gb: "memory = 100000000000.B"
mem200gb: "memory = 200000000000.B"
mem500gb: "memory = 500000000000.B"
mem1tb: "memory = 1000000000000.B"
mem2tb: "memory = 2000000000000.B"
mem5tb: "memory = 5000000000000.B"
mem10tb: "memory = 10000000000000.B"
mem20tb: "memory = 20000000000000.B"
mem50tb: "memory = 50000000000000.B"
mem100tb: "memory = 100000000000000.B"
mem200tb: "memory = 200000000000000.B"
mem500tb: "memory = 500000000000000.B"
mem1gib: "memory = 1073741824.B"
mem2gib: "memory = 2147483648.B"
mem4gib: "memory = 4294967296.B"
mem8gib: "memory = 8589934592.B"
mem16gib: "memory = 17179869184.B"
mem32gib: "memory = 34359738368.B"
mem64gib: "memory = 68719476736.B"
mem128gib: "memory = 137438953472.B"
mem256gib: "memory = 274877906944.B"
mem512gib: "memory = 549755813888.B"
mem1tib: "memory = 1099511627776.B"
mem2tib: "memory = 2199023255552.B"
mem4tib: "memory = 4398046511104.B"
mem8tib: "memory = 8796093022208.B"
mem16tib: "memory = 17592186044416.B"
mem32tib: "memory = 35184372088832.B"
mem64tib: "memory = 70368744177664.B"
mem128tib: "memory = 140737488355328.B"
mem256tib: "memory = 281474976710656.B"
mem512tib: "memory = 562949953421312.B"
cpu1: "cpus = 1"
cpu2: "cpus = 2"
cpu5: "cpus = 5"
cpu10: "cpus = 10"
cpu20: "cpus = 20"
cpu50: "cpus = 50"
cpu100: "cpus = 100"
cpu200: "cpus = 200"
cpu500: "cpus = 500"
cpu1000: "cpus = 1000"
debug: false
container: "docker"
engines:
- type: "docker"
id: "docker"
image: "quay.io/biocontainers/samtools:1.19.2--h50ea8bc_1"
target_registry: "images.viash-hub.com"
target_tag: "v0.2"
namespace_separator: "/"
setup:
- type: "docker"
run:
- "samtools --version 2>&1 | grep -E '^(samtools|Using htslib)' | \\\nsed 's#Using\
\ ##;s# \\([0-9\\.]*\\)$#: \\1#' > /var/software_versions.txt\n"
entrypoint: []
cmd: null
- type: "native"
id: "native"
build_info:
config: "src/samtools/samtools_fastq/config.vsh.yaml"
runner: "executable"
engine: "docker|native"
output: "target/executable/samtools/samtools_fastq"
executable: "target/executable/samtools/samtools_fastq/samtools_fastq"
viash_version: "0.9.0-RC7"
git_commit: "f22ab0eab58dcd6bff89d8d73fe951953ff1260f"
git_remote: "https://github.com/viash-hub/biobox"
package_config:
name: "biobox"
version: "v0.2"
description: "A collection of bioinformatics tools for working with sequence data.\n"
info: null
viash_version: "0.9.0-RC7"
source: "src"
target: "target"
config_mods:
- ".requirements.commands := ['ps']\n"
- ".engines += { type: \"native\" }"
- ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
- ".engines[.type == 'docker'].target_tag := 'v0.2'"
keywords:
- "bioinformatics"
- "modules"
- "sequencing"
license: "MIT"
organization: "vsh"
links:
repository: "https://github.com/viash-hub/biobox"
issue_tracker: "https://github.com/viash-hub/biobox/issues"

1803
target/executable/samtools/samtools_fastq/samtools_fastq Executable file
View File

File diff suppressed because it is too large Load Diff

199
target/executable/samtools/samtools_flagstat/.config.vsh.yaml Normal file
View File

@@ -0,0 +1,199 @@
name: "samtools_flagstat"
namespace: "samtools"
version: "v0.2"
authors:
- name: "Emma Rousseau"
roles:
- "author"
- "maintainer"
info:
links:
email: "emma@data-intuitive.com"
github: "emmarousseau"
linkedin: "emmarousseau1"
organizations:
- name: "Data Intuitive"
href: "https://www.data-intuitive.com"
role: "Bioinformatician"
argument_groups:
- name: "Inputs"
arguments:
- type: "file"
name: "--bam"
description: "BAM input files.\n"
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--bai"
description: "BAM index file.\n"
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- name: "Outputs"
arguments:
- type: "file"
name: "--output"
description: "File containing samtools stats output.\n"
info: null
example:
- "output.flagstat"
must_exist: true
create_parent: true
required: true
direction: "output"
multiple: false
multiple_sep: ";"
resources:
- type: "bash_script"
path: "script.sh"
is_executable: true
description: "Counts the number of alignments in SAM/BAM/CRAM files for each FLAG\
\ type."
test_resources:
- type: "bash_script"
path: "test.sh"
is_executable: true
- type: "file"
path: "test_data"
info: null
status: "enabled"
requirements:
commands:
- "ps"
keywords:
- "stats"
- "mapping"
- "counts"
- "bam"
- "sam"
- "cram"
license: "MIT/Expat"
references:
doi:
- "10.1093/bioinformatics/btp352"
- "10.1093/gigascience/giab008"
links:
repository: "https://github.com/samtools/samtools"
homepage: "https://www.htslib.org/"
documentation: "https://www.htslib.org/doc/samtools-flagstat.html"
runners:
- type: "executable"
id: "executable"
docker_setup_strategy: "ifneedbepullelsecachedbuild"
- type: "nextflow"
id: "nextflow"
directives:
tag: "$id"
auto:
simplifyInput: true
simplifyOutput: false
transcript: false
publish: false
config:
labels:
mem1gb: "memory = 1000000000.B"
mem2gb: "memory = 2000000000.B"
mem5gb: "memory = 5000000000.B"
mem10gb: "memory = 10000000000.B"
mem20gb: "memory = 20000000000.B"
mem50gb: "memory = 50000000000.B"
mem100gb: "memory = 100000000000.B"
mem200gb: "memory = 200000000000.B"
mem500gb: "memory = 500000000000.B"
mem1tb: "memory = 1000000000000.B"
mem2tb: "memory = 2000000000000.B"
mem5tb: "memory = 5000000000000.B"
mem10tb: "memory = 10000000000000.B"
mem20tb: "memory = 20000000000000.B"
mem50tb: "memory = 50000000000000.B"
mem100tb: "memory = 100000000000000.B"
mem200tb: "memory = 200000000000000.B"
mem500tb: "memory = 500000000000000.B"
mem1gib: "memory = 1073741824.B"
mem2gib: "memory = 2147483648.B"
mem4gib: "memory = 4294967296.B"
mem8gib: "memory = 8589934592.B"
mem16gib: "memory = 17179869184.B"
mem32gib: "memory = 34359738368.B"
mem64gib: "memory = 68719476736.B"
mem128gib: "memory = 137438953472.B"
mem256gib: "memory = 274877906944.B"
mem512gib: "memory = 549755813888.B"
mem1tib: "memory = 1099511627776.B"
mem2tib: "memory = 2199023255552.B"
mem4tib: "memory = 4398046511104.B"
mem8tib: "memory = 8796093022208.B"
mem16tib: "memory = 17592186044416.B"
mem32tib: "memory = 35184372088832.B"
mem64tib: "memory = 70368744177664.B"
mem128tib: "memory = 140737488355328.B"
mem256tib: "memory = 281474976710656.B"
mem512tib: "memory = 562949953421312.B"
cpu1: "cpus = 1"
cpu2: "cpus = 2"
cpu5: "cpus = 5"
cpu10: "cpus = 10"
cpu20: "cpus = 20"
cpu50: "cpus = 50"
cpu100: "cpus = 100"
cpu200: "cpus = 200"
cpu500: "cpus = 500"
cpu1000: "cpus = 1000"
debug: false
container: "docker"
engines:
- type: "docker"
id: "docker"
image: "quay.io/biocontainers/samtools:1.19.2--h50ea8bc_1"
target_registry: "images.viash-hub.com"
target_tag: "v0.2"
namespace_separator: "/"
setup:
- type: "docker"
run:
- "samtools --version 2>&1 | grep -E '^(samtools|Using htslib)' | \\\nsed 's#Using\
\ ##;s# \\([0-9\\.]*\\)$#: \\1#' > /var/software_versions.txt\n"
entrypoint: []
cmd: null
- type: "native"
id: "native"
build_info:
config: "src/samtools/samtools_flagstat/config.vsh.yaml"
runner: "executable"
engine: "docker|native"
output: "target/executable/samtools/samtools_flagstat"
executable: "target/executable/samtools/samtools_flagstat/samtools_flagstat"
viash_version: "0.9.0-RC7"
git_commit: "f22ab0eab58dcd6bff89d8d73fe951953ff1260f"
git_remote: "https://github.com/viash-hub/biobox"
package_config:
name: "biobox"
version: "v0.2"
description: "A collection of bioinformatics tools for working with sequence data.\n"
info: null
viash_version: "0.9.0-RC7"
source: "src"
target: "target"
config_mods:
- ".requirements.commands := ['ps']\n"
- ".engines += { type: \"native\" }"
- ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
- ".engines[.type == 'docker'].target_tag := 'v0.2'"
keywords:
- "bioinformatics"
- "modules"
- "sequencing"
license: "MIT"
organization: "vsh"
links:
repository: "https://github.com/viash-hub/biobox"
issue_tracker: "https://github.com/viash-hub/biobox/issues"

1109
target/executable/samtools/samtools_flagstat/samtools_flagstat Executable file
View File

File diff suppressed because it is too large Load Diff

209
target/executable/samtools/samtools_idxstats/.config.vsh.yaml Normal file
View File

@@ -0,0 +1,209 @@
name: "samtools_idxstats"
namespace: "samtools"
version: "v0.2"
authors:
- name: "Emma Rousseau"
roles:
- "author"
- "maintainer"
info:
links:
email: "emma@data-intuitive.com"
github: "emmarousseau"
linkedin: "emmarousseau1"
organizations:
- name: "Data Intuitive"
href: "https://www.data-intuitive.com"
role: "Bioinformatician"
argument_groups:
- name: "Inputs"
arguments:
- type: "file"
name: "--bam"
description: "BAM input file."
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--bai"
description: "BAM index file."
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--fasta"
description: "Reference file the CRAM was created with (optional)."
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- name: "Outputs"
arguments:
- type: "file"
name: "--output"
description: "File containing samtools stats output in tab-delimited format.\n"
info: null
example:
- "output.idxstats"
must_exist: true
create_parent: true
required: true
direction: "output"
multiple: false
multiple_sep: ";"
resources:
- type: "bash_script"
path: "script.sh"
is_executable: true
description: "Reports alignment summary statistics for a BAM file."
test_resources:
- type: "bash_script"
path: "test.sh"
is_executable: true
- type: "file"
path: "test_data"
info: null
status: "enabled"
requirements:
commands:
- "ps"
keywords:
- "stats"
- "mapping"
- "counts"
- "chromosome"
- "bam"
- "sam"
- "cram"
license: "MIT/Expat"
references:
doi:
- "10.1093/bioinformatics/btp352"
- "10.1093/gigascience/giab008"
links:
repository: "https://github.com/samtools/samtools"
homepage: "https://www.htslib.org/"
documentation: "https://www.htslib.org/doc/samtools-idxstats.html"
runners:
- type: "executable"
id: "executable"
docker_setup_strategy: "ifneedbepullelsecachedbuild"
- type: "nextflow"
id: "nextflow"
directives:
tag: "$id"
auto:
simplifyInput: true
simplifyOutput: false
transcript: false
publish: false
config:
labels:
mem1gb: "memory = 1000000000.B"
mem2gb: "memory = 2000000000.B"
mem5gb: "memory = 5000000000.B"
mem10gb: "memory = 10000000000.B"
mem20gb: "memory = 20000000000.B"
mem50gb: "memory = 50000000000.B"
mem100gb: "memory = 100000000000.B"
mem200gb: "memory = 200000000000.B"
mem500gb: "memory = 500000000000.B"
mem1tb: "memory = 1000000000000.B"
mem2tb: "memory = 2000000000000.B"
mem5tb: "memory = 5000000000000.B"
mem10tb: "memory = 10000000000000.B"
mem20tb: "memory = 20000000000000.B"
mem50tb: "memory = 50000000000000.B"
mem100tb: "memory = 100000000000000.B"
mem200tb: "memory = 200000000000000.B"
mem500tb: "memory = 500000000000000.B"
mem1gib: "memory = 1073741824.B"
mem2gib: "memory = 2147483648.B"
mem4gib: "memory = 4294967296.B"
mem8gib: "memory = 8589934592.B"
mem16gib: "memory = 17179869184.B"
mem32gib: "memory = 34359738368.B"
mem64gib: "memory = 68719476736.B"
mem128gib: "memory = 137438953472.B"
mem256gib: "memory = 274877906944.B"
mem512gib: "memory = 549755813888.B"
mem1tib: "memory = 1099511627776.B"
mem2tib: "memory = 2199023255552.B"
mem4tib: "memory = 4398046511104.B"
mem8tib: "memory = 8796093022208.B"
mem16tib: "memory = 17592186044416.B"
mem32tib: "memory = 35184372088832.B"
mem64tib: "memory = 70368744177664.B"
mem128tib: "memory = 140737488355328.B"
mem256tib: "memory = 281474976710656.B"
mem512tib: "memory = 562949953421312.B"
cpu1: "cpus = 1"
cpu2: "cpus = 2"
cpu5: "cpus = 5"
cpu10: "cpus = 10"
cpu20: "cpus = 20"
cpu50: "cpus = 50"
cpu100: "cpus = 100"
cpu200: "cpus = 200"
cpu500: "cpus = 500"
cpu1000: "cpus = 1000"
debug: false
container: "docker"
engines:
- type: "docker"
id: "docker"
image: "quay.io/biocontainers/samtools:1.19.2--h50ea8bc_1"
target_registry: "images.viash-hub.com"
target_tag: "v0.2"
namespace_separator: "/"
setup:
- type: "docker"
run:
- "samtools --version 2>&1 | grep -E '^(samtools|Using htslib)' | \\\nsed 's#Using\
\ ##;s# \\([0-9\\.]*\\)$#: \\1#' > /var/software_versions.txt\n"
entrypoint: []
cmd: null
- type: "native"
id: "native"
build_info:
config: "src/samtools/samtools_idxstats/config.vsh.yaml"
runner: "executable"
engine: "docker|native"
output: "target/executable/samtools/samtools_idxstats"
executable: "target/executable/samtools/samtools_idxstats/samtools_idxstats"
viash_version: "0.9.0-RC7"
git_commit: "f22ab0eab58dcd6bff89d8d73fe951953ff1260f"
git_remote: "https://github.com/viash-hub/biobox"
package_config:
name: "biobox"
version: "v0.2"
description: "A collection of bioinformatics tools for working with sequence data.\n"
info: null
viash_version: "0.9.0-RC7"
source: "src"
target: "target"
config_mods:
- ".requirements.commands := ['ps']\n"
- ".engines += { type: \"native\" }"
- ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
- ".engines[.type == 'docker'].target_tag := 'v0.2'"
keywords:
- "bioinformatics"
- "modules"
- "sequencing"
license: "MIT"
organization: "vsh"
links:
repository: "https://github.com/viash-hub/biobox"
issue_tracker: "https://github.com/viash-hub/biobox/issues"

1133
target/executable/samtools/samtools_idxstats/samtools_idxstats Executable file
View File

File diff suppressed because it is too large Load Diff

215
target/executable/samtools/samtools_index/.config.vsh.yaml Normal file
View File

@@ -0,0 +1,215 @@
name: "samtools_index"
namespace: "samtools"
version: "v0.2"
authors:
- name: "Emma Rousseau"
roles:
- "author"
- "maintainer"
info:
links:
email: "emma@data-intuitive.com"
github: "emmarousseau"
linkedin: "emmarousseau1"
organizations:
- name: "Data Intuitive"
href: "https://www.data-intuitive.com"
role: "Bioinformatician"
argument_groups:
- name: "Inputs"
arguments:
- type: "file"
name: "--input"
description: "Input file name"
info: null
must_exist: true
create_parent: true
required: true
direction: "input"
multiple: false
multiple_sep: ";"
- name: "Outputs"
arguments:
- type: "file"
name: "--output"
alternatives:
- "-o"
description: "Output file name"
info: null
example:
- "out.bam.bai"
must_exist: true
create_parent: true
required: true
direction: "output"
multiple: false
multiple_sep: ";"
- name: "Options"
arguments:
- type: "boolean_true"
name: "--bai"
alternatives:
- "-b"
description: "Generate BAM index"
info: null
direction: "input"
- type: "boolean_true"
name: "--csi"
alternatives:
- "-c"
description: "Create a CSI index for BAM files instead of the traditional BAI\
\ \nindex. This will be required for genomes with larger chromosome \nsizes.\n"
info: null
direction: "input"
- type: "integer"
name: "--min_shift"
alternatives:
- "-m"
description: "Create a CSI index, with a minimum interval size of 2^INT.\n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
resources:
- type: "bash_script"
path: "script.sh"
is_executable: true
description: "Index SAM/BAM/CRAM files."
test_resources:
- type: "bash_script"
path: "test.sh"
is_executable: true
- type: "file"
path: "test_data"
info: null
status: "enabled"
requirements:
commands:
- "ps"
keywords:
- "index"
- "bam"
- "sam"
- "cram"
license: "MIT/Expat"
references:
doi:
- "10.1093/bioinformatics/btp352"
- "10.1093/gigascience/giab008"
links:
repository: "https://github.com/samtools/samtools"
homepage: "https://www.htslib.org/"
documentation: "https://www.htslib.org/doc/samtools-index.html"
runners:
- type: "executable"
id: "executable"
docker_setup_strategy: "ifneedbepullelsecachedbuild"
- type: "nextflow"
id: "nextflow"
directives:
tag: "$id"
auto:
simplifyInput: true
simplifyOutput: false
transcript: false
publish: false
config:
labels:
mem1gb: "memory = 1000000000.B"
mem2gb: "memory = 2000000000.B"
mem5gb: "memory = 5000000000.B"
mem10gb: "memory = 10000000000.B"
mem20gb: "memory = 20000000000.B"
mem50gb: "memory = 50000000000.B"
mem100gb: "memory = 100000000000.B"
mem200gb: "memory = 200000000000.B"
mem500gb: "memory = 500000000000.B"
mem1tb: "memory = 1000000000000.B"
mem2tb: "memory = 2000000000000.B"
mem5tb: "memory = 5000000000000.B"
mem10tb: "memory = 10000000000000.B"
mem20tb: "memory = 20000000000000.B"
mem50tb: "memory = 50000000000000.B"
mem100tb: "memory = 100000000000000.B"
mem200tb: "memory = 200000000000000.B"
mem500tb: "memory = 500000000000000.B"
mem1gib: "memory = 1073741824.B"
mem2gib: "memory = 2147483648.B"
mem4gib: "memory = 4294967296.B"
mem8gib: "memory = 8589934592.B"
mem16gib: "memory = 17179869184.B"
mem32gib: "memory = 34359738368.B"
mem64gib: "memory = 68719476736.B"
mem128gib: "memory = 137438953472.B"
mem256gib: "memory = 274877906944.B"
mem512gib: "memory = 549755813888.B"
mem1tib: "memory = 1099511627776.B"
mem2tib: "memory = 2199023255552.B"
mem4tib: "memory = 4398046511104.B"
mem8tib: "memory = 8796093022208.B"
mem16tib: "memory = 17592186044416.B"
mem32tib: "memory = 35184372088832.B"
mem64tib: "memory = 70368744177664.B"
mem128tib: "memory = 140737488355328.B"
mem256tib: "memory = 281474976710656.B"
mem512tib: "memory = 562949953421312.B"
cpu1: "cpus = 1"
cpu2: "cpus = 2"
cpu5: "cpus = 5"
cpu10: "cpus = 10"
cpu20: "cpus = 20"
cpu50: "cpus = 50"
cpu100: "cpus = 100"
cpu200: "cpus = 200"
cpu500: "cpus = 500"
cpu1000: "cpus = 1000"
debug: false
container: "docker"
engines:
- type: "docker"
id: "docker"
image: "quay.io/biocontainers/samtools:1.19.2--h50ea8bc_1"
target_registry: "images.viash-hub.com"
target_tag: "v0.2"
namespace_separator: "/"
setup:
- type: "docker"
run:
- "samtools --version 2>&1 | grep -E '^(samtools|Using htslib)' | \\\nsed 's#Using\
\ ##;s# \\([0-9\\.]*\\)$#: \\1#' > /var/software_versions.txt\n"
entrypoint: []
cmd: null
- type: "native"
id: "native"
build_info:
config: "src/samtools/samtools_index/config.vsh.yaml"
runner: "executable"
engine: "docker|native"
output: "target/executable/samtools/samtools_index"
executable: "target/executable/samtools/samtools_index/samtools_index"
viash_version: "0.9.0-RC7"
git_commit: "f22ab0eab58dcd6bff89d8d73fe951953ff1260f"
git_remote: "https://github.com/viash-hub/biobox"
package_config:
name: "biobox"
version: "v0.2"
description: "A collection of bioinformatics tools for working with sequence data.\n"
info: null
viash_version: "0.9.0-RC7"
source: "src"
target: "target"
config_mods:
- ".requirements.commands := ['ps']\n"
- ".engines += { type: \"native\" }"
- ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
- ".engines[.type == 'docker'].target_tag := 'v0.2'"
keywords:
- "bioinformatics"
- "modules"
- "sequencing"
license: "MIT"
organization: "vsh"
links:
repository: "https://github.com/viash-hub/biobox"
issue_tracker: "https://github.com/viash-hub/biobox/issues"

1180
target/executable/samtools/samtools_index/samtools_index Executable file
View File

File diff suppressed because it is too large Load Diff

358
target/executable/samtools/samtools_sort/.config.vsh.yaml Normal file
View File

@@ -0,0 +1,358 @@
name: "samtools_sort"
namespace: "samtools"
version: "v0.2"
authors:
- name: "Emma Rousseau"
roles:
- "author"
- "maintainer"
info:
links:
email: "emma@data-intuitive.com"
github: "emmarousseau"
linkedin: "emmarousseau1"
organizations:
- name: "Data Intuitive"
href: "https://www.data-intuitive.com"
role: "Bioinformatician"
argument_groups:
- name: "Inputs"
arguments:
- type: "file"
name: "--input"
description: "SAM/BAM/CRAM input file."
info: null
must_exist: true
create_parent: true
required: true
direction: "input"
multiple: false
multiple_sep: ";"
- name: "Outputs"
arguments:
- type: "file"
name: "--output"
description: "Write final output to file.\n"
info: null
example:
- "out.bam"
must_exist: true
create_parent: true
required: true
direction: "output"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--output_fmt"
alternatives:
- "-O"
description: "Specify output format (SAM, BAM, CRAM).\n"
info: null
example:
- "BAM"
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--output_fmt_option"
description: "Specify a single output file format option in the form\nof OPTION\
\ or OPTION=VALUE.\n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--reference"
description: "Reference sequence FASTA FILE.\n"
info: null
example:
- "ref.fa"
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean_true"
name: "--write_index"
description: "Automatically index the output files.\n"
info: null
direction: "input"
- type: "string"
name: "--prefix"
alternatives:
- "-T"
description: "Write temporary files to PREFIX.nnnn.bam.\n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean_true"
name: "--no_PG"
description: "Do not add a PG line.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--template_coordinate"
description: "Sort by template-coordinate.\n"
info: null
direction: "input"
- type: "string"
name: "--input_fmt_option"
description: "Specify a single input file format option in the form\nof OPTION\
\ or OPTION=VALUE.\n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- name: "Options"
arguments:
- type: "integer"
name: "--compression"
alternatives:
- "-l"
description: "Set compression level, from 0 (uncompressed) to 9 (best).\n"
info: null
default:
- 0
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean_true"
name: "--uncompressed"
alternatives:
- "-u"
description: "Output uncompressed data (equivalent to --compression 0).\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--minimiser"
alternatives:
- "-M"
description: "Use minimiser for clustering unaligned/unplaced reads.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--not_reverse"
alternatives:
- "-R"
description: "Do not use reverse strand (only compatible with --minimiser)\n"
info: null
direction: "input"
- type: "integer"
name: "--kmer_size"
alternatives:
- "-K"
description: "Kmer size to use for minimiser.\n"
info: null
example:
- 20
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--order"
alternatives:
- "-I"
description: "Order minimisers by their position in FILE FASTA.\n"
info: null
example:
- "ref.fa"
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--window"
alternatives:
- "-w"
description: "Window size for minimiser INDEXING VIA --order REF.FA.\n"
info: null
example:
- 100
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean_true"
name: "--homopolymers"
alternatives:
- "-H"
description: "Squash homopolymers when computing minimiser.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--natural_sort"
alternatives:
- "-n"
description: "Sort by read name (natural): cannot be used with samtools index.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--ascii_sort"
alternatives:
- "-N"
description: "Sort by read name (ASCII): cannot be used with samtools index.\n"
info: null
direction: "input"
- type: "string"
name: "--tag"
alternatives:
- "-t"
description: "Sort by value of TAG. Uses position as secondary index \n(or read\
\ name if --natural_sort is set).\n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
resources:
- type: "bash_script"
path: "script.sh"
is_executable: true
description: "Sort SAM/BAM/CRAM file."
test_resources:
- type: "bash_script"
path: "test.sh"
is_executable: true
- type: "file"
path: "test_data"
info: null
status: "enabled"
requirements:
commands:
- "ps"
keywords:
- "sort"
- "bam"
- "sam"
- "cram"
license: "MIT/Expat"
references:
doi:
- "10.1093/bioinformatics/btp352"
- "10.1093/gigascience/giab008"
links:
repository: "https://github.com/samtools/samtools"
homepage: "https://www.htslib.org/"
documentation: "https://www.htslib.org/doc/samtools-sort.html"
runners:
- type: "executable"
id: "executable"
docker_setup_strategy: "ifneedbepullelsecachedbuild"
- type: "nextflow"
id: "nextflow"
directives:
tag: "$id"
auto:
simplifyInput: true
simplifyOutput: false
transcript: false
publish: false
config:
labels:
mem1gb: "memory = 1000000000.B"
mem2gb: "memory = 2000000000.B"
mem5gb: "memory = 5000000000.B"
mem10gb: "memory = 10000000000.B"
mem20gb: "memory = 20000000000.B"
mem50gb: "memory = 50000000000.B"
mem100gb: "memory = 100000000000.B"
mem200gb: "memory = 200000000000.B"
mem500gb: "memory = 500000000000.B"
mem1tb: "memory = 1000000000000.B"
mem2tb: "memory = 2000000000000.B"
mem5tb: "memory = 5000000000000.B"
mem10tb: "memory = 10000000000000.B"
mem20tb: "memory = 20000000000000.B"
mem50tb: "memory = 50000000000000.B"
mem100tb: "memory = 100000000000000.B"
mem200tb: "memory = 200000000000000.B"
mem500tb: "memory = 500000000000000.B"
mem1gib: "memory = 1073741824.B"
mem2gib: "memory = 2147483648.B"
mem4gib: "memory = 4294967296.B"
mem8gib: "memory = 8589934592.B"
mem16gib: "memory = 17179869184.B"
mem32gib: "memory = 34359738368.B"
mem64gib: "memory = 68719476736.B"
mem128gib: "memory = 137438953472.B"
mem256gib: "memory = 274877906944.B"
mem512gib: "memory = 549755813888.B"
mem1tib: "memory = 1099511627776.B"
mem2tib: "memory = 2199023255552.B"
mem4tib: "memory = 4398046511104.B"
mem8tib: "memory = 8796093022208.B"
mem16tib: "memory = 17592186044416.B"
mem32tib: "memory = 35184372088832.B"
mem64tib: "memory = 70368744177664.B"
mem128tib: "memory = 140737488355328.B"
mem256tib: "memory = 281474976710656.B"
mem512tib: "memory = 562949953421312.B"
cpu1: "cpus = 1"
cpu2: "cpus = 2"
cpu5: "cpus = 5"
cpu10: "cpus = 10"
cpu20: "cpus = 20"
cpu50: "cpus = 50"
cpu100: "cpus = 100"
cpu200: "cpus = 200"
cpu500: "cpus = 500"
cpu1000: "cpus = 1000"
debug: false
container: "docker"
engines:
- type: "docker"
id: "docker"
image: "quay.io/biocontainers/samtools:1.19.2--h50ea8bc_1"
target_registry: "images.viash-hub.com"
target_tag: "v0.2"
namespace_separator: "/"
setup:
- type: "docker"
run:
- "samtools --version 2>&1 | grep -E '^(samtools|Using htslib)' | \\\nsed 's#Using\
\ ##;s# \\([0-9\\.]*\\)$#: \\1#' > /var/software_versions.txt\n"
entrypoint: []
cmd: null
- type: "native"
id: "native"
build_info:
config: "src/samtools/samtools_sort/config.vsh.yaml"
runner: "executable"
engine: "docker|native"
output: "target/executable/samtools/samtools_sort"
executable: "target/executable/samtools/samtools_sort/samtools_sort"
viash_version: "0.9.0-RC7"
git_commit: "f22ab0eab58dcd6bff89d8d73fe951953ff1260f"
git_remote: "https://github.com/viash-hub/biobox"
package_config:
name: "biobox"
version: "v0.2"
description: "A collection of bioinformatics tools for working with sequence data.\n"
info: null
viash_version: "0.9.0-RC7"
source: "src"
target: "target"
config_mods:
- ".requirements.commands := ['ps']\n"
- ".engines += { type: \"native\" }"
- ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
- ".engines[.type == 'docker'].target_tag := 'v0.2'"
keywords:
- "bioinformatics"
- "modules"
- "sequencing"
license: "MIT"
organization: "vsh"
links:
repository: "https://github.com/viash-hub/biobox"
issue_tracker: "https://github.com/viash-hub/biobox/issues"

1583
target/executable/samtools/samtools_sort/samtools_sort Executable file
View File

File diff suppressed because it is too large Load Diff

427
target/executable/samtools/samtools_stats/.config.vsh.yaml Normal file
View File

@@ -0,0 +1,427 @@
name: "samtools_stats"
namespace: "samtools"
version: "v0.2"
authors:
- name: "Emma Rousseau"
roles:
- "author"
- "maintainer"
info:
links:
email: "emma@data-intuitive.com"
github: "emmarousseau"
linkedin: "emmarousseau1"
organizations:
- name: "Data Intuitive"
href: "https://www.data-intuitive.com"
role: "Bioinformatician"
argument_groups:
- name: "Inputs"
arguments:
- type: "file"
name: "--input"
description: "Input file.\n"
info: null
must_exist: true
create_parent: true
required: true
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--bai"
description: "Index file.\n"
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--fasta"
description: "Reference file the CRAM was created with.\n"
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--coverage"
alternatives:
- "-c"
description: "Coverage distribution min;max;step. Default: [1, 1000, 1].\n"
info: null
example:
- 1
- 1000
- 1
required: false
direction: "input"
multiple: true
multiple_sep: ";"
- type: "boolean_true"
name: "--remove_dups"
alternatives:
- "-d"
description: "Exclude from statistics reads marked as duplicates.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--customized_index_file"
alternatives:
- "-X"
description: "Use a customized index file.\n"
info: null
direction: "input"
- type: "string"
name: "--required_flag"
alternatives:
- "-f"
description: "Required flag, 0 for unset. See also `samtools flags`. Default:\
\ `\"0\"`.\n"
info: null
example:
- "0"
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--filtering_flag"
alternatives:
- "-F"
description: "Filtering flag, 0 for unset. See also `samtools flags`. Default:\
\ `0`.\n"
info: null
example:
- "0"
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "double"
name: "--GC_depth"
description: "The size of GC-depth bins (decreasing bin size increases memory\
\ requirement). Default: `20000`.\n"
info: null
example:
- 20000.0
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--insert_size"
alternatives:
- "-i"
description: "Maximum insert size. Default: `8000`.\n"
info: null
example:
- 8000
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--id"
alternatives:
- "-I"
description: "Include only listed read group or sample name.\n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--read_length"
alternatives:
- "-l"
description: "Include in the statistics only reads with the given read length.\
\ Default: `-1`.\n"
info: null
example:
- -1
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "double"
name: "--most_inserts"
alternatives:
- "-m"
description: "Report only the main part of inserts. Default: `0.99`.\n"
info: null
example:
- 0.99
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--split_prefix"
alternatives:
- "-P"
description: "Path or string prefix for filepaths output by --split (default is\
\ input filename).\n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--trim_quality"
alternatives:
- "-q"
description: "The BWA trimming parameter. Default: `0`.\n"
info: null
example:
- 0
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--ref_seq"
alternatives:
- "-r"
description: "Reference sequence (required for GC-depth and mismatches-per-cycle\
\ calculation).\n"
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--split"
alternatives:
- "-S"
description: "Also write statistics to separate files split by tagged field.\n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--target_regions"
alternatives:
- "-t"
description: "Do stats in these regions only. Tab-delimited file chr,from,to,\
\ 1-based, inclusive.\n"
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean_true"
name: "--sparse"
alternatives:
- "-x"
description: "Suppress outputting IS rows where there are no insertions.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--remove_overlaps"
alternatives:
- "-p"
description: "Remove overlaps of paired-end reads from coverage and base count\
\ computations.\n"
info: null
direction: "input"
- type: "integer"
name: "--cov_threshold"
alternatives:
- "-g"
description: "Only bases with coverage above this value will be included in the\
\ target percentage computation. Default: `0`.\n"
info: null
example:
- 0
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--input_fmt_option"
description: "Specify a single input file format option in the form of OPTION\
\ or OPTION=VALUE.\n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--reference"
description: "Reference sequence FASTA FILE.\n"
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- name: "Outputs"
arguments:
- type: "file"
name: "--output"
alternatives:
- "-o"
description: "Output file.\n"
info: null
example:
- "out.txt"
must_exist: true
create_parent: true
required: true
direction: "output"
multiple: false
multiple_sep: ";"
resources:
- type: "bash_script"
path: "script.sh"
is_executable: true
description: "Reports alignment summary statistics for a BAM file."
test_resources:
- type: "bash_script"
path: "test.sh"
is_executable: true
- type: "file"
path: "test_data"
info: null
status: "enabled"
requirements:
commands:
- "ps"
keywords:
- "statistics"
- "counts"
- "bam"
- "sam"
- "cram"
license: "MIT/Expat"
references:
doi:
- "10.1093/bioinformatics/btp352"
- "10.1093/gigascience/giab008"
links:
repository: "https://github.com/samtools/samtools"
homepage: "https://www.htslib.org/"
documentation: "https://www.htslib.org/doc/samtools-stats.html"
runners:
- type: "executable"
id: "executable"
docker_setup_strategy: "ifneedbepullelsecachedbuild"
- type: "nextflow"
id: "nextflow"
directives:
tag: "$id"
auto:
simplifyInput: true
simplifyOutput: false
transcript: false
publish: false
config:
labels:
mem1gb: "memory = 1000000000.B"
mem2gb: "memory = 2000000000.B"
mem5gb: "memory = 5000000000.B"
mem10gb: "memory = 10000000000.B"
mem20gb: "memory = 20000000000.B"
mem50gb: "memory = 50000000000.B"
mem100gb: "memory = 100000000000.B"
mem200gb: "memory = 200000000000.B"
mem500gb: "memory = 500000000000.B"
mem1tb: "memory = 1000000000000.B"
mem2tb: "memory = 2000000000000.B"
mem5tb: "memory = 5000000000000.B"
mem10tb: "memory = 10000000000000.B"
mem20tb: "memory = 20000000000000.B"
mem50tb: "memory = 50000000000000.B"
mem100tb: "memory = 100000000000000.B"
mem200tb: "memory = 200000000000000.B"
mem500tb: "memory = 500000000000000.B"
mem1gib: "memory = 1073741824.B"
mem2gib: "memory = 2147483648.B"
mem4gib: "memory = 4294967296.B"
mem8gib: "memory = 8589934592.B"
mem16gib: "memory = 17179869184.B"
mem32gib: "memory = 34359738368.B"
mem64gib: "memory = 68719476736.B"
mem128gib: "memory = 137438953472.B"
mem256gib: "memory = 274877906944.B"
mem512gib: "memory = 549755813888.B"
mem1tib: "memory = 1099511627776.B"
mem2tib: "memory = 2199023255552.B"
mem4tib: "memory = 4398046511104.B"
mem8tib: "memory = 8796093022208.B"
mem16tib: "memory = 17592186044416.B"
mem32tib: "memory = 35184372088832.B"
mem64tib: "memory = 70368744177664.B"
mem128tib: "memory = 140737488355328.B"
mem256tib: "memory = 281474976710656.B"
mem512tib: "memory = 562949953421312.B"
cpu1: "cpus = 1"
cpu2: "cpus = 2"
cpu5: "cpus = 5"
cpu10: "cpus = 10"
cpu20: "cpus = 20"
cpu50: "cpus = 50"
cpu100: "cpus = 100"
cpu200: "cpus = 200"
cpu500: "cpus = 500"
cpu1000: "cpus = 1000"
debug: false
container: "docker"
engines:
- type: "docker"
id: "docker"
image: "quay.io/biocontainers/samtools:1.19.2--h50ea8bc_1"
target_registry: "images.viash-hub.com"
target_tag: "v0.2"
namespace_separator: "/"
setup:
- type: "docker"
run:
- "samtools --version 2>&1 | grep -E '^(samtools|Using htslib)' | \\\nsed 's#Using\
\ ##;s# \\([0-9\\.]*\\)$#: \\1#' > /var/software_versions.txt\n"
entrypoint: []
cmd: null
- type: "native"
id: "native"
build_info:
config: "src/samtools/samtools_stats/config.vsh.yaml"
runner: "executable"
engine: "docker|native"
output: "target/executable/samtools/samtools_stats"
executable: "target/executable/samtools/samtools_stats/samtools_stats"
viash_version: "0.9.0-RC7"
git_commit: "f22ab0eab58dcd6bff89d8d73fe951953ff1260f"
git_remote: "https://github.com/viash-hub/biobox"
package_config:
name: "biobox"
version: "v0.2"
description: "A collection of bioinformatics tools for working with sequence data.\n"
info: null
viash_version: "0.9.0-RC7"
source: "src"
target: "target"
config_mods:
- ".requirements.commands := ['ps']\n"
- ".engines += { type: \"native\" }"
- ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
- ".engines[.type == 'docker'].target_tag := 'v0.2'"
keywords:
- "bioinformatics"
- "modules"
- "sequencing"
license: "MIT"
organization: "vsh"
links:
repository: "https://github.com/viash-hub/biobox"
issue_tracker: "https://github.com/viash-hub/biobox/issues"

1714
target/executable/samtools/samtools_stats/samtools_stats Executable file
View File

File diff suppressed because it is too large Load Diff

691
target/executable/samtools/samtools_view/.config.vsh.yaml Normal file
View File

@@ -0,0 +1,691 @@
name: "samtools_view"
namespace: "samtools"
version: "v0.2"
authors:
- name: "Emma Rousseau"
roles:
- "author"
- "maintainer"
info:
links:
email: "emma@data-intuitive.com"
github: "emmarousseau"
linkedin: "emmarousseau1"
organizations:
- name: "Data Intuitive"
href: "https://www.data-intuitive.com"
role: "Bioinformatician"
argument_groups:
- name: "Inputs"
arguments:
- type: "file"
name: "--input"
description: "Input SAM, BAM, or CRAM file."
info: null
must_exist: true
create_parent: true
required: true
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--fai_reference"
alternatives:
- "-t"
description: "A tab-delimited FILE. Each line must contain the reference name\
\ in the first column\nand the length of the reference in the second column,\
\ with one line for each distinct\nreference. Any additional fields beyond the\
\ second column are ignored. This file also\ndefines the order of the reference\
\ sequences in sorting. If you run: `samtools faidx <ref.fa>',\nthe resulting\
\ index file <ref.fa>.fai can be used as this FILE.\n"
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--reference"
alternatives:
- "-T"
description: "A FASTA format reference FILE, optionally compressed by bgzip and\
\ ideally indexed by samtools faidx.\nIf an index is not present one will be\
\ generated for you, if the reference file is local.\nIf the reference file\
\ is not local, but is accessed instead via an https://, s3:// or other URL,\n\
the index file will need to be supplied by the server alongside the reference.\
\ It is possible to\nhave the reference and index files in different locations\
\ by supplying both to this option separated\nby the string \"##idx##\", for\
\ example:\n--reference ftp://x.com/ref.fa##idx##ftp://y.com/index.fa.fai\n\
However, note that only the location of the reference will be stored in the\
\ output file header.\nIf this method is used to make CRAM files, the cram reader\
\ may not be able to find the index,\nand may not be able to decode the file\
\ unless it can get the references it needs using a different\nmethod.\n"
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--target_file"
alternatives:
- "-L"
description: "Only output alignments overlapping the input BED FILE [null].\n"
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--region_file"
description: "Use an index and multi-region iterator to only output alignments\
\ overlapping the input BED FILE.\nEquivalent to --use_index --target_file FILE.\n"
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--qname_file"
alternatives:
- "-N"
description: "Output only alignments with read names listed in FILE. If FILE starts\
\ with ^ then the operation is\nnegated and only outputs alignment with read\
\ groups not listed in FILE. It is not permissible to mix\nboth the filter-in\
\ and filter-out style syntax in the same command.\n"
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--read_group_file"
alternatives:
- "-R"
description: "Output alignments in read groups listed in FILE [null]. If FILE\
\ starts with ^ then the operation is\nnegated and only outputs alignment with\
\ read names not listed in FILE. It is not permissible to mix\nboth the filter-in\
\ and filter-out style syntax in the same command. Note that records with no\
\ RG tag\nwill also be output when using this option. This behaviour may change\
\ in a future release.\n"
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean_true"
name: "--use_index"
alternatives:
- "-M"
description: "Use the multi-region iterator on the union of a BED file and command-line\
\ region arguments.\nThis avoids re-reading the same regions of files so can\
\ sometimes be much faster. Note this also\nremoves duplicate sequences. Without\
\ this a sequence that overlaps multiple regions specified on\nthe command line\
\ will be reported multiple times. The usage of a BED file is optional and its\
\ path\nhas to be preceded by --target_file option.\n"
info: null
direction: "input"
- name: "Outputs"
arguments:
- type: "file"
name: "--output"
alternatives:
- "-o"
description: "Output to FILE instead of [stdout]."
info: null
example:
- "output.bam"
must_exist: true
create_parent: true
required: true
direction: "output"
multiple: false
multiple_sep: ";"
- type: "boolean_true"
name: "--bam"
alternatives:
- "-b"
description: "Output in the BAM format."
info: null
direction: "input"
- type: "boolean_true"
name: "--cram"
alternatives:
- "-C"
description: "Output in the CRAM format (requires --reference).\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--fast"
description: "Enable fast compression. This also changes the default output format\
\ to BAM,\nbut this can be overridden by the explicit format options or using\
\ a filename\nwith a known suffix.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--uncompressed"
alternatives:
- "-u"
description: "Output uncompressed data. This also changes the default output format\
\ to BAM,\nbut this can be overridden by the explicit format options or using\
\ a filename\nwith a known suffix.\nThis option saves time spent on compression/decompression\
\ and is thus preferred\nwhen the output is piped to another samtools command.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--with_header"
description: "Include the header in the output.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--header_only"
alternatives:
- "-H"
description: "Output the header only.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--no_header"
description: "When producing SAM format, output alignment records but not headers.\n\
This is the default; the option can be used to reset the effect of \n--with_header/--header_only.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--count"
alternatives:
- "-c"
description: "Instead of printing the alignments, only count them and print the\
\ total number.\nAll filter options, such as --require_flags, --excl_flags,\
\ and --min_MQ, are taken\ninto account. The --unmap option is ignored in this\
\ mode.\n"
info: null
direction: "input"
- type: "file"
name: "--output_unselected"
alternatives:
- "-U"
description: "Write alignments that are not selected by the various filter options\
\ to FILE.\nWhen this option is used, all alignments (or all alignments intersecting\
\ the regions\nspecified) are written to either the output file or this file,\
\ but never both.\n"
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean_true"
name: "--unmap"
alternatives:
- "-p"
description: "Set the UNMAP flag on alignments that are not selected by the filter\
\ options.\nThese alignments are then written to the normal output. This is\
\ not compatible\nwith --output_unselected.\n"
info: null
direction: "input"
- type: "string"
name: "--read_group"
alternatives:
- "-r"
description: "Output alignments in read group STR [null]. Note that records with\
\ no RG tag will also be output\nwhen using this option. This behaviour may\
\ change in a future release.\n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--tag"
alternatives:
- "-d"
description: "Only output alignments with tag STR1 and associated value STR2,\
\ which can be a string or an integer\n[null].\nThe value can be omitted, in\
\ which case only the tag is considered.\nNote that this option does not specify\
\ a tag type. For example, use --tag XX:42 to select alignments\nwith an XX:i:42\
\ field, not --tag XX:i:42.\n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--tag_file"
alternatives:
- "-D"
description: "Only output alignments with tag STR and associated values listed\
\ in FILE.\n"
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--min_MQ"
alternatives:
- "-q"
description: "Skip alignments with MAPQ smaller than INT.\n"
info: null
default:
- 0
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--library"
alternatives:
- "-l"
description: "Only output alignments in library STR.\n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--min_qlen"
alternatives:
- "-m"
description: "Only output alignments with number of CIGAR bases consuming query\
\ sequence >= INT.\n"
info: null
default:
- 0
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--expr"
alternatives:
- "-e"
description: "Only include alignments that match the filter expression STR. The\
\ syntax for these expressions is\ndescribed in the main samtools.\n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--require_flags"
alternatives:
- "-f"
description: "Only output alignments with all bits set in FLAG present in the\
\ FLAG field. FLAG can be specified\nin hex by beginning with `0x' (i.e. /^0x[0-9A-F]+/),\
\ in octal by beginning with `0' (i.e. /^0[0-7]+/),\nas a decimal number not\
\ beginning with '0' or as a comma-separated list of flag names.\n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--excl_flags"
alternatives:
- "-F"
description: "Do not output alignments with any bits set in FLAG present in the\
\ FLAG field. FLAG can be specified\nin hex by beginning with `0x' (i.e. /^0x[0-9A-F]+/),\
\ in octal by beginning with `0' (i.e. /^0[0-7]+/),\nas a decimal number not\
\ beginning with '0' or as a comma-separated list of flag names.\n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--excl_all_flags"
alternatives:
- "-G"
description: "Do not output alignments with all bits set in INT present in the\
\ FLAG field. This is the opposite of\n--require_flags such that --require_flags\
\ 12 --exclude_all_flags 12 is the same as no filtering at all.\nFLAG can be\
\ specified in hex by beginning with `0x' (i.e. /^0x[0-9A-F]+/), in octal by\
\ beginning with `0'\n(i.e. /^0[0-7]+/), as a decimal number not beginning with\
\ '0' or as a comma-separated list of flag names.\n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--incl_flags"
alternatives:
- "--rf"
description: "Only output alignments with any bit set in FLAG present in the FLAG\
\ field. FLAG can be specified in hex\nby beginning with `0x' (i.e. /^0x[0-9A-F]+/),\
\ in octal by beginning with `0' (i.e. /^0[0-7]+/), as a decimal\nnumber not\
\ beginning with '0' or as a comma-separated list of flag names.\n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--remove_tag"
alternatives:
- "-x"
description: "Read tag(s) to exclude from output (repeatable) [null]. This can\
\ be a single tag or a comma separated list.\nAlternatively the option itself\
\ can be repeated multiple times.\nIf the list starts with a `^' then it is\
\ negated and treated as a request to remove all tags except those in STR.\n\
The list may be empty, so --remove_tag ^ will remove all tags.\nNote that tags\
\ will only be removed from reads that pass filtering.\n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--keep_tag"
description: "This keeps only tags listed in STR and is directly equivalent to\
\ --remove_tag ^STR. Specifying an empty list\nwill remove all tags. If both\
\ --keep_tag and --remove_tag are specified then --keep_tag has precedence.\n\
Note that tags will only be removed from reads that pass filtering.\n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean_true"
name: "--remove_B"
alternatives:
- "-B"
description: "Collapse the backward CIGAR operation.\n"
info: null
direction: "input"
- type: "string"
name: "--add_flags"
description: "Adds flag(s) to read. FLAG can be specified in hex by beginning\
\ with `0x' (i.e. /^0x[0-9A-F]+/), in octal\nby beginning with `0' (i.e. /^0[0-7]+/),\
\ as a decimal number not beginning with '0' or as a comma-separated\nlist of\
\ flag names.\n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--remove_flags"
description: "Remove flag(s) from read. FLAG is specified in the same way as with\
\ the --add_flags option.\n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "double"
name: "--subsample"
description: "Output only a proportion of the input alignments, as specified by\
\ 0.0 <= FLOAT <= 1.0, which gives the fraction\nof templates/pairs to be kept.\
\ This subsampling acts in the same way on all of the alignment records in the\
\ same\ntemplate or read pair, so it never keeps a read but not its mate.\n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--subsample_seed"
description: "Subsampling seed used to influence which subset of reads is kept.\
\ When subsampling data that has previously\nbeen subsampled, be sure to use\
\ a different seed value from those used previously; otherwise more reads will\n\
be retained than expected.\n"
info: null
default:
- 0
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean_true"
name: "--fetch_pairs"
alternatives:
- "-P"
description: "Retrieve pairs even when the mate is outside of the requested region.\
\ Enabling this option also turns on the\nmulti-region iterator (-M). A region\
\ to search must be specified, either on the command-line, or using the\n--target_file\
\ option. The input file must be an indexed regular file.\nThis option first\
\ scans the requested region, using the RNEXT and PNEXT fields of the records\
\ that have the\nPAIRED flag set and pass other filtering options to find where\
\ paired reads are located. These locations are\nused to build an expanded region\
\ list, and a set of QNAMEs to allow from the new regions. It will then make\n\
a second pass, collecting all reads from the originally-specified region list\
\ together with reads from additional\nlocations that match the allowed set\
\ of QNAMEs. Any other filtering options used will be applied to all reads\n\
found during this second pass.\nAs this option links reads using RNEXT and PNEXT,\
\ it is important that these fields are set accurately. Use\n'samtools fixmate'\
\ to correct them if necessary.\nNote that this option does not work with the\
\ --count, --output-unselected or --unmap options.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--customized_index"
alternatives:
- "-X"
description: "Include customized index file as a part of arguments. See EXAMPLES\
\ section for sample of usage.\n"
info: null
direction: "input"
- type: "string"
name: "--sanitize"
alternatives:
- "-z"
description: "Perform some sanity checks on the state of SAM record fields, fixing\
\ up common mistakes made by aligners.\nThese include soft-clipping alignments\
\ when they extend beyond the end of the reference, marking records as\nunmapped\
\ when they have reference * or position 0, and ensuring unmapped alignments\
\ have no CIGAR or mapping\nquality for unmapped alignments and no MD, NM, CG\
\ or SM tags.\nFLAGs is a comma-separated list of keywords chosen from the following\
\ list.\n\nunmap: The UNMAPPED BAM flag. This is set for reads with position\
\ <= 0, reference name \"*\" or reads starting\nbeyond the end of the reference.\
\ Note CIGAR \"*\" is permitted for mapped data so does not trigger this.\n\n\
pos: Position and reference name fields. These may be cleared when a sequence\
\ is unmapped due to the\ncoordinates being beyond the end of the reference.\
\ Selecting this may change the sort order of the file,\nso it is not a part\
\ of the on compound argument.\nmqual: Mapping quality. This is set to zero\
\ for unmapped reads.\ncigar: Modifies CIGAR fields, either by adding soft-clips\
\ for reads that overlap the end of the reference or\n by clearing it\
\ for unmapped reads.\naux: For unmapped data, some auxiliary fields are meaningless\
\ and will be removed. These include NM, MD, CG and SM.\noff: Perform no sanity\
\ fixing. This is the default\non: Sanitize data in a way that guarantees the\
\ same sort order. This is everything except for pos.\nall: All sanitizing options,\
\ including pos.\n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean_true"
name: "--no_PG"
description: "Do not add a @PG line to the header of the output file.\n"
info: null
direction: "input"
- type: "string"
name: "--input_fmt_option"
description: "Specify a single input file format option in the form of OPTION\
\ or OPTION=VALUE.\n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--output_fmt"
alternatives:
- "-O"
description: "Specify output format (SAM, BAM, CRAM).\n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--output_fmt_option"
description: "Specify a single output file format option in the form of OPTION\
\ or OPTION=VALUE.\n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean_true"
name: "--write_index"
description: "Automatically index the output files.\n"
info: null
direction: "input"
resources:
- type: "bash_script"
path: "script.sh"
is_executable: true
description: "Views and converts SAM/BAM/CRAM files."
test_resources:
- type: "bash_script"
path: "test.sh"
is_executable: true
- type: "file"
path: "test_data"
info: null
status: "enabled"
requirements:
commands:
- "ps"
keywords:
- "view"
- "convert"
- "bam"
- "sam"
- "cram"
license: "MIT/Expat"
references:
doi:
- "10.1093/bioinformatics/btp352"
- "10.1093/gigascience/giab008"
links:
repository: "https://github.com/samtools/samtools"
homepage: "https://www.htslib.org/"
documentation: "https://www.htslib.org/doc/samtools-view.html"
runners:
- type: "executable"
id: "executable"
docker_setup_strategy: "ifneedbepullelsecachedbuild"
- type: "nextflow"
id: "nextflow"
directives:
tag: "$id"
auto:
simplifyInput: true
simplifyOutput: false
transcript: false
publish: false
config:
labels:
mem1gb: "memory = 1000000000.B"
mem2gb: "memory = 2000000000.B"
mem5gb: "memory = 5000000000.B"
mem10gb: "memory = 10000000000.B"
mem20gb: "memory = 20000000000.B"
mem50gb: "memory = 50000000000.B"
mem100gb: "memory = 100000000000.B"
mem200gb: "memory = 200000000000.B"
mem500gb: "memory = 500000000000.B"
mem1tb: "memory = 1000000000000.B"
mem2tb: "memory = 2000000000000.B"
mem5tb: "memory = 5000000000000.B"
mem10tb: "memory = 10000000000000.B"
mem20tb: "memory = 20000000000000.B"
mem50tb: "memory = 50000000000000.B"
mem100tb: "memory = 100000000000000.B"
mem200tb: "memory = 200000000000000.B"
mem500tb: "memory = 500000000000000.B"
mem1gib: "memory = 1073741824.B"
mem2gib: "memory = 2147483648.B"
mem4gib: "memory = 4294967296.B"
mem8gib: "memory = 8589934592.B"
mem16gib: "memory = 17179869184.B"
mem32gib: "memory = 34359738368.B"
mem64gib: "memory = 68719476736.B"
mem128gib: "memory = 137438953472.B"
mem256gib: "memory = 274877906944.B"
mem512gib: "memory = 549755813888.B"
mem1tib: "memory = 1099511627776.B"
mem2tib: "memory = 2199023255552.B"
mem4tib: "memory = 4398046511104.B"
mem8tib: "memory = 8796093022208.B"
mem16tib: "memory = 17592186044416.B"
mem32tib: "memory = 35184372088832.B"
mem64tib: "memory = 70368744177664.B"
mem128tib: "memory = 140737488355328.B"
mem256tib: "memory = 281474976710656.B"
mem512tib: "memory = 562949953421312.B"
cpu1: "cpus = 1"
cpu2: "cpus = 2"
cpu5: "cpus = 5"
cpu10: "cpus = 10"
cpu20: "cpus = 20"
cpu50: "cpus = 50"
cpu100: "cpus = 100"
cpu200: "cpus = 200"
cpu500: "cpus = 500"
cpu1000: "cpus = 1000"
debug: false
container: "docker"
engines:
- type: "docker"
id: "docker"
image: "quay.io/biocontainers/samtools:1.19.2--h50ea8bc_1"
target_registry: "images.viash-hub.com"
target_tag: "v0.2"
namespace_separator: "/"
setup:
- type: "docker"
run:
- "samtools --version 2>&1 | grep -E '^(samtools|Using htslib)' | \\\nsed 's#Using\
\ ##;s# \\([0-9\\.]*\\)$#: \\1#' > /var/software_versions.txt\n"
entrypoint: []
cmd: null
- type: "native"
id: "native"
build_info:
config: "src/samtools/samtools_view/config.vsh.yaml"
runner: "executable"
engine: "docker|native"
output: "target/executable/samtools/samtools_view"
executable: "target/executable/samtools/samtools_view/samtools_view"
viash_version: "0.9.0-RC7"
git_commit: "f22ab0eab58dcd6bff89d8d73fe951953ff1260f"
git_remote: "https://github.com/viash-hub/biobox"
package_config:
name: "biobox"
version: "v0.2"
description: "A collection of bioinformatics tools for working with sequence data.\n"
info: null
viash_version: "0.9.0-RC7"
source: "src"
target: "target"
config_mods:
- ".requirements.commands := ['ps']\n"
- ".engines += { type: \"native\" }"
- ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
- ".engines[.type == 'docker'].target_tag := 'v0.2'"
keywords:
- "bioinformatics"
- "modules"
- "sequencing"
license: "MIT"
organization: "vsh"
links:
repository: "https://github.com/viash-hub/biobox"
issue_tracker: "https://github.com/viash-hub/biobox/issues"

2375
target/executable/samtools/samtools_view/samtools_view Executable file
View File

File diff suppressed because it is too large Load Diff

199
target/executable/seqtk/seqtk_sample/.config.vsh.yaml Normal file
View File

@@ -0,0 +1,199 @@
name: "seqtk_sample"
namespace: "seqtk"
version: "v0.2"
authors:
- name: "Jakub Majercik"
roles:
- "author"
- "maintainer"
info:
links:
email: "jakub@data-intuitive.com"
github: "jakubmajercik"
linkedin: "jakubmajercik"
organizations:
- name: "Data Intuitive"
href: "https://www.data-intuitive.com"
role: "Bioinformatics Engineer"
argument_groups:
- name: "Inputs"
arguments:
- type: "file"
name: "--input"
description: "The input FASTA/Q file."
info: null
must_exist: true
create_parent: true
required: true
direction: "input"
multiple: false
multiple_sep: ";"
- name: "Outputs"
arguments:
- type: "file"
name: "--output"
description: "The output FASTA/Q file."
info: null
must_exist: true
create_parent: true
required: true
direction: "output"
multiple: false
multiple_sep: ";"
- name: "Options"
arguments:
- type: "integer"
name: "--seed"
description: "Seed for random generator."
info: null
example:
- 42
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "double"
name: "--fraction_number"
description: "Fraction or number of sequences to sample."
info: null
example:
- 0.1
required: true
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean_true"
name: "--two_pass_mode"
description: "Twice as slow but with much reduced memory"
info: null
direction: "input"
resources:
- type: "bash_script"
path: "script.sh"
is_executable: true
description: "Subsamples sequences from FASTA/Q files."
test_resources:
- type: "bash_script"
path: "test.sh"
is_executable: true
- type: "file"
path: "test_data"
info: null
status: "enabled"
requirements:
commands:
- "ps"
keywords:
- "sample"
- "FASTA"
- "FASTQ"
license: "MIT"
links:
repository: "https://github.com/lh3/seqtk/tree/v1.4"
runners:
- type: "executable"
id: "executable"
docker_setup_strategy: "ifneedbepullelsecachedbuild"
- type: "nextflow"
id: "nextflow"
directives:
tag: "$id"
auto:
simplifyInput: true
simplifyOutput: false
transcript: false
publish: false
config:
labels:
mem1gb: "memory = 1000000000.B"
mem2gb: "memory = 2000000000.B"
mem5gb: "memory = 5000000000.B"
mem10gb: "memory = 10000000000.B"
mem20gb: "memory = 20000000000.B"
mem50gb: "memory = 50000000000.B"
mem100gb: "memory = 100000000000.B"
mem200gb: "memory = 200000000000.B"
mem500gb: "memory = 500000000000.B"
mem1tb: "memory = 1000000000000.B"
mem2tb: "memory = 2000000000000.B"
mem5tb: "memory = 5000000000000.B"
mem10tb: "memory = 10000000000000.B"
mem20tb: "memory = 20000000000000.B"
mem50tb: "memory = 50000000000000.B"
mem100tb: "memory = 100000000000000.B"
mem200tb: "memory = 200000000000000.B"
mem500tb: "memory = 500000000000000.B"
mem1gib: "memory = 1073741824.B"
mem2gib: "memory = 2147483648.B"
mem4gib: "memory = 4294967296.B"
mem8gib: "memory = 8589934592.B"
mem16gib: "memory = 17179869184.B"
mem32gib: "memory = 34359738368.B"
mem64gib: "memory = 68719476736.B"
mem128gib: "memory = 137438953472.B"
mem256gib: "memory = 274877906944.B"
mem512gib: "memory = 549755813888.B"
mem1tib: "memory = 1099511627776.B"
mem2tib: "memory = 2199023255552.B"
mem4tib: "memory = 4398046511104.B"
mem8tib: "memory = 8796093022208.B"
mem16tib: "memory = 17592186044416.B"
mem32tib: "memory = 35184372088832.B"
mem64tib: "memory = 70368744177664.B"
mem128tib: "memory = 140737488355328.B"
mem256tib: "memory = 281474976710656.B"
mem512tib: "memory = 562949953421312.B"
cpu1: "cpus = 1"
cpu2: "cpus = 2"
cpu5: "cpus = 5"
cpu10: "cpus = 10"
cpu20: "cpus = 20"
cpu50: "cpus = 50"
cpu100: "cpus = 100"
cpu200: "cpus = 200"
cpu500: "cpus = 500"
cpu1000: "cpus = 1000"
debug: false
container: "docker"
engines:
- type: "docker"
id: "docker"
image: "quay.io/biocontainers/seqtk:1.4--he4a0461_2"
target_registry: "images.viash-hub.com"
target_tag: "v0.2"
namespace_separator: "/"
entrypoint: []
cmd: null
- type: "native"
id: "native"
build_info:
config: "src/seqtk/seqtk_sample/config.vsh.yaml"
runner: "executable"
engine: "docker|native"
output: "target/executable/seqtk/seqtk_sample"
executable: "target/executable/seqtk/seqtk_sample/seqtk_sample"
viash_version: "0.9.0-RC7"
git_commit: "f22ab0eab58dcd6bff89d8d73fe951953ff1260f"
git_remote: "https://github.com/viash-hub/biobox"
package_config:
name: "biobox"
version: "v0.2"
description: "A collection of bioinformatics tools for working with sequence data.\n"
info: null
viash_version: "0.9.0-RC7"
source: "src"
target: "target"
config_mods:
- ".requirements.commands := ['ps']\n"
- ".engines += { type: \"native\" }"
- ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
- ".engines[.type == 'docker'].target_tag := 'v0.2'"
keywords:
- "bioinformatics"
- "modules"
- "sequencing"
license: "MIT"
organization: "vsh"
links:
repository: "https://github.com/viash-hub/biobox"
issue_tracker: "https://github.com/viash-hub/biobox/issues"

1154
target/executable/seqtk/seqtk_sample/seqtk_sample Executable file
View File

File diff suppressed because it is too large Load Diff

222
target/executable/seqtk/seqtk_subseq/.config.vsh.yaml Normal file
View File

@@ -0,0 +1,222 @@
name: "seqtk_subseq"
namespace: "seqtk"
version: "v0.2"
authors:
- name: "Theodoro Gasperin Terra Camargo"
roles:
- "author"
- "maintainer"
info:
links:
email: "theodorogtc@gmail.com"
github: "tgaspe"
linkedin: "theodoro-gasperin-terra-camargo"
organizations:
- name: "Data Intuitive"
href: "https://www.data-intuitive.com"
role: "Bioinformatician"
argument_groups:
- name: "Inputs"
arguments:
- type: "file"
name: "--input"
description: "The input FASTA/Q file."
info: null
example:
- "input.fa"
must_exist: true
create_parent: true
required: true
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--name_list"
description: "List of sequence names (name.lst) or genomic regions (reg.bed) to\
\ extract.\n"
info: null
example:
- "list.lst"
must_exist: true
create_parent: true
required: true
direction: "input"
multiple: false
multiple_sep: ";"
- name: "Outputs"
arguments:
- type: "file"
name: "--output"
alternatives:
- "-o"
description: "The output FASTA/Q file."
info: null
default:
- "output.fa"
must_exist: true
create_parent: true
required: true
direction: "output"
multiple: false
multiple_sep: ";"
- name: "Options"
arguments:
- type: "boolean_true"
name: "--tab"
alternatives:
- "-t"
description: "TAB delimited output."
info: null
direction: "input"
- type: "boolean_true"
name: "--strand_aware"
alternatives:
- "-s"
description: "Strand aware."
info: null
direction: "input"
- type: "integer"
name: "--sequence_line_length"
alternatives:
- "-l"
description: "Sequence line length of input fasta file. Default: 0.\n"
info: null
example:
- 0
required: false
direction: "input"
multiple: false
multiple_sep: ";"
resources:
- type: "bash_script"
path: "script.sh"
is_executable: true
description: "Extract subsequences from FASTA/Q files. Takes as input a FASTA/Q file\
\ and a name.lst (sequence ids file) or a reg.bed (genomic regions file).\n"
test_resources:
- type: "bash_script"
path: "test.sh"
is_executable: true
info: null
status: "enabled"
requirements:
commands:
- "ps"
keywords:
- "subseq"
- "FASTA"
- "FASTQ"
license: "MIT"
links:
repository: "https://github.com/lh3/seqtk/tree/v1.4"
runners:
- type: "executable"
id: "executable"
docker_setup_strategy: "ifneedbepullelsecachedbuild"
- type: "nextflow"
id: "nextflow"
directives:
tag: "$id"
auto:
simplifyInput: true
simplifyOutput: false
transcript: false
publish: false
config:
labels:
mem1gb: "memory = 1000000000.B"
mem2gb: "memory = 2000000000.B"
mem5gb: "memory = 5000000000.B"
mem10gb: "memory = 10000000000.B"
mem20gb: "memory = 20000000000.B"
mem50gb: "memory = 50000000000.B"
mem100gb: "memory = 100000000000.B"
mem200gb: "memory = 200000000000.B"
mem500gb: "memory = 500000000000.B"
mem1tb: "memory = 1000000000000.B"
mem2tb: "memory = 2000000000000.B"
mem5tb: "memory = 5000000000000.B"
mem10tb: "memory = 10000000000000.B"
mem20tb: "memory = 20000000000000.B"
mem50tb: "memory = 50000000000000.B"
mem100tb: "memory = 100000000000000.B"
mem200tb: "memory = 200000000000000.B"
mem500tb: "memory = 500000000000000.B"
mem1gib: "memory = 1073741824.B"
mem2gib: "memory = 2147483648.B"
mem4gib: "memory = 4294967296.B"
mem8gib: "memory = 8589934592.B"
mem16gib: "memory = 17179869184.B"
mem32gib: "memory = 34359738368.B"
mem64gib: "memory = 68719476736.B"
mem128gib: "memory = 137438953472.B"
mem256gib: "memory = 274877906944.B"
mem512gib: "memory = 549755813888.B"
mem1tib: "memory = 1099511627776.B"
mem2tib: "memory = 2199023255552.B"
mem4tib: "memory = 4398046511104.B"
mem8tib: "memory = 8796093022208.B"
mem16tib: "memory = 17592186044416.B"
mem32tib: "memory = 35184372088832.B"
mem64tib: "memory = 70368744177664.B"
mem128tib: "memory = 140737488355328.B"
mem256tib: "memory = 281474976710656.B"
mem512tib: "memory = 562949953421312.B"
cpu1: "cpus = 1"
cpu2: "cpus = 2"
cpu5: "cpus = 5"
cpu10: "cpus = 10"
cpu20: "cpus = 20"
cpu50: "cpus = 50"
cpu100: "cpus = 100"
cpu200: "cpus = 200"
cpu500: "cpus = 500"
cpu1000: "cpus = 1000"
debug: false
container: "docker"
engines:
- type: "docker"
id: "docker"
image: "quay.io/biocontainers/seqtk:1.4--he4a0461_2"
target_registry: "images.viash-hub.com"
target_tag: "v0.2"
namespace_separator: "/"
setup:
- type: "docker"
run:
- "echo $(echo $(seqtk 2>&1) | sed -n 's/.*\\(Version: [^ ]*\\).*/\\1/p') > /var/software_versions.txt\n"
entrypoint: []
cmd: null
- type: "native"
id: "native"
build_info:
config: "src/seqtk/seqtk_subseq/config.vsh.yaml"
runner: "executable"
engine: "docker|native"
output: "target/executable/seqtk/seqtk_subseq"
executable: "target/executable/seqtk/seqtk_subseq/seqtk_subseq"
viash_version: "0.9.0-RC7"
git_commit: "f22ab0eab58dcd6bff89d8d73fe951953ff1260f"
git_remote: "https://github.com/viash-hub/biobox"
package_config:
name: "biobox"
version: "v0.2"
description: "A collection of bioinformatics tools for working with sequence data.\n"
info: null
viash_version: "0.9.0-RC7"
source: "src"
target: "target"
config_mods:
- ".requirements.commands := ['ps']\n"
- ".engines += { type: \"native\" }"
- ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
- ".engines[.type == 'docker'].target_tag := 'v0.2'"
keywords:
- "bioinformatics"
- "modules"
- "sequencing"
license: "MIT"
organization: "vsh"
links:
repository: "https://github.com/viash-hub/biobox"
issue_tracker: "https://github.com/viash-hub/biobox/issues"

1210
target/executable/seqtk/seqtk_subseq/seqtk_subseq Executable file
View File

File diff suppressed because it is too large Load Diff

2689
target/executable/star/star_align_reads/.config.vsh.yaml Normal file
View File

File diff suppressed because it is too large Load Diff

6135
target/executable/star/star_align_reads/star_align_reads Executable file
View File

File diff suppressed because it is too large Load Diff

359
target/executable/star/star_genome_generate/.config.vsh.yaml Normal file
View File

@@ -0,0 +1,359 @@
name: "star_genome_generate"
namespace: "star"
version: "v0.2"
authors:
- name: "Sai Nirmayi Yasa"
roles:
- "author"
- "maintainer"
info:
links:
email: "nirmayi@data-intuitive.com"
github: "sainirmayi"
linkedin: "sai-nirmayi-yasa"
organizations:
- name: "Data Intuitive"
href: "https://www.data-intuitive.com"
role: "Junior Bioinformatics Researcher"
argument_groups:
- name: "Input"
arguments:
- type: "file"
name: "--genome_fasta_files"
description: "Path(s) to the fasta files with the genome sequences, separated\
\ by spaces. These files should be plain text FASTA files, they *cannot* be\
\ zipped.\n"
info: null
must_exist: true
create_parent: true
required: true
direction: "input"
multiple: true
multiple_sep: ";"
- type: "file"
name: "--sjdb_gtf_file"
description: "Path to the GTF file with annotations"
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--sjdb_overhang"
description: "Length of the donor/acceptor sequence on each side of the junctions,\
\ ideally = (mate_length - 1)"
info: null
example:
- 100
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--sjdb_gtf_chr_prefix"
description: "Prefix for chromosome names in a GTF file (e.g. 'chr' for using\
\ ENSMEBL annotations with UCSC genomes)"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--sjdb_gtf_feature_exon"
description: "Feature type in GTF file to be used as exons for building transcripts"
info: null
example:
- "exon"
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--sjdb_gtf_tag_exon_parent_transcript"
description: "GTF attribute name for parent transcript ID (default \"transcript_id\"\
\ works for GTF files)"
info: null
example:
- "transcript_id"
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--sjdb_gtf_tag_exon_parent_gene"
description: "GTF attribute name for parent gene ID (default \"gene_id\" works\
\ for GTF files)"
info: null
example:
- "gene_id"
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--sjdb_gtf_tag_exon_parent_gene_name"
description: "GTF attribute name for parent gene name"
info: null
example:
- "gene_name"
required: false
direction: "input"
multiple: true
multiple_sep: ";"
- type: "string"
name: "--sjdb_gtf_tag_exon_parent_gene_type"
description: "GTF attribute name for parent gene type"
info: null
example:
- "gene_type"
- "gene_biotype"
required: false
direction: "input"
multiple: true
multiple_sep: ";"
- type: "long"
name: "--limit_genome_generate_ram"
description: "Maximum available RAM (bytes) for genome generation"
info: null
example:
- 31000000000
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--genome_sa_index_nbases"
description: "Length (bases) of the SA pre-indexing string. Typically between\
\ 10 and 15. Longer strings will use much more memory, but allow faster searches.\
\ For small genomes, this parameter must be scaled down to min(14, log2(GenomeLength)/2\
\ - 1)."
info: null
example:
- 14
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--genome_chr_bin_nbits"
description: "Defined as log2(chrBin), where chrBin is the size of the bins for\
\ genome storage. Each chromosome will occupy an integer number of bins. For\
\ a genome with large number of contigs, it is recommended to scale this parameter\
\ as min(18, log2[max(GenomeLength/NumberOfReferences,ReadLength)])."
info: null
example:
- 18
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--genome_sa_sparse_d"
description: "Suffux array sparsity, i.e. distance between indices. Use bigger\
\ numbers to decrease needed RAM at the cost of mapping speed reduction."
info: null
example:
- 1
required: false
min: 0
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--genome_suffix_length_max"
description: "Maximum length of the suffixes, has to be longer than read length.\
\ Use -1 for infinite length."
info: null
example:
- -1
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--genome_transform_type"
description: "Type of genome transformation\n None ... no transformation\n\
\ Haploid ... replace reference alleles with alternative alleles from VCF\
\ file (e.g. consensus allele)\n Diploid ... create two haplotypes for each\
\ chromosome listed in VCF file, for genotypes 1|2, assumes perfect phasing\
\ (e.g. personal genome)\n"
info: null
example:
- "None"
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--genome_transform_vcf"
description: "path to VCF file for genome transformation"
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- name: "Output"
arguments:
- type: "file"
name: "--index"
description: "STAR index directory."
info: null
default:
- "STAR_index"
must_exist: true
create_parent: true
required: true
direction: "output"
multiple: false
multiple_sep: ";"
resources:
- type: "bash_script"
path: "script.sh"
is_executable: true
description: "Create index for STAR\n"
test_resources:
- type: "bash_script"
path: "test.sh"
is_executable: true
info: null
status: "enabled"
requirements:
commands:
- "ps"
keywords:
- "genome"
- "index"
- "align"
license: "MIT"
references:
doi:
- "10.1093/bioinformatics/bts635"
links:
repository: "https://github.com/alexdobin/STAR"
documentation: "https://github.com/alexdobin/STAR/blob/master/doc/STARmanual.pdf"
runners:
- type: "executable"
id: "executable"
docker_setup_strategy: "ifneedbepullelsecachedbuild"
- type: "nextflow"
id: "nextflow"
directives:
tag: "$id"
auto:
simplifyInput: true
simplifyOutput: false
transcript: false
publish: false
config:
labels:
mem1gb: "memory = 1000000000.B"
mem2gb: "memory = 2000000000.B"
mem5gb: "memory = 5000000000.B"
mem10gb: "memory = 10000000000.B"
mem20gb: "memory = 20000000000.B"
mem50gb: "memory = 50000000000.B"
mem100gb: "memory = 100000000000.B"
mem200gb: "memory = 200000000000.B"
mem500gb: "memory = 500000000000.B"
mem1tb: "memory = 1000000000000.B"
mem2tb: "memory = 2000000000000.B"
mem5tb: "memory = 5000000000000.B"
mem10tb: "memory = 10000000000000.B"
mem20tb: "memory = 20000000000000.B"
mem50tb: "memory = 50000000000000.B"
mem100tb: "memory = 100000000000000.B"
mem200tb: "memory = 200000000000000.B"
mem500tb: "memory = 500000000000000.B"
mem1gib: "memory = 1073741824.B"
mem2gib: "memory = 2147483648.B"
mem4gib: "memory = 4294967296.B"
mem8gib: "memory = 8589934592.B"
mem16gib: "memory = 17179869184.B"
mem32gib: "memory = 34359738368.B"
mem64gib: "memory = 68719476736.B"
mem128gib: "memory = 137438953472.B"
mem256gib: "memory = 274877906944.B"
mem512gib: "memory = 549755813888.B"
mem1tib: "memory = 1099511627776.B"
mem2tib: "memory = 2199023255552.B"
mem4tib: "memory = 4398046511104.B"
mem8tib: "memory = 8796093022208.B"
mem16tib: "memory = 17592186044416.B"
mem32tib: "memory = 35184372088832.B"
mem64tib: "memory = 70368744177664.B"
mem128tib: "memory = 140737488355328.B"
mem256tib: "memory = 281474976710656.B"
mem512tib: "memory = 562949953421312.B"
cpu1: "cpus = 1"
cpu2: "cpus = 2"
cpu5: "cpus = 5"
cpu10: "cpus = 10"
cpu20: "cpus = 20"
cpu50: "cpus = 50"
cpu100: "cpus = 100"
cpu200: "cpus = 200"
cpu500: "cpus = 500"
cpu1000: "cpus = 1000"
debug: false
container: "docker"
engines:
- type: "docker"
id: "docker"
image: "ubuntu:22.04"
target_registry: "images.viash-hub.com"
target_tag: "v0.2"
namespace_separator: "/"
setup:
- type: "docker"
run:
- "apt-get update && \\\n apt-get install -y --no-install-recommends ${PACKAGES}\
\ && \\\n cd /tmp && \\\n wget --no-check-certificate https://github.com/alexdobin/STAR/archive/refs/tags/${STAR_VERSION}.zip\
\ && \\\n unzip ${STAR_VERSION}.zip && \\\n cd STAR-${STAR_VERSION}/source\
\ && \\\n make STARstatic CXXFLAGS_SIMD=-std=c++11 && \\\n cp STAR /usr/local/bin\
\ && \\\n cd / && \\\n rm -rf /tmp/STAR-${STAR_VERSION} /tmp/${STAR_VERSION}.zip\
\ && \\\n apt-get --purge autoremove -y ${PACKAGES} && \\\n apt-get clean\n"
env:
- "STAR_VERSION 2.7.11b"
- "PACKAGES gcc g++ make wget zlib1g-dev unzip xxd"
- type: "docker"
run:
- "STAR --version | sed 's#\\(.*\\)#star: \"\\1\"#' > /var/software_versions.txt\n"
entrypoint: []
cmd: null
- type: "native"
id: "native"
build_info:
config: "src/star/star_genome_generate/config.vsh.yaml"
runner: "executable"
engine: "docker|native"
output: "target/executable/star/star_genome_generate"
executable: "target/executable/star/star_genome_generate/star_genome_generate"
viash_version: "0.9.0-RC7"
git_commit: "f22ab0eab58dcd6bff89d8d73fe951953ff1260f"
git_remote: "https://github.com/viash-hub/biobox"
package_config:
name: "biobox"
version: "v0.2"
description: "A collection of bioinformatics tools for working with sequence data.\n"
info: null
viash_version: "0.9.0-RC7"
source: "src"
target: "target"
config_mods:
- ".requirements.commands := ['ps']\n"
- ".engines += { type: \"native\" }"
- ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
- ".engines[.type == 'docker'].target_tag := 'v0.2'"
keywords:
- "bioinformatics"
- "modules"
- "sequencing"
license: "MIT"
organization: "vsh"
links:
repository: "https://github.com/viash-hub/biobox"
issue_tracker: "https://github.com/viash-hub/biobox/issues"

1496
target/executable/star/star_genome_generate/star_genome_generate Executable file
View File

File diff suppressed because it is too large Load Diff

637
target/executable/umi_tools/umi_tools_dedup/.config.vsh.yaml Normal file
View File

@@ -0,0 +1,637 @@
name: "umi_tools_dedup"
namespace: "umi_tools"
version: "v0.2"
authors:
- name: "Emma Rousseau"
roles:
- "author"
- "maintainer"
info:
links:
email: "emma@data-intuitive.com"
github: "emmarousseau"
linkedin: "emmarousseau1"
organizations:
- name: "Data Intuitive"
href: "https://www.data-intuitive.com"
role: "Bioinformatician"
argument_groups:
- name: "Inputs"
arguments:
- type: "file"
name: "--input"
alternatives:
- "--stdin"
description: "Input BAM or SAM file. Use --in_sam to specify SAM format."
info: null
must_exist: true
create_parent: true
required: true
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean_true"
name: "--in_sam"
description: "By default, inputs are assumed to be in BAM format. Use this options\
\ to specify the use of SAM\nformat for input.\n"
info: null
direction: "input"
- type: "file"
name: "--bai"
description: "BAM index"
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--random_seed"
description: "Random seed to initialize number generator with."
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- name: "Outputs"
arguments:
- type: "file"
name: "--output"
alternatives:
- "--stdout"
description: "Deduplicated BAM file."
info: null
must_exist: true
create_parent: true
required: true
direction: "output"
multiple: false
multiple_sep: ";"
- type: "boolean_true"
name: "--out_sam"
description: "By default, outputa are written in BAM format. Use this options\
\ to specify the use of SAM format\nfor output.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--paired"
description: "BAM is paired end - output both read pairs. This will also force\
\ the use of the template length\nto determine reads with the same mapping coordinates.\n"
info: null
direction: "input"
- type: "string"
name: "--output_stats"
description: "Generate files containing UMI based deduplication statistics files\
\ with this prefix in the file names.\n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--extract_umi_method"
description: "Specify the method by which the barcodes were encoded in the read.\n\
The options are:\n * read_id (default) \n * tag\n * umis\n"
info: null
example:
- "read_id"
required: false
choices:
- "read_id"
- "tag"
- "umis"
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--umi_tag"
description: "The tag containing the UMI sequence. This is only required if the\
\ extract_umi_method is set to tag.\n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--umi_separator"
description: "The separator used to separate the UMI from the read sequence. This\
\ is only required if the\nextract_umi_method is set to id_read. Default: `_`.\n"
info: null
example:
- "_"
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--umi_tag_split"
description: "Separate the UMI in tag by <SPLIT> and take the first element."
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--umi_tag_delimiter"
description: "Separate the UMI in by <DELIMITER> and concatenate the elements."
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--cell_tag"
description: "The tag containing the cell barcode sequence. This is only required\
\ if the extract_umi_method\nis set to tag.\n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--cell_tag_split"
description: "Separate the cell barcode in tag by <SPLIT> and take the first element."
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--cell_tag_delimiter"
description: "Separate the cell barcode in by <DELIMITER> and concatenate the\
\ elements."
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- name: "Grouping Options"
arguments:
- type: "string"
name: "--method"
description: "The method to use for grouping reads. \nThe options are: \n * unique\n\
\ * percentile\n * cluster\n * adjacency\n * directional (default)\n"
info: null
example:
- "directional"
required: false
choices:
- "unique"
- "percentile"
- "cluster"
- "adjacency"
- "directional"
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--edit_distance_threshold"
description: "For the adjacency and cluster methods the threshold for the edit\
\ distance to connect two\nUMIs in the network can be increased. The default\
\ value of 1 works best unless the UMI is\nvery long (>14bp). Default: `1`.\n"
info: null
example:
- 1
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean_true"
name: "--spliced_is_unique"
description: "Causes two reads that start in the same position on the same strand\
\ and having the same UMI\nto be considered unique if one is spliced and the\
\ other is not. (Uses the 'N' cigar operation\nto test for splicing).\n"
info: null
direction: "input"
- type: "integer"
name: "--soft_clip_threshold"
description: "Mappers that soft clip will sometimes do so rather than mapping\
\ a spliced read if there is only\na small overhang over the exon junction.\
\ By setting this option, you can treat reads with at\nleast this many bases\
\ soft-clipped at the 3' end as spliced. Default: `4`.\n"
info: null
example:
- 4
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--multimapping_detection_method"
description: "If the sam/bam contains tags to identify multimapping reads, you\
\ can specify for use when selecting\nthe best read at a given loci. Supported\
\ tags are `NH`, `X0` and `XT`. If not specified, the read\nwith the highest\
\ mapping quality will be selected.\n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean_true"
name: "--read_length"
description: "Use the read length as a criteria when deduping, for e.g. sRNA-Seq."
info: null
direction: "input"
- name: "Single-cell RNA-Seq Options"
arguments:
- type: "boolean_true"
name: "--per_gene"
description: "Reads will be grouped together if they have the same gene. This\
\ is useful if your library prep\ngenerates PCR duplicates with non identical\
\ alignment positions such as CEL-Seq. Note this option\nis hardcoded to be\
\ on with the count command. I.e. counting is always performed per-gene. Must\
\ be\ncombined with either --gene_tag or --per_contig option.\n"
info: null
direction: "input"
- type: "string"
name: "--gene_tag"
description: "Deduplicate per gene. The gene information is encoded in the bam\
\ read tag specified.\n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--assigned_status_tag"
description: "BAM tag which describes whether a read is assigned to a gene. Defaults\
\ to the same value as given\nfor --gene_tag.\n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--skip_tags_regex"
description: "Use in conjunction with the --assigned_status_tag option to skip\
\ any reads where the tag matches\nthis regex. Default (\"^[__|Unassigned]\"\
) matches anything which starts with \"__\" or \"Unassigned\".\n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean_true"
name: "--per_contig"
description: "Deduplicate per contig (field 3 in BAM; RNAME). All reads with the\
\ sam contig will be considered to\nhave the same alignment position. This is\
\ useful if you have aligned to a reference transcriptome\nwith one transcript\
\ per gene. If you have aligned to a transcriptome with more than one transcript\n\
per gene, you can supply a map between transcripts and gene using the --gene_transcript_map\
\ option.\n"
info: null
direction: "input"
- type: "file"
name: "--gene_transcript_map"
description: "A file containing a mapping between gene names and transcript names.\
\ The file should be tab\nseparated with the gene name in the first column and\
\ the transcript name in the second column.\n"
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean_true"
name: "--per_cell"
description: "Reads will only be grouped together if they have the same cell barcode.\
\ Can be combined with\n--per_gene.\n"
info: null
direction: "input"
- name: "SAM/BAM Options"
arguments:
- type: "integer"
name: "--mapping_quality"
description: "Minimium mapping quality (MAPQ) for a read to be retained. Default:\
\ `0`.\n"
info: null
example:
- 0
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--unmapped_reads"
description: "How unmapped reads should be handled. \nThe options are:\n * \"\
discard\": Discard all unmapped reads. (default)\n * \"use\": If read2\
\ is unmapped, deduplicate using read1 only. Requires --paired.\n * \"output\"\
: Output unmapped reads/read pairs without UMI grouping/deduplication. Only\
\ available in umi_tools group.\n"
info: null
example:
- "discard"
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--chimeric_pairs"
description: "How chimeric pairs should be handled. \nThe options are:\n * \"\
discard\": Discard all chimeric read pairs.\n * \"use\": Deduplicate using\
\ read1 only. (default)\n * \"output\": Output chimeric pairs without UMI\
\ grouping/deduplication. Only available in\n umi_tools group.\n"
info: null
example:
- "use"
required: false
choices:
- "discard"
- "use"
- "output"
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--unpaired_reads"
description: "How unpaired reads should be handled. \nThe options are: \n * \"\
discard\": Discard all unmapped reads.\n * \"use\": If read2 is unmapped, deduplicate\
\ using read1 only. Requires --paired. (default)\n * \"output\": Output unmapped\
\ reads/read pairs without UMI grouping/deduplication. Only available\n \
\ in umi_tools group.\n"
info: null
example:
- "use"
required: false
choices:
- "discard"
- "use"
- "output"
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean_true"
name: "--ignore_umi"
description: "Ignore the UMI and group reads using mapping coordinates only."
info: null
direction: "input"
- type: "double"
name: "--subset"
description: "Only consider a fraction of the reads, chosen at random. This is\
\ useful for doing saturation\nanalyses.\n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--chrom"
description: "Only consider a single chromosome. This is useful for debugging/testing\
\ purposes."
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- name: "Group/Dedup Options"
arguments:
- type: "boolean_true"
name: "--no_sort_output"
description: "By default, output is sorted. This involves the use of a temporary\
\ unsorted file (saved in\n--temp_dir). Use this option to turn off sorting.\n"
info: null
direction: "input"
- type: "boolean_true"
name: "--buffer_whole_contig"
description: "Forces dedup to parse an entire contig before yielding any reads\
\ for deduplication. This is the\nonly way to absolutely guarantee that all\
\ reads with the same start position are grouped together\nfor deduplication\
\ since dedup uses the start position of the read, not the alignment coordinate\
\ on\nwhich the reads are sorted. However, by default, dedup reads for another\
\ 1000bp before outputting\nread groups which will avoid any reads being missed\
\ with short read sequencing (<1000bp).\n"
info: null
direction: "input"
- name: "Common Options"
arguments:
- type: "file"
name: "--log"
alternatives:
- "-L"
description: "File with logging information."
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean_true"
name: "--log2stderr"
description: "Send logging information to stderr."
info: null
direction: "input"
- type: "integer"
name: "--verbose"
alternatives:
- "-v"
description: "Log level. The higher, the more output. Default: `0`.\n"
info: null
example:
- 0
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--error"
alternatives:
- "-E"
description: "File with error information."
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--temp_dir"
description: "Directory for temporary files. If not set, the bash environmental\
\ variable TMPDIR is used.\n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--compresslevel"
description: "Level of Gzip compression to use. Default=6 matches GNU gzip rather\
\ than python gzip default.\nDefault: `6`.\n"
info: null
example:
- 6
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--timeit"
description: "Store timing information in file."
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--timeit_name"
description: "Name in timing file for this class of jobs. Default: `all`.\n"
info: null
example:
- "all"
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--timeit_header"
description: "Add header for timing information."
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
resources:
- type: "bash_script"
path: "script.sh"
is_executable: true
description: "Deduplicate reads based on the mapping co-ordinate and the UMI attached\
\ to the read.\n"
test_resources:
- type: "bash_script"
path: "test.sh"
is_executable: true
- type: "file"
path: "test_data"
info: null
status: "enabled"
requirements:
commands:
- "ps"
keywords:
- "umi_tools"
- "deduplication"
- "dedup"
license: "MIT"
references:
doi:
- "10.1101/gr.209601.116"
links:
repository: "https://github.com/CGATOxford/UMI-tools"
homepage: "https://umi-tools.readthedocs.io/en/latest/"
documentation: "https://umi-tools.readthedocs.io/en/latest/reference/dedup.html"
runners:
- type: "executable"
id: "executable"
docker_setup_strategy: "ifneedbepullelsecachedbuild"
- type: "nextflow"
id: "nextflow"
directives:
tag: "$id"
auto:
simplifyInput: true
simplifyOutput: false
transcript: false
publish: false
config:
labels:
mem1gb: "memory = 1000000000.B"
mem2gb: "memory = 2000000000.B"
mem5gb: "memory = 5000000000.B"
mem10gb: "memory = 10000000000.B"
mem20gb: "memory = 20000000000.B"
mem50gb: "memory = 50000000000.B"
mem100gb: "memory = 100000000000.B"
mem200gb: "memory = 200000000000.B"
mem500gb: "memory = 500000000000.B"
mem1tb: "memory = 1000000000000.B"
mem2tb: "memory = 2000000000000.B"
mem5tb: "memory = 5000000000000.B"
mem10tb: "memory = 10000000000000.B"
mem20tb: "memory = 20000000000000.B"
mem50tb: "memory = 50000000000000.B"
mem100tb: "memory = 100000000000000.B"
mem200tb: "memory = 200000000000000.B"
mem500tb: "memory = 500000000000000.B"
mem1gib: "memory = 1073741824.B"
mem2gib: "memory = 2147483648.B"
mem4gib: "memory = 4294967296.B"
mem8gib: "memory = 8589934592.B"
mem16gib: "memory = 17179869184.B"
mem32gib: "memory = 34359738368.B"
mem64gib: "memory = 68719476736.B"
mem128gib: "memory = 137438953472.B"
mem256gib: "memory = 274877906944.B"
mem512gib: "memory = 549755813888.B"
mem1tib: "memory = 1099511627776.B"
mem2tib: "memory = 2199023255552.B"
mem4tib: "memory = 4398046511104.B"
mem8tib: "memory = 8796093022208.B"
mem16tib: "memory = 17592186044416.B"
mem32tib: "memory = 35184372088832.B"
mem64tib: "memory = 70368744177664.B"
mem128tib: "memory = 140737488355328.B"
mem256tib: "memory = 281474976710656.B"
mem512tib: "memory = 562949953421312.B"
cpu1: "cpus = 1"
cpu2: "cpus = 2"
cpu5: "cpus = 5"
cpu10: "cpus = 10"
cpu20: "cpus = 20"
cpu50: "cpus = 50"
cpu100: "cpus = 100"
cpu200: "cpus = 200"
cpu500: "cpus = 500"
cpu1000: "cpus = 1000"
debug: false
container: "docker"
engines:
- type: "docker"
id: "docker"
image: "quay.io/biocontainers/umi_tools:1.1.5--py39hf95cd2a_1"
target_registry: "images.viash-hub.com"
target_tag: "v0.2"
namespace_separator: "/"
setup:
- type: "docker"
run:
- "umi_tools -v | sed 's/ version//g' > /var/software_versions.txt\n"
entrypoint: []
cmd: null
- type: "native"
id: "native"
build_info:
config: "src/umi_tools/umi_tools_dedup/config.vsh.yaml"
runner: "executable"
engine: "docker|native"
output: "target/executable/umi_tools/umi_tools_dedup"
executable: "target/executable/umi_tools/umi_tools_dedup/umi_tools_dedup"
viash_version: "0.9.0-RC7"
git_commit: "f22ab0eab58dcd6bff89d8d73fe951953ff1260f"
git_remote: "https://github.com/viash-hub/biobox"
package_config:
name: "biobox"
version: "v0.2"
description: "A collection of bioinformatics tools for working with sequence data.\n"
info: null
viash_version: "0.9.0-RC7"
source: "src"
target: "target"
config_mods:
- ".requirements.commands := ['ps']\n"
- ".engines += { type: \"native\" }"
- ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
- ".engines[.type == 'docker'].target_tag := 'v0.2'"
keywords:
- "bioinformatics"
- "modules"
- "sequencing"
license: "MIT"
organization: "vsh"
links:
repository: "https://github.com/viash-hub/biobox"
issue_tracker: "https://github.com/viash-hub/biobox/issues"

Some files were not shown because too many files have changed in this diff Show More