Files
rnaseq/target/executable/workflows/prepare_genome/.config.vsh.yaml
CI 54557aa596 Build branch main with version main (fd0354d)
Build pipeline: vsh-ci-template-w7zwh

Source commit: fd0354dae8

Source message: Point to new assets dir
2024-10-04 07:16:21 +00:00

540 lines
14 KiB
YAML

name: "prepare_genome"
namespace: "workflows"
version: "main"
argument_groups:
- name: "Input"
arguments:
- type: "file"
name: "--fasta"
description: "Path to FASTA genome file."
info: null
must_exist: true
create_parent: true
required: true
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--gtf"
description: "Path to GTF annotation file. This parameter is *mandatory* if --genome\
\ is not specified."
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--gff"
description: "Path to GFF3 annotation file. Required if \"--gtf\" is not specified."
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--additional_fasta"
description: "FASTA file to concatenate to genome FASTA file e.g. containing spike-in\
\ sequences."
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--transcript_fasta"
description: "Path to FASTA transcriptome file."
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--gene_bed"
description: "Path to BED file containing gene intervals. This will be created\
\ from the GTF file if not specified."
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--splicesites"
description: "Splice sites file required for HISAT2."
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean"
name: "--skip_bbsplit"
description: "Skip BBSplit for removal of non-reference genome reads."
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--bbsplit_fasta_list"
description: "Path to comma-separated file containing a list of reference genomes\
\ to filter reads against with BBSplit. To use BBSplit, \"--skip_bbsplit\" must\
\ be explicitly set to \"false\". The file should contain 2 (comma separated)\
\ columns - short name and full path to reference genome(s)"
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--star_index"
description: "Path to directory or tar.gz archive for pre-built STAR index."
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--rsem_index"
description: "Path to directory or tar.gz archive for pre-built RSEM index."
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "extra_rsem_prepare_reference_args"
description: "Extra arguments to pass to rsem-prepare-reference command in addition\
\ to defaults defined by the pipeline."
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--salmon_index"
description: "Path to directory or tar.gz archive for pre-built Salmon index."
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--kallisto_index"
description: "Path to directory or tar.gz archive for pre-built Kallisto index."
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--bbsplit_index"
description: "Path to directory or tar.gz archive for pre-built BBSplit index."
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--pseudo_aligner_kmer_size"
description: "Kmer length passed to indexing step of pseudoaligners."
info: null
default:
- 31
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean"
name: "--gencode"
description: "Specify if the GTF annotation is in GENCODE format."
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--biotype"
description: "Biotype value to use while appending entries to GTF file when additional\
\ fasta file is provided."
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean"
name: "--filter_gtf"
description: "Whether to filter the GTF or not?"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--aligner"
description: "Specifies the alignment algorithm to use - available options are\
\ 'star_salmon', 'star_rsem' and 'hisat2'."
info: null
default:
- "star_salmon"
required: false
choices:
- "star_salmon"
- "star_rsem"
- "hisat2"
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--pseudo_aligner"
description: "Specifies the pseudo aligner to use - available options are 'salmon'.\
\ Runs in addition to '--aligner'."
info: null
default:
- "salmon"
required: false
choices:
- "salmon"
- "kallisto"
direction: "input"
multiple: false
multiple_sep: ";"
- name: "Output"
arguments:
- type: "file"
name: "--fasta_uncompressed"
info: null
default:
- "reference_genome.fasta"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--gtf_uncompressed"
info: null
default:
- "gene_annotation.gtf"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--transcript_fasta_uncompressed"
info: null
default:
- "transcriptome.fasta"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--gene_bed_uncompressed"
info: null
default:
- "gene_annotation.bed"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--star_index_uncompressed"
description: "Path to STAR index."
info: null
default:
- "STAR_index"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--rsem_index_uncompressed"
description: "Path to directory or tar.gz archive for pre-built RSEM index."
info: null
default:
- "RSEM_index"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--salmon_index_uncompressed"
description: "Path to Salmon index."
info: null
default:
- "Salmon_index"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--kallisto_index_uncompressed"
description: "Path to Kallisto index."
info: null
default:
- "Kallisto_index"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--bbsplit_index_uncompressed"
description: "Path to BBSplit index."
info: null
default:
- "BBSplit_index"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--chrom_sizes"
description: "File containing chromosome lengths"
info: null
default:
- "reference_genome.fasta.sizes"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--fai"
description: "FASTA index file"
info: null
default:
- "reference_genome.fasta.fai"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
resources:
- type: "nextflow_script"
path: "main.nf"
is_executable: true
entrypoint: "run_wf"
description: "A subworkflow for preparing all the required genome references\n"
info: null
status: "enabled"
requirements:
commands:
- "ps"
dependencies:
- name: "gunzip"
repository:
type: "local"
- name: "gffread"
repository:
type: "vsh"
repo: "vsh/biobox"
tag: "v0.2.0"
- name: "cat_additional_fasta"
repository:
type: "local"
- name: "gtf2bed"
repository:
type: "local"
- name: "preprocess_transcripts_fasta"
repository:
type: "local"
- name: "gtf_filter"
repository:
type: "local"
- name: "rsem/rsem_prepare_reference"
repository:
type: "vsh"
repo: "vsh/biobox"
tag: "v0.2.0"
- name: "getchromsizes"
repository:
type: "local"
- name: "untar"
repository:
type: "vsh"
repo: "craftbox"
tag: "v0.1.0"
- name: "star/star_genome_generate"
repository:
type: "vsh"
repo: "vsh/biobox"
tag: "v0.2.0"
- name: "bbmap_bbsplit"
repository:
type: "local"
- name: "salmon/salmon_index"
repository:
type: "vsh"
repo: "vsh/biobox"
tag: "v0.2.0"
- name: "kallisto/kallisto_index"
repository:
type: "local"
repositories:
- type: "vsh"
name: "biobox"
repo: "vsh/biobox"
tag: "v0.2.0"
- type: "vsh"
name: "craftbox"
repo: "craftbox"
tag: "v0.1.0"
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: "native"
id: "native"
build_info:
config: "src/workflows/prepare_genome/config.vsh.yaml"
runner: "executable"
engine: "native"
output: "target/executable/workflows/prepare_genome"
executable: "target/executable/workflows/prepare_genome/prepare_genome"
viash_version: "0.9.0"
git_commit: "fd0354dae813d953b107e8fa856f3cd4e7939f2b"
git_remote: "https://x-access-token:ghs_qP68SGVqiugFlLowIn73iXH8gzJeuD4MgS5A@github.com/viash-hub/rnaseq"
dependencies:
- "target/nextflow/gunzip"
- "target/dependencies/vsh/vsh/biobox/v0.2.0/nextflow/gffread"
- "target/nextflow/cat_additional_fasta"
- "target/nextflow/gtf2bed"
- "target/nextflow/preprocess_transcripts_fasta"
- "target/nextflow/gtf_filter"
- "target/dependencies/vsh/vsh/biobox/v0.2.0/nextflow/rsem/rsem_prepare_reference"
- "target/nextflow/getchromsizes"
- "target/dependencies/vsh/vsh/craftbox/v0.1.0/nextflow/untar"
- "target/dependencies/vsh/vsh/biobox/v0.2.0/nextflow/star/star_genome_generate"
- "target/nextflow/bbmap_bbsplit"
- "target/dependencies/vsh/vsh/biobox/v0.2.0/nextflow/salmon/salmon_index"
- "target/nextflow/kallisto/kallisto_index"
package_config:
version: "main"
info:
test_resources:
- path: "gs://viash-hub-test-data/rnaseq/v1"
dest: "testData"
repositories:
- type: "vsh"
name: "biobox"
repo: "vsh/biobox"
tag: "v0.2.0"
- type: "vsh"
name: "craftbox"
repo: "craftbox"
tag: "v0.1.0"
viash_version: "0.9.0"
source: "src"
target: "target"
config_mods:
- ".requirements.commands := ['ps']\n.runners[.type == 'nextflow'].directives.tag\
\ := '$id'\n"
- ".engines += { type: \"native\" }"
- ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
- ".engines[.type == 'docker'].target_tag := 'main'"
organization: "vsh"