Files
rnaseq/target/nextflow/picard_markduplicates/.config.vsh.yaml
CI b649544267 Build branch main with version main (d63250a)
Build pipeline: viash-hub.rnaseq.main-p26ls

Source commit: d63250ae70

Source message: add checks
2024-11-27 17:19:29 +00:00

238 lines
6.5 KiB
YAML

name: "picard_markduplicates"
version: "main"
argument_groups:
- name: "Input"
arguments:
- type: "file"
name: "--bam"
description: "Input BAM file"
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--fasta"
description: "Reference genome FASTA file"
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--fai"
description: "Reference genome FASTA index"
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--extra_picard_args"
description: "Additional argument to be passed to Picard MarkDuplicates"
info: null
default:
- "--ASSUME_SORTED true --REMOVE_DUPLICATES false --VALIDATION_STRINGENCY LENIENT\
\ --TMP_DIR tmp"
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- name: "Output"
arguments:
- type: "file"
name: "--output_bam"
description: "BAM file with duplicate reads marked/removed"
info: null
default:
- "$id.MarkDuplicates.bam"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--bai"
description: "An optional BAM index file. If desired, --CREATE_INDEX must be passed\
\ as a flag"
info: null
default:
- "$id.MarkDuplicates.bam.bai"
must_exist: false
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--metrics"
description: "Duplicate metrics file generated by picard"
info: null
default:
- "$id.MarkDuplicates.metrics.txt"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
resources:
- type: "bash_script"
path: "script.sh"
is_executable: true
description: "Locate and tag duplicate reads in a BAM file\n"
test_resources:
- type: "bash_script"
path: "test.sh"
is_executable: true
- type: "file"
path: "test.paired_end.sorted.bam"
- type: "file"
path: "genome.fasta"
info:
migration_info:
git_repo: "https://github.com/nf-core/rnaseq.git"
paths:
- "modules/nf-core/picard/markduplicates/main.nf"
- "modules/nf-core/picard/markduplicates/meta.yml"
last_sha: "55398de6ab7577acfe9b1180016a93d7af7eb859"
status: "enabled"
requirements:
commands:
- "ps"
repositories:
- type: "vsh"
name: "biobox"
repo: "biobox"
tag: "main"
- type: "vsh"
name: "craftbox"
repo: "craftbox"
tag: "v0.1.0"
runners:
- type: "executable"
id: "executable"
docker_setup_strategy: "ifneedbepullelsecachedbuild"
- type: "nextflow"
id: "nextflow"
directives:
tag: "$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: "docker"
id: "docker"
image: "ubuntu:22.04"
target_registry: "images.viash-hub.com"
target_tag: "main"
namespace_separator: "/"
setup:
- type: "docker"
run:
- "apt-get update && \\\napt-get install -y build-essential openjdk-17-jdk wget\
\ && \\\nwget --no-check-certificate https://github.com/broadinstitute/picard/releases/download/3.1.1/picard.jar\
\ && \\\nmv picard.jar /usr/local/bin \n"
env:
- "PICARD=/usr/local/bin/picard.jar"
entrypoint: []
cmd: null
- type: "native"
id: "native"
build_info:
config: "src/picard_markduplicates/config.vsh.yaml"
runner: "nextflow"
engine: "docker|native"
output: "target/nextflow/picard_markduplicates"
executable: "target/nextflow/picard_markduplicates/main.nf"
viash_version: "0.9.0"
git_commit: "d63250ae704b6bd9a11792c4f979be2309999a2e"
git_remote: "https://x-access-token:ghs_ri9q8QB7jMaviilgc8bYrtSqMrabrg3q8JZY@github.com/viash-hub/rnaseq"
package_config:
name: "rnaseq"
version: "main"
info:
test_resources:
- path: "gs://viash-hub-test-data/rnaseq/v1"
dest: "testData"
repositories:
- type: "vsh"
name: "biobox"
repo: "biobox"
tag: "main"
- 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"