From e92a40852c88caaff1e9d6411464bd0e831282d3 Mon Sep 17 00:00:00 2001
From: Mia Croiset <mia.croiset@ens-lyon.fr>
Date: Mon, 12 Jun 2023 16:51:35 +0200
Subject: [PATCH] refactorisation remove gatk module
---
.../custom/gatk4/markduplicates/main.nf | 54 --------------
.../custom/gatk4/markduplicates/meta.yml | 72 -------------------
subworkflows/local/hicstuff_sub.nf | 4 --
3 files changed, 130 deletions(-)
delete mode 100644 modules/nf-core/custom/gatk4/markduplicates/main.nf
delete mode 100644 modules/nf-core/custom/gatk4/markduplicates/meta.yml
diff --git a/modules/nf-core/custom/gatk4/markduplicates/main.nf b/modules/nf-core/custom/gatk4/markduplicates/main.nf
deleted file mode 100644
index 223fa7c..0000000
--- a/modules/nf-core/custom/gatk4/markduplicates/main.nf
+++ /dev/null
@@ -1,54 +0,0 @@
-process GATK4_MARKDUPLICATES {
- tag "$meta.id"
- label 'process_medium'
-
- conda "bioconda::gatk4=4.4.0.0"
- container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
- 'https://depot.galaxyproject.org/singularity/gatk4:4.4.0.0--py36hdfd78af_0':
- 'quay.io/biocontainers/gatk4:4.4.0.0--py36hdfd78af_0' }"
-
- input:
- tuple val(meta), path(bam)
- path fasta
- path fasta_fai
-
- output:
- tuple val(meta), path("*cram"), emit: cram, optional: true
- tuple val(meta), path("*bam"), emit: bam, optional: true
- tuple val(meta), path("*.crai"), emit: crai, optional: true
- tuple val(meta), path("*.bai"), emit: bai, optional: true
- tuple val(meta), path("*.metrics"), emit: metrics
- path "versions.yml", emit: versions
-
- when:
- task.ext.when == null || task.ext.when
-
- script:
- def args = task.ext.args ?: ''
- prefix = task.ext.prefix ?: "${meta.id}"
- def input_list = bam.collect{"--INPUT $it"}.join(' ')
- def reference = fasta ? "--REFERENCE_SEQUENCE ${fasta}" : ""
-
- def avail_mem = 3072
- if (!task.memory) {
- log.info '[GATK MarkDuplicates] Available memory not known - defaulting to 3GB. Specify process memory requirements to change this.'
- } else {
- avail_mem = (task.memory.mega*0.8).intValue()
- }
- """
- gatk --java-options "-Xmx${avail_mem}M" MarkDuplicates \\
- $input_list \\
- --OUTPUT ${prefix} \\
- --METRICS_FILE ${prefix}.metrics \\
- --TMP_DIR . \\
- ${reference} \\
- $args
- if [[ ${prefix} == *.cram ]]&&[[ -f ${prefix}.bai ]]; then
- mv ${prefix}.bai ${prefix}.crai
- fi
- cat <<-END_VERSIONS > versions.yml
- "${task.process}":
- gatk4: \$(echo \$(gatk --version 2>&1) | sed 's/^.*(GATK) v//; s/ .*\$//')
- END_VERSIONS
- """
-}
\ No newline at end of file
diff --git a/modules/nf-core/custom/gatk4/markduplicates/meta.yml b/modules/nf-core/custom/gatk4/markduplicates/meta.yml
deleted file mode 100644
index ae7443d..0000000
--- a/modules/nf-core/custom/gatk4/markduplicates/meta.yml
+++ /dev/null
@@ -1,72 +0,0 @@
-name: gatk4_markduplicates
-description: This tool locates and tags duplicate reads in a BAM or SAM file, where duplicate reads are defined as originating from a single fragment of DNA.
-keywords:
- - markduplicates
- - bam
- - sort
-tools:
- - gatk4:
- description:
- Developed in the Data Sciences Platform at the Broad Institute, the toolkit offers a wide variety of tools
- with a primary focus on variant discovery and genotyping. Its powerful processing engine
- and high-performance computing features make it capable of taking on projects of any size.
- homepage: https://gatk.broadinstitute.org/hc/en-us
- documentation: https://gatk.broadinstitute.org/hc/en-us/articles/360037052812-MarkDuplicates-Picard-
- tool_dev_url: https://github.com/broadinstitute/gatk
- doi: 10.1158/1538-7445.AM2017-3590
- licence: ["MIT"]
-
-input:
- - meta:
- type: map
- description: |
- Groovy Map containing sample information
- e.g. [ id:'test', single_end:false ]
- - bam:
- type: file
- description: Sorted BAM file
- pattern: "*.{bam}"
- - fasta:
- type: file
- description: Fasta file
- pattern: "*.{fasta}"
- - fasta_fai:
- type: file
- description: Fasta index file
- pattern: "*.{fai}"
-
-output:
- - meta:
- type: map
- description: |
- Groovy Map containing sample information
- e.g. [ id:'test', single_end:false ]
- - versions:
- type: file
- description: File containing software versions
- pattern: "versions.yml"
- - bam:
- type: file
- description: Marked duplicates BAM file
- pattern: "*.{bam}"
- - cram:
- type: file
- description: Marked duplicates CRAM file
- pattern: "*.{cram}"
- - bai:
- type: file
- description: BAM index file
- pattern: "*.{bam.bai}"
- - crai:
- type: file
- description: CRAM index file
- pattern: "*.{cram.crai}"
- - metrics:
- type: file
- description: Duplicate metrics file generated by GATK
- pattern: "*.{metrics.txt}"
-
-authors:
- - "@ajodeh-juma"
- - "@FriederikeHanssen"
- - "@maxulysse"
\ No newline at end of file
diff --git a/subworkflows/local/hicstuff_sub.nf b/subworkflows/local/hicstuff_sub.nf
index 9bb3406..221d646 100644
--- a/subworkflows/local/hicstuff_sub.nf
+++ b/subworkflows/local/hicstuff_sub.nf
@@ -8,7 +8,6 @@ include { BUILD_MATRIX_COOL_ALT } from '../../modules/local/hicstuff/build_matri
include { FILTER_EVENT } from '../../modules/local/hicstuff/filter_event'
include { DISTANCE_LAW } from '../../modules/local/hicstuff/distance_law'
include { FILTER_PCR } from '../../modules/local/hicstuff/filter_pcr'
-include { GATK4_MARKDUPLICATES } from '../../modules/nf-core/custom/gatk4/markduplicates/main'
include { SAMTOOLS_SORT } from '../../modules/nf-core/custom/samtools/sort/main'
include { SAMTOOLS_SORT_N } from '../../modules/nf-core/custom/samtools_n/sort/main'
include { FILTER_PAIR } from '../../modules/local/filterbam/main'
@@ -137,9 +136,6 @@ workflow HICSTUFF_SUB {
FILTER_PCR.out.idx_pairs_pcrfree.set{ ch_idx_pairs }
}
- //TODO rajouter filtres + distance law + filtres PCR en options
- // pour les PCR filter, soit le hicstuff soit PICARD
-
BUILD_MATRIX(
ch_idx_pairs,
FRAGMENT_ENZYME.out.fragments_list.collect()
--
GitLab