Merge branch 'master' into biobambam/bammerge

modules/gatk4/markduplicates/main.nf

@@ -1,6 +1,6 @@
 process GATK4_MARKDUPLICATES {
     tag "$meta.id"
-    label 'process_low'
+    label 'process_medium'
 
     conda (params.enable_conda ? "bioconda::gatk4=4.2.6.1" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?

modules/maxquant/lfq/main.nf

@@ -0,0 +1,37 @@
+process MAXQUANT_LFQ {
+    tag "$meta.id"
+    label 'process_long'
+    conda (params.enable_conda ? "bioconda::maxquant=2.0.3.0=py310hdfd78af_1" : null)
+    if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
+        container "https://depot.galaxyproject.org/singularity/maxquant:2.0.3.0--py310hdfd78af_1"
+    } else {
+        container "quay.io/biocontainers/maxquant:2.0.3.0--py310hdfd78af_1"
+    }
+
+    input:
+    tuple val(meta), path(fasta), path(paramfile)
+    path raw
+
+    output:
+    tuple val(meta), path("*.txt"), emit: maxquant_txt
+    path "versions.yml"          , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+
+    """
+    cat <<-END_VERSIONS > versions.yml
+        "${task.process}":
+            maxquant: \$(maxquant --version 2>&1 > /dev/null | cut -f2 -d\" \")
+    END_VERSIONS
+    sed \"s_<numThreads>.*_<numThreads>$task.cpus</numThreads>_\" ${paramfile} > mqpar_changed.xml
+    sed -i \"s|PLACEHOLDER|\$PWD/|g\" mqpar_changed.xml
+    mkdir temp
+    maxquant mqpar_changed.xml
+    mv combined/txt/*.txt .
+    """
+}

modules/maxquant/lfq/meta.yml

@@ -0,0 +1,52 @@
+name: maxquant_lfq
+description: Run standard proteomics data analysis with MaxQuant, mostly dedicated to label-free. Paths to fasta and raw files needs to be marked by "PLACEHOLDER"
+keywords:
+  - sort
+tools:
+  - maxquant:
+      description: MaxQuant is a quantitative proteomics software package designed for analyzing large mass-spectrometric data sets. License restricted.
+      homepage: None
+      documentation: None
+      tool_dev_url: None
+      doi: ""
+      licence: ["http://www.coxdocs.org/lib/exe/fetch.php?media=license_agreement.pdf"]
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+
+  - raw:
+      type: file
+      description: raw files with mass spectra
+      pattern: "*.{raw,RAW,Raw}"
+
+  - fasta:
+      type: file
+      description: fasta file with protein sequences
+      pattern: "*.{fasta}"
+
+  - parfile:
+      type: file
+      description: MaxQuant parameter file (XML)
+      pattern: "*.{xml}"
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - versions:
+      type: file
+      description: File containing software version
+      pattern: "versions.yml"
+  - maxquant_txt:
+      type: file
+      description: tables with peptides and protein information
+      pattern: "*.{txt}"
+
+authors:
+  - "@veitveit"

tests/config/pytest_modules.yml

@@ -1214,6 +1214,10 @@ maxbin2:
   - modules/maxbin2/**
   - tests/modules/maxbin2/**
 
+maxquant/lfq:
+  - modules/maxquant/lfq/**
+  - tests/modules/maxquant/lfq/**
+
 md5sum:
   - modules/md5sum/**
   - tests/modules/md5sum/**

tests/config/test_data.config

@@ -430,5 +430,17 @@ params {
                 ncbi_user_settings              = "${test_data_dir}/generic/config/ncbi_user_settings.mkfg"
             }
         }
+	'proteomics' {
+	    'msspectra' {
+	        ups_file1                       = "${test_data_dir}/proteomics/msspectra/OVEMB150205_12.raw"
+	        ups_file2                       = "${test_data_dir}/proteomics/msspectra/OVEMB150205_14.raw"
+	    }
+	    'database' {
+            yeast_ups                       = "${test_data_dir}/proteomics/database/yeast_UPS.fasta"
+        }
+	    'parameter' {
+	        maxquant                        = "${test_data_dir}/proteomics/parameter/mqpar.xml"
+	    }
+	}
     }
 }

tests/modules/maxquant/lfq/main.nf

@@ -0,0 +1,17 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { MAXQUANT_LFQ } from '../../../../modules/maxquant/lfq/main.nf' addParams( options: [:] )
+
+workflow test_maxquant_lfq {
+        
+    input = [ [ id:'test' ], // meta map
+              file(params.test_data['proteomics']['database']['yeast_ups'], checkIfExists: true), file(params.test_data['proteomics']['parameter']['maxquant'] , checkIfExists: true)
+            ]
+
+
+    rawfiles = [file(params.test_data['proteomics']['msspectra']['ups_file1']) , file(params.test_data['proteomics']['msspectra']['ups_file2'])]
+
+    MAXQUANT_LFQ ( input, rawfiles.collect() )
+}

tests/modules/maxquant/lfq/nextflow.config

@@ -0,0 +1,5 @@
+process {
+
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+
+}

tests/modules/maxquant/lfq/test.yml

@@ -0,0 +1,8 @@
+- name: maxquant lfq
+  command: nextflow run ./tests/modules/maxquant/lfq -entry test_maxquant_lfq  -c tests/config/nextflow.config
+  tags:
+    - maxquant
+    - maxquant/lfq
+  files:
+    - path: output/maxquant/proteinGroups.txt
+      md5sum: 0d0f6aab54fe6dc717d1307bbc207324