Merge pull request #308 from drpatelh/updates

Add antibody directory to consensus peaks in IGV session

Author: JoseEspinosa

CHANGELOG.md

@@ -3,7 +3,7 @@
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/)
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
-## [[2.0.0](https://github.com/nf-core/chipseq/releases/tag/2.0.0)] - 2022-09-30
+## [[2.0.0](https://github.com/nf-core/chipseq/releases/tag/2.0.0)] - 2022-10-03
 
 ### Enhancements & fixes
 

bin/igv_files_to_session.py

@@ -24,10 +24,16 @@
 ## REQUIRED PARAMETERS
 argParser.add_argument("XML_OUT", help="XML output file.")
 argParser.add_argument(
-    "LIST_FILE", help="Tab-delimited file containing two columns i.e. file_name\tcolour. Header isnt required."
+    "LIST_FILE",
+    help="Tab-delimited file containing two columns i.e. file_name\tcolour. Header isnt required.",
 )
 argParser.add_argument(
-    "GENOME", help="Full path to genome fasta file or shorthand for genome available in IGV e.g. hg19."
+    "REPLACE_FILE",
+    help="Tab-delimited file containing two columns i.e. file_name\treplacement_file_name. Header isnt required.",
+)
+argParser.add_argument(
+    "GENOME",
+    help="Full path to genome fasta file or shorthand for genome available in IGV e.g. hg19.",
 )
 
 ## OPTIONAL PARAMETERS
@@ -65,10 +71,20 @@ def makedir(path):
 ############################################
 
 
-def igv_files_to_session(XMLOut, ListFile, Genome, PathPrefix=""):
+def igv_files_to_session(XMLOut, ListFile, ReplaceFile, Genome, PathPrefix=""):
 
     makedir(os.path.dirname(XMLOut))
 
+    replaceFileDict = {}
+    fin = open(ReplaceFile, "r")
+    while True:
+        line = fin.readline()
+        if line:
+            ofile, rfile = line.strip().split("\t")
+            replaceFileDict[ofile] = rfile
+        else:
+            break
+            fin.close()
     fileList = []
     fin = open(ListFile, "r")
     while True:
@@ -77,10 +93,17 @@ def igv_files_to_session(XMLOut, ListFile, Genome, PathPrefix=""):
             ifile, colour = line.strip().split("\t")
             if len(colour.strip()) == 0:
                 colour = "0,0,178"
+            for ofile, rfile in replaceFileDict.items():
+                if ofile in ifile:
+                    ifile = ifile.replace(ofile, rfile)
             fileList.append((PathPrefix.strip() + ifile, colour))
         else:
             break
-            fout.close()
+            fin.close()
+    fout = open("igv_files.txt", "w")
+    for ifile, colour in fileList:
+        fout.write(ifile + "\n")
+    fout.close()
 
     ## ADD RESOURCES SECTION
     XMLStr = '<?xml version="1.0" encoding="UTF-8" standalone="no"?>\n'
@@ -138,7 +161,6 @@ def igv_files_to_session(XMLOut, ListFile, Genome, PathPrefix=""):
                 'id="%s" name="%s" renderer="BASIC_FEATURE" sortable="false" visible="true" windowFunction="count"/>\n'
                 % (ifile, os.path.basename(ifile))
             )
-
     XMLStr += "\t</Panel>\n"
     # XMLStr += '\t<HiddenAttributes>\n\t\t<Attribute name="DATA FILE"/>\n\t\t<Attribute name="DATA TYPE"/>\n\t\t<Attribute name="NAME"/>\n\t</HiddenAttributes>\n'
     XMLStr += "</Session>"
@@ -153,7 +175,13 @@ def igv_files_to_session(XMLOut, ListFile, Genome, PathPrefix=""):
 ############################################
 ############################################
 
-igv_files_to_session(XMLOut=args.XML_OUT, ListFile=args.LIST_FILE, Genome=args.GENOME, PathPrefix=args.PATH_PREFIX)
+igv_files_to_session(
+    XMLOut=args.XML_OUT,
+    ListFile=args.LIST_FILE,
+    ReplaceFile=args.REPLACE_FILE,
+    Genome=args.GENOME,
+    PathPrefix=args.PATH_PREFIX,
+)
 
 ############################################
 ############################################

modules/local/deseq2_qc.nf

@@ -2,7 +2,9 @@ process DESEQ2_QC {
     tag "$meta.id"
     label 'process_medium'
 
-    conda (params.enable_conda ? "conda-forge::r-base=4.0 bioconda::bioconductor-deseq2=1.28.0 bioconda::bioconductor-biocparallel bioconda::bioconductor-tximport bioconda::bioconductor-complexheatmap conda-forge::r-optparse conda-forge::r-ggplot2 conda-forge::r-rcolorbrewer conda-forge::r-pheatmap" : null)
+    // (Bio)conda packages have intentionally not been pinned to a specific version
+    // This was to avoid the pipeline failing due to package conflicts whilst creating the environment when using -profile conda
+    conda (params.enable_conda ? "conda-forge::r-base bioconda::bioconductor-deseq2 bioconda::bioconductor-biocparallel bioconda::bioconductor-tximport bioconda::bioconductor-complexheatmap conda-forge::r-optparse conda-forge::r-ggplot2 conda-forge::r-rcolorbrewer conda-forge::r-pheatmap" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
         'https://depot.galaxyproject.org/singularity/mulled-v2-8849acf39a43cdd6c839a369a74c0adc823e2f91:ab110436faf952a33575c64dd74615a84011450b-0' :
         'quay.io/biocontainers/mulled-v2-8849acf39a43cdd6c839a369a74c0adc823e2f91:ab110436faf952a33575c64dd74615a84011450b-0' }"

modules/local/igv.nf

@@ -9,28 +9,34 @@ process IGV {
         'quay.io/biocontainers/python:3.8.3' }"
 
     input:
+    val aligner_dir
+    val peak_dir
     path fasta
-    path ("${bigwig_publish_dir}/*")
-    path ("${peak_publish_dir}/*")
-    path ("${consensus_publish_dir}/*")
-    val bigwig_publish_dir
-    val peak_publish_dir
-    val consensus_publish_dir
+    path ("${aligner_dir}/mergedLibrary/bigwig/*")
+    path ("${aligner_dir}/mergedLibrary/macs2/${peak_dir}/*")
+    path ("${aligner_dir}/mergedLibrary/macs2/${peak_dir}/consensus/*")
+    path ("mappings/*")
 
     output:
     path "*files.txt"  , emit: txt
     path "*.xml"       , emit: xml
     path "versions.yml", emit: versions
 
     script: // scripts are bundled with the pipeline in nf-core/chipseq/bin/
+    def consensus_dir = "${aligner_dir}/mergedLibrary/macs2/${peak_dir}/consensus/*"
     """
     find * -type l -name "*.bigWig" -exec echo -e ""{}"\\t0,0,178" \\; > bigwig.igv.txt
     find * -type l -name "*Peak" -exec echo -e ""{}"\\t0,0,178" \\; > peaks.igv.txt
     # Avoid error when consensus not produced
-    find * -type l -name "*.bed" -exec echo -e ""{}"\\t0,0,178" \\; | { grep "^$consensus_publish_dir" || test \$? = 1; } > bed.igv.txt
+    find * -type l -name "*.bed" -exec echo -e ""{}"\\t0,0,178" \\; | { grep "^$consensus_dir" || test \$? = 1; } > consensus.igv.txt
 
-    cat *.txt > igv_files.txt
-    igv_files_to_session.py igv_session.xml igv_files.txt ../../genome/${fasta.getName()} --path_prefix '../../'
+    touch replace_paths.txt
+    if [ -d "mappings" ]; then
+        cat mappings/* > replace_paths.txt
+    fi
+
+    cat *.igv.txt > igv_files_orig.txt
+    igv_files_to_session.py igv_session.xml igv_files_orig.txt replace_paths.txt ../../genome/${fasta.getName()} --path_prefix '../../'
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":

modules/local/macs2_consensus.nf

@@ -17,6 +17,7 @@ process MACS2_CONSENSUS {
     tuple val(meta), path("*.bed")          , emit: bed
     tuple val(meta), path("*.saf")          , emit: saf
     tuple val(meta), path("*.pdf")          , emit: pdf
+    tuple val(meta), path("*.antibody.txt") , emit: txt
     tuple val(meta), path("*.boolean.txt")  , emit: boolean_txt
     tuple val(meta), path("*.intersect.txt"), emit: intersect_txt
     path "versions.yml"                     , emit: versions
@@ -25,7 +26,6 @@ process MACS2_CONSENSUS {
     task.ext.when == null || task.ext.when
 
     script: // This script is bundled with the pipeline, in nf-core/chipseq/bin/
-
     def prefix       = task.ext.prefix    ?: "${meta.id}"
     def peak_type    = params.narrow_peak ? 'narrowPeak' : 'broadPeak'
     def mergecols    = params.narrow_peak ? (2..10).join(',') : (2..9).join(',')
@@ -49,6 +49,8 @@ process MACS2_CONSENSUS {
 
     plot_peak_intersect.r -i ${prefix}.boolean.intersect.txt -o ${prefix}.boolean.intersect.plot.pdf
 
+    echo "${prefix}.bed\t${meta.id}/${prefix}.bed" > ${prefix}.antibody.txt
+
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
         python: \$(python --version | sed 's/Python //g')

workflows/chipseq.nf

@@ -543,6 +543,7 @@ workflow CHIPSEQ {
     //  Consensus peaks analysis
     //
     ch_macs2_consensus_bed_lib   = Channel.empty()
+    ch_macs2_consensus_txt_lib   = Channel.empty()
     ch_deseq2_pca_multiqc        = Channel.empty()
     ch_deseq2_clustering_multiqc = Channel.empty()
     if (!params.skip_consensus_peaks) {
@@ -579,6 +580,7 @@ workflow CHIPSEQ {
             ch_antibody_peaks
         )
         ch_macs2_consensus_bed_lib = MACS2_CONSENSUS.out.bed
+        ch_macs2_consensus_txt_lib = MACS2_CONSENSUS.out.txt
         ch_versions = ch_versions.mix(MACS2_CONSENSUS.out.versions)
 
         if (!params.skip_peak_annotation) {
@@ -653,26 +655,13 @@ workflow CHIPSEQ {
     //
     if (!params.skip_igv) {
         IGV (
+            params.aligner,
+            params.narrow_peak ? 'narrowPeak' : 'broadPeak',
             PREPARE_GENOME.out.fasta,
             UCSC_BEDGRAPHTOBIGWIG.out.bigwig.collect{it[1]}.ifEmpty([]),
             ch_macs2_peaks.collect{it[1]}.ifEmpty([]),
             ch_macs2_consensus_bed_lib.collect{it[1]}.ifEmpty([]),
-            { "${params.aligner}/mergedLibrary/bigwig" },
-            { 
-                [
-                    "${params.aligner}/mergedLibrary/macs2",
-                    params.narrow_peak ? '/narrowPeak' : '/broadPeak'
-                ]
-                .join('') 
-            },
-            { 
-                [
-                    "${params.aligner}/mergedLibrary/macs2",
-                    params.narrow_peak ? '/narrowPeak' : '/broadPeak',
-                    '/consensus'
-                ]
-                .join('') 
-            }
+            ch_macs2_consensus_txt_lib.collect{it[1]}.ifEmpty([])
         )
         ch_versions = ch_versions.mix(IGV.out.versions)
     }