Merge pull request #404 from JoseEspinosa/updates

Switch from macs2 to macs3

CHANGELOG.md

@@ -27,6 +27,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - [[#385](https://github.com/nf-core/chipseq/issues/385)] - Fix `--save_unaligned` description in schema.
 - [[PR #392](https://github.com/nf-core/chipseq/pull/392)] - Adding line numbers to warnings/errors messages in `bin/check_samplesheet.py`.
 - [[#396](https://github.com/nf-core/chipseq/issues/396)] - Check that samplesheet samples IDs do only have alphanumeric characters, dots, dashes or underscores.
+- [[#378](https://github.com/nf-core/chipseq/issues/378)] - Switch from macs2 to macs3.
 
 ### Software dependencies
 
@@ -35,6 +36,8 @@ Note, since the pipeline is now using Nextflow DSL2, each process will be run wi
 | Dependency | Old version | New version |
 | ---------- | ----------- | ----------- |
 | `chromap`  | 0.2.1       | 0.2.4       |
+| `macs2`    | 2.2.7.1     |             |
+| `macs3`    |             | 3.0.1       |
 | `multiqc`  | 1.13        | 1.14        |
 | `picard`   | 2.27.4      | 3.0.0       |
 | `samtools` | 1.15.1      | 1.17        |

CITATIONS.md

@@ -46,7 +46,7 @@
 
   > Heinz S, Benner C, Spann N, Bertolino E, Lin YC, Laslo P, Cheng JX, Murre C, Singh H, Glass CK. Simple combinations of lineage-determining transcription factors prime cis-regulatory elements required for macrophage and B cell identities. Mol Cell. 2010 May 28;38(4):576-89. doi: 10.1016/j.molcel.2010.05.004. PubMed PMID: 20513432; PubMed Central PMCID: PMC2898526.
 
-- [MACS2](https://www.ncbi.nlm.nih.gov/pubmed/18798982/)
+- [MACS3](https://www.ncbi.nlm.nih.gov/pubmed/18798982/)
 
   > Zhang Y, Liu T, Meyer CA, Eeckhoute J, Johnson DS, Bernstein BE, Nusbaum C, Myers RM, Brown M, Li W, Liu XS. Model-based analysis of ChIP-Seq (MACS). Genome Biol. 2008;9(9):R137. doi: 10.1186/gb-2008-9-9-r137. Epub 2008 Sep 17. PubMed PMID: 18798982; PubMed Central PMCID: PMC2592715.
 

README.md

@@ -59,7 +59,7 @@ You can find numerous talks on the [nf-core events page](https://nf-co.re/events
    5. Generate gene-body meta-profile from bigWig files ([`deepTools`](https://deeptools.readthedocs.io/en/develop/content/tools/plotProfile.html))
    6. Calculate genome-wide IP enrichment relative to control ([`deepTools`](https://deeptools.readthedocs.io/en/develop/content/tools/plotFingerprint.html))
    7. Calculate strand cross-correlation peak and ChIP-seq quality measures including NSC and RSC ([`phantompeakqualtools`](https://github.com/kundajelab/phantompeakqualtools))
-   8. Call broad/narrow peaks ([`MACS2`](https://github.com/macs3-project/MACS))
+   8. Call broad/narrow peaks ([`MACS3`](https://github.com/macs3-project/MACS))
    9. Annotate peaks relative to gene features ([`HOMER`](http://homer.ucsd.edu/homer/download.html))
    10. Create consensus peakset across all samples and create tabular file to aid in the filtering of the data ([`BEDTools`](https://github.com/arq5x/bedtools2/))
    11. Count reads in consensus peaks ([`featureCounts`](http://bioinf.wehi.edu.au/featureCounts/))

assets/multiqc/frip_score_header.txt

@@ -1,7 +1,7 @@
 #id: 'frip_score'
-#section_name: 'MERGED LIB: MACS2 FRiP score'
+#section_name: 'MERGED LIB: MACS3 FRiP score'
 #description: "is generated by calculating the fraction of all mapped reads that fall
-#              into the MACS2 called peak regions. A read must overlap a peak by at least 20% to be counted.
+#              into the MACS3 called peak regions. A read must overlap a peak by at least 20% to be counted.
 #              See <a href='https://www.encodeproject.org/data-standards/terms/' target='_blank'>FRiP score</a>."
 #plot_type: 'bargraph'
 #anchor: 'frip_score'

assets/multiqc/peak_count_header.txt

@@ -1,7 +1,7 @@
 #id: 'peak_count'
-#section_name: 'MERGED LIB: MACS2 peak count'
+#section_name: 'MERGED LIB: MACS3 peak count'
 #description: "is calculated from total number of peaks called by
-#	       <a href='https://github.com/taoliu/MACS' target='_blank'>MACS2</a>"
+#	       <a href='https://github.com/taoliu/MACS' target='_blank'>MACS3</a>"
 #plot_type: 'bargraph'
 #anchor: 'peak_count'
 #pconfig:

assets/multiqc_config.yml

@@ -72,7 +72,7 @@ module_order:
       anchor: "mlib_featurecounts"
       info: "This section of the report shows featureCounts results for the number of reads assigned to merged library consensus peaks."
       path_filters:
-        - "./macs2/featurecounts/*.summary"
+        - "./macs3/featurecounts/*.summary"
 
 report_section_order:
   peak_count:

assets/schema_input.json

@@ -33,15 +33,30 @@
                     }
                 ]
             },
+            "replicate": {
+                "type": "integer",
+                "errorMessage": "Replicate id not an integer!",
+                "meta": ["replicate"]
+            },
             "antibody": {
                 "type": "string",
                 "pattern": "^\\S+$",
-                "errorMessage": "Antibody entry cannot contain spaces"
+                "errorMessage": "Antibody entry cannot contain spaces",
+                "dependentRequired": ["control"],
+                "meta": ["antibody"]
             },
             "control": {
                 "type": "string",
                 "pattern": "^\\S+$",
-                "errorMessage": "Control entry cannot contain spaces"
+                "errorMessage": "Control entry cannot contain spaces",
+                "dependentRequired": ["antibody", "control_replicate"],
+                "meta": ["control"]
+            },
+            "control_replicate": {
+                "type": "string",
+                "pattern": "^\\S+$",
+                "errorMessage": "Control entry cannot contain spaces",
+                "meta": ["control_replicate"]
             }
         },
         "required": ["sample", "fastq_1"]

bin/macs2_merged_expand.py → bin/macs3_merged_expand.py

@@ -17,15 +17,15 @@
 ############################################
 
 Description = "Add sample boolean files and aggregate columns from merged MACS narrow or broad peak file."
-Epilog = """Example usage: python macs2_merged_expand.py <MERGED_INTERVAL_FILE> <SAMPLE_NAME_LIST> <OUTFILE> --is_narrow_peak --min_replicates 1"""
+Epilog = """Example usage: python macs3_merged_expand.py <MERGED_INTERVAL_FILE> <SAMPLE_NAME_LIST> <OUTFILE> --is_narrow_peak --min_replicates 1"""
 
 argParser = argparse.ArgumentParser(description=Description, epilog=Epilog)
 
 ## REQUIRED PARAMETERS
-argParser.add_argument("MERGED_INTERVAL_FILE", help="Merged MACS2 interval file created using linux sort and mergeBed.")
+argParser.add_argument("MERGED_INTERVAL_FILE", help="Merged MACS3 interval file created using linux sort and mergeBed.")
 argParser.add_argument(
     "SAMPLE_NAME_LIST",
-    help="Comma-separated list of sample names as named in individual MACS2 broadPeak/narrowPeak output file e.g. SAMPLE_R1 for SAMPLE_R1_peak_1.",
+    help="Comma-separated list of sample names as named in individual MACS3 broadPeak/narrowPeak output file e.g. SAMPLE_R1 for SAMPLE_R1_peak_1.",
 )
 argParser.add_argument("OUTFILE", help="Full path to output directory.")
 
@@ -76,7 +76,7 @@ def makedir(path):
 ## sort -k1,1 -k2,2n <MACS_NARROWPEAK_FILE_LIST> | mergeBed -c 2,3,4,5,6,7,8,9,10 -o collapse,collapse,collapse,collapse,collapse,collapse,collapse,collapse,collapse > merged_peaks.txt
 
 
-def macs2_merged_expand(MergedIntervalTxtFile, SampleNameList, OutFile, isNarrow=False, minReplicates=1):
+def macs3_merged_expand(MergedIntervalTxtFile, SampleNameList, OutFile, isNarrow=False, minReplicates=1):
     makedir(os.path.dirname(OutFile))
 
     combFreqDict = {}
@@ -208,7 +208,7 @@ def macs2_merged_expand(MergedIntervalTxtFile, SampleNameList, OutFile, isNarrow
 ############################################
 ############################################
 
-macs2_merged_expand(
+macs3_merged_expand(
     MergedIntervalTxtFile=args.MERGED_INTERVAL_FILE,
     SampleNameList=args.SAMPLE_NAME_LIST.split(","),
     OutFile=args.OUTFILE,

bin/plot_macs2_qc.r → bin/plot_macs3_qc.r

@@ -20,7 +20,7 @@ library(scales)
 option_list <- list(make_option(c("-i", "--peak_files"), type="character", default=NULL, help="Comma-separated list of peak files.", metavar="path"),
                     make_option(c("-s", "--sample_ids"), type="character", default=NULL, help="Comma-separated list of sample ids associated with peak files. Must be unique and in same order as peaks files input.", metavar="string"),
                     make_option(c("-o", "--outdir"), type="character", default='./', help="Output directory", metavar="path"),
-                    make_option(c("-p", "--outprefix"), type="character", default='macs2_peakqc', help="Output prefix", metavar="string"))
+                    make_option(c("-p", "--outprefix"), type="character", default='macs3_peakqc', help="Output prefix", metavar="string"))
 
 opt_parser <- OptionParser(option_list=option_list)
 opt <- parse_args(opt_parser)

conf/modules.config

@@ -540,7 +540,7 @@ if (!params.skip_plot_fingerprint) {
 }
 
 process {
-    withName: 'MACS2_CALLPEAK' {
+    withName: 'MACS3_CALLPEAK' {
         ext.args   = [
             '--keep-dup all',
             params.narrow_peak          ? '' : "--broad --broad-cutoff ${params.broad_cutoff}",
@@ -550,7 +550,7 @@ process {
             params.aligner == "chromap" ? "--format BAM" : '' //TODO check if not needed anymore with new chromap versions
         ].join(' ').trim()
         publishDir = [
-            path: { "${params.outdir}/${params.aligner}/merged_library/macs2/${params.narrow_peak ? 'narrow_peak' : 'broad_peak'}" },
+            path: { "${params.outdir}/${params.aligner}/merged_library/macs3/${params.narrow_peak ? 'narrow_peak' : 'broad_peak'}" },
             mode: params.publish_dir_mode,
             saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
         ]
@@ -559,14 +559,14 @@ process {
     withName: 'FRIP_SCORE' {
         ext.args   = '-bed -c -f 0.20'
         publishDir = [
-            path: { "${params.outdir}/${params.aligner}/merged_library/macs2/${params.narrow_peak ? 'narrow_peak' : 'broad_peak'}/qc" },
+            path: { "${params.outdir}/${params.aligner}/merged_library/macs3/${params.narrow_peak ? 'narrow_peak' : 'broad_peak'}/qc" },
             enabled: false
         ]
     }
 
     withName: 'MULTIQC_CUSTOM_PEAKS' {
         publishDir = [
-            path: { "${params.outdir}/${params.aligner}/merged_library/macs2/${params.narrow_peak ? 'narrow_peak' : 'broad_peak'}/qc" },
+            path: { "${params.outdir}/${params.aligner}/merged_library/macs3/${params.narrow_peak ? 'narrow_peak' : 'broad_peak'}/qc" },
             mode: params.publish_dir_mode,
             saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
         ]
@@ -575,11 +575,11 @@ process {
 
 if (!params.skip_peak_annotation) {
     process {
-        withName: '.*:BAM_PEAKS_CALL_QC_ANNOTATE_MACS2_HOMER:HOMER_ANNOTATEPEAKS' {
+        withName: '.*:BAM_PEAKS_CALL_QC_ANNOTATE_MACS3_HOMER:HOMER_ANNOTATEPEAKS' {
             ext.args   = '-gid'
             ext.prefix = { "${meta.id}_peaks" }
             publishDir = [
-                path: { "${params.outdir}/${params.aligner}/merged_library/macs2/${params.narrow_peak ? 'narrow_peak' : 'broad_peak'}" },
+                path: { "${params.outdir}/${params.aligner}/merged_library/macs3/${params.narrow_peak ? 'narrow_peak' : 'broad_peak'}" },
                 mode: params.publish_dir_mode,
                 saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
             ]
@@ -588,20 +588,20 @@ if (!params.skip_peak_annotation) {
 
     if (!params.skip_peak_qc) {
         process {
-            withName: 'PLOT_MACS2_QC' {
-                ext.args   = '-o ./ -p macs2_peak'
+            withName: 'PLOT_MACS3_QC' {
+                ext.args   = '-o ./ -p macs3_peak'
                 publishDir = [
-                    path: { "${params.outdir}/${params.aligner}/merged_library/macs2/${params.narrow_peak ? 'narrow_peak' : 'broad_peak'}/qc" },
+                    path: { "${params.outdir}/${params.aligner}/merged_library/macs3/${params.narrow_peak ? 'narrow_peak' : 'broad_peak'}/qc" },
                     mode: params.publish_dir_mode,
                     saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
                 ]
             }
 
             withName: 'PLOT_HOMER_ANNOTATEPEAKS' {
                 ext.args   = '-o ./'
-                ext.prefix = 'macs2_annotatePeaks'
+                ext.prefix = 'macs3_annotatePeaks'
                 publishDir = [
-                    path: { "${params.outdir}/${params.aligner}/merged_library/macs2/${params.narrow_peak ? 'narrow_peak' : 'broad_peak'}/qc" },
+                    path: { "${params.outdir}/${params.aligner}/merged_library/macs3/${params.narrow_peak ? 'narrow_peak' : 'broad_peak'}/qc" },
                     mode: params.publish_dir_mode,
                     saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
                 ]
@@ -612,11 +612,11 @@ if (!params.skip_peak_annotation) {
 
 if (!params.skip_consensus_peaks) {
     process {
-        withName: 'MACS2_CONSENSUS' {
+        withName: 'MACS3_CONSENSUS' {
             ext.when   = { meta.multiple_groups || meta.replicates_exist }
             ext.prefix = { "${meta.id}.consensus_peaks" }
             publishDir = [
-                path: { "${params.outdir}/${params.aligner}/merged_library/macs2/${params.narrow_peak ? 'narrow_peak' : 'broad_peak'}/consensus/${meta.id}" },
+                path: { "${params.outdir}/${params.aligner}/merged_library/macs3/${params.narrow_peak ? 'narrow_peak' : 'broad_peak'}/consensus/${meta.id}" },
                 mode: params.publish_dir_mode,
                 saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
             ]
@@ -626,7 +626,7 @@ if (!params.skip_consensus_peaks) {
             ext.args   = '-F SAF -O --fracOverlap 0.2'
             ext.prefix = { "${meta.id}.consensus_peaks" }
             publishDir = [
-                path: { "${params.outdir}/${params.aligner}/merged_library/macs2/${params.narrow_peak ? 'narrow_peak' : 'broad_peak'}/consensus/${meta.id}" },
+                path: { "${params.outdir}/${params.aligner}/merged_library/macs3/${params.narrow_peak ? 'narrow_peak' : 'broad_peak'}/consensus/${meta.id}" },
                 mode: params.publish_dir_mode,
                 saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
             ]
@@ -639,7 +639,7 @@ if (!params.skip_consensus_peaks) {
                 ext.args   = '-gid'
                 ext.prefix = { "${meta.id}.consensus_peaks" }
                 publishDir = [
-                    path: { "${params.outdir}/${params.aligner}/merged_library/macs2/${params.narrow_peak ? 'narrow_peak' : 'broad_peak'}/consensus/${meta.id}" },
+                    path: { "${params.outdir}/${params.aligner}/merged_library/macs3/${params.narrow_peak ? 'narrow_peak' : 'broad_peak'}/consensus/${meta.id}" },
                     mode: params.publish_dir_mode,
                     saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
                 ]
@@ -648,7 +648,7 @@ if (!params.skip_consensus_peaks) {
             withName: 'ANNOTATE_BOOLEAN_PEAKS' {
                 ext.prefix = { "${meta.id}.consensus_peaks" }
                 publishDir = [
-                    path: { "${params.outdir}/${params.aligner}/merged_library/macs2/${params.narrow_peak ? 'narrow_peak' : 'broad_peak'}/consensus/${meta.id}" },
+                    path: { "${params.outdir}/${params.aligner}/merged_library/macs3/${params.narrow_peak ? 'narrow_peak' : 'broad_peak'}/consensus/${meta.id}" },
                     mode: params.publish_dir_mode,
                     saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
                 ]
@@ -668,7 +668,7 @@ if (!params.skip_consensus_peaks) {
                 ].join(' ').trim()
                 ext.prefix = { "${meta.id}.consensus_peaks" }
                 publishDir = [
-                    path: { "${params.outdir}/${params.aligner}/merged_library/macs2/${params.narrow_peak ? 'narrow_peak' : 'broad_peak'}/consensus/${meta.id}/deseq2" },
+                    path: { "${params.outdir}/${params.aligner}/merged_library/macs3/${params.narrow_peak ? 'narrow_peak' : 'broad_peak'}/consensus/${meta.id}/deseq2" },
                     mode: params.publish_dir_mode,
                     saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
                 ]