Merge pull request #200 from CCBR/iss-190-kls

fix: check whether contrastsheet param is null

CHANGELOG.md

@@ -1,19 +1,30 @@
 ## CHAMPAGNE development version
 
+### New features
+
 - Create a script (`bin/champagne`) to provide an interface to the champagne CLI that works out-of-the-box without the need to install the python package with `pip`. (#180, @kelly-sovacool)
   - However, any dependencies not in the Python Standard Library must be installed for this to work. See the dependencies list in `pyproject.toml`.
+- Allow additional columns in the sample sheet beyond the minimum required header. (#176, @kelly-sovacool)
+- Add a workflow entry point to download fastq files from SRA. (#176, @kelly-sovacool)
+- Add `test_human` profile with chipseq data from ENCODE. (#176, @kelly-sovacool)
+
+### Bug fixes
+
 - Fix configuration files for compatibility with using the GitHub repo as the source. (#173, @kelly-sovacool)
   - These equivalent commands now work:
     ```sh
     nextflow run CCBR/CHAMPAGNE
     champagne run --main CCBR/CHAMPAGNE
     ```
 - Allow multiple samples to use the same input. (#176, @kelly-sovacool)
-- Allow additional columns in the sample sheet beyond the minimum required header. (#176, @kelly-sovacool)
+- In the biowulf config profile, switch variable $SLURM_JOBID to $SLURM_JOB_ID. (@kelly-sovacool)
+- Increase resource allocations for chipseeker and deeptools. (#192, @slsevilla)
+- Check the validity of the contrastsheet earlier on in the workflow. (#192, @slsevilla; #200, @kelly-sovacool)
+
+### Misc
+
 - Change the peak widths histogram type from overlay to stack. (#176, @kelly-sovacool)
-- Add a workflow entry point to download fastq files from SRA. (#176, @kelly-sovacool)
-- Add `test_human` profile with chipseq data from ENCODE. (#176, @kelly-sovacool)
-- In biowulf config profile, switch variable $SLURM_JOBID to $SLURM_JOB_ID. (@kelly-sovacool)
+- Documentation improvements. (#192, @slsevilla)
 
 ## CHAMPAGNE 0.3.0
 

conf/full_mm10.config

@@ -5,7 +5,6 @@ params {
     genome = 'mm10'
     outdir = "results/full_mm10"
     input = "${projectDir}/assets/samplesheet_full_mm10.csv"
-    contrasts = 'true'
     contrastsheet = "${projectDir}/assets/contrasts_full_mm10.yml"
     sicer {
         species = "mm10" // supported species https://github.com/zanglab/SICER2/blob/master/sicer/lib/GenomeData.py

conf/test_human.config

@@ -5,7 +5,7 @@ params {
     genome = 'hg38'
     outdir = "results/human"
     input = "assets/samplesheet_human.csv"
-    contrasts = false //'assets/contrasts_human.yml'
+    contrastsheet = null //'assets/contrasts_human.yml'
     //read_length = 50
     sicer.species = "${params.genome}" // supported species https://github.com/zanglab/SICER2/blob/master/sicer/lib/GenomeData.py
 

conf/test_mm10.config

@@ -5,7 +5,6 @@ params {
     genome = 'mm10'
     outdir = "results/test_mm10"
     input = "${projectDir}/assets/samplesheet_test_mm10.csv"
-    contrasts = 'true'
     contrastsheet = "${projectDir}/assets/contrasts_test_mm10.yml"
     read_length = 50
     sicer.species = "mm10" // supported species https://github.com/zanglab/SICER2/blob/master/sicer/lib/GenomeData.py

main.nf

@@ -37,7 +37,7 @@ include { PHANTOM_PEAKS
           MULTIQC                  } from "./modules/local/qc.nf"
 
 
-contrastsheet = params.contrastsheet ?: "/assets/contrast_test.ymls"
+contrast_sheet = params.contrastsheet ? Channel.fromPath(file(params.contrastsheet, checkIfExists: true)) : params.contrastsheet
 
 workflow.onComplete {
     if (!workflow.stubRun && !workflow.commandLine.contains('-preview')) {
@@ -67,7 +67,7 @@ workflow {
 }
 
 workflow CHIPSEQ {
-    INPUT_CHECK(file(params.input, checkIfExists: true), params.seq_center, file(contrastsheet))
+    INPUT_CHECK(file(params.input, checkIfExists: true), params.seq_center, contrast_sheet)
 
     INPUT_CHECK.out.reads.set { raw_fastqs }
     raw_fastqs | CUTADAPT
@@ -131,7 +131,9 @@ workflow CHIPSEQ {
                 [ [ sample_basename: meta_split[0], tool: meta_split[1] ], bed ]
             }
             .set{ ch_consensus_peaks }
-        if (params.contrasts) {
+
+        ch_contrasts = INPUT_CHECK.out.contrasts
+        if (!ch_contrasts.ifEmpty(null)) {
             // TODO use consensus peaks for regions of interest in diffbind
             CALL_PEAKS.out.bam_peaks
                 .combine(deduped_bam)

nextflow.config

@@ -2,7 +2,6 @@ nextflow.enable.dsl = 2
 
 params {
     input = null
-    contrasts = false
     seq_center = null
     read_length = null
     genome = null

subworkflows/local/input_check.nf

@@ -20,8 +20,8 @@ workflow INPUT_CHECK {
             .set { reads }
 
         // Run check on the contrast manifest
-        contrasts=Channel.empty()
-        if (params.contrasts) {
+        ch_contrasts = Channel.empty()
+        if (contrastsheet) {
             CHECK_CONTRASTS(valid_csv, contrastsheet)
                 .csv
                 .flatten()
@@ -31,13 +31,13 @@ workflow INPUT_CHECK {
                     [ sample_basename: meta.sample_basename, group: meta.group, contrast: meta.contrast ]
                 }
                 .unique()
-                .set{ contrasts }
+                .set{ ch_contrasts }
         }
 
     emit:
         reads                               = reads      // channel: [ val(meta), [ reads ] ]
         csv                                 = valid_csv
-        contrasts                           = contrasts
+        contrasts                           = ch_contrasts
         versions                            = SAMPLESHEET_CHECK.out.versions // channel: [ versions.yml ]
 }