Merge pull request #369 from genomic-medicine-sweden/368-fix-jasen-fi…

…rst-bug

Fix jasen first bug

CHANGELOG.md

@@ -29,6 +29,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - Fixed resfinder `--species` arg
 - Fixed `nextflow.hopper.config` `symlinkDir`
 - Removed serotypefinder from saureus workflow
+- Fixed jasen running only on the first row/sample in csv
 
 ### Changed
 

configs/nextflow.dev.config

@@ -111,6 +111,7 @@ profiles {
 		params.species = 'streptococcus pyogenes'
 		params.speciesDir = 'spyogenes'
 		params.mlstScheme = 'spyogenes'
+		params.symlinkDir = "/access/jasen/spyogenes/"
 		params.referenceGenome = "${params.root}/assets/genomes/streptococcus_pyogenes/GCF_000006785.2.fasta"
 		params.referenceGenomeIdx = "${params.root}/assets/genomes/streptococcus_pyogenes/GCF_000006785.2.fasta.fai"
 		params.referenceGenomeGff = "${params.root}/assets/genomes/streptococcus_pyogenes/GCF_000006785.2.gff"

nextflow-modules/modules/seqtk/main.nf

@@ -3,7 +3,8 @@ process seqtk_sample {
   scratch params.scratch
 
   input:
-    tuple val(sampleID), path(reads), val(sample_size)
+    tuple val(sampleID), path(reads)
+    val sample_size
 
   output:
     tuple val(sampleID), path("*.fastq.gz"), emit: reads

workflows/bacterial_base.nf

@@ -26,6 +26,7 @@ workflow CALL_BACTERIAL_BASE {
         referenceGenome
         referenceGenomeDir
         inputSamples
+        targetSampleSize
 
     main:
         ch_versions = Channel.empty()
@@ -42,11 +43,12 @@ workflow CALL_BACTERIAL_BASE {
             .map{ row -> get_reads(row) }
             .set{ ch_raw_reads }
 
-        // downsample reads
-        seqtk_sample( ch_raw_reads.map(row -> [row[0], row[1], params.targetSampleSize]) ).reads
-            .concat( ch_raw_reads )    // add raw reads channel
-            .first()                   // if seqtk was not run the first row is the raw reads
-            .set{ ch_sampled_reads }  // create sampled reads channel
+        if ( params.targetSampleSize ) {
+            // downsample reads
+            seqtk_sample( ch_raw_reads, targetSampleSize ).reads.set{ ch_sampled_reads }
+        } else {
+            ch_raw_reads.set{ ch_sampled_reads }
+        }
 
         // reads trim and clean and recreate reads channel if the reads were trimmed
         assembly_trim_clean(ch_sampled_reads.join(ch_meta)).set { ch_clean_reads_w_meta }

workflows/escherichia_coli.nf

@@ -45,11 +45,13 @@ workflow CALL_ESCHERICHIA_COLI {
     serotypefinderDb = file(params.serotypefinderDb, checkIfExists: true)
     shigapassDb = file(params.shigapassDb, checkIfExists: true)
     virulencefinderDb = file(params.virulencefinderDb, checkIfExists: true)
+    // schemas and values
+    targetSampleSize = params.targetSampleSize ? params.targetSampleSize : Channel.of([])
 
     main:
         ch_versions = Channel.empty()
 
-        CALL_BACTERIAL_BASE( coreLociBed, referenceGenome, referenceGenomeDir, inputSamples )
+        CALL_BACTERIAL_BASE( coreLociBed, referenceGenome, referenceGenomeDir, inputSamples, targetSampleSize )
 
         CALL_BACTERIAL_BASE.out.assembly.set{ch_assembly}
         CALL_BACTERIAL_BASE.out.reads.set{ch_reads}

workflows/klebsiella_pneumoniae.nf

@@ -43,11 +43,13 @@ workflow CALL_KLEBSIELLA_PNEUMONIAE {
     pointfinderDb = file(params.pointfinderDb, checkIfExists: true)
     serotypefinderDb = file(params.serotypefinderDb, checkIfExists: true)
     virulencefinderDb = file(params.virulencefinderDb, checkIfExists: true)
+    // schemas and values
+    targetSampleSize = params.targetSampleSize ? params.targetSampleSize : Channel.of([])
 
     main:
         ch_versions = Channel.empty()
 
-        CALL_BACTERIAL_BASE( coreLociBed, referenceGenome, referenceGenomeDir, inputSamples )
+        CALL_BACTERIAL_BASE( coreLociBed, referenceGenome, referenceGenomeDir, inputSamples, targetSampleSize )
 
         CALL_BACTERIAL_BASE.out.assembly.set{ch_assembly}
         CALL_BACTERIAL_BASE.out.reads.set{ch_reads}

workflows/mycobacterium_tuberculosis.nf

@@ -33,11 +33,13 @@ workflow CALL_MYCOBACTERIUM_TUBERCULOSIS {
     tbdbBed = file(params.tbdbBed, checkIfExists: true)
     tbdbBedIdx = file(params.tbdbBedIdx, checkIfExists: true)
     tbGradingRulesBed = file(params.tbGradingRulesBed, checkIfExists: true)
+    // schemas and values
+    targetSampleSize = params.targetSampleSize ? params.targetSampleSize : Channel.of([])
 
     main:
         ch_versions = Channel.empty()
 
-        CALL_BACTERIAL_BASE( coreLociBed, referenceGenome, referenceGenomeDir, inputSamples )
+        CALL_BACTERIAL_BASE( coreLociBed, referenceGenome, referenceGenomeDir, inputSamples, targetSampleSize )
 
         CALL_BACTERIAL_BASE.out.assembly.set{ch_assembly}
         CALL_BACTERIAL_BASE.out.reads.set{ch_reads}

workflows/staphylococcus_aureus.nf

@@ -41,11 +41,13 @@ workflow CALL_STAPHYLOCOCCUS_AUREUS {
     resfinderDb = file(params.resfinderDb, checkIfExists: true)
     pointfinderDb = file(params.pointfinderDb, checkIfExists: true)
     virulencefinderDb = file(params.virulencefinderDb, checkIfExists: true)
+    // schemas and values
+    targetSampleSize = params.targetSampleSize ? params.targetSampleSize : Channel.of([])
 
     main:
         ch_versions = Channel.empty()
 
-        CALL_BACTERIAL_BASE( coreLociBed, referenceGenome, referenceGenomeDir, inputSamples )
+        CALL_BACTERIAL_BASE( coreLociBed, referenceGenome, referenceGenomeDir, inputSamples, targetSampleSize )
 
         CALL_BACTERIAL_BASE.out.assembly.set{ch_assembly}
         CALL_BACTERIAL_BASE.out.reads.set{ch_reads}

workflows/streptococcus.nf

@@ -53,11 +53,12 @@ workflow CALL_STREPTOCOCCUS {
     mlstScheme = params.mlstScheme ? params.mlstScheme : Channel.of([])
     species = params.species ? params.species : Channel.of([])
     speciesDir = params.speciesDir ? params.speciesDir : Channel.of([])
+    targetSampleSize = params.targetSampleSize ? params.targetSampleSize : Channel.of([])
 
     main:
         ch_versions = Channel.empty()
 
-        CALL_BACTERIAL_BASE( coreLociBed, referenceGenome, referenceGenomeDir, inputSamples )
+        CALL_BACTERIAL_BASE( coreLociBed, referenceGenome, referenceGenomeDir, inputSamples, targetSampleSize )
 
         CALL_BACTERIAL_BASE.out.assembly.set{ch_assembly}
         CALL_BACTERIAL_BASE.out.reads.set{ch_reads}

workflows/streptococcus_pyogenes.nf

@@ -47,11 +47,12 @@ workflow CALL_STREPTOCOCCUS_PYOGENES {
     mlstScheme = params.mlstScheme ? params.mlstScheme : Channel.of([])
     species = params.species ? params.species : Channel.of([])
     speciesDir = params.speciesDir ? params.speciesDir : Channel.of([])
+    targetSampleSize = params.targetSampleSize ? params.targetSampleSize : Channel.of([])
 
     main:
         ch_versions = Channel.empty()
 
-        CALL_BACTERIAL_BASE( coreLociBed, referenceGenome, referenceGenomeDir, inputSamples )
+        CALL_BACTERIAL_BASE( coreLociBed, referenceGenome, referenceGenomeDir, inputSamples, targetSampleSize )
 
         CALL_BACTERIAL_BASE.out.assembly.set{ch_assembly}
         CALL_BACTERIAL_BASE.out.reads.set{ch_reads}