Fix handling of ONT samples re fastqc & postalignqc

genomic-medicine-sweden · Jan 30, 2025 · b0499ab · b0499ab
1 parent b7476b0
commit b0499ab
Show file tree

Hide file tree

Showing 10 changed files with 44 additions and 17 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -44,6 +44,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - Fixed channel problem by changing `Channel.of([])` to `Channel.value([])`
 - Fixed `nextflow.hopper.config` re singularity image path
 - Fixed sccmec version file
+- Fixed handling of ONT samples re fastqc & postalignqc
 
 ### Changed
 

diff --git a/nextflow-modules/modules/fastqc/main.nf b/nextflow-modules/modules/fastqc/main.nf
@@ -3,14 +3,17 @@ process fastqc {
   scratch params.scratch
 
   input:
-    tuple val(sample_id), path(reads)
+    tuple val(sample_id), path(reads), val(platform)
 
   output:
     tuple val(sample_id), path(summary_output), emit: summary
     tuple val(sample_id), path(output)        , emit: output
     tuple val(sample_id), path(html_output)   , emit: html
     path "*versions.yml"                      , emit: versions
 
+  when:
+    platform == "illumina"
+
   script:
     def args          = task.ext.args ?: ''
     def old_new_pairs = reads instanceof Path || reads.size() == 1 ? [[ reads, "${sample_id}.${reads.extension}" ]] : reads.withIndex().collect { entry, index -> [ entry, "${sample_id}_${index + 1}.${entry.extension}" ] }

diff --git a/nextflow-modules/modules/prp/main.nf b/nextflow-modules/modules/prp/main.nf
@@ -117,15 +117,15 @@ process post_align_qc {
   scratch params.scratch
 
   input:
-    tuple val(sample_id), path(bam)
+    tuple val(sample_id), path(bam), val(platform)
     path reference
     path bed
 
   output:
     tuple val(sample_id), path(output), emit: qc
 
   when:
-    task.ext.when
+    task.ext.when && platform == "illumina"
 
   script:
     output = "${sample_id}_qc.json"

diff --git a/workflows/bacterial_base.nf b/workflows/bacterial_base.nf
@@ -97,11 +97,11 @@ workflow CALL_BACTERIAL_BASE {
         quast(ch_assembly, referenceGenome)
 
         // qc processing
-        fastqc(ch_reads)
+        fastqc(ch_reads_w_meta)
         bwa_mem_ref(ch_reads, referenceGenomeDir)
         samtools_index_ref(bwa_mem_ref.out.bam)
 
-        post_align_qc(bwa_mem_ref.out.bam, referenceGenome, coreLociBed)
+        post_align_qc(bwa_mem_ref.out.bam.join(ch_meta), referenceGenome, coreLociBed)
 
         nanoplot(ch_reads_w_meta)
 
@@ -127,6 +127,7 @@ workflow CALL_BACTERIAL_BASE {
         bam             = bwa_mem_ref.out.bam               // channel: [ val(meta), path(bam)]
         bai             = samtools_index_ref.out.bai        // channel: [ val(meta), path(bai)]
         fastqc          = fastqc.out.output                 // channel: [ val(meta), path(txt)]
+        seqplat_meta    = ch_meta                           // channel: [ val(meta), val(str)]
         metadata        = save_analysis_metadata.out.meta   // channel: [ val(meta), path(json)]
         qc              = post_align_qc.out.qc              // channel: [ val(meta), path(fasta)]
         qc_nano         = nanoplot.out.html                 // channel: [ val(meta), path(html)]

diff --git a/workflows/escherichia_coli.nf b/workflows/escherichia_coli.nf
@@ -60,6 +60,7 @@ workflow CALL_ESCHERICHIA_COLI {
         CALL_BACTERIAL_BASE.out.quast.set{ch_quast}
         CALL_BACTERIAL_BASE.out.qc.set{ch_qc}
         CALL_BACTERIAL_BASE.out.metadata.set{ch_metadata}
+        CALL_BACTERIAL_BASE.out.seqplat_meta.set{ch_seqplat_meta}
         CALL_BACTERIAL_BASE.out.seqrun_meta.set{ch_seqrun_meta}
         CALL_BACTERIAL_BASE.out.reads_w_meta.set{ch_input_meta}
         CALL_BACTERIAL_BASE.out.sourmash.set{ch_sourmash}
@@ -118,8 +119,10 @@ workflow CALL_ESCHERICHIA_COLI {
 
         ch_reads.map { sampleID, reads -> [ sampleID, [] ] }.set{ ch_empty }
 
+        ch_qc_illumina = ch_seqplat_meta.filter { it[1] == 'illumina' } ? ch_qc : ch_empty
+
         ch_quast
-            .join(ch_qc)
+            .join(ch_qc_illumina)
             .join(mlst.out.json)
             .join(chewbbaca_split_results.out.output)
             .join(amrfinderplus.out.output)
@@ -155,7 +158,7 @@ workflow CALL_ESCHERICHIA_COLI {
         create_yaml(create_analysis_result.out.json.join(ch_sourmash).join(ch_ska), params.speciesDir)
 
         ch_quast
-            .join(ch_qc)
+            .join(ch_qc_illumina)
             .join(chewbbaca_split_results.out.output)
             .set{ cdmInput }
 

diff --git a/workflows/klebsiella_pneumoniae.nf b/workflows/klebsiella_pneumoniae.nf
@@ -58,6 +58,7 @@ workflow CALL_KLEBSIELLA_PNEUMONIAE {
         CALL_BACTERIAL_BASE.out.quast.set{ch_quast}
         CALL_BACTERIAL_BASE.out.qc.set{ch_qc}
         CALL_BACTERIAL_BASE.out.metadata.set{ch_metadata}
+        CALL_BACTERIAL_BASE.out.seqplat_meta.set{ch_seqplat_meta}
         CALL_BACTERIAL_BASE.out.seqrun_meta.set{ch_seqrun_meta}
         CALL_BACTERIAL_BASE.out.reads_w_meta.set{ch_input_meta}
         CALL_BACTERIAL_BASE.out.sourmash.set{ch_sourmash}
@@ -115,8 +116,10 @@ workflow CALL_KLEBSIELLA_PNEUMONIAE {
 
         ch_reads.map { sampleID, reads -> [ sampleID, [] ] }.set{ ch_empty }
 
+        ch_qc_illumina = ch_seqplat_meta.filter { it[1] == 'illumina' } ? ch_qc : ch_empty
+
         ch_quast
-            .join(ch_qc)
+            .join(ch_qc_illumina)
             .join(mlst.out.json)
             .join(chewbbaca_split_results.out.output)
             .join(amrfinderplus.out.output)
@@ -152,7 +155,7 @@ workflow CALL_KLEBSIELLA_PNEUMONIAE {
         create_yaml(create_analysis_result.out.json.join(ch_sourmash).join(ch_ska), params.speciesDir)
 
         ch_quast
-            .join(ch_qc)
+            .join(ch_qc_illumina)
             .join(chewbbaca_split_results.out.output)
             .set{ cdmInput }
 

diff --git a/workflows/mycobacterium_tuberculosis.nf b/workflows/mycobacterium_tuberculosis.nf
@@ -45,6 +45,7 @@ workflow CALL_MYCOBACTERIUM_TUBERCULOSIS {
         CALL_BACTERIAL_BASE.out.reads.set{ch_reads}
         CALL_BACTERIAL_BASE.out.quast.set{ch_quast}
         CALL_BACTERIAL_BASE.out.metadata.set{ch_metadata}
+        CALL_BACTERIAL_BASE.out.seqplat_meta.set{ch_seqplat_meta}
         CALL_BACTERIAL_BASE.out.seqrun_meta.set{ch_seqrun_meta}
         CALL_BACTERIAL_BASE.out.reads_w_meta.set{ch_input_meta}
         CALL_BACTERIAL_BASE.out.sourmash.set{ch_sourmash}
@@ -63,8 +64,10 @@ workflow CALL_MYCOBACTERIUM_TUBERCULOSIS {
 
         ch_reads.map { sampleID, reads -> [ sampleID, [] ] }.set{ ch_empty }
 
+        ch_qc_illumina = ch_seqplat_meta.filter { it[1] == 'illumina' } ? ch_qc : ch_empty
+
         ch_quast
-            .join(ch_qc)
+            .join(ch_qc_illumina)
             .join(ch_empty)
             .join(ch_empty)
             .join(ch_empty)
@@ -105,7 +108,7 @@ workflow CALL_MYCOBACTERIUM_TUBERCULOSIS {
         create_yaml(add_grading_bed_track.out.json.join(ch_sourmash).join(ch_ska), params.speciesDir)
 
         ch_quast
-            .join(ch_qc)
+            .join(ch_qc_illumina)
             .join(ch_empty)
             .set{ cdmInput }
 

diff --git a/workflows/staphylococcus_aureus.nf b/workflows/staphylococcus_aureus.nf
@@ -57,6 +57,7 @@ workflow CALL_STAPHYLOCOCCUS_AUREUS {
         CALL_BACTERIAL_BASE.out.quast.set{ch_quast}
         CALL_BACTERIAL_BASE.out.qc.set{ch_qc}
         CALL_BACTERIAL_BASE.out.metadata.set{ch_metadata}
+        CALL_BACTERIAL_BASE.out.seqplat_meta.set{ch_seqplat_meta}
         CALL_BACTERIAL_BASE.out.seqrun_meta.set{ch_seqrun_meta}
         CALL_BACTERIAL_BASE.out.reads_w_meta.set{ch_input_meta}
         CALL_BACTERIAL_BASE.out.sourmash.set{ch_sourmash}
@@ -114,8 +115,10 @@ workflow CALL_STAPHYLOCOCCUS_AUREUS {
 
         ch_reads.map { sampleID, reads -> [ sampleID, [] ] }.set{ ch_empty }
 
+        ch_qc_illumina = ch_seqplat_meta.filter { it[1] == 'illumina' } ? ch_qc : ch_empty
+
         ch_quast
-            .join(ch_qc)
+            .join(ch_qc_illumina)
             .join(mlst.out.json)
             .join(chewbbaca_split_results.out.output)
             .join(amrfinderplus.out.output)
@@ -151,7 +154,7 @@ workflow CALL_STAPHYLOCOCCUS_AUREUS {
         create_yaml(create_analysis_result.out.json.join(ch_sourmash).join(ch_ska), params.speciesDir)
 
         ch_quast
-            .join(ch_qc)
+            .join(ch_qc_illumina)
             .join(chewbbaca_split_results.out.output)
             .set{ cdmInput }
 

diff --git a/workflows/streptococcus.nf b/workflows/streptococcus.nf
@@ -67,6 +67,7 @@ workflow CALL_STREPTOCOCCUS {
         CALL_BACTERIAL_BASE.out.quast.set{ch_quast}
         CALL_BACTERIAL_BASE.out.qc.set{ch_qc}
         CALL_BACTERIAL_BASE.out.metadata.set{ch_metadata}
+        CALL_BACTERIAL_BASE.out.seqplat_meta.set{ch_seqplat_meta}
         CALL_BACTERIAL_BASE.out.seqrun_meta.set{ch_seqrun_meta}
         CALL_BACTERIAL_BASE.out.reads_w_meta.set{ch_input_meta}
         CALL_BACTERIAL_BASE.out.sourmash.set{ch_sourmash}
@@ -125,9 +126,15 @@ workflow CALL_STREPTOCOCCUS {
         virulencefinder(ch_reads, params.useVirulenceDbs, virulencefinderDb)
 
         ch_reads.map{ sampleID, reads -> [ sampleID, [] ] }.set{ ch_empty }
+
+        if (species == "streptococcus") {
+            ch_empty.set{ ch_qc_illumina }
+        } else {
+            ch_qc_illumina = ch_seqplat_meta.filter { it[1] == 'illumina' } ? ch_qc : ch_empty
+        }
 
         ch_quast
-            .join(ch_empty)
+            .join(ch_qc_illumina)
             .join(mlst.out.json)
             .join(chewbbaca_split_results.out.output)
             .join(amrfinderplus.out.output)
@@ -163,7 +170,7 @@ workflow CALL_STREPTOCOCCUS {
         create_yaml(create_analysis_result.out.json.join(ch_sourmash).join(ch_ska), speciesDir)
 
         ch_quast
-            .join(ch_empty)
+            .join(ch_qc_illumina)
             .join(chewbbaca_split_results.out.output)
             .set{ cdmInput }
 

diff --git a/workflows/streptococcus_pyogenes.nf b/workflows/streptococcus_pyogenes.nf
@@ -61,6 +61,7 @@ workflow CALL_STREPTOCOCCUS_PYOGENES {
         CALL_BACTERIAL_BASE.out.quast.set{ch_quast}
         CALL_BACTERIAL_BASE.out.qc.set{ch_qc}
         CALL_BACTERIAL_BASE.out.metadata.set{ch_metadata}
+        CALL_BACTERIAL_BASE.out.seqplat_meta.set{ch_seqplat_meta}
         CALL_BACTERIAL_BASE.out.seqrun_meta.set{ch_seqrun_meta}
         CALL_BACTERIAL_BASE.out.reads_w_meta.set{ch_input_meta}
         CALL_BACTERIAL_BASE.out.sourmash.set{ch_sourmash}
@@ -118,8 +119,10 @@ workflow CALL_STREPTOCOCCUS_PYOGENES {
 
         ch_reads.map { sampleID, reads -> [ sampleID, [] ] }.set{ ch_empty }
 
+        ch_qc_illumina = ch_seqplat_meta.filter { it[1] == 'illumina' } ? ch_qc : ch_empty
+
         ch_quast
-            .join(ch_qc)
+            .join(ch_qc_illumina)
             .join(mlst.out.json)
             .join(chewbbaca_split_results.out.output)
             .join(amrfinderplus.out.output)
@@ -155,7 +158,7 @@ workflow CALL_STREPTOCOCCUS_PYOGENES {
         create_yaml(create_analysis_result.out.json.join(ch_sourmash).join(ch_ska), speciesDir)
 
         ch_quast
-            .join(ch_qc)
+            .join(ch_qc_illumina)
             .join(chewbbaca_split_results.out.output)
             .set{ cdmInput }