report adjustments and updates for stability

workflows/create_summary_report.nf

@@ -1,4 +1,4 @@
-include { summary_report } from './process/summary_report'
+include { summary_report; summary_report_fasta; summary_report_default } from './process/summary_report'
 include { plot_coverages } from '../modules/plot_coverages.nf'
 
 workflow create_summary_report_wf {
@@ -9,22 +9,29 @@ workflow create_summary_report_wf {
         kraken2
         alignments
         samples_list
-    main:
+        main:
         version_ch = Channel.fromPath(workflow.projectDir + "/configs/container.config")
 
         pangolin_results = pangolin.map {it -> it[1]}.collectFile(name: 'pangolin_results.csv', skip: 1, keepHeader: true)
         president_results = president.map {it -> it[1]}.collectFile(name: 'president_results.tsv', skip: 1, keepHeader: true)
         nextclade_results = nextclade.map {it -> it[1]}.collectFile(name: 'nextclade_results.tsv', skip: 1, keepHeader: true)
-        kraken2_results = kraken2.map {it -> it[2]}.collect()
+
         alignment_files = alignments.map {it -> it[0]}.collect()
         if (params.fasta || workflow.profile.contains('test_fasta')) {
-            coverage_plots = Channel.from( ['deactivated'] ).collect()
+
+            summary_report_fasta(version_ch, pangolin_results, president_results, nextclade_results)
+
         } else {
+            kraken2_results = kraken2.map {it -> it[2]}.collect()
             // sort by sample name, group in lists of 6, collect the grouped plots
             coverage_plots = plot_coverages(alignments.map{it -> it[0]}.toSortedList({ a, b -> a.simpleName <=> b.simpleName }).flatten().collate(6), \
                                             alignments.map{it -> it[1]}.toSortedList({ a, b -> a.simpleName <=> b.simpleName }).flatten().collate(6)).collect()
+
+            if (params.samples) { summary_report(version_ch, pangolin_results, president_results, nextclade_results, kraken2_results, coverage_plots, samples_list) }
+            else { summary_report_default(version_ch, pangolin_results, president_results, nextclade_results, kraken2_results, coverage_plots) }
+
         }
 
-        summary_report(version_ch, pangolin_results, president_results, nextclade_results, kraken2_results, coverage_plots, samples_list)
+
 
 } 

workflows/process/nextclade.nf

@@ -5,6 +5,7 @@ process nextclade {
         tuple val(name), path(consensus)
     output:
         tuple val(name), path("${name}_clade.tsv")
+    script:
     """
     nextclade --input-fasta ${consensus} --output-tsv tmp.tsv
     cat tmp.tsv | tr -d "\r" > ${name}_clade.tsv

workflows/process/summary_report.nf

@@ -15,17 +15,44 @@ process summary_report {
         path("poreCov_summary_report_*.tsv")
 
     shell:
-    if (params.fasta || workflow.profile.contains('test_fasta'))            
         '''
+        echo 'sample,num_unclassified,num_sarscov2,num_human' > kraken2_results.csv
+        for KF in !{kraken2_results}; do
+        NUNCLASS=$(awk -v ORS= '$5=="0" {print $3}' $KF)
+        NSARS=$(awk -v ORS= '$5=="2697049" {print $3}' $KF)
+        NHUM=$(awk '$5=="9606" {print $3}' $KF)
+        echo "${KF%.kreport},${NUNCLASS:-0},${NSARS:-0},${NHUM:-0}" >> kraken2_results.csv
+        done
+
         summary_report.py \
             -v !{version_config} \
             --porecov_version !{workflow.revision}:!{workflow.commitId}:!{workflow.scriptId} \
+            --primer !{params.primerV} \
             -p !{pangolin_results} \
             -q !{president_results} \
             -n !{nextclade_results} \
+            -k kraken2_results.csv \
+            -c $(echo !{coverage_plots} | tr ' ' ',') \
             -s !{samples_list}
         '''
-    else
+}
+
+process summary_report_default {
+        publishDir "${params.output}/", mode: 'copy'
+        label 'fastcov'
+    input:
+        path(version_config)
+        path(pangolin_results)
+        path(president_results)
+        path(nextclade_results)
+        path(kraken2_results)
+        path(coverage_plots)
+    output:
+	    path("poreCov_summary_report_*.html")
+        path("poreCov_summary_report_*.xlsx")
+        path("poreCov_summary_report_*.tsv")
+
+    shell:
         '''
         echo 'sample,num_unclassified,num_sarscov2,num_human' > kraken2_results.csv
         for KF in !{kraken2_results}; do
@@ -43,7 +70,31 @@ process summary_report {
             -q !{president_results} \
             -n !{nextclade_results} \
             -k kraken2_results.csv \
-            -c $(echo !{coverage_plots} | tr ' ' ',') \
-            -s !{samples_list}
+            -c $(echo !{coverage_plots} | tr ' ' ',') 
         '''
+}
+
+process summary_report_fasta {
+        publishDir "${params.output}/", mode: 'copy'
+        label 'fastcov'
+    input:
+        path(version_config)
+        path(pangolin_results)
+        path(president_results)
+        path(nextclade_results)
+    output:
+	    path("poreCov_summary_report_*.html")
+        path("poreCov_summary_report_*.xlsx")
+        path("poreCov_summary_report_*.tsv")
+
+    script:          
+        """
+        summary_report.py \
+            -v ${version_config} \
+            --porecov_version ${workflow.revision}:${workflow.commitId}:${workflow.scriptId} \
+            -p ${pangolin_results} \
+            -q ${president_results} \
+            -n ${nextclade_results} \
+            -s "deactivated"
+        """
 }