Merge pull request icgc-argo-workflows#26 from ICGC-ARGO-Structural-Variation-CN-WG/facets@0.4.0

Facets@0.4.0
[release]

Author: abenjak

facets/Dockerfile

@@ -18,6 +18,9 @@ RUN mkdir -p /tools
 ENV PATH="/tools:${PATH}"
 COPY facetsRun.R /tools/
 
+# Add results script:
+COPY facetsResults.sh /tools/
+
 ENTRYPOINT ["/usr/bin/env"]
 
 CMD ["/bin/bash"]

facets/facetsResults.sh

@@ -0,0 +1,60 @@
+#!/bin/bash
+
+function usage() {
+  if [ -n "$1" ]; then
+    echo -e "Error: $1\n";
+  fi
+  echo "extracts facets metrics and archives facets results"
+  echo "Usage: $0 [-s summary] [-c cncf] [-p plot]"
+  echo "  -s, --summary   facets summary file"
+  echo "  -c, --cncf      facets cncf file"
+  echo "  -p, --plot      facets plot file"
+  echo ""
+  exit 1
+}
+
+# parse params
+while [[ "$#" > 0 ]]; do case $1 in
+  -s|--summary) SUMMARY="$2"; shift;shift;;
+  -c|--cncf) CNCF="$2";shift;shift;;
+  -p|--plot) PLOT="$2";shift;shift;;
+  *) usage "Unknown parameter passed: $1"; shift; shift;;
+esac; done
+
+# verify mandatory inputs
+if [ -z "$SUMMARY" ]; then usage "Summary file not provided"; fi;
+
+# verify input files
+
+if [ ! -f "$SUMMARY" ]; then usage "Input file $SUMMARY does not exist"; fi;
+
+
+echo "{
+  \"tool\": {
+    \"name\": \"facets\",
+    \"version\": \"$(grep Version $SUMMARY | sed -E -e 's/.+= //g' -e 's/ $//')\"
+  },
+  \"metrics\": {" > facets_metrics.json
+
+# fill json report from facets summary file
+tail -n+2 $SUMMARY | sed -E -e 's/\# /    \"/' -e 's/ \= (.+) $/\": \"\1\",/g' -e 's/\"([0-9\.\-]+)\"/\1/g' -e 's/dipt =/dipt" : ,/' -e 's/(loglik.+),/\1\n  }\n}/' >> facets_metrics.json
+
+# make tar_content.json
+# cncf and plot can be missing from facets results, but if produced both will be available
+if [[ -f "$CNCF" && -f "$PLOT" ]]
+then
+ echo "{
+  \"facets_metrics\": \"facets_metrics.json\",
+  \"facets_summary\": \"$(basename $SUMMARY)\",
+  \"facets_cncf\": \"$(basename $CNCF)\",
+  \"facets_plot\": \"$(basename $PLOT)\"
+}" > tar_content.json
+else
+echo "{
+  \"facets_metrics\": \"facets_metrics.json\",
+  \"facets_summary\": \"$(basename $SUMMARY)\"
+}" > tar_content.json
+fi
+
+# tar the results
+tar -czf $(basename -s .out $SUMMARY).tgz facets_metrics.json tar_content.json $SUMMARY $CNCF $PLOT

facets/main.nf

@@ -29,7 +29,7 @@
 /* this block is auto-generated based on info from pkg.json where   */
 /* changes can be made if needed, do NOT modify this block manually */
 nextflow.enable.dsl = 2
-version = '0.3.0'  // package version
+version = '0.4.0'
 
 container = [
     'ghcr.io': 'ghcr.io/icgc-argo-structural-variation-cn-wg/icgc-argo-sv-copy-number.facets'
@@ -45,7 +45,7 @@ params.container = ""
 
 params.cpus = 1
 params.mem = 30  // GB
-params.publish_dir = "facets_outdir"  // set to empty string will disable publishDir
+params.publish_dir = ""  // set to empty string will disable publishDir
 params.help = null
 
 // tool specific parmas go here, add / change as needed
@@ -118,15 +118,16 @@ process facets {
 
 
   output:
-    path "*.Rdata", emit: output_Rdata
-    path "*.out", emit: output_summary
-    path "*.cncf.txt", optional: true, emit: output_cncf
-    path "*.cncf.pdf", optional: true, emit: output_plot
+    path "*.tgz", emit: facets_results
 
 
   shell:
     '''
+        #run facets
         facetsRun.R --seed !{params.seed} --minNDepth !{params.minNDepth} --maxNDepth !{params.maxNDepth} --snp_nbhd !{params.snp_nbhd} --minGC !{params.minGC} --maxGC !{params.maxGC} --cval !{params.cval} --pre_cval !{params.pre_cval} --genome !{params.genome} --min_nhet !{params.min_nhet} --outPrefix !{params.tumor_id} --tumorName !{params.tumor_id} !{pileup}
+        
+        #fetch results (cncf and plot can be missing from facets results, but if produced both will be available)
+        facetsResults.sh -s !{params.tumor_id}.out $(if [[ -f !{params.tumor_id}.cncf.txt && -f !{params.tumor_id}.cncf.pdf ]]; then echo -c !{params.tumor_id}.cncf.txt -p !{params.tumor_id}.cncf.pdf; fi)
     '''
 }
 

facets/pkg.json

@@ -1,6 +1,6 @@
 {
     "name": "facets",
-    "version": "0.3.0",
+    "version": "0.4.0",
     "description": "facets tool",
     "main": "main.nf",
     "deprecated": false,

facets/tests/checker.nf

@@ -34,7 +34,7 @@
 /* this block is auto-generated based on info from pkg.json where   */
 /* changes can be made if needed, do NOT modify this block manually */
 nextflow.enable.dsl = 2
-version = '0.3.0'  // package version
+version = '0.4.0'
 
 container = [
     'ghcr.io': 'ghcr.io/icgc-argo-structural-variation-cn-wg/icgc-argo-sv-copy-number.facets'
@@ -66,11 +66,12 @@ process file_smart_diff {
   output:
     stdout()
 
-  script:
-    """
-    diff ${output_file} ${expected_file} \
+  shell:
+    '''
+    tar -zxvf !{output_file} test.out
+    diff $(basename -s .tgz !{output_file}).out !{expected_file} \
       && ( echo "Test PASSED" && exit 0 ) || ( echo "Test FAILED, output file mismatch." && exit 1 )
-    """
+    '''
 }
 
 
@@ -87,7 +88,7 @@ workflow checker {
     )
 
     file_smart_diff(
-      facets.out.output_summary,
+      facets.out.facets_results,
       expected_output
     )
 }