test(picard): Refactor markduplicates to use pytest-workflow

software/picard/markduplicates/test/input/test.paired_end.sorted.bam

@@ -1 +0,0 @@
-../../../../../tests/data/bam/test.paired_end.sorted.bam

software/picard/markduplicates/test/main.nf

@@ -1,18 +0,0 @@
-#!/usr/bin/env nextflow
-
-nextflow.enable.dsl = 2
-
-include { PICARD_MARKDUPLICATES } from '../main.nf' addParams( options: [:] )
-
-workflow test {
-
-    def input = []
-    input = [ [ id:'test', single_end:false ], // meta map
-              file("${baseDir}/input/test.paired_end.sorted.bam", checkIfExists: true) ]
-
-    PICARD_MARKDUPLICATES ( input )
-}
-
-workflow {
-    test()
-}

software/picard/markduplicates/test/nextflow.config

@@ -1,20 +0,0 @@
-
-params {
-    outdir = "output/"
-    publish_dir_mode = "copy"
-    enable_conda = false
-}
-
-profiles {
-    conda  {
-        params.enable_conda = true
-    }
-    docker {
-        docker.enabled = true
-        docker.runOptions = '-u \$(id -u):\$(id -g)'
-    }
-    singularity {
-        singularity.enabled = true
-        singularity.autoMounts = true
-    }
-}

software/picard/markduplicates/test/output/picard/test.MarkDuplicates.metrics.txt

@@ -1,13 +0,0 @@
-## htsjdk.samtools.metrics.StringHeader
-# MarkDuplicates INPUT=[test.paired_end.sorted.bam] OUTPUT=test.bam METRICS_FILE=test.MarkDuplicates.metrics.txt    MAX_SEQUENCES_FOR_DISK_READ_ENDS_MAP=50000 MAX_FILE_HANDLES_FOR_READ_ENDS_MAP=8000 SORTING_COLLECTION_SIZE_RATIO=0.25 TAG_DUPLICATE_SET_MEMBERS=false REMOVE_SEQUENCING_DUPLICATES=false TAGGING_POLICY=DontTag CLEAR_DT=true DUPLEX_UMI=false ADD_PG_TAG_TO_READS=true REMOVE_DUPLICATES=false ASSUME_SORTED=false DUPLICATE_SCORING_STRATEGY=SUM_OF_BASE_QUALITIES PROGRAM_RECORD_ID=MarkDuplicates PROGRAM_GROUP_NAME=MarkDuplicates READ_NAME_REGEX=<optimized capture of last three ':' separated fields as numeric values> OPTICAL_DUPLICATE_PIXEL_DISTANCE=100 MAX_OPTICAL_DUPLICATE_SET_SIZE=300000 VERBOSITY=INFO QUIET=false VALIDATION_STRINGENCY=STRICT COMPRESSION_LEVEL=5 MAX_RECORDS_IN_RAM=500000 CREATE_INDEX=false CREATE_MD5_FILE=false GA4GH_CLIENT_SECRETS=client_secrets.json USE_JDK_DEFLATER=false USE_JDK_INFLATER=false
-## htsjdk.samtools.metrics.StringHeader
-# Started on: Fri Aug 07 15:11:32 GMT 2020
-
-## METRICS CLASS	picard.sam.DuplicationMetrics
-LIBRARY	UNPAIRED_READS_EXAMINED	READ_PAIRS_EXAMINED	SECONDARY_OR_SUPPLEMENTARY_RDS	UNMAPPED_READS	UNPAIRED_READ_DUPLICATES	READ_PAIR_DUPLICATES	READ_PAIR_OPTICAL_DUPLICATES	PERCENT_DUPLICATION	ESTIMATED_LIBRARY_SIZE
-Unknown Library	0	10000	0	0	0	0	0	0	
-
-## HISTOGRAM	java.lang.Double
-set_size	all_sets	non_optical_sets
-1.0	10000	10000
-

tests/software/picard/main.nf

@@ -4,6 +4,7 @@ nextflow.enable.dsl = 2
 
 include { PICARD_MERGESAMFILES } from '../../../software/picard/mergesamfiles/main.nf' addParams( options: [:] )
 include { PICARD_COLLECTMULTIPLEMETRICS } from '../../../software/picard/collectmultiplemetrics/main.nf' addParams( options: [:] )
+include { PICARD_MARKDUPLICATES } from '../../../software/picard/markduplicates/main.nf' addParams( options: [:] )
 
 workflow test_picard_mergesamfiles {
 
@@ -27,3 +28,12 @@ workflow test_picard_collectmultiplemetrics {
         file("${launchDir}/tests/data/fasta/E_coli/NC_010473.fa", checkIfExists: true)
     )
 }
+
+workflow test_picard_markduplicates  {
+
+    def input = []
+    input = [ [ id:'test', single_end:false ], // meta map
+              file("${launchDir}/tests/data/bam/test.paired_end.sorted.bam", checkIfExists: true) ]
+
+    PICARD_MARKDUPLICATES ( input )
+}

tests/software/picard/test.yml

@@ -23,3 +23,13 @@
     - path: output/picard/test.CollectMultipleMetrics.quality_by_cycle_metrics
     - path: output/picard/test.CollectMultipleMetrics.quality_distribution.pdf
     - path: output/picard/test.CollectMultipleMetrics.quality_distribution_metrics
+
+- name: Run picard MarkDuplicates
+  command: nextflow run ./tests/software/picard -profile docker -entry test_picard_markduplicates -c tests/config/nextflow.config
+  tags:
+    - picard
+    - picard_markduplicates
+  files:
+    - path: output/picard/test.MarkDuplicates.metrics.txt
+    - path: output/picard/test.bam
+      md5sum: 50407a1ee722f2bf6a20471c8a7fd6b0