Merge pull request #92 from icgc-argo/payload-gen-dna-seq-qc.0.5.1.0

Payload gen dna seq qc.0.5.1.0

Author: junjun-zhang

…76aa24d3eed.lane.bam.ubam_qc_metrics.tgz …19a2ce8bbb7.lane.bam.ubam_qc_metrics.tgztests/data/C0HVY.2.6d3111fbcbc26c34bb97d76aa24d3eed.lane.bam.ubam_qc_metrics.tgz renamed to tests/data/C0HVY.2.b2e20ab4ae30dbcf1ee2319a2ce8bbb7.lane.bam.ubam_qc_metrics.tgz tests/data/C0HVY.2.6d3111fbcbc26c34bb97d76aa24d3eed.lane.bam.ubam_qc_metrics.tgz renamed to tests/data/C0HVY.2.b2e20ab4ae30dbcf1ee2319a2ce8bbb7.lane.bam.ubam_qc_metrics.tgz

@@ -22,8 +22,8 @@
  *   Junjun Zhang <junjun.zhang@oicr.on.ca>
  */
 
-nextflow.preview.dsl=2
-version = '0.4.1.0'
+nextflow.enable.dsl=2
+version = '0.5.1.0'
 
 params.seq_experiment_analysis = ""
 params.qc_files = []
@@ -32,12 +32,14 @@ params.wf_version = ""
 params.container_version = ""
 params.cpus = 1
 params.mem = 1  // GB
+params.publish_dir = ""
 
 
 process payloadGenDnaSeqQc {
   container "quay.io/icgc-argo/payload-gen-dna-seq-qc:payload-gen-dna-seq-qc.${params.container_version ?: version}"
   cpus params.cpus
   memory "${params.mem} GB"
+  publishDir "${params.publish_dir}/${task.process.replaceAll(':', '_')}", enabled: "${params.publish_dir ? true : ''}"
 
   input:
     path seq_experiment_analysis

…574a01a325e.lane.bam.ubam_qc_metrics.tgz …536bfd08019.lane.bam.ubam_qc_metrics.tgztests/data/D0RE2.1.156db267eead7aea8e05b574a01a325e.lane.bam.ubam_qc_metrics.tgz renamed to tests/data/D0RE2.1.604a62a7e9472e9e2818a536bfd08019.lane.bam.ubam_qc_metrics.tgz tests/data/D0RE2.1.156db267eead7aea8e05b574a01a325e.lane.bam.ubam_qc_metrics.tgz renamed to tests/data/D0RE2.1.604a62a7e9472e9e2818a536bfd08019.lane.bam.ubam_qc_metrics.tgz

@@ -94,13 +94,16 @@ def get_rg_id_from_ubam_qc(tar, metadata):
 
     for rg in metadata.get("read_groups"):
         rg_id_in_bam = rg.get("read_group_id_in_bam") if rg.get("read_group_id_in_bam") else rg.get("submitter_read_group_id")
-        md5sum_from_metadata = hashlib.md5(rg_id_in_bam.encode('utf-8')).hexdigest()
+        seq_file_name = rg.get("file_r1")
+        bam_name = seq_file_name if seq_file_name.endswith('.bam') else ''
+        md5sum_from_metadata = hashlib.md5(("%s %s" % (bam_name, rg_id_in_bam)).encode('utf-8')).hexdigest()
         if md5sum_from_metadata == md5sum_from_filename:
             return rg.get("filename_friendly_rg_id")
 
     # up to this point no match found, then something wrong
     sys.exit('Error: unable to match ubam qc metric tar "%s" to read group id' % tar_basename)
 
+
 def get_dupmetrics(file_to_upload):
     library = []
     with tarfile.open(file_to_upload, 'r') as tar:

…43e7fd7060a.lane.bam.ubam_qc_metrics.tgz …c1c5b7fd5eb.lane.bam.ubam_qc_metrics.tgztests/data/D0RH0.2.db2e15cf9008af2ecda8743e7fd7060a.lane.bam.ubam_qc_metrics.tgz renamed to tests/data/D0RH0.2.da2fc67e6d0a0ff8b4e4dc1c5b7fd5eb.lane.bam.ubam_qc_metrics.tgz tests/data/D0RH0.2.db2e15cf9008af2ecda8743e7fd7060a.lane.bam.ubam_qc_metrics.tgz renamed to tests/data/D0RH0.2.da2fc67e6d0a0ff8b4e4dc1c5b7fd5eb.lane.bam.ubam_qc_metrics.tgz

@@ -22,15 +22,15 @@
  *   Junjun Zhang <junjun.zhang@oicr.on.ca>
  */
 
-nextflow.preview.dsl=2
+nextflow.enable.dsl=2
 
 params.seq_experiment_analysis = ""
 params.qc_files = [ ]
 params.wf_name = "dna-seq-alignment"
 params.wf_version = "0.5.0-dev"
 params.container_version = ""
 
-include payloadGenDnaSeqQc from "../payload-gen-dna-seq-qc" params(params)
+include {payloadGenDnaSeqQc} from "../payload-gen-dna-seq-qc" params(params)
 
 workflow {
   main:
@@ -40,7 +40,4 @@ workflow {
       params.wf_name,
       params.wf_version
     )
-  publish:
-    payloadGenDnaSeqQc.out.payload to: 'outdir', overwrite: true
-    payloadGenDnaSeqQc.out.qc_files to: 'outdir', overwrite: true
 }

tools/payload-gen-dna-seq-qc/payload-gen-dna-seq-qc.nf

@@ -6,6 +6,7 @@
                 "data/grch38-aligned.merged-multi-library.duplicates_metrics.tgz",
                 "data/SA610149.3.20200214.wgs.grch38.cram.oxog_metrics.tgz"
               ],
+  "publish_dir": "output",
   "cpus": 1,
   "mem": 0.5
 }