Extract read length from submitter metadata

.gitlab-ci.yml

@@ -38,7 +38,8 @@ parseMetadata:
   - stranded=$(singularity run 'docker://bicf/python3:2.0.1_indev' python3 ./workflow/scripts/parseMeta.py -r Replicate_RID -m "./test_data/meta/metaTest.csv" -p stranded)
   - spike=$(singularity run 'docker://bicf/python3:2.0.1_indev' python3 ./workflow/scripts/parseMeta.py -r Replicate_RID -m "./test_data/meta/metaTest.csv" -p spike)
   - species=$(singularity run 'docker://bicf/python3:2.0.1_indev' python3 ./workflow/scripts/parseMeta.py -r Replicate_RID -m "./test_data/meta/metaTest.csv" -p species)
-  - echo -e "${endsMeta},${endsManual},${stranded},${spike},${species},${exp},${study},${rep}" > design.csv
+  - readLength=$(singularity run 'docker://bicf/python3:2.0.1_indev' python3 ./workflow/scripts/parseMeta.py -r Replicate_RID -m "./test_data/meta/metaTest.stageNew.csv" -p readLength)
+  - echo -e "${endsMeta},${endsManual},${stranded},${spike},${species},${readLength},${exp},${study},${rep}" > design.csv
   - pytest -m parseMetadata
 
 inferMetadata:

workflow/rna-seq.nf

@@ -237,8 +237,12 @@ process parseMetadata {
     species=\$(python3 ${script_parseMeta} -r ${repRID} -m "${experiment}" -p species)
     echo -e "LOG: species metadata parsed: \${species}" >> ${repRID}.parseMetadata.log
 
+    # get read length metadata
+    readLength=\$(python3 ${script_parseMeta} -r ${repRID} -m "${experiment}" -p readLength)
+    echo -e "LOG: read length metadata parsed: \${readLength}" >> ${repRID}.parseMetadata.log
+
     # gave design file
-    echo -e "\${endsMeta},\${endsManual},\${stranded},\${spike},\${species},\${exp},\${study}" > design.csv
+    echo -e "\${endsMeta},\${endsManual},\${stranded},\${spike},\${species},\${readLength},\${exp},\${study}" > design.csv
     """
 }
 
@@ -248,6 +252,7 @@ endsManual = Channel.create()
 strandedMeta = Channel.create()
 spikeMeta = Channel.create()
 speciesMeta = Channel.create()
+readLengthMeta = Channel.create()
 expRID = Channel.create()
 studyRID = Channel.create()
 metadata.splitCsv(sep: ",", header: false).separate(
@@ -256,6 +261,7 @@ metadata.splitCsv(sep: ",", header: false).separate(
   strandedMeta,
   spikeMeta,
   speciesMeta,
+  readLengthMeta,
   expRID,
   studyRID
 )

workflow/scripts/parseMeta.py

@@ -102,5 +102,10 @@ def main():
             exit(1)
         print(species)
 
+    # Get read length metadata from 'Experiment Settings.csv'
+    if (args.parameter == "readLength"):
+        readLength = metaFile.Read_Length.unique()
+        print(readLength)
+
 if __name__ == '__main__':
     main()

workflow/tests/test_parseMetadata.py

@@ -17,7 +17,7 @@ def readLine(fileName):
     data = False
     file = open(fileName, "r")
     line = file.readline()
-    if line.strip() == "uk,se,unstranded,no,Homo sapiens,Experiment_RID,Study_RID,Replicate_RID":
+    if line.strip() == "uk,se,unstranded,no,Homo sapiens,75,Experiment_RID,Study_RID,Replicate_RID":
         data = True
 
     return data