Initial code

workflow/rna-seq.nf

@@ -20,6 +20,7 @@ Channel.from(params.repRID)
   .into {
     repRID_getBag
     repRID_getData
+    repRID_parseMetadata
     repRID_trimData
   }
 
@@ -33,7 +34,6 @@ derivaConfig = Channel.fromPath("${baseDir}/conf/replicate_export_config.json")
  * getData: get bagit file from consortium
  */
 process getBag {
-  executor 'local'
   tag "${repRID_getBag}"
   publishDir "${logsDir}/getBag", mode: 'symlink', pattern: "${repRID_getBag}.getBag.err"
 
@@ -66,7 +66,6 @@ process getData {
 
   input:
     val repRID_getData
-    executor 'local'
     path cookies, stageAs: 'deriva-cookies.txt' from bdbag
     path bagit
 
@@ -77,7 +76,6 @@ process getData {
     file("**/Experiment.csv") into experimentMeta
     file ("${repRID_getData}.getData.err")
 
-
   script:
     """
     hostname >>${repRID_getData}.getData.err
@@ -94,6 +92,29 @@ process getData {
     """
 }
 
+/*
+ * parseMetadata: parses metadata to extract experiment parameters
+*/
+process parseMetadata {
+  tag "${repRID_parseMetadata}"
+  publishDir "${logsDir}/parseMetadata", mode: 'symlink', pattern: "${repRID_parseMetadata}.parseMetadata.err"
+
+  input:
+    val repRID_parseMetadata
+    file fileMeta
+    file experimentSettingsMeta
+    file experimentMeta
+
+  output:
+
+  script:
+    """
+    hostname >>${repRID_parseMetadata}.parseMetadata.err
+    ulimit -a >>${repRID_parseMetadata}.parseMetadata.err
+    """
+
+}
+
 /*
  * trimData: trims any adapter or non-host sequences from the data
 */

workflow/scripts/parseMeta.py

+#!/usr/bin/env python3
+
+import argparse
+import pandas as pd
+
+def get_args():
+    parser = argparse.ArgumentParser()
+    parser.add_argument('-r', '--repRID',help="The replicate RID.",required=True)
+    parser.add_argument('-m', '--metaFile',help="The metadata file to extract.",required=True)
+    parser.add_argument('-p', '--parameter',help="The parameter to extract.",required=True)
+    args = parser.parse_args()
+    return args
+
+
+def main():
+    args = get_args()
+    metaFile = pd.read_csv(args.metaFile,sep="\t",header=None)
+    if (args.parameter == "repRID"):
+        if (len(metaFile.Replicate_RID.unique()) > 1):
+            #ERROR
+        if not (metaFile.Replicate_RID == arg$repRID):
+            #ERROR
+        if (len(fileFile[fileFile["File_Type"] == "FastQ"].RID) > 2):
+            #ERROR
+
+
+if __name__ == '__main__':
+    main()
\ No newline at end of file