Merge pull request #893 from maxplanck-ie/3primeseq_KS

3primeseq ks

.ci_stuff/test_dag.sh

@@ -215,8 +215,10 @@ if [ ${PIPESTATUS[0]} -ne 0 ] || [ $WC -ne 657 ]; then exit 1 ; fi
 WC=`mRNA-seq --mode alignment,alignment-free -i PE_input -o output --rMats --sampleSheet .ci_stuff/test_sampleSheet_multiComp.tsv --snakemakeOptions " --dryrun --conda-prefix /tmp" .ci_stuff/organism.yaml | tee >(cat 1>&2) | grep -v "Conda environment" | sed '/^\s*$/d' | wc -l`
 if [ ${PIPESTATUS[0]} -ne 0 ] || [ $WC -ne 869 ]; then exit 1 ; fi
 # three prime sequencing
-WC=`mRNA-seq -i PE_input -o output --three-prime-seq --sampleSheet .ci_stuff/test_sampleSheet.tsv --snakemakeOptions " --dryrun --conda-prefix /tmp" .ci_stuff/organism.yaml | tee >(cat 1>&2) | grep -v "Conda environment" | sed '/^\s*$/d' | wc -l`
-if [ ${PIPESTATUS[0]} -ne 0 ] || [ $WC -ne 1332 ]; then exit 1 ; fi
+WC=`mRNA-seq -i PE_input -o output --mode three-prime-seq --sampleSheet .ci_stuff/test_sampleSheet.tsv --snakemakeOptions " --dryrun --conda-prefix /tmp" .ci_stuff/organism.yaml | tee >(cat 1>&2) | grep -v "Conda environment" | sed '/^\s*$/d' | wc -l`
+if [ ${PIPESTATUS[0]} -ne 0 ] || [ $WC -ne 618 ]; then exit 1 ; fi
+WC=`mRNA-seq -i PE_input -o output --mode three-prime-seq,deepTools_qc --sampleSheet .ci_stuff/test_sampleSheet.tsv --snakemakeOptions " --dryrun --conda-prefix /tmp" .ci_stuff/organism.yaml | tee >(cat 1>&2) | grep -v "Conda environment" | sed '/^\s*$/d' | wc -l`
+if [ ${PIPESTATUS[0]} -ne 0 ] || [ $WC -ne 1199 ]; then exit 1 ; fi
 #allelic
 WC=`mRNA-seq -m allelic-mapping,deepTools_qc -i PE_input -o output --snakemakeOptions " --dryrun --conda-prefix /tmp" --VCFfile allelic_input/file.vcf.gz --strains strain1,strain2 .ci_stuff/organism.yaml | tee >(cat 1>&2) | grep -v "Conda environment" | sed '/^\s*$/d' | wc -l`
 if [ ${PIPESTATUS[0]} -ne 0 ] || [ $WC -ne 1357 ]; then exit 1 ; fi

snakePipes/workflows/mRNA-seq/Snakefile

@@ -112,7 +112,7 @@ else:
     include: os.path.join(maindir, "shared", "rules", "featureCounts.snakefile")
 
 # Three Prime Sequencing mode
-if "threePrimeSeq" in mode:
+if "three-prime-seq" in mode:
     include: os.path.join(maindir, "shared", "rules", "three_prime_seq.snakefile")
 
 ##Genomic_contamination
@@ -292,7 +292,7 @@ def run_deepTools_qc():
 
 def run_threePrimeSeq():
     file_list = []
-    if "threePrimeSeq" in mode: 
+    if "three-prime-seq" in mode: 
         file_list += [
             "three_prime_seq/combined_polyA.png",
             "three_prime_seq/counts.tsv",

snakePipes/workflows/mRNA-seq/defaults.yaml

@@ -36,8 +36,6 @@ trimmer: cutadapt
 trimmerOptions:
 
 ## three prime seq options
-## whether to conduct three prime sequencing at all
-threePrimeSeq: False
 # fastp options for three prime sequencing only
 threePrimeTrimmerOptions: -x --poly_x_min_len 6 -3 5 -q 5 -l 20 -y
 # STAR fastp options for three prime sequencing only

snakePipes/workflows/mRNA-seq/mRNA-seq

@@ -31,8 +31,7 @@ def parse_args(defaults={"verbose": False, "configFile": None,
                          "fromBAM": False, "bamExt": ".bam", "pairedEnd": True,
                          "UMIDedup": False,
                          "UMIDedupOpts": "", "bcPattern": "NNNNCCCCCCCCC",
-                         "UMIDedupSep": "_", "UMIBarcode": False, "rMats": False, 
-                         "threePrimeSeq": False}):
+                         "UMIDedupSep": "_", "UMIBarcode": False, "rMats": False}):
     """
     Parse arguments from the command line.
     """
@@ -50,7 +49,7 @@ def parse_args(defaults={"verbose": False, "configFile": None,
     # Workflow options
     optional = parser.add_argument_group('Options')
     optional.add_argument("-m", "--mode",
-                          help="workflow running modes (available: 'alignment-free, alignment, allelic-mapping, deepTools_qc')"
+                          help="workflow running modes (available: 'alignment-free, alignment, allelic-mapping, deepTools_qc, three-prime-seq')"
                           " (default: '%(default)s')",
                           default=defaults["mode"])
 
@@ -122,13 +121,6 @@ def parse_args(defaults={"verbose": False, "configFile": None,
                           help="Run differential splicing analysis using rMats-turbo. Note that this flag requires --sampleSheet to be specified.",
                           default=defaults["rMats"])
 
-    optional.add_argument("--three-prime-seq",
-                          dest="three_prime_seq",
-                          action="store_true",
-                          help="Assume library is from 3' sequencing data (e.g. Lexogen QuantSeq 3' mRNA-seq), using "
-                          "methods and scripts codeveloped by Valerie Hilgers, Devon Ryan, and Andrew Rezansoff. ",
-                          default=defaults["threePrimeSeq"])
-
     return parser
 
 
@@ -156,7 +148,7 @@ def main():
         args.SNPfile = os.path.abspath(args.SNPfile)
         args.NMaskedIndex = os.path.abspath(args.NMaskedIndex)
     modeTemp = args.mode.split(",")
-    validModes = set(["alignment", "alignment-free", "deepTools_qc", "allelic-mapping"])
+    validModes = set(["alignment", "alignment-free", "deepTools_qc", "allelic-mapping","three-prime-seq"])
     for mode in modeTemp:
         if mode not in validModes:
             sys.exit("{} is not a valid mode!\n".format(mode))
@@ -168,16 +160,15 @@ def main():
         args.aligner = "EXTERNAL_BAM"
     if args.rMats and not args.sampleSheet:
         sys.exit("--rMats flag requires a sampleSheet (specified with --sampleSheet).\n")
-    if args.three_prime_seq:
+    if "three_prime_seq" in mode:
         if not args.sampleSheet:
-            sys.exit("--three-prime-seq requires a sampleSheet "
+            sys.exit("mode three-prime-seq requires a sampleSheet "
                      "(specified with --sampleSheet).\n")
-        args.aligner = "STAR"
-        args.alignerOptions = defaults['threePrimeAlignerOptions']
-        args.trimmerOptions = defaults['threePrimeTrimmerOptions']
-        args.trimmer = "fastp"
-        args.trim = True
-        args.mode += ",threePrimeSeq"
+        aligner = "STAR"
+        alignerOptions = defaults['threePrimeAlignerOptions']
+        trimmerOptions = defaults['threePrimeTrimmerOptions']
+        trimmer = "fastp"
+        trim = True
 
     ## End workflow-specific checks