Merge pull request #923 from maxplanck-ie/dev_KS

Removed mode Gruen from scRNAseq entirely

snakePipes/workflows/scRNAseq/cluster.yaml

@@ -1,27 +1,15 @@
 STAR:
     memory: 6G
-sc_bam_featureCounts_genomic:
-    memory: 4G
 bamPE_fragment_size:
     memory: 3G
-combine_sample_counts:
-    memory: 10G
-cluster_cells_raceid:
-    memory: 6G
-cluster_cells_monocle:
-    memory: 6G
 annotation_bed2fasta:
     memory: 4G
-filter_cells_monocle:
-    memory: 16G
-filter_cells_raceid:
-    memory: 12G
 STARsolo:
     memory: 6G
 SalmonAlevin:
-    memory: 6G
+    memory: 10G
 AlevinForVelocity:
-    memory: 6G
+    memory: 10G
 cellsort_bam:
     memory: 10G
 velocyto:

snakePipes/workflows/scRNAseq/defaults.yaml

@@ -30,18 +30,10 @@ reads: ["_R1","_R2"]
 mode: STARsolo
 ## Number of reads to downsample from each FASTQ file
 downsample:
-## Options for trimming
-trim: False
-trimmer: cutadapt
-trimmerOptions: -a A{'30'}
 ## --twopassMode Basic is not compatible with --outStd in all STAR versions
 alignerOptions: ""
 ## further options
 filterGTF: "-v -P 'decay|pseudogene' "
-cellBarcodeFile:
-cellBarcodePattern: "NNNNNNXXXXXX"
-splitLib: False
-cellNames:
 ##mode STARsolo options
 myKit: CellSeq384
 BCwhiteList:
@@ -51,17 +43,12 @@ skipVelocyto: False
 alevinLibraryType: "ISR"
 prepProtocol: "chromiumV3"
 expectCells: 
-readLengthFrx: 0.2
 #generic options
 libraryType: 1
 bwBinSize: 10
 verbose: False
 plotFormat: pdf
 dnaContam: False
-## Parameters for th statistical analysis
-cellFilterMetric: gene_universe
-#Option to skip RaceID to save time
-skipRaceID: False
 #umi_tools options:
 UMIBarcode: False
 bcPattern: NNNNCCCCCCCCC #default: 4 base umi barcode, 9 base cell barcode (eg. RELACS barcode)

snakePipes/workflows/scRNAseq/internals.snakefile

@@ -16,20 +16,7 @@ import sys
 ## we trim only R2 with transfered barcode info under "FASTQ_barcoded"
 ## only cutadapt is supported right now due to poly-A trimming 
 
-if mode == "Gruen":
-    fastq_dir = "FASTQ_barcoded"
-    if trim:
-        fastq_indir_trim = "FASTQ_barcoded"
-        if trimmer == "trimgalore":
-            fastq_dir = "FASTQ_TrimGalore"
-        elif trimmer == "cutadapt":
-            fastq_dir = "FASTQ_Cutadapt"
-        elif trimmer == "fastp":
-            fastq_dir = "FASTQ_fastp"
-    else:
-        fastq_indir_trim = None	
-    aligner = "STAR_genomic"
-elif mode == "STARsolo":
+if mode == "STARsolo":
     fastq_indir_trim = None
     fastq_dir = "originalFASTQ"
     aligner = "STARsolo"
@@ -52,12 +39,6 @@ if not cf.is_paired(infiles,ext,reads):
     print("This workflow requires paired-end read data!")
     exit(1)
 
-## print deprecation message for modeGruen
-if mode=="Gruen":
-    print("Mode Gruen has been deprecated! Please use mode STARsolo or Alevin for your analysis.")
-    exit(1)
-
-
 if mode == "STARsolo":
     if myKit == "10Xv2":
         BCwhiteList = os.path.join(maindir,"workflows","scRNAseq","10x_737K-august-2016.txt")
@@ -84,21 +65,3 @@ pairedEnd = False
 ##some rules use a hardcoded reads[0] for SE
 reads = reads[::-1]
 
-### barcode pattern extraction #################################################
-pattern = re.compile("[N]+")
-
-if pattern.search(cellBarcodePattern) is not None:
-    UMI_offset = pattern.search(cellBarcodePattern).start() + 1 
-    UMI_length = pattern.search(cellBarcodePattern).end() - UMI_offset + 1
-else:
-    print("Provided barcode pattern does not contain any 'N'! Exit...\n")
-    exit(1)
-
-pattern = re.compile("[X]+")
-
-if pattern.search(cellBarcodePattern) is not None:
-    CELLI_offset = pattern.search(cellBarcodePattern).start() + 1
-    CELLI_length = pattern.search(cellBarcodePattern).end() - CELLI_offset + 1 
-else:
-    print("Provided barcode pattern does not contain any 'X'! Exit...\n")
-    exit(1)