correct fastq list/str handling and add whitelist info for non-10X

Snakefile

@@ -48,7 +48,7 @@ def _get_config(sample, item):
     return CHEMISTRY[DEFAULTS["chemistry"]][item]
   except KeyError:
     return DEFAULTS[item]
-  
+
 # assemble outputs for rule all
 SAMPLE_OUTS = []
 for x in SAMPLES:

chemistry.yaml

@@ -30,24 +30,28 @@ chromiumV2:
     STAR_R1: --soloUMIlen 10 --clip5pNbases 56 0 --soloCBstart 1 --soloCBlen 16 --soloUMIstart 17 --outFilterMultimapNmax 1  --outFilterMismatchNmax 999  --outFilterMismatchNoverReadLmax 0.2
     STAR_R2: --soloUMIlen 10
 dropseq:
+  bc_whitelist: None
   illumina:
     filter_R1_length: 50
     STAR_R1: --soloUMIlen 8 --clip5pNbases 50 0 --soloCBstart 1 --soloCBlen 12 --soloUMIstart 13 --outFilterMultimapNmax 1  --outFilterMismatchNmax 999  --outFilterMismatchNoverReadLmax 0.2
     STAR_R2: --soloUMIlen 8 --soloCBstart 1 --soloCBlen 12 --soloUMIstart 13
 microwellseq:
+  bc_whitelist: None
   bc_cut: CGACTCACTACAGGG...TCGGTGACACGATCG
   illumina:
     filter_R1_length: 54
     STAR_R1: --soloUMIlen 6 --clip5pNbases 54 0 --soloCBstart 1 --soloCBlen 18 --soloUMIstart 19 --outFilterMultimapNmax 1  --outFilterMismatchNmax 999  --outFilterMismatchNoverReadLmax 0.2
     STAR_R2:  --soloUMIlen 6 --soloCBstart 1 --soloCBlen 18 --soloUMIstart 19
 bd:
+  bc_whitelist: None
   bc_cut: ACTGGCCTGCGA...GGTAGCGGTGACA
   illumina:
     filter_R1_length: 53
     STAR_R1: --soloUMIlen 8 --clip5pNbases 53 0 --soloCBstart 1 --soloCBlen 27 --soloUMIstart 28 --outFilterMultimapNmax 1  --outFilterMismatchNmax 999  --outFilterMismatchNoverReadLmax 0.2
     STAR_R2: --soloUMIlen 8 --soloCBstart 1 --soloCBlen 27 --soloUMIstart 28
 indrop:
+  bc_whitelist: None
   illumina:
     filter_R1_length: 32
     STAR_R1: --soloUMIlen 6 --clip5pNbases 32 0 --soloCBstart 1 --soloCBlen 8 --soloUMIstart 9 --outFilterMultimapNmax 1  --outFilterMismatchNmax 999  --outFilterMismatchNoverReadLmax 0.2
-    STAR_R2: --soloUMIlen 6 --soloCBstart 1 --soloCBlen 8 --soloUMIstart 9
+    STAR_R2: --soloUMIlen 6 --soloCBstart 1 --soloCBlen 8 --soloUMIstart 9

config.yaml

@@ -14,15 +14,15 @@ STAR:
 
 STAR_INDEX:
 # path to STAR genome index
-  "index/cr2020A_star"
+  "/pl/active/amc_heme/ref/cr2020A_star"
 
 WHITELIST_V3:  
 # path to Chromium V3 whitelist
-  "whitelist/3M-february-2018.txt"
+  "/pl/active/amc_heme/ref/3M-february-2018.txt"
 
 WHITELIST_V2:
 # path to Chromium V2 whitelist
-  "whitelist/737K-august-2016.txt"
+  "/pl/active/amc_heme/ref/737K-august-2016.txt"
 
 POLYA_SITES:
 # polya_db 3 on GRCh38 with 5 bases upstream and 3 bases
@@ -53,7 +53,7 @@ SAMPLES:
 #   star_args (STAR_R1, STAR_R2, STAR_paired)
 #   extra star_args (STAR_R1_extra_args, STAR_R2_extra_args, STAR_paired_extra_args)
   test:
-    basename: sample
+    basename: sample-
     platform: illumina
     chemistry: chromiumV2
   test2:
@@ -73,4 +73,4 @@ report_section_order:
   star:
     order: 100
   featureCounts:
-    order: -1000
+    order: -1000

rules/count.snake

@@ -147,9 +147,10 @@ rule filter_R1:
     mem_mb = 8000
   shell:
     """
-    if [[ {params.length} == 'False') ]]; then
+    if [[ {params.length} == 'False' ]]; then
       ln -s {input} {output}
     else
+      samtools index {input}
       samtools view -h {input} | grep -v 'CB:Z:-\|UB:Z:-' | samtools view -b - > {params.temp}
       set +e
       python3 inst/scripts/filter_bam_correct.py -i {params.temp} -o {params.temp2} -l {params.length} -s -c 20
@@ -183,6 +184,7 @@ rule filter_R2:
     mem_mb = 8000
   shell:
     """
+    samtools index {input}
     samtools view -h {input} | grep -v 'CB:Z:-\|UB:Z:-' | samtools view -b - > {params.temp}
     samtools index {params.temp}
     python3 inst/scripts/filter_bam.py -i {params.temp} -o {output}
@@ -210,9 +212,10 @@ rule filter_paired:
     mem_mb = 8000
   shell:
     """
-    if [[ {params.length} == 'False') ]]; then
+    if [[ {params.length} == 'False' ]]; then
       ln -s {input} {output}
     else
+      samtools index {input}
       samtools view -h {input} | grep -v 'CB:Z:-\|UB:Z:-' | samtools view -b - > {params.temp}
       set +e
       python3 inst/scripts/filter_bam_correct.py -i {params.temp} -o {params.temp2} -l {params.length}

rules/cutadapt_star.snake

@@ -7,7 +7,10 @@ import pandas as pd
 
 """ Extract per-sample fastq paths """
 def _get_fq_paths(wildcards):
-    fqs = map(lambda x: os.path.join(DATA, x + "*R1*"), SAMPLES[wildcards.sample]["basename"])
+    basename = SAMPLES[wildcards.sample]["basename"]
+    if isinstance(basename, str):
+      basename = [basename]
+    fqs = map(lambda x: os.path.join(DATA, x + "*R1*"), basename)
     fqs = map(lambda x: glob.glob(x), fqs)
     fqs = list(chain.from_iterable(fqs))