update config and Snakefile to reflect new naming

Snakefile

@@ -6,6 +6,7 @@ configfile: "config.yaml"
 
 DATA = config["DATA"]
 RESULTS = config["RESULTS"]
+PAIRED_SAMPLES = config["PAIRED_SAMPLES"]
 R1_SAMPLES = config["R1_SAMPLES"]
 R2_SAMPLES = config["R2_SAMPLES"]
 STAR_INDEX = config["STAR_INDEX"]
@@ -14,12 +15,18 @@ FASTQS = config["FASTQS"]
 WHITELIST_V2 = config["WHITELIST_V2"]
 WHITELIST_V3 = config["WHITELIST_V3"]
 STAR = config["STAR"]
-READS = ["R1", "R2"]
+READS = ["paired", "R1", "R2"]
 
 import json
 with open('chemistry.json') as fp:
    chemistry = json.load(fp)
 
+# paired positional approach
+PAIREDs = []
+if PAIRED_SAMPLES:
+  PAIREDs.extend(expand("{results}/counts/{sample}_{read}_counts.tsv.gz", results = RESULTS, sample = PAIRED_SAMPLES, read = "paired"))
+  PAIREDs.extend(expand("{results}/{sample}/{sample}_{read}_Aligned.sortedByCoord.out.bam", results = RESULTS, sample = PAIRED_SAMPLES, read = "paired"))
+  PAIREDs.extend(expand("{results}/bed/{sample}_{read}.bed.gz", results = RESULTS, sample = PAIRED_SAMPLES, read = "paired"))  
 # read 1 positional approach
 R1s = []
 if R1_SAMPLES:
@@ -33,16 +40,14 @@ if R2_SAMPLES:
   R2s.extend(expand("{results}/{sample}/{sample}_{read}_Aligned.sortedByCoord.out.bam", results = RESULTS, sample = R2_SAMPLES, read = "R2"))
   R2s.extend(expand("{results}/bed/{sample}_{read}.bed.gz", results = RESULTS, sample = R2_SAMPLES, read = "R2"))
 # combine
-R12s = R1s + R2s # +expand("{results}/report/multiqc_report.html", results = RESULTS)
-R12s = R12s + expand("{data}/{sample}_R1.fastq.gz", data = DATA, sample = R1_SAMPLES) + expand("{data}/{sample}_R2.fastq.gz", data = DATA, sample = R1_SAMPLES)
-print(R12s)
+R12Ps = PAIREDs + R1s + R2s #+ expand("{results}/report/multiqc_report.html", results = RESULTS)
+print(R12Ps)
 
 rule all:
   input:
     R12s = R12s
 
 include: "rules/check_versions.snake"
-include: "rules/download.snake"
 include: "rules/cutadapt_star.snake"
 include: "rules/count.snake"
-include: "rules/qc.snake"
+include: "rules/qc.snake"

chemistry.json

@@ -3,42 +3,47 @@
         "length": "58",
         "bc_cut": "",
         "R1": "[WHITELIST_V3,\"--soloUMIlen 12 --clip5pNbases 58 0 --soloCBstart 1 --soloCBlen 16 --soloUMIstart 17\"]",
-        "R2": "[WHITELIST_V3,\"--soloUMIlen 12\"]"
+        "R2": "[WHITELIST_V3,\"--soloUMIlen 12\"]",
+        "paired": "--alignEndsProtrude 58 ConcordantPair"
     },
     "chromiumV3UG": {
         "length": "58",
         "bc_cut": "",
-        "R1": "[WHITELIST_V3,\"--soloUMIlen 9 --clip5pNbases 58 --soloCBstart 23 --soloCBlen 16 --soloUMIstart 39\"]",
-        "R2": "[WHITELIST_V3,\"--soloUMIlen 9\"]"
+        "R1": "[WHITELIST_V3,\"--soloUMIlen 9 --clip5pNbases 58 --soloCBstart 23 --soloCBlen 16 --soloUMIstart 39\"]"
     },
     "chromiumV2": {
         "length": "56",
         "bc_cut": "",
         "R1": "[WHITELIST_V2,\"--soloUMIlen 10 --clip5pNbases 56 0 --soloCBstart 1 --soloCBlen 16 --soloUMIstart 17\"]",
-        "R2": "[WHITELIST_V2,\"--soloUMIlen 10\"]"
+        "R2": "[WHITELIST_V2,\"--soloUMIlen 10\"]",
+        "paired": "--alignEndsProtrude 56 ConcordantPair"
     },
     "dropseq": {
         "length": "50",
         "bc_cut": "",
         "R1": "[\"None --soloUMIlen 8 --clip5pNbases 50 0 --soloCBstart 1 --soloCBlen 12 --soloUMIstart 13\"]",
-        "R2": "[\"None --soloUMIlen 8 --soloCBstart 1 --soloCBlen 12 --soloUMIstart 13\"]"
+        "R2": "[\"None --soloUMIlen 8 --soloCBstart 1 --soloCBlen 12 --soloUMIstart 13\"]",
+        "paired": "--alignEndsProtrude 50 ConcordantPair"
     },
     "microwellseq": {
         "length": "54",
         "bc_cut": "CGACTCACTACAGGG...TCGGTGACACGATCG",
         "R1": "[\"None --soloUMIlen 6 --clip5pNbases 54 0 --soloCBstart 1 --soloCBlen 18 --soloUMIstart 19\"]",
-        "R2": "[\"None --soloUMIlen 6 --soloCBstart 1 --soloCBlen 18 --soloUMIstart 19\"]"
+        "R2": "[\"None --soloUMIlen 6 --soloCBstart 1 --soloCBlen 18 --soloUMIstart 19\"]",
+        "paired": "--alignEndsProtrude 54 ConcordantPair"
     },
     "bd": {
         "length": "53",
         "bc_cut": "ACTGGCCTGCGA...GGTAGCGGTGACA",
         "R1": "[\"None --soloUMIlen 8 --clip5pNbases 53 0 --soloCBstart 1 --soloCBlen 27 --soloUMIstart 28\"]",
-        "R2": "[\"None --soloUMIlen 8 --soloCBstart 1 --soloCBlen 27 --soloUMIstart 28\"]"
+        "R2": "[\"None --soloUMIlen 8 --soloCBstart 1 --soloCBlen 27 --soloUMIstart 28\"]",
+        "paired": "--alignEndsProtrude 53 ConcordantPair"
     },
     "indrop": {
         "length": "32",
         "bc_cut": "",
         "R1": "[\"None --soloUMIlen 6 --clip5pNbases 32 0 --soloCBstart 1 --soloCBlen 8 --soloUMIstart 9\"]",
-        "R2": "[\"None --soloUMIlen 6 --soloCBstart 1 --soloCBlen 8 --soloUMIstart 9\"]"
+        "R2": "[\"None --soloUMIlen 6 --soloCBstart 1 --soloCBlen 8 --soloUMIstart 9\"]",
+        "paired": "--alignEndsProtrude 32 ConcordantPair"
     }
 }

config.yaml

@@ -36,12 +36,15 @@ POLYA_SITES:
 FASTQS:
   "sample_fastqs.tsv"
 
-R1_SAMPLES:
+PAIRED_SAMPLES:
 # Sample basenames
   - test
   - test2
   - test3
 
+R1_SAMPLES:
+# Sample basenames
+
 R2_SAMPLES:
   - test
   - test2

rules/cutadapt_star.snake

@@ -29,12 +29,18 @@ def _get_chem_version_R2(wildcards):
     args = eval(chemistry[chem_version]["R2"])
     return args
 
-""" Extract per-capture chemistry from gex libs (paired)"""
+""" Extract per-capture chemistry from gex libs (R1/paired)"""
 def _get_chem_version_R1(wildcards):
     chem_version = SAMPLES_DF[SAMPLES_DF.capture == wildcards.sample].chemistry.unique()[0]
     args = eval(chemistry[chem_version]["R1"])
     return args
 
+""" Extract per-capture extra arguments for gex paired alignments """
+def _get_chem_version_paired(wildcards):
+    chem_version = SAMPLES_DF[SAMPLES_DF.capture == wildcards.sample].chemistry.unique()[0]
+    args = eval(chemistry[chem_version]["paired"])
+    return args
+
 """ Extract per-capture extra arguments for gex libs """
 def _get_extra_args(wildcards):
     captures_filtered = SAMPLES_DF[SAMPLES_DF.capture == wildcards.sample]
@@ -215,6 +221,7 @@ rule starsolo_paired:
       "{results}/{sample}/{sample}_paired_Aligned.sortedByCoord.out.bam"
     params:
       chemistry = _get_chem_version_R1,
+      star_args_paired = _get_chem_version_paired,
       extra_args = _get_extra_args,
       out_dir = "{results}/{sample}/{sample}_paired_", 
       job_name = "star_paired"
@@ -232,6 +239,7 @@ rule starsolo_paired:
       --readFilesCommand gunzip -c \
       --runThreadN 12 \
       --soloCBwhitelist {params.chemistry} \
+      {star_args_paired} \
       --soloBarcodeMate 1 \
       --outFilterMultimapNmax 1 \
       --outFilterMismatchNmax 999 \