Optional mpileup params, incr default mindepth

Set default mindepth to:

--ignore-RG --min-MQ 1 --max-depth 250000 --max-idepth 250000

Add mpileup_parameters as option. Update example files as well since they are
to outdated. Not sure why the coverage goes down by 2, bam file is still the
same. Code seems similar as well. Perhaps change in mpileup version.

README.rst

@@ -25,8 +25,20 @@ Run
 ::
 
     usage: sufam [-h] [--sample_name SAMPLE_NAME] [--format {matrix,sufam}]
+                [--mpileup-parameters MPILEUP_PARAMETERS] [--version]
                 reffa vcf bam
 
+    So U Found A Mutation? (SUFAM)
+
+    Found a mutation in one or more samples? Now you want to check if they are in
+    another sample. Unfortunately mutect, varscan or whatever other variant caller
+    is not calling them. Use SUFAM. The super sensitive validation caller that
+    calls everything on a given position. All you need is a vcf with the mutations
+    that you are interested in and the sam/bam file of the sample where you want to
+    find the same inconsipicuous mutation.
+
+    Author: inodb
+
     positional arguments:
     reffa                 Reference genome (fasta)
     vcf                   VCF with mutations to be validated
@@ -35,9 +47,13 @@ Run
     optional arguments:
     -h, --help            show this help message and exit
     --sample_name SAMPLE_NAME
-                            Set name of sample, used in output.
+                            Set name of sample, used in output [name of bam].
     --format {matrix,sufam}
-                            Set output format
+                            Set output format [sufam]
+    --mpileup-parameters MPILEUP_PARAMETERS
+                            Set options for mpileup [--ignore-RG --min-MQ 1 --max-
+                            depth 250000 --max-idepth 250000]
+    --version             show program's version number and exit
 
 Example
 ~~~~~~~

example/sufam.log

@@ -1,8 +1,6 @@
 Running:
-samtools view -bh tests/test_data/subset1.bam 17:7574012-7574012 | samtools mpileup -R -q 1 -f tests/test_data/human_g1k_v37_chr17.fa - | grep -P '^17\t7574012\t'
+samtools view -bh tests/test_data/subset1.bam 17:7574012-7574012 | samtools mpileup --ignore-RG --min-MQ 1 --max-depth 250000 --max-idepth 250000 -f tests/test_data/human_g1k_v37_chr17.fa - | awk '$2 == 7574012'
 [mpileup] 1 samples in 1 input files
-<mpileup> Set max per-file depth to 8000
 Running:
-samtools view -bh tests/test_data/subset1.bam 17:7574012-7574012 | samtools mpileup -R -q 1 -f tests/test_data/human_g1k_v37_chr17.fa - | grep -P '^17\t7574012\t'
+samtools view -bh tests/test_data/subset1.bam 17:7574012-7574012 | samtools mpileup --ignore-RG --min-MQ 1 --max-depth 250000 --max-idepth 250000 -f tests/test_data/human_g1k_v37_chr17.fa - | awk '$2 == 7574012'
 [mpileup] 1 samples in 1 input files
-<mpileup> Set max per-file depth to 8000

example/sufam.tsv

@@ -1,3 +1,3 @@
 sample	chrom	pos	ref	cov	A	C	G	T	*	-	+	val_ref	val_alt	val_al_type	val_al_count	val_maf	most_common_indel	most_common_indel_count	most_common_indel_maf	most_common_indel_type	most_common_al	most_common_al_count	most_common_al_maf	most_common_count	most_common_maf
-tests/test_data/subset1.bam	17	7574012	C	675	225	450	0	0	0	nan	nan	C	G	snv	0	0.0	nan	nan	nan	nan	A	225	0.333333333333	225	0.333333333333
-tests/test_data/subset1.bam	17	7574012	C	675	225	450	0	0	0	nan	nan	C	A	snv	225	0.333333333333	nan	nan	nan	nan	A	225	0.333333333333	225	0.333333333333
+tests/test_data/subset1.bam	17	7574012	C	673	223	450	0	0	0	nan	nan	C	G	snv	0	0.0	nan	nan	nan	nan	A	223	0.331352154532	223	0.331352154532
+tests/test_data/subset1.bam	17	7574012	C	673	223	450	0	0	0	nan	nan	C	A	snv	223	0.331352154532	nan	nan	nan	nan	A	223	0.331352154532	223	0.331352154532

sufam/__main__.py

@@ -178,7 +178,8 @@ def _write_bp(outfile, bp, header, output_format):
         raise(Exception("Unrecognized output format"))
 
 
-def validate_mutations(vcffile, bam, reffa, sample, output_format, outfile):
+def validate_mutations(vcffile, bam, reffa, sample, output_format, outfile,
+                       mpileup_parameters=mpileup_parser.MPILEUP_DEFAULT_PARAMS):
     """Check if mutations in vcf are in bam"""
     header = []
     output_header = "sample chrom pos ref cov A C G T * - + " \
@@ -209,7 +210,7 @@ def validate_mutations(vcffile, bam, reffa, sample, output_format, outfile):
             "cov": 0, "A": 0, "C": 0, "G": 0, "T": 0,
             "val_ref": record["REF"], "val_alt": record["ALT"],
             "val_al_type": record_type, "val_al_count": 0, "val_maf": 0})
-        bp_lines = mpileup_parser.run_and_parse(bam, record["CHROM"], record["POS"], record["POS"], reffa)
+        bp_lines = mpileup_parser.run_and_parse(bam, record["CHROM"], record["POS"], record["POS"], reffa, mpileup_parameters)
         bpdf = get_baseparser_extended_df(sample, bp_lines, record["REF"], record["ALT"])
         if bpdf is None:
             bp = no_cov
@@ -225,13 +226,17 @@ def main():
     parser.add_argument("vcf", type=str, help="VCF with mutations to be validated")
     parser.add_argument("bam", type=str, help="BAM to find mutations in")
     parser.add_argument("--sample_name", type=str, default=None, help="Set name "
-                        "of sample, used in output.")
-    parser.add_argument("--format", type=str, choices=["matrix", "sufam"], default="sufam", help="Set output format")
+                        "of sample, used in output [name of bam].")
+    parser.add_argument("--format", type=str, choices=["matrix", "sufam"], default="sufam",
+                        help="Set output format [sufam]")
+    parser.add_argument("--mpileup-parameters", type=str,  default=mpileup_parser.MPILEUP_DEFAULT_PARAMS,
+                        help="Set options for mpileup [{}]".format(mpileup_parser.MPILEUP_DEFAULT_PARAMS))
     parser.add_argument("--version", action='version', version=sufam.__version__)
     args = parser.parse_args()
     if args.sample_name is None:
         args.sample_name = args.bam
-    validate_mutations(args.vcf, args.bam, args.reffa, args.sample_name, args.format, sys.stdout)
+    validate_mutations(args.vcf, args.bam, args.reffa, args.sample_name,
+                       args.format, sys.stdout, mpileup_parameters=args.mpileup_parameters)
 
 
 if __name__ == "__main__":

sufam/mpileup_parser.py

@@ -11,6 +11,8 @@
 from sufam.mutation import Mutation, MutationsAtSinglePosition
 from collections import Counter
 
+MPILEUP_DEFAULT_PARAMS = '--ignore-RG --min-MQ 1 --max-depth 250000 --max-idepth 250000'
+
 
 class ParseString(object):
 
@@ -92,12 +94,14 @@ def parse(line):
     return '\t'.join([toks[0], toks[1], ref, cov]) + '\t' + str(ParseString(ref, toks[4]))
 
 
-def run(bam, chrom, pos1, pos2, reffa):
+def run(bam, chrom, pos1, pos2, reffa, parameters):
     """Run mpileup on given chrom and pos"""
     posmin = min(pos1, pos2)
     posmax = max(pos1, pos2)
     cmd = "samtools view -bh {bam} {chrom}:{pos1}-{pos2} " \
-        "| samtools mpileup -R -q 1 -f {reffa} -".format(bam=bam, chrom=chrom, pos1=posmin, pos2=posmax, reffa=reffa)
+        "| samtools mpileup {parameters} -f {reffa} -".format(bam=bam, chrom=chrom,
+                                                              pos1=posmin, pos2=posmax,
+                                                              reffa=reffa, parameters=parameters)
     if pos1 == pos2:
         cmd += " | awk '$2 == {pos}'".format(pos=pos1)
     else:
@@ -116,12 +120,12 @@ def run(bam, chrom, pos1, pos2, reffa):
         return stdout
 
 
-def run_and_parse(bam, chrom, pos1, pos2, reffa):
-    return [parse(line) for line in run(bam, chrom, pos1, pos2, reffa).split("\n")[:-1]]
+def run_and_parse(bam, chrom, pos1, pos2, reffa, mpileup_parameters=MPILEUP_DEFAULT_PARAMS):
+    return [parse(line) for line in run(bam, chrom, pos1, pos2, reffa, mpileup_parameters).split("\n")[:-1]]
 
 
-def run_and_get_mutations(bam, chrom, pos1, pos2, reffa):
-    return [get_mutations(line) for line in run(bam, chrom, pos1, pos2, reffa).split("\n")[:-1]]
+def run_and_get_mutations(bam, chrom, pos1, pos2, reffa, mpileup_parameters=MPILEUP_DEFAULT_PARAMS):
+    return [get_mutations(line) for line in run(bam, chrom, pos1, pos2, reffa, mpileup_parameters).split("\n")[:-1]]
 
 
 def main():