types2files["GDNA"].add(filename) files2types[filename].add("GDNA") if re.search(regex["NRNA"], filename) and key not in NRNA: NRNA[key] = row types2files["NRNA"].add(filename) files2types[filename].add("NRNA") if re.search(regex["SDNA"], filename) and key not in SDNA: SDNA[key] = row types2files["SDNA"].add(filename) files2types[filename].add("SDNA") if re.search(regex["TRNA"], filename) and key not in TRNA: TRNA[key] = row types2files["TRNA"].add(filename) files2types[filename].add("TRNA") f.close() progress.done() if sum(map(len, [GDNA, SDNA, NRNA, TRNA])) == 0: print("No read counts available for testing", file=sys.stderr) sys.exit(0) fatal = False for f in files2types: if len(files2types[f]) < 1: print("Filename %s does not match any read type regular expression." % (f, ), file=sys.stderr) fatal = True elif len(files2types[f]) > 1: print( "Filename %s matches more than one read type regular expression." %
alt = r[snvheaders[3]].strip() if r.get('INFO:INDEL'): continue if len(ref) != 1: continue if not re.search(r'^[ACGT](,[ACGT])*$', alt): continue # for h in r: # if r.get(h): # usedsnvheaders.add(h) snvkey = (filename, chr, locus, ref, alt) if snvkey not in snvdata: snvdata[snvkey] = r progress.update() progress.done() chrreg = ChromLabelRegistry() for snvfile in snvchroms: chrreg.add_labels(snvfile,snvchroms[snvfile]) snvdata1 = {} for (sf, chr, locus, ref, alt), r in snvdata.iteritems(): chrom = chrreg.label2chrom(sf,chr) assert(chrom) snvkey = (chrom,locus,ref,alt) if snvkey not in snvdata1: snvdata1[snvkey] = (chrom,locus,ref,alt,r) for bamfile in opt.alignments: