def filterChimericReads(IOstream, distance):
line = common.outputHeader(IOstream)
while line != "":
multiMaps = list()
multiMaps.append(line)
readID = line.split()[0]
line = IOstream.readline()
while line != "" and line.split()[0] == readID:
multiMaps.append(line)
line = IOstream.readline()
splitMappings = set()
for i in range(len(multiMaps) - 1):
for j in range(i + 1, len(multiMaps)):
splitted_i, splitted_j = multiMaps[i].split(
), multiMaps[j].split()
ipos_b, ipos_e = common.beg_end_of_seq(splitted_i[5])
jpos_b, jpos_e = common.beg_end_of_seq(splitted_j[5])
if (jpos_b - ipos_e) >= -distance:
splitMappings.add(multiMaps[i])
splitMappings.add(multiMaps[j])
elif (ipos_b - jpos_e) >= -distance:
splitMappings.add(multiMaps[i])
splitMappings.add(multiMaps[j])
for outputLine in multiMaps:
if outputLine not in splitMappings:
sys.stdout.write(outputLine)
def filterByQuality(IOstream, quality):
line = common.outputHeader(IOstream)
while line != "":
readQuality = int(line.split()[4])
if readQuality >= quality:
sys.stdout.write(line)
line = IOstream.readline()
def outputMultimappedReads(IOstream,multimappedReadsSet):
IOstream.seek(0)
line = common.outputHeader(IOstream)
while line!='':
readID = line.split()[0]
if readID in multimappedReadsSet:
sys.stdout.write(line)
line = IOstream.readline()
def filterByReference(IOstream):
line = common.outputHeader(IOstream)
while line != "":
multiMaps = list()
multiMaps.append(line)
readID = line.split()[0]
line = IOstream.readline()
while line != "" and line.split()[0] == readID:
multiMaps.append(line)
line = IOstream.readline()
readsMultimappedSameRef = set()
for i in range(len(multiMaps) - 1):
for j in range(i + 1, len(multiMaps)):
if common.compareReadIDReferences(multiMaps[i],
multiMaps[j]) == 0:
readsMultimappedSameRef.add(multiMaps[i])
readsMultimappedSameRef.add(multiMaps[j])
for outputLine in multiMaps:
if outputLine in readsMultimappedSameRef:
sys.stdout.write(outputLine)
import functools
import argparse
if __name__=='__main__':
parser = argparse.ArgumentParser(description="Sort a SAM file by several criteria, for now you cannot sort by pos or ref only, only id, id/pos, id/ref, id/pos/ref. The order used between read IDs is the alphabetic order. For sorting using samtools use the sortSam2 script.")
parser.add_argument("-id", dest="id", action="store_true", help="Allows sorting of SAM file by read ID")
parser.add_argument("-pos", dest="pos", action="store_true", help="Allows sorting of SAM file by position number")
parser.add_argument("-ref", dest="ref", action="store_true", help="Allows sorting of SAM file by reference number")
args = parser.parse_args()
toBeSorted = list()
line = common.outputHeader(sys.stdin)
while line!="":
toBeSorted.append(line)
line = sys.stdin.readline()
if args.pos and args.ref and args.id:
toBeSorted.sort(key=functools.cmp_to_key(common.compareReadIDReferencesPositions))
elif args.id and args.pos:
toBeSorted.sort(key=functools.cmp_to_key(common.compareReadIDPositions))
elif args.id and args.ref:
toBeSorted.sort(key=functools.cmp_to_key(common.compareReadIDReferences))
elif args.id: