def parseSam(refDict):
infn, outfn = sys.argv[1], sys.argv[2]
bamfile = pysam.Samfile(infn, "rb")
out = open(outfn, 'w')
counter = 0
currid = ""
tidDict = {}
for ar in bamfile.fetch():
query_id = ar.qname
if ar.tid in tidDict:
target_id = tidDict[ar.tid]
else:
target_id = bamfile.getrname(ar.tid)
tidDict[ar.tid] = target_id
if ar.is_secondary:
counter += 1
continue
target_start = ar.aend - ar.alen
target_end = ar.aend
target_strand = "+"
if ar.is_reverse:
target_strand = "-"
if currid == query_id:
counter += 1
continue
currid = query_id
alignedpositions = ar.aligned_pairs
alignedQuery = buildAlignmentSequence(ar.seq, alignedpositions, 0)
alignedTarget = buildAlignmentSequence(refDict[target_id],
alignedpositions, 1)
aq = alignedQuery
at = alignedTarget
states = insDelHmm.outputDelInsCython(aq, at, t_log, e_log)
#if 1 in states or 0 in states:
if len(states) > 1:
insDelHmm.printSummaryFast(query_id, target_id, target_start,
target_end, target_strand, states,
alignedQuery, alignedTarget, out)
counter += 1
def parseSam(refDict):
infn , outfn = sys.argv[1], sys.argv[2]
bamfile = pysam.Samfile( infn, "rb" )
out = open(outfn, 'w')
counter = 0
currid = ""
tidDict = {}
for ar in bamfile.fetch():
query_id = ar.qname
if ar.tid in tidDict:
target_id = tidDict[ar.tid]
else:
target_id = bamfile.getrname(ar.tid)
tidDict[ar.tid] = target_id
if ar.is_secondary:
counter += 1
continue
target_start = ar.aend-ar.alen
target_end = ar.aend
target_strand = "+"
if ar.is_reverse:
target_strand = "-"
if currid == query_id:
counter += 1
continue
currid = query_id
alignedpositions = ar.aligned_pairs
alignedQuery = buildAlignmentSequence(ar.seq, alignedpositions, 0)
alignedTarget = buildAlignmentSequence(refDict[target_id], alignedpositions, 1)
aq = alignedQuery
at = alignedTarget
states = insDelHmm.outputDelInsCython (aq, at, t_log, e_log)
#if 1 in states or 0 in states:
if len(states) > 1:
insDelHmm.printSummaryFast(query_id, target_id, target_start, target_end, target_strand, states, alignedQuery, alignedTarget, out)
counter += 1
def parseRm5():
infn, outfn = sys.argv[1], sys.argv[2]
out = open(outfn, 'w')
counter = 0
currid = ""
for line in open(infn, buffering=100000):
values = line.rstrip("\n").split(" ")
query_id, query_length, query_start, query_end, query_strand = values[
0], int(values[1]), int(values[2]), int(values[3]), values[4]
if currid == query_id:
counter += 1
continue
currid = query_id
target_id, target_length, target_start, target_end, target_strand = values[
6], int(values[7]), int(values[8]), int(values[9]), values[10]
alignedQuery = values[17]
alignedTarget = values[19]
aligned = values[18]
score = int(values[11])
if target_strand == "-":
alignedQuery = alignedQuery[::-1]
alignedTarget = alignedTarget[::-1]
aligned = aligned[::-1]
aq = alignedQuery
at = alignedTarget
states = insDelHmm.outputDelInsCython(aq, at, t_log, e_log)
#if 1 in states or 0 in states:
if len(states) > 1:
insDelHmm.printSummaryFast(query_id, target_id, target_start,
target_end, target_strand, states,
alignedQuery, alignedTarget, out)
counter += 1
def parseRm5():
infn , outfn = sys.argv[1], sys.argv[2]
out = open(outfn, 'w')
counter = 0
currid = ""
for line in open(infn, buffering=100000):
values = line.rstrip("\n").split(" ")
query_id, query_length, query_start, query_end, query_strand = values[0], int(values[1]), int(values[2]), int(values[3]), values[4]
if currid == query_id:
counter += 1
continue
currid = query_id
target_id, target_length, target_start, target_end, target_strand = values[6], int(values[7]), int(values[8]), int(values[9]), values[10]
alignedQuery = values[17]
alignedTarget = values[19]
aligned = values[18]
score = int(values[11])
if target_strand == "-":
alignedQuery = alignedQuery[::-1]
alignedTarget = alignedTarget[::-1]
aligned = aligned[::-1]
aq = alignedQuery
at = alignedTarget
states = insDelHmm.outputDelInsCython (aq, at, t_log, e_log)
#if 1 in states or 0 in states:
if len(states) > 1:
insDelHmm.printSummaryFast(query_id, target_id, target_start, target_end, target_strand, states, alignedQuery, alignedTarget, out)
counter += 1