def build_ivals(fp, genome_db, reads_db):
for row in bowtie_parser.read(fp):
src_seq = get_src_sequence(genome_db, row)
read_seq = get_read_sequence(reads_db, row)
yield src_seq, read_seq
import bowtie_parser
import sys
files = sys.argv[2:]
dict1 = {}
fp = open(sys.argv[1], 'w')
for file in files:
dict = {}
for n, line in enumerate(bowtie_parser.read(open(file))):
contig_id = line.seqid
length = int(contig_id.split('_')[3])+33-1
start = line.start
read = line.read
if dict.has_key(contig_id):
for index in range(start,int(start)+len(read)):
dict[contig_id][1][index]=1
else:
count_mapped = [0]*length
dict[contig_id]=[length]
dict[contig_id].append(count_mapped)
for key in dict.keys():
mapped_bases = dict[key][1].count(1)
dict[key][1] = mapped_bases
mapped_percent = dict[key][1]/float(dict[key][0])
dict[key].append(mapped_percent)
group_index = file.find('group')
###
parser = optparse.OptionParser()
parser.add_option('-M', '--max-reads', dest='max_reads', default=0, type=int,
help='only use first M reads, then exit')
(options, args) = parser.parse_args()
bowtie_mapping_file, = args
bowtie_fp = open(bowtie_mapping_file)
###
# iterate over the bowtie mapping file (output from bowtie)
for n, line in enumerate(bowtie_parser.read(bowtie_fp)):
# print out status/progress.
if n % 10000 == 0:
print>>sys.stderr, 'scanning reads', n
if options.max_reads and n > options.max_reads:
print>>sys.stderr, 'EXITING EARLY; -M specified as %d' % \
options.max_reads
break
# retrieve mismatches from the bowtie mapping
mismatches = line.mismatches.strip()
# record the mismatch positions
if mismatches:
mismatches = [ x for x in mismatches.split(',') if 'N' not in x ]