)
parser.add_argument('--bed', type=str, required=True,
help='Path to Flux bed'
)
parser.add_argument('--fastq', type=str, required=True,
help='Path to Flux FASTQ'
)
parser.add_argument('--ignore-b-tails', action='store_const', const=True,
default=False,
help='Don\'t count reads for which the last 10 bases have Q <= 15'
)
parser.add_argument('-x', '--bowtie-idx', required=True,
help='Path to Bowtie 1 index. Specify its basename.'
)
args = parser.parse_args()
reference_index = BowtieIndexReference(args.bowtie_idx)
truths = [0 for i in xrange(args.length)]
recalls = [0 for i in xrange(args.length)]
k = 0
b_tail_count, read_count = 0, 0
with open(args.bed) as bed_stream:
with open(args.fastq) as fastq_stream:
while True:
bed_line = bed_stream.readline().strip()
if not bed_line: break
read_name = fastq_stream.readline().strip()[1:]
seq = fastq_stream.readline().strip().upper()
fastq_stream.readline()
qual = fastq_stream.readline().strip()
read_count += 1
if args.ignore_b_tails and all(
import argparse
# Print file's docstring if -h is invoked
parser = argparse.ArgumentParser(description=__doc__,
formatter_class=argparse.RawDescriptionHelpFormatter)
parser.add_argument('--bowtie2-idx', type=str, required=False,
default=None,
help=('Path to Bowtie 2 genome index used to determine '
'whether junctions are canonical. Canonical/'
'noncanonical status and intron length '
'distribution are output only if this '
'is specified.')
)
args = parser.parse_args()
if args.bowtie2_idx is not None:
from count_introns import BowtieIndexReference
reference_index = BowtieIndexReference(args.bowtie2_idx)
intron_lengths = defaultdict(int)
motif_counts = defaultdict(int)
exons = defaultdict(set)
for line in sys.stdin:
if line[0] == '#': continue
tokens = line.strip().split('\t')
if tokens[2].lower() != 'exon': continue
'''key: transcript_id
value: (rname, exon start (1-based), exon end (1-based))
transcript_id in token 12 is decked with " on the left and "; on the
right; kill them in key below.
'''
attribute = tokens[-1].split(';')
id_index = [i for i, name in enumerate(attribute)
description=__doc__,
formatter_class=argparse.RawDescriptionHelpFormatter)
parser.add_argument(
'--bowtie2-idx',
type=str,
required=False,
default=None,
help=('Path to Bowtie 2 genome index used to determine '
'whether junctions are canonical. Canonical/'
'noncanonical status and intron length '
'distribution are output only if this '
'is specified.'))
args = parser.parse_args()
if args.bowtie2_idx is not None:
from count_introns import BowtieIndexReference
reference_index = BowtieIndexReference(args.bowtie2_idx)
intron_lengths = defaultdict(int)
motif_counts = defaultdict(int)
exons = defaultdict(set)
for line in sys.stdin:
if line[0] == '#': continue
tokens = line.strip().split('\t')
if tokens[2].lower() != 'exon': continue
'''key: transcript_id
value: (rname, exon start (1-based), exon end (1-based))
transcript_id in token 12 is decked with " on the left and "; on the
right; kill them in key below.
'''
attribute = tokens[-1].split(';')
id_index = [
parser.add_argument('--fastq',
type=str,
required=True,
help='Path to Flux FASTQ')
parser.add_argument(
'--ignore-b-tails',
action='store_const',
const=True,
default=False,
help='Don\'t count reads for which the last 10 bases have Q <= 15')
parser.add_argument('-x',
'--bowtie-idx',
required=True,
help='Path to Bowtie 1 index. Specify its basename.')
args = parser.parse_args()
reference_index = BowtieIndexReference(args.bowtie_idx)
truths = [0 for i in xrange(args.length)]
recalls = [0 for i in xrange(args.length)]
k = 0
b_tail_count, read_count = 0, 0
with open(args.bed) as bed_stream:
with open(args.fastq) as fastq_stream:
while True:
bed_line = bed_stream.readline().strip()
if not bed_line: break
read_name = fastq_stream.readline().strip()[1:]
seq = fastq_stream.readline().strip().upper()
fastq_stream.readline()
qual = fastq_stream.readline().strip()
read_count += 1
if args.ignore_b_tails and all(
