def main(argv=None):
"""script main.
parses command line options in sys.argv, unless *argv* is given.
"""
if not argv:
argv = sys.argv
# setup command line parser
parser = E.OptionParser(version="%prog version: $Id$",
usage=globals()["__doc__"])
parser.add_option(
"--guess-format",
dest="guess_format",
type="choice",
choices=('sanger', 'solexa', 'phred64', 'illumina-1.8', 'integer'),
help="The default behaviour of the script is to guess the quality "
"format of the input fastq file. The user can specify the "
"quality format of the input file using the --guess-format option. "
"The script will use this format if the "
"sequence qualities are ambiguous.[default=%default].")
parser.add_option(
"--target-format",
dest="target_format",
type="choice",
choices=('sanger', 'solexa', 'phred64', 'illumina-1.8', 'integer'),
help="The script will convert quality scores to the destination "
"format unless [default=%default].")
parser.set_defaults(
target_format=None,
guess_format=None,
min_quality=10,
)
# add common options (-h/--help, ...) and parse command line
(options, args) = E.Start(parser, argv=argv)
c = E.Counter()
if options.target_format:
iterator = Fastq.iterate_convert(options.stdin,
format=options.target_format,
guess=options.guess_format)
else:
iterator = Fastq.iterate_guess(options.stdin,
guess=options.guess_format)
options.stdout.write("read\tnfailed\tnN\t%s\n" %
("\t".join(Stats.Summary().getHeaders())))
min_quality = options.min_quality
for record in iterator:
c.input += 1
quals = record.toPhred()
nfailed = len([x for x in quals if x < min_quality])
nns = record.seq.count("N") + record.seq.count(".")
options.stdout.write(
"%s\t%i\t%i\t%s\n" %
(record.identifier, nfailed, nns, str(Stats.Summary(quals))))
c.output += 1
# write footer and output benchmark information.
E.info("%s" % str(c))
E.Stop()
def main(argv=None):
"""script main.
parses command line options in sys.argv, unless *argv* is given.
"""
if not argv:
argv = sys.argv
# setup command line parser
parser = E.OptionParser(version="%prog version: $Id: cgat_script_template.py 2871 2010-03-03 10:20:44Z andreas $",
usage=globals()["__doc__"])
parser.add_option("--guess-format", dest="guess_format", type="choice",
choices=('sanger', 'solexa', 'phred64',
'illumina-1.8', 'integer'),
help="The default behaviour of the script is to guess \
the quality format of the input fastq file. The user \
can specify the quality format of the input file using \
the --format option. The script will use this format if \
sequences qualities are ambiguous.[default=%default].")
parser.add_option("-f", "--change-format", dest="change_format",
type="choice", choices=('sanger', 'solexa', 'phred64',
'illumina-1.8', 'integer'),
help="The script guesses the quality format of the input \
file and converts quality scores to the destination \
format unless --format is specified [default=%default].")
parser.set_defaults(
change_format=None,
guess_format=None,
min_quality=10)
# add common options (-h/--help, ...) and parse command line
(options, args) = E.Start(parser, argv=argv)
if options.change_format:
iterator = Fastq.iterate_convert(options.stdin,
format=options.change_format,
guess=options.guess_format)
else:
iterator = Fastq.iterate_guess(options.stdin,
guess=options.guess_format)
min_quality = options.min_quality
number_of_reads = 0
number_of_bases = 0
read_lengths = []
read_qualities = []
bases_below_min = 0
for record in iterator:
number_of_reads += 1
quals = record.toPhred()
length_read = len(quals)
number_of_bases += length_read
bases_below_min += len([x for x in quals if x < min_quality])
read_lengths.append(length_read)
read_qualities.append(np.mean(quals))
mean_length = round(np.mean(read_lengths), 2)
median_length = round(np.median(read_lengths), 2)
mean_quality = round(np.mean(read_qualities), 2)
median_quality = round(np.median(read_qualities), 2)
options.stdout.write(
"reads\tbases\tmean_length\tmedian_length\tmean_quality\tmedian_quality\tnfailed\n")
options.stdout.write(
"%i\t%i\t%s\t%s\t%s\t%s\t%i\n" % (number_of_reads, number_of_bases,
str(mean_length),
str(median_length),
str(mean_quality),
str(median_quality),
bases_below_min))
E.Stop()
def main(argv=None):
"""script main.
parses command line options in sys.argv, unless *argv* is given.
"""
if not argv:
argv = sys.argv
# setup command line parser
parser = E.OptionParser(version="%prog version: $Id$",
usage=globals()["__doc__"])
parser.add_option("--guess-format",
dest="guess_format",
type="choice",
choices=('sanger', 'solexa', 'phred64', 'illumina-1.8',
'integer'),
help="The default behaviour of the script is to guess \
the quality format of the input fastq file. The user \
can specify the quality format of the input file using \
the --format option. The script will use this format if \
sequences qualities are ambiguous.[default=%default].")
parser.add_option(
"-f",
"--target-format",
dest="change_format",
type="choice",
choices=('sanger', 'solexa', 'phred64', 'illumina-1.8', 'integer'),
help="The script guesses the quality format of the input \
file and converts quality scores to the destination \
format unless --format is specified [default=%default].")
parser.set_defaults(change_format=None, guess_format=None, min_quality=10)
# add common options (-h/--help, ...) and parse command line
(options, args) = E.Start(parser, argv=argv)
if options.change_format:
iterator = Fastq.iterate_convert(options.stdin,
format=options.change_format,
guess=options.guess_format)
else:
iterator = Fastq.iterate_guess(options.stdin,
guess=options.guess_format)
min_quality = options.min_quality
number_of_reads = 0
number_of_bases = 0
read_lengths = []
read_qualities = []
bases_below_min = 0
for record in iterator:
number_of_reads += 1
quals = record.toPhred()
length_read = len(quals)
number_of_bases += length_read
bases_below_min += len([x for x in quals if x < min_quality])
read_lengths.append(length_read)
read_qualities.append(np.mean(quals))
mean_length = round(np.mean(read_lengths), 2)
median_length = round(np.median(read_lengths), 2)
mean_quality = round(np.mean(read_qualities), 2)
median_quality = round(np.median(read_qualities), 2)
options.stdout.write(
"reads\tbases\tmean_length\tmedian_length\tmean_quality\tmedian_quality\tnfailed\n"
)
options.stdout.write("%i\t%i\t%s\t%s\t%s\t%s\t%i\n" %
(number_of_reads, number_of_bases, str(mean_length),
str(median_length), str(mean_quality),
str(median_quality), bases_below_min))
E.Stop()
def main(argv=None):
"""script main.
parses command line options in sys.argv, unless *argv* is given.
"""
if not argv:
argv = sys.argv
# setup command line parser
parser = E.OptionParser(version="%prog version: $Id: cgat_script_template.py 2871 2010-03-03 10:20:44Z andreas $",
usage=globals()["__doc__"])
parser.add_option("--guess-format", dest="guess_format", type="choice",
choices=(
'sanger', 'solexa', 'phred64', 'illumina-1.8', 'integer'),
help="The default behaviour of the script is to guess the quality format of the input fastq file. The user can specify \
the quality format of the input file using the --format option. The script will use this format if the \
sequence qualities are ambiguous.[default=%default]." )
parser.add_option("-f", "--change-format", dest="change_format", type="choice",
choices=(
'sanger', 'solexa', 'phred64', 'illumina-1.8', 'integer'),
help="The script will guess the quality format of the input file and convert \
quality scores to the destination format unless --format is specified [default=%default]." )
parser.set_defaults(
change_format=None,
guess_format=None,
min_quality=10,
)
# add common options (-h/--help, ...) and parse command line
(options, args) = E.Start(parser, argv=argv)
c = E.Counter()
if options.change_format:
iterator = Fastq.iterate_convert(options.stdin,
format=options.change_format,
guess=options.guess_format)
else:
iterator = Fastq.iterate_guess(options.stdin,
guess=options.guess_format)
options.stdout.write("read\tnfailed\tnN\t%s\n" %
("\t".join(Stats.Summary().getHeaders())))
min_quality = options.min_quality
for record in iterator:
c.input += 1
quals = record.toPhred()
nfailed = len([x for x in quals if x < min_quality])
nns = record.seq.count("N") + record.seq.count(".")
options.stdout.write("%s\t%i\t%i\t%s\n" % (record.identifier,
nfailed,
nns,
str(Stats.Summary(quals))
))
c.output += 1
# write footer and output benchmark information.
E.info("%s" % str(c))
E.Stop()
