def build_parser(parser):
parser.add_argument(
'infile',
type=Opener('rU'),
help=
('Input CSV file to process, minimally containing the field `tax_id`. '
'Use "-" for stdin.'))
parser = taxtastic.utils.add_database_args(parser)
parser.add_argument(
'-o',
'--outfile',
default=sys.stdout,
type=Opener('wt'),
help='Modified version of input file [default: stdout]')
parser.add_argument(
'--taxid-column',
default='tax_id',
help='name of column containing tax_ids to be replaced [%(default)s]')
parser.add_argument(
'--unknowns',
type=Opener('wt'),
help=('optional output file containing rows with unknown tax_ids '
'having no replacements in merged table'))
parser.add_argument(
'-a',
'--unknown-action',
choices=['drop', 'ignore', 'error'],
default='error',
help=('action to perform for tax_ids with no replacement '
'in merged table [%(default)s]'))
def build_parser(parser):
parser = add_database_args(parser)
parser.add_argument(
'source_name',
help='name of source identifying names and nodes to extract')
parser.add_argument('-o',
'--outfile',
type=Opener('w'),
default=sys.stdout)
def main(arguments):
parser = argparse.ArgumentParser(
description=__doc__,
formatter_class=argparse.RawDescriptionHelpFormatter)
parser.add_argument('--binary', default='esl-alimerge')
inputs = parser.add_argument_group('input files')
inputs.add_argument('sto_1', type=Opener('r'))
inputs.add_argument('sto_2', type=Opener('r'))
outputs = parser.add_argument_group('output files')
outputs.add_argument('fasta_1', type=Opener('w'))
outputs.add_argument('fasta_2', type=Opener('w'))
args = parser.parse_args(arguments)
input1_names = {
line.split()[0]
for line in args.sto_1 if line.strip() and not line.startswith('#')
}
with tempfile.NamedTemporaryFile('w+t', dir='.') as tf:
cmd = [
args.binary, '--dna', '--outformat', 'afa', '-o', tf.name,
args.sto_1.name, args.sto_2.name
]
sys.stderr.write(' '.join(cmd) + '\n')
p = subprocess.Popen(cmd)
p.communicate()
merged = fastalite(tf)
for seq in merged:
if seq.id in input1_names:
args.fasta_1.write(reformat(seq))
else:
args.fasta_2.write(reformat(seq))
def build_parser(parser):
parser = add_database_args(parser)
parser.add_argument('new_nodes',
metavar='FILE',
type=Opener('r'),
help='yaml file specifying new nodes')
parser.add_argument(
'--source-name',
dest='source_name',
help=("""Provides the default source name for new nodes. The
value is overridden by "source_name" in the input
file. If not provided, "source_name" is required in each
node or name definition. This source name is created if
it does not exist."""))
def main(arguments):
parser = argparse.ArgumentParser(
description=__doc__,
formatter_class=argparse.RawDescriptionHelpFormatter)
parser.add_argument(
'fastq',
help='reads to count in fastq format',
metavar='file.fastq[.bz2|.gz]',
type=Opener(),
)
parser.add_argument(
'read_counts',
help='tabulate read counts and store as a CSV',
metavar='FILE',
type=argparse.FileType('w'),
)
args = parser.parse_args(arguments)
count = sum(1 for _ in fastqlite(args.fastq))
read_counts_writer = csv.writer(args.read_counts)
read_counts_writer.writerow([args.fastq.name, count, count])
def main(arguments=None):
parser = argparse.ArgumentParser(
prog='barcodecop',
description=__doc__,
formatter_class=argparse.RawDescriptionHelpFormatter)
parser.add_argument(
'index',
nargs='+',
type=Opener(),
metavar='file.fastq[.bz2|.gz]',
help='one or two files containing index reads in fastq format')
parser.add_argument('-f',
'--fastq',
type=Opener(),
metavar='file.fastq[.bz2|.gz]',
help='reads to filter in fastq format')
parser.add_argument('-o',
'--outfile',
default=sys.stdout,
type=Opener('w'),
help='output fastq')
parser.add_argument(
'--snifflimit',
type=int,
default=10000,
metavar='N',
help='read no more than N records from the index file [%(default)s]')
parser.add_argument('--head',
type=int,
metavar='N',
help='limit the output file to N records')
parser.add_argument(
'--min-pct-assignment',
type=float,
default=90.0,
metavar='PERCENT',
help=("""warn (or fail with an error; see --strict) if the
most common barcode represents less than PERCENT of the
total [%(default)s]"""))
parser.add_argument(
'--strict',
action='store_true',
default=False,
help=("""fail if conditions of --min-pct-assignment are not met"""))
parser.add_argument(
'--invert',
action='store_true',
default=False,
help='include only sequences *not* matching the most common barcode')
# parser.add_argument('--format', choices=['fasta', 'fastq'], default='fastq')
parser.add_argument('-c',
'--show-counts',
action='store_true',
default=False,
help='tabulate barcode counts and exit')
parser.add_argument('-q',
'--quiet',
action='store_true',
default=False,
help='minimize messages to stderr')
parser.add_argument('-V',
'--version',
action=VersionAction,
version=__version__,
help='Print the version number and exit')
args = parser.parse_args(arguments)
logging.basicConfig(format='%(message)s',
level=logging.ERROR if args.quiet else logging.INFO)
log = logging.getLogger(__name__)
if len(args.index) == 1:
bcseqs = fastqlite(args.index[0])
elif len(args.index) == 2:
bcseqs = combine_dual_indices(*args.index)
else:
log.error('error: please specify either one or two index files')
bc1, bc2 = tee(bcseqs, 2)
# determine the most common barcode
barcode_counts = Counter(
[str(seq.seq) for seq in islice(bc1, args.snifflimit)])
barcodes, counts = zip(*barcode_counts.most_common())
most_common_bc = barcodes[0]
most_common_pct = 100 * float(counts[0]) / sum(counts)
log.info('most common barcode: {} ({}/{} = {:.2f}%)'.format(
most_common_bc, counts[0], sum(counts), most_common_pct))
if args.show_counts:
for bc, count in barcode_counts.most_common():
print('{}\t{}\t{}'.format(bc, seqdiff(most_common_bc, bc), count))
return None
if most_common_pct < args.min_pct_assignment:
msg = 'frequency of most common barcode is less than {}%'.format(
args.min_pct_assignment)
if args.strict:
log.error('Error: ' + msg)
sys.exit(1)
else:
log.warning('Warning: ' + msg)
if not args.fastq:
log.error('specify a fastq format file to filter using -f/--fastq')
sys.exit(1)
seqs = fastqlite(args.fastq)
filtered = islice(filter(bc2, seqs, most_common_bc, args.invert),
args.head)
for seq in filtered:
args.outfile.write(as_fastq(seq))
def main(arguments=None):
parser = argparse.ArgumentParser(
prog='barcodecop',
description=__doc__,
formatter_class=argparse.RawDescriptionHelpFormatter)
parser.add_argument(
'index',
nargs='+',
type=Opener(),
metavar='file.fastq[.bz2|.gz]',
help='one or two files containing index reads in fastq format')
parser.add_argument('-f',
'--fastq',
type=Opener(),
metavar='file.fastq[.bz2|.gz]',
help='reads to filter in fastq format')
parser.add_argument('-o',
'--outfile',
default=sys.stdout,
type=Opener('w'),
help='output fastq')
parser.add_argument(
'--snifflimit',
type=int,
default=10000,
metavar='N',
help='read no more than N records from the index file [%(default)s]')
parser.add_argument('--head',
type=int,
metavar='N',
help='limit the output file to N records')
parser.add_argument(
'--invert',
action='store_true',
default=False,
help='include only sequences failing filtering criteria')
parser.add_argument('-q',
'--quiet',
action='store_true',
default=False,
help='minimize messages to stderr')
parser.add_argument('-V',
'--version',
action=VersionAction,
version=__version__,
help='Print the version number and exit')
match_options = parser.add_argument_group('Barcode matching options')
match_options.add_argument(
'--match-filter',
action='store_true',
default=False,
help=('filter reads based on exact match to most common barcode '
'[default: no match filter]'))
match_options.add_argument(
'--min-pct-assignment',
type=float,
default=90.0,
metavar='PERCENT',
help=("""warn (or fail with an error; see --strict) if the
most common barcode represents less than PERCENT of the
total [%(default)s]"""))
match_options.add_argument(
'--strict',
action='store_true',
default=False,
help=("""fail if conditions of --min-pct-assignment are not met"""))
match_options.add_argument('-c',
'--show-counts',
action='store_true',
default=False,
help='tabulate barcode counts and exit')
qual_options = parser.add_argument_group(
'Barcode quality filtering options')
qual_options.add_argument(
'--qual-filter',
action='store_true',
default=False,
help=
'filter reads based on minimum index quality [default: no quality filter]'
)
qual_options.add_argument(
'-p',
'--min-qual',
type=int,
default=MIN_QUAL,
help="""reject seqs with mean barcode quality score less than
this value; for dual index, both barcodes must meet the
threshold [%(default)s]""")
qual_options.add_argument('--encoding',
default='phred',
choices=['phred'],
help="""quality score encoding; see
https://en.wikipedia.org/wiki/FASTQ_format [%(default)s]""")
args = parser.parse_args(arguments)
logging.basicConfig(format='%(message)s',
level=logging.ERROR if args.quiet else logging.INFO)
log = logging.getLogger(__name__)
# when provided with dual barcodes, concatenate into a single
# namedtuple with attributes qual and qual1; generate a filter
# function appropriate for either case.
if len(args.index) == 1:
bcseqs = fastqlite(args.index[0])
qual_filter = get_qual_filter(args.min_qual, args.encoding)
elif len(args.index) == 2:
qual_filter = get_qual_filter(args.min_qual,
args.encoding,
paired=True)
bcseqs = combine_dual_indices(*args.index)
else:
log.error('error: please specify either one or two index files')
# use bc1 to determine most common barcode
bc1, bc2 = tee(bcseqs, 2)
# determine the most common barcode
barcode_counts = Counter(
[str(seq.seq) for seq in islice(bc1, args.snifflimit)])
barcodes, counts = list(zip(*barcode_counts.most_common()))
most_common_bc = barcodes[0]
most_common_pct = 100 * float(counts[0]) / sum(counts)
log.info('most common barcode: {} ({}/{} = {:.2f}%)'.format(
most_common_bc, counts[0], sum(counts), most_common_pct))
if args.show_counts:
for bc, count in barcode_counts.most_common():
print(('{}\t{}\t{}'.format(bc, seqdiff(most_common_bc, bc),
count)))
return None
if most_common_pct < args.min_pct_assignment:
msg = 'frequency of most common barcode is less than {}%'.format(
args.min_pct_assignment)
if args.strict:
log.error('Error: ' + msg)
sys.exit(1)
else:
log.warning('Warning: ' + msg)
if not args.fastq:
log.error('specify a fastq format file to filter using -f/--fastq')
sys.exit(1)
ifilterfun = filterfalse if args.invert else filter
seqs = fastqlite(args.fastq)
filtered = zip_longest(seqs, bc2)
if args.match_filter:
filtered = ifilterfun(get_match_filter(most_common_bc), filtered)
if args.qual_filter:
filtered = ifilterfun(qual_filter, filtered)
for seq, bc in islice(filtered, args.head):
assert seq.id == bc.id
args.outfile.write(as_fastq(seq))