def subparser(subparsers):
subparser = subparsers.add_parser('gather')
subparser.add_argument('query', help='query signature')
subparser.add_argument(
'databases',
nargs='+',
help='signatures/SBTs to search',
)
subparser.add_argument('-q',
'--quiet',
action='store_true',
help='suppress non-error output')
subparser.add_argument('-d', '--debug', action='store_true')
subparser.add_argument(
'-n',
'--num-results',
default=None,
type=int,
metavar='N',
help=
'number of results to report (default: terminate at --threshold-bp)')
subparser.add_argument('--traverse-directory',
action='store_true',
help='search all signatures underneath directories')
subparser.add_argument('-o',
'--output',
metavar='FILE',
help='output CSV containing matches to this file')
subparser.add_argument(
'--save-matches',
metavar='FILE',
help='save the matched signatures from the database to the '
'specified file')
subparser.add_argument(
'--threshold-bp',
metavar='REAL',
type=float,
default=5e4,
help=
'reporting threshold (in bp) for estimated overlap with remaining query (default=50kb)'
)
subparser.add_argument(
'--output-unassigned',
metavar='FILE',
help='output unassigned portions of the query as a signature to the '
'specified file')
subparser.add_argument(
'--scaled',
metavar='FLOAT',
type=float,
default=0,
help='downsample query to the specified scaled factor')
subparser.add_argument('--ignore-abundance',
action='store_true',
help='do NOT use k-mer abundances if present')
subparser.add_argument('--md5',
default=None,
help='select the signature with this md5 as query')
add_ksize_arg(subparser, 31)
add_moltype_args(subparser)
def subparser(subparsers):
subparser = subparsers.add_parser('categorize')
subparser.add_argument('sbt_name', help='name of SBT to load')
subparser.add_argument('queries',
nargs='+',
help='list of signatures to categorize')
subparser.add_argument('-q',
'--quiet',
action='store_true',
help='suppress non-error output')
add_ksize_arg(subparser, 31)
subparser.add_argument(
'--threshold',
default=0.08,
type=float,
help='minimum threshold for reporting matches; default=0.08')
subparser.add_argument('--traverse-directory', action="store_true")
subparser.add_argument('--ignore-abundance',
action='store_true',
help='do NOT use k-mer abundances if present')
add_moltype_args(subparser)
# TODO: help messages in these
subparser.add_argument('--csv', help='output summary CSV to this file')
subparser.add_argument('--load-csv', default=None)
def subparser(subparsers):
subparser = subparsers.add_parser('watch')
subparser.add_argument('sbt_name', help='name of SBT to search')
subparser.add_argument('inp_file', nargs='?', default='/dev/stdin')
subparser.add_argument('-q',
'--quiet',
action='store_true',
help='suppress non-error output')
subparser.add_argument('-o',
'--output',
help='save signature generated from data here')
subparser.add_argument('--threshold',
metavar='T',
default=0.05,
type=float,
help='minimum threshold for matches (default=0.05)')
subparser.add_argument(
'--input-is-protein',
action='store_true',
help='Consume protein sequences - no translation needed')
add_moltype_args(subparser)
subparser.add_argument(
'-n',
'--num-hashes',
type=int,
default=500,
help='number of hashes to use in each sketch (default: %(default)i)')
subparser.add_argument('--name',
type=str,
default='stdin',
help='name to use for generated signature')
add_ksize_arg(subparser, 31)
def subparser(subparsers):
subparser = subparsers.add_parser('filter')
subparser.add_argument('signatures', nargs='+')
subparser.add_argument('-q',
'--quiet',
action='store_true',
help='suppress non-error output')
subparser.add_argument(
'-o',
'--output',
metavar='FILE',
help='output signature to this file (default stdout)')
subparser.add_argument(
'--md5',
type=str,
default=None,
help='select signatures whose md5 contains this substring')
subparser.add_argument(
'--name',
type=str,
default=None,
help='select signatures whose name contains this substring')
subparser.add_argument('-m',
'--min-abundance',
type=int,
default=1,
help='keep hashes >= this minimum abundance')
subparser.add_argument('-M',
'--max-abundance',
type=int,
default=None,
help='keep hashes <= this maximum abundance')
add_ksize_arg(subparser, 31)
add_moltype_args(subparser)
def subparser(subparsers):
subparser = subparsers.add_parser('search')
subparser.add_argument('query', help='query signature')
subparser.add_argument(
'databases',
nargs='+',
help='signatures/SBTs to search',
)
subparser.add_argument('--traverse-directory',
action='store_true',
help='search all signatures underneath directories')
subparser.add_argument('-q',
'--quiet',
action='store_true',
help='suppress non-error output')
subparser.add_argument(
'--threshold',
metavar='T',
default=0.08,
type=float,
help='minimum threshold for reporting matches; default=0.08')
subparser.add_argument(
'--save-matches',
metavar='FILE',
help='output matching signatures to the specified file')
subparser.add_argument(
'--best-only',
action='store_true',
help='report only the best match (with greater speed)')
subparser.add_argument('-n',
'--num-results',
default=3,
type=int,
metavar='N',
help='number of results to report')
subparser.add_argument('--containment',
action='store_true',
help='evaluate containment rather than similarity')
subparser.add_argument(
'--ignore-abundance',
action='store_true',
help='do NOT use k-mer abundances if present; note: has no effect if '
'--containment is specified')
subparser.add_argument(
'--scaled',
metavar='FLOAT',
type=float,
default=0,
help='downsample query to this scaled factor (yields greater speed)')
subparser.add_argument('-o',
'--output',
metavar='FILE',
help='output CSV containing matches to this file')
subparser.add_argument('--md5',
default=None,
help='select the signature with this md5 as query')
add_ksize_arg(subparser, 31)
add_moltype_args(subparser)
def subparser(subparsers):
subparser = subparsers.add_parser('index',
description=__doc__,
usage=usage)
subparser.add_argument(
'sbt_name', help='name to save index into; .sbt.zip or .sbt.json file')
subparser.add_argument('signatures',
nargs='+',
help='signatures to load into SBT')
subparser.add_argument(
'--from-file',
help='a file containing a list of signatures file to load')
subparser.add_argument('-q',
'--quiet',
action='store_true',
help='suppress non-error output')
add_ksize_arg(subparser, 31)
subparser.add_argument(
'-d',
'--n_children',
metavar='D',
type=int,
default=2,
help='number of children for internal nodes; default=2')
subparser.add_argument(
'--traverse-directory',
action='store_true',
help='load all signatures underneath any directories')
subparser.add_argument('--append',
action='store_true',
default=False,
help='add signatures to an existing SBT')
subparser.add_argument('-x',
'--bf-size',
metavar='S',
type=float,
default=1e5,
help='Bloom filter size used for internal nodes')
subparser.add_argument(
'-f',
'--force',
action='store_true',
help='try loading all files with --traverse-directory')
subparser.add_argument(
'-s',
'--sparseness',
metavar='FLOAT',
type=float,
default=.0,
help='What percentage of internal nodes will not be saved; ranges '
'from 0.0 (save all nodes) to 1.0 (no nodes saved)')
subparser.add_argument(
'--scaled',
metavar='FLOAT',
type=float,
default=0,
help='downsample signatures to the specified scaled factor')
add_moltype_args(subparser)
def subparser(subparsers):
subparser = subparsers.add_parser('overlap')
subparser.add_argument('signature1')
subparser.add_argument('signature2')
subparser.add_argument('-q',
'--quiet',
action='store_true',
help='suppress non-error output')
add_ksize_arg(subparser, 31)
add_moltype_args(subparser)
def subparser(subparsers):
subparser = subparsers.add_parser('export')
subparser.add_argument('filename')
subparser.add_argument('-q',
'--quiet',
action='store_true',
help='suppress non-error output')
subparser.add_argument(
'-o',
'--output',
metavar='FILE',
help='output signature to this file (default stdout)')
add_ksize_arg(subparser, 31)
add_moltype_args(subparser)
def subparser(subparsers):
subparser = subparsers.add_parser('index')
subparser.add_argument('csv', help='taxonomy spreadsheet')
subparser.add_argument('lca_db_out', help='output database name')
subparser.add_argument(
'signatures', nargs='+',
help='one or more sourmash signatures'
)
subparser.add_argument(
'--scaled', metavar='S', default=10000, type=float
)
add_ksize_arg(subparser, 31)
add_moltype_args(subparser)
subparser.add_argument(
'-q', '--quiet', action='store_true',
help='suppress non-error output'
)
subparser.add_argument(
'-d', '--debug', action='store_true',
help='output debugging output'
)
subparser.add_argument(
'-C', '--start-column', metavar='C', default=2, type=int,
help='column at which taxonomic assignments start; default=2'
)
subparser.add_argument(
'--tabs', action='store_true',
help='input spreadsheet is tab-delimited; default is commas'
)
subparser.add_argument(
'--no-headers', action='store_true',
help='no headers present in taxonomy spreadsheet'
)
subparser.add_argument(
'--split-identifiers', action='store_true',
help='split names in signatures on whitspace and period'
)
subparser.add_argument('-f', '--force', action='store_true')
subparser.add_argument(
'--traverse-directory', action='store_true',
help='load all signatures underneath directories'
)
subparser.add_argument(
'--report', help='output a report on anomalies, if any'
)
subparser.add_argument(
'--require-taxonomy', action='store_true',
help='ignore signatures with no taxonomy entry'
)
def subparser(subparsers):
subparser = subparsers.add_parser('compare')
subparser.add_argument('signatures',
nargs='*',
help='list of signatures to compare',
default=[])
subparser.add_argument('-q',
'--quiet',
action='store_true',
help='suppress non-error output')
add_ksize_arg(subparser)
add_moltype_args(subparser)
subparser.add_argument(
'-o',
'--output',
metavar='F',
help='file to which output will be written; default is terminal '
'(standard output)')
subparser.add_argument('--ignore-abundance',
action='store_true',
help='do NOT use k-mer abundances even if present')
subparser.add_argument('--containment',
action='store_true',
help='calculate containment instead of similarity')
subparser.add_argument(
'--traverse-directory',
action='store_true',
help='compare all signatures underneath directories')
subparser.add_argument(
'--from-file',
help='a file containing a list of signatures file to compare')
subparser.add_argument('-f',
'--force',
action='store_true',
help='continue past errors in file loading')
subparser.add_argument(
'--csv',
metavar='F',
help='write matrix to specified file in CSV format (with column '
'headers)')
subparser.add_argument(
'-p',
'--processes',
metavar='N',
type=int,
default=None,
help='Number of processes to use to calculate similarity')
def subparser(subparsers):
subparser = subparsers.add_parser('merge')
subparser.add_argument('signatures', nargs='+')
subparser.add_argument('-q',
'--quiet',
action='store_true',
help='suppress non-error output')
subparser.add_argument(
'-o',
'--output',
metavar='FILE',
help='output signature to this file (default stdout)')
subparser.add_argument('--flatten',
action='store_true',
help='remove abundances from all signatures')
add_ksize_arg(subparser, 31)
add_moltype_args(subparser)
def subparser(subparsers):
subparser = subparsers.add_parser('rename')
subparser.add_argument('sigfiles', nargs='+')
subparser.add_argument('name')
subparser.add_argument('-q',
'--quiet',
action='store_true',
help='suppress non-error output')
subparser.add_argument('-d',
'--debug',
action='store_true',
help='print debugging output')
subparser.add_argument('-o',
'--output',
metavar='FILE',
help='output to this file')
add_ksize_arg(subparser, 31)
add_moltype_args(subparser)
def subparser(subparsers):
subparser = subparsers.add_parser('intersect')
subparser.add_argument('signatures', nargs='+')
subparser.add_argument('-q',
'--quiet',
action='store_true',
help='suppress non-error output')
subparser.add_argument(
'-o',
'--output',
metavar='FILE',
help='output signature to this file (default stdout)')
subparser.add_argument(
'-A',
'--abundances-from',
metavar='FILE',
help='intersect with & take abundances from this signature')
add_ksize_arg(subparser, 31)
add_moltype_args(subparser)
def subparser(subparsers):
subparser = subparsers.add_parser('downsample')
subparser.add_argument('signatures', nargs="+")
subparser.add_argument(
'--scaled', type=int, default=0,
help='scaled value to downsample to'
)
subparser.add_argument(
'--num', metavar='N', type=int, default=0,
help='num value to downsample to'
)
subparser.add_argument(
'-q', '--quiet', action='store_true',
help='suppress non-error output'
)
subparser.add_argument(
'-o', '--output', metavar='FILE',
help='output signature to this file (default stdout)'
)
add_ksize_arg(subparser, 31)
add_moltype_args(subparser)
def subparser(subparsers):
subparser = subparsers.add_parser('extract')
subparser.add_argument('signatures', nargs='+')
subparser.add_argument('-q',
'--quiet',
action='store_true',
help='suppress non-error output')
subparser.add_argument(
'-o',
'--output',
metavar='FILE',
help='output signature to this file (default stdout)')
subparser.add_argument(
'--md5',
default=None,
help='select signatures whose md5 contains this substring')
subparser.add_argument(
'--name',
default=None,
help='select signatures whose name contains this substring')
add_ksize_arg(subparser, 31)
add_moltype_args(subparser)
def subparser(subparsers):
subparser = subparsers.add_parser('multigather')
subparser.add_argument(
'--query', nargs='*', default=[], action='append',
help='query signature'
)
subparser.add_argument(
'--query-from-file',
help='file containing list of signature files to query'
)
subparser.add_argument(
'--db', nargs='+', action='append',
help='signatures/SBTs to search',
)
subparser.add_argument(
'-q', '--quiet', action='store_true',
help='suppress non-error output'
)
subparser.add_argument(
'-d', '--debug', action='store_true'
)
subparser.add_argument(
'--traverse-directory', action='store_true',
help='search all signatures underneath directories'
)
subparser.add_argument(
'--threshold-bp', metavar='REAL', type=float, default=5e4,
help='threshold (in bp) for reporting results (default=50,000)'
)
subparser.add_argument(
'--scaled', metavar='FLOAT', type=float, default=0,
help='downsample query to the specified scaled factor'
)
subparser.add_argument(
'--ignore-abundance', action='store_true',
help='do NOT use k-mer abundances if present'
)
add_ksize_arg(subparser, 31)
add_moltype_args(subparser)
def main():
p = argparse.ArgumentParser()
p.add_argument('signatures', nargs='+')
p.add_argument('-q',
'--quiet',
action='store_true',
help='suppress non-error output')
p.add_argument('-o',
'--output',
metavar='FILE',
help='output histogram to this file (in CSV format)')
p.add_argument(
'--abundances',
metavar='FILE',
help='output hashes and abundances to this file (in CSV format)')
p.add_argument('--md5',
default=None,
help='select signatures whose md5 contains this substring')
p.add_argument('--name',
default=None,
help='select signatures whose name contains this substring')
p.add_argument('--max',
type=int,
default=None,
help='max value for histogram range (default none)')
p.add_argument('--min',
type=int,
default=None,
help='min value for histogram range (default none)')
p.add_argument('--bins',
type=int,
default=10,
help='number of bins (default 10)')
add_ksize_arg(p, 31)
add_moltype_args(p)
args = p.parse_args()
return abundhist(args)
def subparser(subparsers):
subparser = subparsers.add_parser('dump')
subparser.add_argument('filenames', nargs='+')
add_ksize_arg(subparser, 31)
