def test_eq(self):
a = OptionParam(flag='-i', name='input')
b = OptionParam(flag='-i', name='i')
self.assertEqual(a, b)
a.on(2)
b.on(1)
self.assertNotEqual(a, b)
a = OptionParam(flag='-o', name='i')
b = OptionParam(flag='-i', name='i')
self.assertNotEqual(a, b)
def run_cmpress(cm, force=False):
'''Compress the CM database.
Parameters
----------
cm : str
The file path to CM database.
force : boolean
Whether to overwrite.'''
params = [
OptionParam('-F', name='force', help='force overwrite'),
ArgmntParam(name='cm', help='cm file to press')]
cmpress = Dumpling('cmpress', params=Parameters(*params))
cmpress.update(cm=cm, force=force)
cmpress()
return cmpress
def run_hmmpress(hmm, force=False):
'''Compress the HMM database.
Parameters
----------
hmm : str
The file path to HMM database.
force : boolean
Whether to overwrite.'''
params = [
OptionParam('-f', name='force', help='force overwrite'),
ArgmntParam(name='hmm', help='hmm file to press')
]
hmmpress = Dumpling('hmmpress', params=Parameters(*params))
hmmpress.update(hmm=hmm, force=force)
hmmpress()
return hmmpress
from os.path import join
from os import makedirs
from logging import getLogger
import re
from skbio import read
from skbio.metadata import Feature
from skbio.io.format.genbank import _parse_features
from dumpling import (check_choice, Dumpling, OptionParam, Parameters)
from ..parsers.embl import _parse_records
params = [
OptionParam('-i',
'query',
help='FASTA/Genbank input file (default reads from stdin).'),
OptionParam('-a', help='File to store protein translations.'),
OptionParam('-d', help='File to store nuc sequence of predicted gene.'),
OptionParam(
'-s',
help='Write all potential genes (with scores) to the selected file.'),
OptionParam('-t',
help=('Write a training file (if none exists); '
'otherwise, read and use the specified training file.')),
OptionParam('-o', 'output',
help='output file (default writes to stdout).'),
OptionParam('-f',
'fmt',
action=check_choice(('gbk', 'gff', 'sco')),
help='output format (gbk, gff, or sco). Default is gbk.'),
#
# Distributed under the terms of the Modified BSD License.
#
# The full license is in the file COPYING.txt, distributed with this software.
# ----------------------------------------------------------------------------
from logging import getLogger
from os.path import exists, join, basename, splitext
from subprocess import CalledProcessError
from dumpling import check_range, Dumpling, ArgmntParam, OptionParam, Parameters
params = [
OptionParam('-searchWL',
action=check_range(6, 9),
help='Length of search window used to discover CRISPRs (range: 6-9). Default: 8'),
OptionParam('-minNR', help='Minimum number of repeats a CRISPR must contain. Default: 3'),
OptionParam('-minRL', help='Minimum length of the CRISPR repeats. Default: 23'),
OptionParam('-maxRL', help='Maximum length of the CRISPR repeats. Default: 47'),
OptionParam('-minSL', help='Minimum length of the CRISPR spacers. Default: 26'),
OptionParam('-maxSL', help='Maximum length of the CRISPR spacers. Default: 50'),
OptionParam('-gff',
help='Output summary results in gff format containing only the positions of the CRISPR arrays. Default: false'),
OptionParam('-gffFull',
help='Output detailed results in gff format containing positions of CRISPR arrays and all repeat units. Default: false'),
OptionParam('-spacers',
help='Output a fasta formatted file containing the spacers. Default: false'),
OptionParam('-h', help='Output this handy help message'),
ArgmntParam(name='query', help='input file of fna sequence'),
# ----------------------------------------------------------------------------
# Copyright (c) 2015--, micronota development team.
#
# Distributed under the terms of the Modified BSD License.
#
# The full license is in the file COPYING.txt, distributed with this software.
# ----------------------------------------------------------------------------
from dumpling import OptionParam, ArgmntParam
_scan_params = [
OptionParam('--tblout',
name='out',
help='save parseable table of hits to file'),
# set default to 1 instead of all available cores.
OptionParam('--cpu',
name='cpus',
value=1,
help='number of parallel CPU workers to use for multithreads'),
ArgmntParam(name='db', help='HMM/CM database file'),
ArgmntParam(name='query', help='input sequence to scan')
]
#
# Distributed under the terms of the Modified BSD License.
#
# The full license is in the file COPYING.txt, distributed with this software.
# ----------------------------------------------------------------------------
from logging import getLogger
from os.path import join, splitext, basename
from dumpling import Dumpling, OptionParam, ArgmntParam, Parameters
from ._base import _scan_params
cmscan_params = [
OptionParam('--rfam', help='Set all filter thresholds as if the search space were more than 20 Gb.'),
OptionParam('--noali', value=True,
help='Omit the alignment section from the main output. This can greatly reduce the output volume.')]
cmscan_params.extend(_scan_params)
def run_cmpress(cm, force=False):
'''Compress the CM database.
Parameters
----------
cm : str
The file path to CM database.
force : boolean
Whether to overwrite.'''
params = [
#
# Distributed under the terms of the Modified BSD License.
#
# The full license is in the file COPYING.txt, distributed with this software.
# ----------------------------------------------------------------------------
from os.path import join, basename, splitext
from logging import getLogger
import re
import pandas as pd
from dumpling import (check_choice, Dumpling, OptionParam, Parameters)
blast_params = [
OptionParam('--threads', 'cpus', help='number of cpu threads.'),
OptionParam('--gapopen', help='Gap open penalty.'),
OptionParam('--gapextend', help='Gap extension penalty.'),
OptionParam('--matrix', help='Scoring matrix.'),
OptionParam('--seg', help='Enable SEG masking.'),
OptionParam(
'--max-target-seqs',
'-k',
help='The maximum number of hits per query to keep alignments for.'),
OptionParam(
'--top',
help=
'Keep alignments within the given percentage range of the top alignment'
),
OptionParam('--evalue',
'-e',