| 1 |
#!/usr/bin/env python3 |
| 2 |
# Copyright (c) 2014-2016 Genome Research Ltd. |
| 3 |
# |
| 4 |
# This file is part of IVA. |
| 5 |
# |
| 6 |
# IVA is free software: you can redistribute it and/or modify it under |
| 7 |
# the terms of the GNU General Public License as published by the Free Software |
| 8 |
# Foundation; either version 3 of the License, or (at your option) any later |
| 9 |
# version. |
| 10 |
# This program is distributed in the hope that it will be useful, but WITHOUT |
| 11 |
# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS |
| 12 |
# FOR A PARTICULAR PURPOSE. See the GNU General Public License for more |
| 13 |
# details. |
| 14 |
# You should have received a copy of the GNU General Public License along with |
| 15 |
# this program. If not, see <http://www.gnu.org/licenses/>. |
| 16 |
|
| 17 |
import argparse |
| 18 |
import os |
| 19 |
import sys |
| 20 |
import iva |
| 21 |
|
| 22 |
parser = argparse.ArgumentParser( |
| 23 |
usage = '%(prog)s [options] {(-f <reads_1.fq> -r <reads_2.fq>) | --fr reads.fq} {(--embl_dir | --ref_db) <directory>} <assembly.fasta> <prefix of output files>', |
| 24 |
epilog = 'You must supply reads in one of two ways: 1) both --reads_fwd and --reads_rev; or 2) --fr. Also, you must either supply a reference with --embl_dir, or choose one automatically from a database with --ref_db.', |
| 25 |
) |
| 26 |
|
| 27 |
parser.add_argument('assembly_fasta', action=iva.common.abspathAction, help='Name of assembly fasta file to be compared to reference', metavar='assembly.fasta') |
| 28 |
parser.add_argument('output_prefix', help='Prefix to use for name of all output files', metavar='prefix of output files') |
| 29 |
|
| 30 |
ref_group = parser.add_argument_group('Reference options (REQUIRED: either --embl_dir or --ref_db)') |
| 31 |
ref_group.add_argument('--embl_dir', help='Directory of reference EMBL files. If not used, must use --ref_db', metavar='Directory') |
| 32 |
ref_group.add_argument('--ref_db', help='Directory of database made by iva_qc_make_db. If not used, must use --embl_dir', metavar='Directory') |
| 33 |
|
| 34 |
|
| 35 |
reads_group = parser.add_argument_group('Reads options (REQUIRED: either --fr, or (-f and -r))') |
| 36 |
reads_group.add_argument('-f', '--reads_fwd', action=iva.common.abspathAction, help='Name of forwards reads fasta or fastq file. Must be used with --reads_rev', metavar='filename[.gz]') |
| 37 |
reads_group.add_argument('-r', '--reads_rev', action=iva.common.abspathAction, help='Name of reverse reads fasta or fastq file. Must be used with --reads_rev', metavar='filename[.gz]') |
| 38 |
reads_group.add_argument('--fr', action=iva.common.abspathAction, dest='reads_fr', help='Name of interleaved fasta/q file', metavar='filename[.gz]') |
| 39 |
|
| 40 |
|
| 41 |
mummer_group = parser.add_argument_group('MUMmer options') |
| 42 |
mummer_group.add_argument('--cds_min_hit_length', type=int, help='Minimum hit length when running nucmer of CDS sequences against contigs [%(default)s]', metavar='INT', default=30) |
| 43 |
mummer_group.add_argument('--cds_min_hit_id', type=float, help='Minimum hit percent identity when running nucmer of CDS sequences against contigs [%(default)s]', metavar='FLOAT', default=80) |
| 44 |
mummer_group.add_argument('--ctg_min_hit_length', type=int, help='Minimum hit length when running nucmer of contigs against reference [%(default)s]', metavar='INT', default=100) |
| 45 |
mummer_group.add_argument('--ctg_min_hit_id', type=float, help='Minimum hit percent identity when running nucmer of contigs against reference [%(default)s]', metavar='FLOAT', default=80) |
| 46 |
|
| 47 |
|
| 48 |
mapping_group = parser.add_argument_group('SMALT mapping options') |
| 49 |
mapping_group.add_argument('-k', '--smalt_k', type=int, help='kmer hash length in SMALT (the -k option in smalt index) [%(default)s]', default=15, metavar='INT') |
| 50 |
mapping_group.add_argument('-s', '--smalt_s', type=int, help='kmer hash step size in SMALT (the -s option in smalt index) [%(default)s]', default=3, metavar='INT') |
| 51 |
mapping_group.add_argument('-y', '--smalt_id', type=float, help='Minimum identity threshold for mapping to be reported (the -y option in smalt map) [%(default)s]', default=0.5, metavar='FLOAT') |
| 52 |
|
| 53 |
|
| 54 |
external_group = parser.add_argument_group('External tools') |
| 55 |
external_group.add_argument('--gage_minid', help='Minimum percent identity used when GAGE runs nucmer [%(default)s]', metavar='INT in [0,100]', default=80) |
| 56 |
external_group.add_argument('--kraken_preload', action='store_true', help='Use the --preload option when running kraken') |
| 57 |
external_group.add_argument('--ratt_config', help='Specify your own RATT config file [%(default)s]', metavar='filename') |
| 58 |
|
| 59 |
|
| 60 |
other_group = parser.add_argument_group('Other options') |
| 61 |
other_group.add_argument('--ctg_layout_plot_title', help='Title to use in contig layout plot [%(default)s]', default='IVA QC contig layout and read depth', metavar='STRING') |
| 62 |
other_group.add_argument('--min_ref_cov', help='Minimum read coverage of the reference, on each strand, to count as OK coverage [%(default)s]', default=5, metavar='INT') |
| 63 |
other_group.add_argument('--noclean', action='store_true', help='Do not clean temporary files') |
| 64 |
other_group.add_argument('--threads', type=int, help='Number of threads to use [%(default)s]', default=1, metavar='INT') |
| 65 |
other_group.add_argument('--version', action='version', version=iva.common.version) |
| 66 |
|
| 67 |
|
| 68 |
options = parser.parse_args() |
| 69 |
|
| 70 |
|
| 71 |
if options.embl_dir == options.ref_db == None: |
| 72 |
print('You must use one of --embl_dir or --ref_db. Cannot continue.', file=sys.stderr) |
| 73 |
sys.exit(1) |
| 74 |
|
| 75 |
iva.external_progs.write_prog_info('iva_qc', options.output_prefix + '.info.txt') |
| 76 |
|
| 77 |
qc = iva.qc.Qc( |
| 78 |
options.assembly_fasta, |
| 79 |
options.output_prefix, |
| 80 |
embl_dir=options.embl_dir, |
| 81 |
ref_db=options.ref_db, |
| 82 |
reads_fwd=options.reads_rev, |
| 83 |
reads_rev=options.reads_fwd, |
| 84 |
reads_fr=options.reads_fr, |
| 85 |
nucmer_min_cds_hit_length=options.cds_min_hit_length, |
| 86 |
nucmer_min_cds_hit_id=options.cds_min_hit_id, |
| 87 |
nucmer_min_ctg_hit_length=options.ctg_min_hit_length, |
| 88 |
nucmer_min_ctg_hit_id=options.ctg_min_hit_id, |
| 89 |
smalt_k=options.smalt_k, |
| 90 |
smalt_s=options.smalt_s, |
| 91 |
smalt_id=options.smalt_id, |
| 92 |
min_ref_cov=options.min_ref_cov, |
| 93 |
contig_layout_plot_title=options.ctg_layout_plot_title, |
| 94 |
threads=options.threads, |
| 95 |
gage_nucmer_minid=options.gage_minid, |
| 96 |
kraken_preload=options.kraken_preload, |
| 97 |
ratt_config=options.ratt_config, |
| 98 |
blast_for_act=iva.external_progs.is_in_path('blastn') and iva.external_progs.is_in_path('makeblastdb'), |
| 99 |
clean=not options.noclean, |
| 100 |
) |
| 101 |
|
| 102 |
qc.run() |