def __init__(self, output_dir):
"""Initialization."""
check_dependencies(['blastn', 'makeblastdb'])
if not os.path.exists(output_dir):
os.makedirs(output_dir)
self.output_dir = output_dir
logger_setup(output_dir, "in_silico_probes.log", "in_silico_probes", __version__, False)
self.logger = logging.getLogger('timestamp')
self.output_fmt = '6 qseqid qlen qseq sseqid slen sseq length mismatch gaps pident bitscore evalue'
self.BlastHit = namedtuple('BlastHit', """query_id
query_len
query_aln_seq
subject_id
subject_len
subject_aln_seq
aln_len
mismatch
gaps
perc_identity
bitscore
evalue""")
def __init__(self, tmp_dir, output_dir, cpus):
"""Initialization."""
self.tmp_dir = tmp_dir
self.output_dir = output_dir
self.cpus = cpus
check_dependencies(['prodigal', 'hmmsearch', 'pfam_search.pl', 'genometk'])
self.tigrfam_hmms = '/srv/whitlam/bio/db/tigrfam/15.0/TIGRFAMs_15.0_HMM/tigrfam.hmm'
self.tigrfam_ext = '_tigrfam.tsv'
self.pfam_hmm_dir = '/srv/db/pfam/27/'
self.pfam_ext = '_pfam.tsv'
self.protein_file_ext = '_protein.faa'
logger_setup(output_dir, "gtdb_protein_pipeline.log", "gtdb_protein_pipeline", __version__, False)
self.logger = logging.getLogger('timestamp')
def main():
# initialize the option parser
parser = argparse.ArgumentParser(
add_help=False,
description=
"BAM-Tk is a software toolkit for dealing with Binary Alignment Map (BAM) files.",
epilog="Written by Corentin Hochart ([email protected]), "
+ "UMR CNRSS 6023 Laboratoire Genome et Environement (LMGE), " +
"as part of the [ANR Eureka](https://anr.fr/Projet-ANR-14-CE02-0004) project."
+ "Released under the terms of the GNU General Public License v3. " +
"bamtk version %s." % version())
subparsers = parser.add_subparsers(help="--", dest='subparser_name')
# pathway reconstruction
mm_featuresparser = subparsers.add_parser('mm_features', description='')
mm_featuresparser.add_argument(
'faidx', help='samtools fasta index of the reference')
mm_featuresparser.add_argument(
'bam_list', help='list of bam format alignement file(s) path')
mm_featuresparser.add_argument('output_dir',
help='directory to write output files')
mm_featuresinput_argument = mm_featuresparser.add_argument_group(
'optional input arguments')
mm_featuresinput_argument.add_argument('-x',
'--extension',
help='bam file prefix',
default='bam')
mm_featuresinput_argument.add_argument('-fx',
'--faidx_extension',
help='faidx file prefix',
default='fasta.fai')
mm_featuresinput_argument.add_argument(
'-t',
'--threads',
help='threads number for "samtools view"',
default='2')
mm_featuresinput_argument.add_argument(
'-Q',
'--mapQ',
help='only include reads with mapping quality >= INT [10]',
default='10')
mm_featuresinput_argument.add_argument(
'-i',
'--id_cutoff',
help='only include reads with identity >= INT [0]',
default=0)
mm_featuresinput_argument.add_argument(
'-m',
'--merge',
help='merge features abundance by field',
action='store_true')
mm_featuresinput_argument.add_argument(
'-s',
'--separator',
help='filed separator for -m/--merge argument',
default='.')
mm_featuresinput_argument.add_argument(
'-g',
'--genome',
help='sum abundance of all features',
action='store_true')
mm_featuresoutput_argument = mm_featuresparser.add_argument_group(
'optional output arguments')
mm_featuresoutput_argument.add_argument(
'-n',
'--feature_normalisation',
help="get the number of features per X reads [Default: 1000000]",
default=1000000,
type=int)
mm_featuresoutput_argument.add_argument(
'-sn',
'--feature_size_normalisation',
help="get the number of features per X bases [Default: 1000]",
default=1000,
type=int)
mm_featuresoutput_argument.add_argument(
'-f',
'--discard_feature_length_normalisation',
help=
"discard feature length normalisation for base count abundance output",
action='store_true')
mm_featuresoutput_argument.add_argument(
'-l',
'--discard_library_size_normalisation',
help=
"discard library size normalisation for reads and bases count abundance output",
action='store_true')
mm_featuresoutput_argument.add_argument(
'-lsn',
'--library_size_normalisation',
help=
"library size normalisation by total number of reads count or by number of aligned reads ",
choices=['total', 'aligned'],
default='total')
mm_featuresoutput_argument.add_argument(
'--removed',
help=
"removed features who do not appears in samples (sum of abundance through sample = 0)",
action='store_true')
mm_featuresparser.add_argument('--silent',
help='suppress output of logger',
action='store_true')
mm_featuresparser.add_argument(
'--force_overwrite',
help='force overwriting of output directory',
action="store_true",
default=False)
mm_featuresparser.add_argument('--version',
help='print version and exit',
action='version',
version='bamtk ' + version())
mm_annotated_features_parser = subparsers.add_parser(
'mm_annotated_features', description='')
mm_annotated_features_parser.add_argument(
'features_dir', help='directory specified during features command')
mm_annotated_features_parser.add_argument(
'features_annotation',
help='features annotation file in tabular format')
mm_annotated_features_parser.add_argument(
'annotation_description',
help='annotation description file in tabular format')
mm_annotated_features_input_argument = mm_annotated_features_parser.add_argument_group(
'optional input arguments')
mm_annotated_features_input_argument.add_argument(
'--library_size',
help=
"Tabular file with sample library size to produce normalised count matrix"
)
mm_annotated_features_output_argument = mm_annotated_features_parser.add_argument_group(
'optional output arguments')
mm_annotated_features_output_argument.add_argument(
'-f',
'--feature_normalisation',
help="get the number of features per X reads [Default: 1000000]",
default=1000000,
type=int)
mm_annotated_features_output_argument.add_argument(
'--removed',
help=
"removed features who do not appears in samples (sum of abundance through sample = 0)",
action='store_true')
mm_annotated_features_parser.add_argument('--silent',
help='suppress output of logger',
action='store_true')
mm_annotated_features_parser.add_argument(
'--force_overwrite',
help='force overwriting of output directory',
action="store_true",
default=False)
mm_wf_parser = subparsers.add_parser(
'mm_wf',
description='Run features and annotate_features command',
epilog=
'bamtk mm_wf ./file.fai ./bam_list.tsv ./features2annotation.tsv ./annotationDescription.tsv ./output'
)
mm_wf_parser.add_argument('faidx',
help='samtools fasta index of the reference')
mm_wf_parser.add_argument(
'bam_list', help='list of bam format alignement file(s) path ')
mm_wf_parser.add_argument(
'features_annotation',
help='features annotation file in tabular format')
mm_wf_parser.add_argument(
'annotation_description',
help='annotation description file in tabular format')
mm_wf_parser.add_argument('output_dir',
help='directory to write output files')
mm_wf_input_argument = mm_wf_parser.add_argument_group(
'optional input arguments')
mm_wf_input_argument.add_argument('-x',
'--extension',
help='bam file prefix',
default='bam')
mm_wf_input_argument.add_argument('-fx',
'--faidx_extension',
help='faidx file prefix',
default='fasta.fai')
mm_wf_input_argument.add_argument(
'-t',
'--threads',
help='threads number for "samtools view"',
default='2')
mm_wf_input_argument.add_argument(
'-Q',
'--mapQ',
help='only include reads with mapping quality >= INT [10]',
default='10')
mm_wf_input_argument.add_argument(
'-i',
'--id_cutoff',
help='only include reads with identity >= INT [0]',
default=0)
mm_wf_output_argument = mm_wf_parser.add_argument_group(
'optional output arguments')
mm_wf_output_argument.add_argument(
'-f',
'--feature_normalisation',
help="get the number of features per X reads [Default: 1000000]",
default=1000000,
type=int)
mm_wf_output_argument.add_argument(
'-g',
'--discard_gene_length_normalisation',
help=
"discard gene length normalisation for base count abundance output",
action='store_true')
mm_wf_output_argument.add_argument(
'--removed',
help=
"removed features who do not appears in samples (sum of abundance through sample = 0)",
action='store_true')
mm_wf_parser.add_argument('--silent',
help='suppress output of logger',
action='store_true')
mm_wf_parser.add_argument('--force_overwrite',
help='force overwriting of output directory',
action="store_true",
default=False)
mm_wf_parser.add_argument('--version',
help='print version and exit',
action='version',
version='bamtk ' + version())
# get and check options
args = None
if (len(sys.argv) == 1 or sys.argv[1] == '-h' or sys.argv == '--help'):
print_help()
sys.exit(0)
else:
args = parser.parse_args()
try:
logger_setup(args.output_dir, "bamtk.log", "bamtk", version(),
args.silent)
except:
logger_setup(None, "bamtk.log", "bamtk", version(), args.silent)
try:
parser = OptionsParser()
if (False):
import cProfile
cProfile.run('parser.parse_options(args)')
else:
parser.parse_options(args)
except SystemExit:
print('Unrecoverable error.')
except:
print("\nUnexpected error:", sys.exc_info()[0])
raise
def main():
parser = argparse.ArgumentParser(
description="This script allow the construction of abundance" +
"matrix from a list of bam file.",
epilog="Written by Corentin Hochart ([email protected]), " +
"UMR CNRSS 6023 Laboratoire Genome et Environement (LMGE). " +
"Released under the terms of the GNU General Public License v3. " +
"MAMa version %s." % version())
parser.add_argument('faidx', help='samtools fasta index of the reference')
parser.add_argument('bam_list',
help='list of bam format alignement file(s) path ')
input_argument = parser.add_argument_group('optional input arguments')
input_argument.add_argument('-x',
'--extension',
help='bam file prefix',
default='bam')
input_argument.add_argument('-t',
'--threads',
help='threads number for "samtools view"',
default='2')
input_argument.add_argument(
'-Q',
'--mapQ',
help='only include reads with mapping quality >= INT [10]',
default='10')
input_argument.add_argument(
'-i',
'--id_cutoff',
help='only include reads with identity >= INT [0]',
default=0)
output_argument = parser.add_argument_group('optional output arguments')
output_argument.add_argument('-a',
'--abundance',
help="reads count abundance output")
output_argument.add_argument(
'-n',
'--normalised',
help=
"reads count normalised abundance output (feature per X reads ; see '-f' argument)"
)
output_argument.add_argument('-r',
'--relative',
help="reads count relative abundance output")
output_argument.add_argument('-ba',
'--base_abundance',
help="base count abundance output")
output_argument.add_argument(
'-bn',
'--base_normalised',
help=
"base count normalised abundance output (feature per X reads ; see '-f' argument)"
)
output_argument.add_argument('-br',
'--base_relative',
help="base count relative abundance output")
output_argument.add_argument(
'-f',
'--feature_normalisation',
help="get the numer of features per X reads [Default: 1000000]",
default=1000000,
type=int)
output_argument.add_argument(
'-g',
'--discard_gene_length_normalisation',
help=
"discard gene length normalisation for base count abundance output",
action='store_true')
output_argument.add_argument(
'--removed',
help=
"removed features who do not appears in samples (sum of abundance through sample = 0)",
action='store_true')
parser.add_argument('--silent',
help='suppress output of logger',
action='store_true')
parser.add_argument('--version',
help='print version and exit',
action='version',
version='MAMa ' + version())
args = parser.parse_args()
try:
logger_setup('log', "MAMa.log", "MAMa", version(), args.silent)
except:
logger_setup(None, "MAMa.log", "MAMa", version(), args.silent)
if not args.abundance and not args.normalised and not args.relative:
parser.error(
'''At least one output file name must be specified with '--relative' and/or '--normalised' and/or '--abundance'.'''
)
matrix_maker(args.faidx, args.bam_list, args.extension, args.threads,
args.mapQ, args.id_cutoff, args.abundance, args.normalised,
args.relative, args.base_abundance, args.base_normalised,
args.base_relative, args.feature_normalisation,
args.discard_gene_length_normalisation, args.removed)
unroot_tree_parser.add_argument('input_tree', help='')
unroot_tree_parser.add_argument('output_tree', help='')
unroot_tree_parser.add_argument('--silent',
help="suppress output",
action='store_true')
# get and check options
args = None
if (len(sys.argv) == 1 or sys.argv[1] == '-h' or sys.argv == '--help'):
print_help()
sys.exit(0)
else:
args = parser.parse_args()
try:
logger_setup(args.output_dir, 'gtdbtk_toolset.log',
'GTDB Tk converter', version(), args.silent)
except:
logger_setup(None, 'gtdbtk_toolset.log', 'GTDB Tk converter',
__version__, args.silent)
# do what we came here to do
try:
parser = OptionsParser()
if False:
# import pstats
# p = pstats.Stats('prof')
# p.sort_stats('cumulative').print_stats(10)
# p.sort_stats('time').print_stats(10)
import cProfile
cProfile.run('parser.parse_options(args)', 'prof')
type=float,
default=0.25,
help=
'minimum percentage of the same amino acid required to retain column')
parser.add_argument(
'--max_consensus',
type=float,
default=0.95,
help=
'maximum percentage of the same amino acid required to retain column')
parser.add_argument(
'--min_perc_taxa',
type=float,
default=0.50,
help='minimum percentage of taxa required to retain column')
parser.add_argument('--out_dir', help='output directory')
args = parser.parse_args()
logger_setup(args.out_dir, "trim_msa.log", "trim_msa", __version__, False)
try:
p = TrimMSA(args.cols_per_gene, args.min_perc_aa, args.min_consensus,
args.max_consensus, args.min_perc_taxa, args.out_dir)
p.run(args.msa, args.marker_list)
except SystemExit:
print "\nControlled exit resulting from an unrecoverable error or warning."
except:
print "\nUnexpected error:", sys.exc_info()[0]
raise