def proc_args(argv):
info(' '.join(sys.argv))
info()
description = 'This script generates target QC reports for each BAM provided as an input. ' \
'Usage: ' + basename(__file__) + ' sample2bam.tsv --bed target.bed --contols sample1:sample2 -o results_dir'
parser = OptionParser(description=description, usage=description)
add_cnf_t_reuse_prjname_donemarker_workdir_genome_debug(parser)
parser.add_option('-o', dest='output_dir', metavar='DIR', default=join(os.getcwd(), 'seq2c'))
parser.add_option('--bed', dest='bed', help='BED file to run Seq2C analysis')
parser.add_option('-c', '--controls', dest='controls', help='Optional control sample names for Seq2C. For multiple controls, separate them using :')
parser.add_option('--seq2c-opts', dest='seq2c_opts', help='Options for the final lr2gene.pl script.')
parser.add_option('--no-prep-bed', dest='prep_bed', help=SUPPRESS_HELP, action='store_false', default=True)
(opts, args) = parser.parse_args()
logger.is_debug = opts.debug
if len(args) == 0:
parser.print_usage()
sys.exit(1)
if len(args) == 1 and not args[0].endswith('.bam'):
sample_names, bam_fpaths = read_samples(verify_file(args[0], is_critical=True, description='Input sample2bam.tsv'))
bam_by_sample = OrderedDict()
for s, b in zip(sample_names, bam_fpaths):
bam_by_sample[s] = b
else:
bam_by_sample = find_bams(args)
run_cnf = determine_run_cnf(opts, is_wgs=not opts.__dict__.get('bed'))
cnf = Config(opts.__dict__, determine_sys_cnf(opts), run_cnf)
check_genome_resources(cnf)
cnf.output_dir = adjust_path(cnf.output_dir)
verify_dir(dirname(cnf.output_dir), is_critical=True)
safe_mkdir(cnf.output_dir)
if not cnf.project_name:
cnf.project_name = basename(cnf.output_dir)
info('Project name: ' + cnf.project_name)
cnf.proc_name = 'Seq2C'
set_up_dirs(cnf)
samples = [
source.TargQC_Sample(name=s_name, dirpath=join(cnf.output_dir, s_name), bam=bam_fpath)
for s_name, bam_fpath in bam_by_sample.items()]
info('Samples: ')
for s in samples:
info(' ' + s.name)
samples.sort(key=lambda _s: _s.key_to_sort())
target_bed = verify_bed(cnf.bed, is_critical=True) if cnf.bed else None
if not cnf.only_summary:
cnf.qsub_runner = adjust_system_path(cnf.qsub_runner)
if not cnf.qsub_runner: critical('Error: qsub-runner is not provided is sys-config.')
verify_file(cnf.qsub_runner, is_critical=True)
return cnf, samples, target_bed, cnf.output_dir
def main():
info(' '.join(sys.argv))
info()
description = 'This script generates target QC reports for each BAM provided as an input.'
parser = OptionParser(description=description)
add_cnf_t_reuse_prjname_donemarker_workdir_genome_debug(parser, threads=1)
parser.add_option('--work-dir', dest='work_dir', metavar='DIR')
parser.add_option('--log-dir', dest='log_dir')
parser.add_option('--only-summary',
dest='only_summary',
action='store_true')
parser.add_option('-o',
dest='output_dir',
metavar='DIR',
default=join(os.getcwd(), 'targetqc'))
parser.add_option('--reannotate',
dest='reannotate',
action='store_true',
default=False,
help='re-annotate BED file with gene names')
parser.add_option('--dedup',
dest='dedup',
action='store_true',
default=False,
help='count duplicates in coverage metrics')
parser.add_option('--bed',
dest='bed',
help='BED file to run targetSeq and Seq2C analysis on.')
parser.add_option(
'--exons',
'--exome',
'--features',
dest='features',
help=
'Annotated CDS/Exon/Gene/Transcripts BED file to make targetSeq exon/amplicon regions reports.'
)
(opts, args) = parser.parse_args()
logger.is_debug = opts.debug
if len(args) == 0:
critical('No BAMs provided to input.')
bam_fpaths = list(set([abspath(a) for a in args]))
bad_bam_fpaths = []
for fpath in bam_fpaths:
if not verify_bam(fpath):
bad_bam_fpaths.append(fpath)
if bad_bam_fpaths:
critical('BAM files cannot be found, empty or not BAMs:' +
', '.join(bad_bam_fpaths))
run_cnf = determine_run_cnf(opts, is_wgs=not opts.__dict__.get('bed'))
cnf = Config(opts.__dict__, determine_sys_cnf(opts), run_cnf)
if not cnf.project_name:
cnf.project_name = basename(cnf.output_dir)
info('Project name: ' + cnf.project_name)
cnf.proc_name = 'TargQC'
set_up_dirs(cnf)
# cnf.name = 'TargQC_' + cnf.project_name
check_genome_resources(cnf)
verify_bed(cnf.bed, is_critical=True)
bed_fpath = adjust_path(cnf.bed)
info('Using amplicons/capture panel ' + bed_fpath)
features_bed_fpath = adjust_path(
cnf.features) if cnf.features else adjust_path(cnf.genome.features)
info('Features: ' + features_bed_fpath)
genes_fpath = None
if cnf.genes:
genes_fpath = adjust_path(cnf.genes)
info('Custom genes list: ' + genes_fpath)
if not cnf.only_summary:
cnf.qsub_runner = adjust_system_path(cnf.qsub_runner)
if not cnf.qsub_runner:
critical('Error: qsub-runner is not provided is sys-config.')
verify_file(cnf.qsub_runner, is_critical=True)
info('*' * 70)
info()
targqc_html_fpath = run_targqc(cnf, cnf.output_dir, bam_fpaths, bed_fpath,
features_bed_fpath, genes_fpath)
if targqc_html_fpath:
send_email(
cnf, 'TargQC report for ' + cnf.project_name + ':\n ' +
targqc_html_fpath)
def read_opts_and_cnfs(extra_opts,
key_for_sample_name=None,
required_keys=list(),
file_keys=list(),
dir_keys=list(),
description='',
extra_msg=None,
proc_name=None,
fpath_for_sample_name=None,
main_output_is_file=False,
main_output_is_dir=True):
options = extra_opts
if main_output_is_file:
options += [(['-o', '--output-file'],
dict(dest='output_file',
metavar='FILE',
help='Output file'))]
options += [(
['--output-dir'],
dict(
dest='output_dir',
metavar='DIR',
help=
'Output directory (or directory name in case of bcbio final dir)',
default=os.getcwd()))]
elif main_output_is_dir:
options += [(
['-o', '--output-dir'],
dict(
dest='output_dir',
metavar='DIR',
help=
'Output directory (or directory name in case of bcbio final dir)',
default=os.getcwd()))]
options += [(['--output-file'],
dict(dest='output_file',
metavar='FILE',
help='Output file'))]
options += [
(['-s', '--sample', '--name'],
dict(
dest='sample',
metavar='NAME',
help=
'Sample name (default is part of name of the first parameter prior to the first - or .'
)),
(['-c', '--caller'],
dict(
dest='caller',
metavar='CALLER_NAME',
help=
'Variant caller name (default is part of name of the first parameter between the first - and following .'
)),
(['-t', '--nt', '--threads'],
dict(dest='threads', type='int', help='Number of threads')),
(
['--clean'],
dict( # do not keep work directory
dest='keep_intermediate',
action='store_false',
help=SUPPRESS_HELP)),
(['--debug'],
dict(dest='debug',
action='store_true',
default=False,
help=SUPPRESS_HELP)),
(['--reuse'],
dict(
dest='reuse_intermediate',
help=
'reuse intermediate non-empty files in the work dir from previous run',
action='store_true')),
(['--sys-cnf'],
dict(
dest='sys_cnf',
metavar='SYS_CNF.yaml',
help=
'System configuration file with paths to external tools and genome resources. The default is '
'(see default one %s)' % defaults['sys_cnf'])),
(['--run-cnf'],
dict(
dest='run_cnf',
metavar='RUN_CNF.yaml',
default=defaults['run_cnf_exome_seq'],
help=
'Customised run details: list of annotations/QC metrics/databases/filtering criteria. '
'The default is %s' % defaults['run_cnf_exome_seq'])),
(['--transcripts'], dict(dest='transcripts_fpath')),
(['--work-dir'],
dict(dest='work_dir', metavar='DIR', help=SUPPRESS_HELP)),
(['--log-dir'], dict(dest='log_dir', metavar='DIR',
help=SUPPRESS_HELP)),
(['--proc-name'], dict(dest='proc_name', help=SUPPRESS_HELP)),
(['--project-name'], dict(dest='project_name')),
(['--no-check'],
dict(dest='no_check', action='store_true', help=SUPPRESS_HELP)),
(['-g', '--genome'], dict(dest='genome')),
(['--email'], dict(dest='email', help=SUPPRESS_HELP)),
(['--done-marker'], dict(dest='done_marker', help=SUPPRESS_HELP)),
]
parser = OptionParser(description=description)
for args, kwargs in options:
parser.add_option(*args, **kwargs)
req_keys_usage = ''
if required_keys:
req_keys_usage = '\nRequired options:'
for args, kwargs in options:
try:
if kwargs['dest'] in required_keys:
req_keys_usage += '\n ' + '/'.join(args)
except:
err(format_exc())
pass
parser.set_usage(parser.get_usage() + req_keys_usage)
(opts, args) = parser.parse_args()
logger.is_debug = opts.debug
run_cnf = determine_run_cnf(opts, is_wgs=not opts.__dict__.get('bed'))
cnf = Config(opts.__dict__, determine_sys_cnf(opts), run_cnf)
errors = check_keys_presence(cnf, required_keys)
if errors:
parser.print_help()
critical(errors)
file_keys = [k for k in file_keys if k in required_keys]
dir_keys = [k for k in dir_keys if k in required_keys]
errors = check_dirs_and_files(cnf, file_keys, dir_keys)
if errors:
critical(errors)
if cnf.sample:
cnf.sample = remove_quotes(cnf.sample)
else:
if not fpath_for_sample_name:
if not key_for_sample_name:
critical('Error: --sample must be provided in options.')
fpath_for_sample_name = cnf[key_for_sample_name]
if not fpath_for_sample_name:
critical('Error: --sample or ' + (str(key_for_sample_name)) +
' must be provided in options.')
key_fname = basename(cnf[key_for_sample_name])
cnf.sample = key_fname.split('.')[0]
if cnf.caller:
cnf.caller = remove_quotes(cnf.caller)
# elif key_for_sample_name and cnf[key_for_sample_name]:
# key_fname = basename(cnf[key_for_sample_name])
# try:
# cnf.caller = cnf.caller or key_fname.split('.')[0].split('-')[1]
# except:
# cnf.caller = ''
else:
cnf.caller = None
cnf.proc_name = cnf.proc_name or proc_name
set_up_dirs(cnf)
info(' '.join(sys.argv))
info()
return cnf
def proc_args(argv):
info(' '.join(sys.argv))
info()
description = 'This script generates target QC reports for each BAM provided as an input.'
parser = OptionParser(description=description)
add_cnf_t_reuse_prjname_donemarker_workdir_genome_debug(parser)
parser.add_option('--log-dir', dest='log_dir')
parser.add_option('--is-wgs',
dest='is_wgs',
action='store_true',
default=False,
help='whole genome sequencing')
parser.add_option('--is-deep-seq',
dest='is_deep_seq',
action='store_true',
default=False,
help='deep targeted sequencing')
parser.add_option('--only-summary',
dest='only_summary',
action='store_true')
parser.add_option('-o',
dest='output_dir',
metavar='DIR',
default=join(os.getcwd(), 'targetqc'))
parser.add_option('-c', '--caller', dest='caller')
parser.add_option('--qc', dest='qc', action='store_true', default=False)
parser.add_option('--no-qc',
dest='qc',
action='store_false',
default=False)
parser.add_option('--qc-caption', dest='qc_caption', help=SUPPRESS_HELP)
parser.add_option('--no-tsv',
dest='tsv',
action='store_false',
default=True,
help=SUPPRESS_HELP)
(opts, args) = parser.parse_args()
logger.is_debug = opts.debug
if len(args) == 0:
critical('No vcf files provided to input.')
run_cnf = determine_run_cnf(opts,
is_targetseq=opts.is_deep_seq,
is_wgs=opts.is_wgs)
cnf = Config(opts.__dict__, determine_sys_cnf(opts), run_cnf)
vcf_fpath_by_sample = read_samples(args, cnf.caller)
info()
if not cnf.project_name:
cnf.project_name = basename(cnf.output_dir)
info('Project name: ' + cnf.project_name)
cnf.proc_name = 'Variants'
set_up_dirs(cnf)
# cnf.name = 'TargQC_' + cnf.project_name
info(' '.join(sys.argv))
samples = [
source.VarSample(s_name, join(cnf.output_dir, s_name), vcf=vcf_fpath)
for s_name, vcf_fpath in vcf_fpath_by_sample.items()
]
samples.sort(key=lambda _s: _s.key_to_sort())
check_genome_resources(cnf)
if not cnf.only_summary:
cnf.qsub_runner = adjust_system_path(cnf.qsub_runner)
if not cnf.qsub_runner:
critical('Error: qsub-runner is not provided is sys-config.')
verify_file(cnf.qsub_runner, is_critical=True)
return cnf, samples