def main():
info(' '.join(sys.argv))
info()
cnf, bcbio_structure = bcbio_summary_script_proc_params(
'expression', BCBioStructure.expression_dir)
step_greetings('Gene expression heatmaps summary for all samples')
report_caption_names = ['Gene counts', 'Exon counts', 'Gene TPM', 'Isoform TPM']
genes_dict, transcripts_dict = _get_gene_transcripts_id(cnf)
for counts_fname, report_caption_name in zip(bcbio_structure.counts_names, report_caption_names):
counts_fpath = join(bcbio_structure.expression_dirpath, counts_fname)
if not verify_file(counts_fpath, silent=True):
raw_counts_fpath = join(bcbio_structure.expression_dirpath, 'raw', 'combined.' + counts_fname.replace('.tsv', ''))
info('Annotating ' + report_caption_name + ' from ' + raw_counts_fpath)
annotate_gene_counts(cnf, raw_counts_fpath, counts_fpath, genes_dict)
verify_file(counts_fpath, is_critical=True, description=counts_fname)
isoforms_found = counts_fname == 'isoform.sf.tpm' and counts_fpath
used_dict = transcripts_dict if isoforms_found else genes_dict
report_fpath = join(safe_mkdir(join(bcbio_structure.expression_dirpath, 'html')),
counts_fname.replace('.tsv', '') + '.html')
make_gene_expression_heatmaps(cnf, bcbio_structure, counts_fpath, used_dict, report_fpath,
report_caption_name, keep_gene_names=isoforms_found)
info('Done')
def main():
info(' '.join(sys.argv))
info()
cnf, bcbio_structure = bcbio_summary_script_proc_params(
BCBioStructure.targqc_name,
BCBioStructure.targqc_summary_dir,
extra_opts=
[(['--bed', '--capture', '--amplicons'],
dict(dest='bed',
help='BED file to run targetSeq and Seq2C analysis on.')),
(['--exons', '--exome', '--features'],
dict(
dest='features',
help=
'Annotated CDS/Exons/Gene/Transcript BED file to make targetSeq exon/amplicon regions reports.'
))])
bed_fpath, features_bed_fpath = adjust_path(cnf.bed), adjust_path(
cnf.features)
summarize_targqc(cnf,
cnf.threads or len(bcbio_structure.samples),
cnf.output_dir,
bcbio_structure.samples,
bed_fpath=bed_fpath,
features_fpath=features_bed_fpath)
def proc_args():
info(' '.join(sys.argv))
info()
cnf, bcbio_structure = bcbio_summary_script_proc_params(
BCBioStructure.seq2c_name,
extra_opts=[
(['--bed', '--capture', '--amplicons'], dict(
dest='bed'
))
],
)
return cnf, bcbio_structure
def main(args):
cnf, bcbio_structure = bcbio_summary_script_proc_params(
BCBioStructure.targqc_name,
BCBioStructure.targqc_summary_dir,
extra_opts=[
(['--mutations'], dict(dest='mutations_fpath', )),
(['--bed', '--capture', '--amplicons'],
dict(dest='bed',
help='a BED file for capture panel or amplicons')),
])
check_system_resources(cnf, required=['bedtools'], optional=[])
process_all(cnf, bcbio_structure)
if not cnf['keep_intermediate']:
shutil.rmtree(cnf['work_dir'])
def main():
info(' '.join(sys.argv))
info()
cnf, bcbio_structure = bcbio_summary_script_proc_params(
BCBioStructure.seq2c_name,
BCBioStructure.cnv_summary_dir,
extra_opts=[
(['--controls', '-c'], dict(
dest='controls',
help='Optional control sample names for Seq2C. For multiple controls, separate them using :',
default=''
)),
(['--seq2c-opts'], dict(
dest='seq2c_opts',
help='Options for the final lr2gene.pl script.',
default=''
)),
(['--bed', '--capture', '--amplicons'], dict(
dest='bed',
help='BED file to run targetSeq and Seq2C analysis on.')
),
(['--reannotate'], dict(
dest='reannotate',
help='re-annotate BED file with gene names',
action='store_true',
default=False)
),
(['--wgs'], dict(
dest='is_wgs',
action='store_true',
default=False)
),
(['--no-prep-bed'], dict(
dest='prep_bed',
help='do not fix input beds and exons',
action='store_false',
default=True)
), # (['--dedup'], dict(
# dest='dedup',
# help='Remove duplicates from the input bedfile.')
# ),
],
)
run_seq2c_bcbio_structure(cnf, bcbio_structure)
def main():
info(' '.join(sys.argv))
info()
cnf, bcbio_structure = bcbio_summary_script_proc_params(
BCBioStructure.fastqc_name, BCBioStructure.fastqc_dir)
step_greetings('FastQC summary for all samples')
final_summary_report_fpath = join(cnf.output_dir,
source.fastqc_name + '.html')
write_fastqc_combo_report(cnf, final_summary_report_fpath,
bcbio_structure.samples)
info()
info('*' * 70)
info('Fastqc summary:')
info(' ' + final_summary_report_fpath)
def main():
info(' '.join(sys.argv))
info()
description = '''
The program filters an annotated VCF file by SnpEff using dbSNP and COSMIC,
setting the value of the FILTER column.
A novel variant (non-dbSNP, non-COSMIC) is considered false positive
if all three conditions (-r -f -n) are met. False positive variants are
annotated PASS in column FILTER if the conditions are satisfied, or with
other value otherwise, where the value is ;-separated list of failed criteria.
'''
dfts = defaults['variant_filtering']
extra_opts = [
(['--caller'],
dict(
dest='caller',
help=
'Variant caller name to process. If not set, processed all variant callers'
)),
(['--wgs'],
dict(
dest='is_wgs',
action='store_true',
default=False,
help=
'Splits vcf2txt runs by samples, thus turns off cohort filtering')
),
(['-b', '--bias'],
dict(dest='bias',
action='store_true',
help='Novel or dbSNP variants with strand bias "2;1" or "2;0" '
'and AF < 0.3 will be considered as false positive.')),
(['-M', '--min-mq'],
dict(
dest='min_mq',
type='float',
help='The filtering mean mapping quality score for variants. '
'The raw variant will be filtered if the mean mapping quality '
'score is less then specified. Default %d' % dfts['min_mq'],
)),
(['-D', '--filt-depth'],
dict(
dest='filt_depth',
type='int',
help='The filtering total depth. The raw variant will be filtered '
'on first place if the total depth is less then [filt_depth]. '
'Default %s' % str(dfts['filt_depth']),
)),
(['-V', '--min-vd'],
dict(
dest='min_vd',
type='int',
help=
'The filtering variant depth. Variants with depth < [min_vd] will '
'be considered false positive. Default is %d (meaning at least %d reads '
'are needed for a variant)' % (dfts['min_vd'], dfts['min_vd']))),
(['-m', '--maf'],
dict(
dest='maf',
type='float',
help='If there is MAF with frequency, it will be considered dbSNP '
'regardless of COSMIC. Default MAF is %f' % dfts['maf'],
)),
(['-r', '--fraction'],
dict(
dest='fraction',
type='float',
help='When a novel variant is present in more than [fraction] '
'of samples and mean allele frequency is less than [freq], '
'it\'s considered as likely false positive. Default %f. '
'Used with -f and -n' % dfts['fraction'],
)),
(['-F', '--ave-freq'],
dict(
dest='ave_freq',
type='float',
help='When the average allele frequency is also below the [freq], '
'the variant is considered likely false positive. '
'Default %f. Used with -r and -n' % dfts['ave_freq'],
)),
(['--min-hotspot-freq'],
dict(
dest='min_hotspot_freq',
type='float',
help=
'The minimum allele frequency hotspot somatic mutations, typically lower then -f.'
'Default: 0.01 or half _min_freq_, whichever is less',
)),
(['-n'],
dict(
dest='sample_cnt',
type='int',
help=
'When the variant is detected in greater or equal [sample_cnt] '
'samples, the variant is considered likely false positive. '
'Default %d. Used with -r and -f' % dfts['sample_cnt'],
)),
(['-R', '--max-ratio'],
dict(
dest='max_ratio',
type='float',
help=
'When a variant is present in more than [fraction] of samples, '
'and AF < 0.3, it\'s considered as likely false positive, '
'even if it\'s in COSMIC. Default %f.' % dfts['max_ratio'],
)),
# This option moved to add_post_bcbio_args()
# (['-f', '--min-freq'], dict(
# dest='min_freq',
# type='float',
# help='When individual allele frequency < freq for variants, '
# 'it was considered likely false poitives. '
# 'Default %f' % defaults['default_min_freq'],
# )),
(['-p'],
dict(
dest='min_p_mean',
type='int',
help='The minimum mean position in reads for variants.'
'Default %d bp' % dfts['min_p_mean'],
)),
(['-q'],
dict(
dest='min_q_mean',
type='float',
help='The minimum mean base quality phred score for variant.'
'Default %d' % dfts['min_q_mean'],
)),
(['-P'],
dict(
dest='filt_p_mean',
type='int',
help='The filtering mean position in reads for variants. '
'The raw variant will be filtered on first place if the mean '
'posititon is less then [filt_p_mean]. '
'Default %s bp' % str(dfts['filt_p_mean']),
)),
(['-Q'],
dict(
dest='filt_q_mean',
type='float',
help='The filtering mean base quality phred score for variants. '
'The raw variant will be filtered on first place '
'if the mean quality is less then [filt_q_mean]. '
'Default %s' % str(dfts['filt_q_mean']),
)),
(['--sn'],
dict(dest='signal_noise',
type='int',
help='Minimal signal/noise value. Default %d' %
dfts['signal_noise'])),
(['-u'],
dict(dest='count_undetermined',
action='store_false',
default=True,
help='Undeteremined won\'t be counted for the sample count.')),
(['-c', '--control'],
dict(
dest='control',
help=
'The control sample name. Any novel or COSMIC variants passing all '
'above filters but also detected in Control sample will be deemed '
'considered false positive. Use only when there\'s control sample.'
)),
(['--datahub-path'],
dict(
dest='datahub_path',
help=
'DataHub directory path to upload final MAFs and CNV (can be remote).',
)),
]
cnf, bcbio_structure = bcbio_summary_script_proc_params(
BCBioStructure.varfilter_name,
description=description,
extra_opts=extra_opts)
info('*' * 70)
info()
filter_bcbio_structure(cnf, bcbio_structure)