def _create_subset_file(in_file, het_region_bed, work_dir, data):
"""Subset the VCF to a set of pre-calculated smaller regions.
"""
cnv_regions = shared.get_base_cnv_regions(data, work_dir)
region_bed = bedutils.intersect_two(het_region_bed, cnv_regions, work_dir, data)
out_file = os.path.join(work_dir, "%s-origsubset.bcf" % utils.splitext_plus(os.path.basename(in_file))[0])
if not utils.file_uptodate(out_file, in_file):
with file_transaction(data, out_file) as tx_out_file:
regions = ("-R %s" % region_bed) if utils.file_exists(region_bed) else ""
cmd = "bcftools view {regions} -o {tx_out_file} -O b {in_file}"
do.run(cmd.format(**locals()), "Extract regions for BubbleTree frequency determination")
return out_file
def _create_subset_file(in_file, het_region_bed, work_dir, data):
"""Subset the VCF to a set of pre-calculated smaller regions.
"""
cnv_regions = shared.get_base_cnv_regions(data, work_dir)
region_bed = bedutils.intersect_two(het_region_bed, cnv_regions, work_dir, data)
out_file = os.path.join(work_dir, "%s-origsubset.bcf" % utils.splitext_plus(os.path.basename(in_file))[0])
if not utils.file_uptodate(out_file, in_file):
with file_transaction(data, out_file) as tx_out_file:
regions = ("-R %s" % region_bed) if utils.file_exists(region_bed) else ""
cmd = "bcftools view {regions} -o {tx_out_file} -O b {in_file}"
do.run(cmd.format(**locals()), "Extract regions for BubbleTree frequency determination")
return out_file
def heterogzygote_counts(paired):
"""Provide tumor/normal counts at population heterozyogte sites with CollectAllelicCounts.
"""
work_dir = utils.safe_makedir(os.path.join(dd.get_work_dir(paired.tumor_data), "structural", "counts"))
key = "germline_het_pon"
het_bed = tz.get_in(["genome_resources", "variation", key], paired.tumor_data)
vr = bedutils.population_variant_regions([x for x in [paired.tumor_data, paired.normal_data] if x])
cur_het_bed = bedutils.intersect_two(het_bed, vr, work_dir, paired.tumor_data)
tumor_counts = _run_collect_allelic_counts(cur_het_bed, key, work_dir, paired.tumor_data)
normal_counts = (_run_collect_allelic_counts(cur_het_bed, key, work_dir, paired.normal_data)
if paired.normal_data else None)
return tumor_counts, normal_counts
def heterogzygote_counts(paired):
"""Provide tumor/normal counts at population heterozyogte sites with CollectAllelicCounts.
"""
work_dir = utils.safe_makedir(os.path.join(dd.get_work_dir(paired.tumor_data), "structural", "counts"))
key = "germline_het_pon"
het_bed = tz.get_in(["genome_resources", "variation", key], paired.tumor_data)
vr = bedutils.population_variant_regions([x for x in [paired.tumor_data, paired.normal_data] if x])
cur_het_bed = bedutils.intersect_two(het_bed, vr, work_dir, paired.tumor_data)
tumor_counts = _run_collect_allelic_counts(cur_het_bed, key, work_dir, paired.tumor_data)
normal_counts = (_run_collect_allelic_counts(cur_het_bed, key, work_dir, paired.normal_data)
if paired.normal_data else None)
if normal_counts:
tumor_counts, normal_counts = _filter_by_normal(tumor_counts, normal_counts, paired.tumor_data)
return tumor_counts, normal_counts
