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 _get_target_access_files(cov_interval, data, work_dir):
"""Retrieve target and access files based on the type of data to process.
pick targets, anti-targets and access files based on analysis type
http://cnvkit.readthedocs.org/en/latest/nonhybrid.html
"""
base_regions = shared.get_base_cnv_regions(data, work_dir)
target_bed = bedutils.merge_overlaps(base_regions, data, out_dir=work_dir)
if cov_interval == "amplicon":
return target_bed, target_bed
elif cov_interval == "genome":
return target_bed, target_bed
else:
access_file = _create_access_file(dd.get_ref_file(data), _sv_workdir(data), data)
return target_bed, access_file
def _get_target_access_files(cov_interval, data, work_dir):
"""Retrieve target and access files based on the type of data to process.
pick targets, anti-targets and access files based on analysis type
http://cnvkit.readthedocs.org/en/latest/nonhybrid.html
"""
base_regions = shared.get_base_cnv_regions(data, work_dir)
target_bed = bedutils.sort_merge(base_regions, data, out_dir=work_dir)
if cov_interval == "amplicon":
return target_bed, target_bed
elif cov_interval == "genome":
return target_bed, target_bed
else:
access_file = _create_access_file(dd.get_ref_file(data), _sv_workdir(data), data)
return target_bed, access_file