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 = regions.get_sv_bed(data)
# if we don't have a configured BED or regions to use for SV caling
if not base_regions:
# For genome calls, subset to regions within 10kb of genes
if cov_interval == "genome":
base_regions = regions.get_sv_bed(data, "transcripts1e4", work_dir)
if base_regions:
base_regions = shared.remove_exclude_regions(base_regions, base_regions, [data])
# Finally, default to the defined variant regions
if not base_regions:
base_regions = dd.get_variant_regions(data)
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 = regions.get_sv_bed(data)
# if we don't have a configured BED or regions to use for SV caling
if not base_regions:
# For genome calls, subset to regions within 10kb of genes
if cov_interval == "genome":
base_regions = regions.get_sv_bed(data, "transcripts1e4", work_dir)
if base_regions:
base_regions = shared.remove_exclude_regions(
base_regions, base_regions, [data])
# Finally, default to the defined variant regions
if not base_regions:
base_regions = dd.get_variant_regions(data)
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 _run_wham(inputs, background_bams):
"""Run WHAM on a defined set of inputs and targets.
"""
out_file = os.path.join(_sv_workdir(inputs[0]), "%s-wham.vcf" % dd.get_sample_name(inputs[0]))
input_bams = [x["align_bam"] for x in inputs]
if not utils.file_exists(out_file):
with file_transaction(inputs[0], out_file) as tx_out_file:
cores = dd.get_cores(inputs[0])
background = "-b %s" % ",".join(background_bams) if background_bams else ""
target_bams = ",".join(x["align_bam"] for x in inputs)
target_bed = shared.remove_exclude_regions(
tz.get_in(["config", "algorithm", "variant_regions"], inputs[0]), out_file, inputs)
ref_file = dd.get_ref_file(inputs[0])
target_str = "-e %s" % target_bed if target_bed else ""
cmd = ("WHAM-BAM -x {cores} -f {ref_file} -t {target_bams} {background} {target_str} > {tx_out_file}")
do.run(cmd.format(**locals()), "Run WHAM")
return out_file
def _run_wham(inputs, background_bams):
"""Run WHAM on a defined set of inputs and targets.
"""
out_file = os.path.join(_sv_workdir(inputs[0]),
"%s-wham.vcf" % dd.get_sample_name(inputs[0]))
input_bams = [x["align_bam"] for x in inputs]
if not utils.file_exists(out_file):
with file_transaction(inputs[0], out_file) as tx_out_file:
cores = dd.get_cores(inputs[0])
background = "-b %s" % ",".join(
background_bams) if background_bams else ""
target_bams = ",".join(x["align_bam"] for x in inputs)
target_bed = shared.remove_exclude_regions(
tz.get_in(["config", "algorithm", "variant_regions"],
inputs[0]), out_file, inputs)
ref_file = dd.get_ref_file(inputs[0])
target_str = "-e %s" % target_bed if target_bed else ""
cmd = (
"WHAM-BAM -x {cores} -f {ref_file} -t {target_bams} {background} {target_str} > {tx_out_file}"
)
do.run(cmd.format(**locals()), "Run WHAM")
return out_file