def _prep_config(items, paired, work_dir):
"""Run initial configuration, generating a run directory for Manta.
"""
assert utils.which("configManta.py"), "Could not find installed configManta.py"
out_file = os.path.join(work_dir, "runWorkflow.py")
if not utils.file_exists(out_file) or _out_of_date(out_file):
config_script = os.path.realpath(utils.which("configManta.py"))
cmd = [utils.get_program_python("configManta.py"), config_script]
if paired:
if paired.normal_bam:
cmd += ["--normalBam=%s" % paired.normal_bam, "--tumorBam=%s" % paired.tumor_bam]
else:
cmd += ["--tumorBam=%s" % paired.tumor_bam]
else:
cmd += ["--bam=%s" % dd.get_align_bam(data) for data in items]
data = paired.tumor_data if paired else items[0]
cmd += ["--referenceFasta=%s" % dd.get_ref_file(data), "--runDir=%s" % work_dir]
if dd.get_coverage_interval(data) not in ["genome"]:
cmd += ["--exome"]
for region in _maybe_limit_chromosomes(data):
cmd += ["--region", region]
resources = config_utils.get_resources("manta", data["config"])
if resources.get("options"):
cmd += [str(x) for x in resources["options"]]
# If we are removing polyX, avoid calling on small indels which require
# excessively long runtimes on noisy WGS runs
if "polyx" in dd.get_exclude_regions(data):
cmd += ["--config", _prep_streamlined_config(config_script, work_dir)]
do.run(cmd, "Configure manta SV analysis")
return out_file
def sample_callable_bed(bam_file, ref_file, data):
"""Retrieve callable regions for a sample subset by defined analysis regions.
"""
from bcbio.heterogeneity import chromhacks
CovInfo = collections.namedtuple("CovInfo",
"callable, raw_callable, depth_files")
noalt_calling = "noalt_calling" in dd.get_tools_on(
data) or "altcontigs" in dd.get_exclude_regions(data)
def callable_chrom_filter(r):
"""Filter to callable region, potentially limiting by chromosomes.
"""
return r.name == "CALLABLE" and (not noalt_calling
or chromhacks.is_nonalt(r.chrom))
out_file = "%s-callable_sample.bed" % os.path.splitext(bam_file)[0]
with shared.bedtools_tmpdir(data):
sv_bed = regions.get_sv_bed(data)
callable_bed, depth_files = coverage.calculate(bam_file, data, sv_bed)
input_regions_bed = dd.get_variant_regions(data)
if not utils.file_uptodate(out_file, callable_bed):
with file_transaction(data, out_file) as tx_out_file:
callable_regions = pybedtools.BedTool(callable_bed)
filter_regions = callable_regions.filter(callable_chrom_filter)
if input_regions_bed:
if not utils.file_uptodate(out_file, input_regions_bed):
input_regions = pybedtools.BedTool(input_regions_bed)
filter_regions.intersect(
input_regions,
nonamecheck=True).saveas(tx_out_file)
else:
filter_regions.saveas(tx_out_file)
return CovInfo(out_file, callable_bed, depth_files)
def _prep_config(items, paired, work_dir):
"""Run initial configuration, generating a run directory for Manta.
"""
assert utils.which("configManta.py"), "Could not find installed configManta.py"
out_file = os.path.join(work_dir, "runWorkflow.py")
if not utils.file_exists(out_file) or _out_of_date(out_file):
config_script = os.path.realpath(utils.which("configManta.py"))
cmd = [sys.executable, config_script]
if paired:
if paired.normal_bam:
cmd += ["--normalBam=%s" % paired.normal_bam, "--tumorBam=%s" % paired.tumor_bam]
else:
cmd += ["--tumorBam=%s" % paired.tumor_bam]
else:
cmd += ["--bam=%s" % dd.get_align_bam(data) for data in items]
data = paired.tumor_data if paired else items[0]
cmd += ["--referenceFasta=%s" % dd.get_ref_file(data), "--runDir=%s" % work_dir]
if dd.get_coverage_interval(data) not in ["genome"]:
cmd += ["--exome"]
for region in _maybe_limit_chromosomes(data):
cmd += ["--region", region]
# If we are removing polyX, avoid calling on small indels which require
# excessively long runtimes on noisy WGS runs
if "polyx" in dd.get_exclude_regions(data):
cmd += ["--config", _prep_streamlined_config(config_script, work_dir)]
do.run(cmd, "Configure manta SV analysis")
return out_file
def _add_config_regions(nblock_regions, ref_regions, data):
"""Add additional nblock regions based on configured regions to call.
Identifies user defined regions which we should not be analyzing.
"""
input_regions_bed = dd.get_variant_regions(data)
if input_regions_bed:
input_regions = pybedtools.BedTool(input_regions_bed)
# work around problem with single region not subtracted correctly.
if len(input_regions) == 1:
str_regions = str(input_regions[0]).strip()
input_regions = pybedtools.BedTool("%s\n%s" %
(str_regions, str_regions),
from_string=True)
input_nblock = ref_regions.subtract(input_regions, nonamecheck=True)
if input_nblock == ref_regions:
raise ValueError(
"Input variant_region file (%s) "
"excludes all genomic regions. Do the chromosome names "
"in the BED file match your genome (chr1 vs 1)?" %
input_regions_bed)
all_intervals = _combine_regions([input_nblock, nblock_regions],
ref_regions)
else:
all_intervals = nblock_regions
if "noalt_calling" in dd.get_tools_on(
data) or "altcontigs" in dd.get_exclude_regions(data):
from bcbio.heterogeneity import chromhacks
remove_intervals = ref_regions.filter(
lambda r: not chromhacks.is_nonalt(r.chrom))
all_intervals = _combine_regions([all_intervals, remove_intervals],
ref_regions)
return all_intervals.merge()
def sample_callable_bed(bam_file, ref_file, data):
"""Retrieve callable regions for a sample subset by defined analysis regions.
"""
from bcbio.heterogeneity import chromhacks
CovInfo = collections.namedtuple("CovInfo", "callable, raw_callable, depth_files")
noalt_calling = "noalt_calling" in dd.get_tools_on(data) or "altcontigs" in dd.get_exclude_regions(data)
def callable_chrom_filter(r):
"""Filter to callable region, potentially limiting by chromosomes.
"""
return r.name == "CALLABLE" and (not noalt_calling or chromhacks.is_nonalt(r.chrom))
out_file = "%s-callable_sample.bed" % os.path.splitext(bam_file)[0]
with shared.bedtools_tmpdir(data):
sv_bed = regions.get_sv_bed(data)
callable_bed, depth_files = coverage.calculate(bam_file, data, sv_bed)
input_regions_bed = dd.get_variant_regions(data)
if not utils.file_uptodate(out_file, callable_bed):
with file_transaction(data, out_file) as tx_out_file:
callable_regions = pybedtools.BedTool(callable_bed)
filter_regions = callable_regions.filter(callable_chrom_filter)
if input_regions_bed:
if not utils.file_uptodate(out_file, input_regions_bed):
input_regions = pybedtools.BedTool(input_regions_bed)
filter_regions.intersect(input_regions, nonamecheck=True).saveas(tx_out_file)
else:
filter_regions.saveas(tx_out_file)
return CovInfo(out_file, callable_bed, depth_files)
def _add_config_regions(nblock_regions, ref_regions, data):
"""Add additional nblock regions based on configured regions to call.
Identifies user defined regions which we should not be analyzing.
"""
input_regions_bed = dd.get_variant_regions(data)
if input_regions_bed:
input_regions = pybedtools.BedTool(input_regions_bed)
# work around problem with single region not subtracted correctly.
if len(input_regions) == 1:
str_regions = str(input_regions[0]).strip()
input_regions = pybedtools.BedTool("%s\n%s" % (str_regions, str_regions),
from_string=True)
input_nblock = ref_regions.subtract(input_regions, nonamecheck=True)
if input_nblock == ref_regions:
raise ValueError("Input variant_region file (%s) "
"excludes all genomic regions. Do the chromosome names "
"in the BED file match your genome (chr1 vs 1)?" % input_regions_bed)
all_intervals = _combine_regions([input_nblock, nblock_regions], ref_regions)
else:
all_intervals = nblock_regions
if "noalt_calling" in dd.get_tools_on(data) or "altcontigs" in dd.get_exclude_regions(data):
from bcbio.heterogeneity import chromhacks
remove_intervals = ref_regions.filter(lambda r: not chromhacks.is_nonalt(r.chrom))
all_intervals = _combine_regions([all_intervals, remove_intervals], ref_regions)
return all_intervals.merge()
def add_highdepth_genome_exclusion(items):
"""Add exclusions to input items to avoid slow runtimes on whole genomes.
"""
out = []
for d in items:
d = utils.deepish_copy(d)
if dd.get_coverage_interval(d) == "genome":
e = dd.get_exclude_regions(d)
if "highdepth" not in e:
e.append("highdepth")
d = dd.set_exclude_regions(d, e)
out.append(d)
return out
def _maybe_limit_chromosomes(data):
"""Potentially limit chromosomes to avoid problematically named HLA contigs.
HLAs have ':' characters in them which confuse downstream processing. If
we have no problematic chromosomes we don't limit anything.
"""
std_chroms = []
prob_chroms = []
noalt_calling = "noalt_calling" in dd.get_tools_on(data) or "altcontigs" in dd.get_exclude_regions(data)
for contig in ref.file_contigs(dd.get_ref_file(data)):
if contig.name.find(":") > 0 or (noalt_calling and not chromhacks.is_nonalt(contig.name)):
prob_chroms.append(contig.name)
else:
std_chroms.append(contig.name)
if len(prob_chroms) > 0:
return std_chroms
else:
return []
def _maybe_limit_chromosomes(data):
"""Potentially limit chromosomes to avoid problematically named HLA contigs.
HLAs have ':' characters in them which confuse downstream processing. If
we have no problematic chromosomes we don't limit anything.
"""
std_chroms = []
prob_chroms = []
noalt_calling = "noalt_calling" in dd.get_tools_on(data) or "altcontigs" in dd.get_exclude_regions(data)
for contig in ref.file_contigs(dd.get_ref_file(data)):
if contig.name.find(":") > 0 or (noalt_calling and not chromhacks.is_nonalt(contig.name)):
prob_chroms.append(contig.name)
else:
std_chroms.append(contig.name)
if len(prob_chroms) > 0:
return std_chroms
else:
return []
def _get_sample_excludes(d):
excludes = dd.get_exclude_regions(d)
# back compatible
if tz.get_in(("config", "algorithm", "remove_lcr"), d, False):
excludes.append("lcr")
return excludes
