def _shared_gatk_call_prep(align_bams, items, ref_file, dbsnp, region, out_file):
"""Shared preparation work for GATK variant calling.
"""
data = items[0]
config = data["config"]
broad_runner = broad.runner_from_config(config)
broad_runner.run_fn("picard_index_ref", ref_file)
for x in align_bams:
bam.index(x, config)
params = ["-R", ref_file]
if dd.is_set_coverage_depth_max(data):
coverage_depth_max = dd.get_coverage_depth_max(data)
# GATK can only downsample to a minimum of 200
coverage_depth_max = max([200, coverage_depth_max])
params += ["--downsample_to_coverage", str(coverage_depth_max),
"--downsampling_type", "BY_SAMPLE"]
coverage_depth_min = tz.get_in(["algorithm", "coverage_depth_min"], config)
if coverage_depth_min and coverage_depth_min < 4:
confidence = "4.0"
params += ["--standard_min_confidence_threshold_for_calling", confidence,
"--standard_min_confidence_threshold_for_emitting", confidence]
for a in annotation.get_gatk_annotations(config):
params += ["--annotation", a]
for x in align_bams:
params += ["-I", x]
if dbsnp:
params += ["--dbsnp", dbsnp]
variant_regions = tz.get_in(["algorithm", "variant_regions"], config)
region = subset_variant_regions(variant_regions, region, out_file, items)
if region:
params += ["-L", bamprep.region_to_gatk(region), "--interval_set_rule", "INTERSECTION"]
return broad_runner, params
def calc_callable_loci(data, region=None, out_file=None):
"""Determine callable bases for an input BAM in the given region.
"""
if out_file is None:
out_file = "%s-callable.bed" % os.path.splitext(data["work_bam"])[0]
max_depth = dd.get_coverage_depth_max(data)
depth = {"max": max_depth * 7 if max_depth > 0 else sys.maxint - 1,
"min": dd.get_coverage_depth_min(data)}
if not utils.file_exists(out_file):
with file_transaction(data, out_file) as tx_out_file:
ref_file = tz.get_in(["reference", "fasta", "base"], data)
region_file, calc_callable = _regions_for_coverage(data, region, ref_file, tx_out_file)
if calc_callable:
_group_by_ctype(_get_coverage_file(data["work_bam"], ref_file, region, region_file, depth,
tx_out_file, data),
depth, region_file, tx_out_file, data)
# special case, do not calculate if we are in a chromosome not covered by BED file
else:
os.rename(region_file, tx_out_file)
return [{"callable_bed": out_file, "config": data["config"], "work_bam": data["work_bam"]}]
def _shared_gatk_call_prep(align_bams, items, ref_file, dbsnp, region,
out_file):
"""Shared preparation work for GATK variant calling.
"""
data = items[0]
config = data["config"]
broad_runner = broad.runner_from_config(config)
broad_runner.run_fn("picard_index_ref", ref_file)
for x in align_bams:
bam.index(x, config)
params = ["-R", ref_file]
if dd.is_set_coverage_depth_max(data):
coverage_depth_max = dd.get_coverage_depth_max(data)
# GATK can only downsample to a minimum of 200
coverage_depth_max = max([200, coverage_depth_max])
params += [
"--downsample_to_coverage",
str(coverage_depth_max), "--downsampling_type", "BY_SAMPLE"
]
coverage_depth_min = tz.get_in(["algorithm", "coverage_depth_min"], config)
if coverage_depth_min and coverage_depth_min < 4:
confidence = "4.0"
params += [
"--standard_min_confidence_threshold_for_calling", confidence,
"--standard_min_confidence_threshold_for_emitting", confidence
]
for a in annotation.get_gatk_annotations(config):
params += ["--annotation", a]
for x in align_bams:
params += ["-I", x]
if dbsnp:
params += ["--dbsnp", dbsnp]
variant_regions = tz.get_in(["algorithm", "variant_regions"], config)
region = subset_variant_regions(variant_regions, region, out_file, items)
if region:
params += [
"-L",
bamprep.region_to_gatk(region), "--interval_set_rule",
"INTERSECTION"
]
return broad_runner, params
