def priority_coverage(data, out_dir):
from bcbio.structural import prioritize
bed_file = dd.get_svprioritize(data)
if not bed_file or not file_exists(bed_file) or prioritize.is_gene_list(
bed_file):
return data
work_dir = safe_makedir(out_dir)
sample = dd.get_sample_name(data)
out_file = os.path.join(work_dir, sample + "_priority_depth.bed")
if file_exists(out_file):
return out_file
nthreads = dd.get_num_cores(data)
in_bam = dd.get_align_bam(data) or dd.get_work_bam(data)
sambamba = config_utils.get_program("sambamba", data, default="sambamba")
with tx_tmpdir(data, work_dir) as tmp_dir:
cleaned_bed = clean_file(bed_file, data, prefix="cov-", simple=True)
with file_transaction(out_file) as tx_out_file:
parse_cmd = "awk '{print $1\"\t\"$2\"\t\"$2\"\t\"$3\"\t\"$10}' | sed '1d'"
cmd = ("{sambamba} depth base -t {nthreads} -L {cleaned_bed} "
"-F \"not unmapped\" "
"{in_bam} | {parse_cmd} > {tx_out_file}")
message = "Calculating coverage of {bed_file} regions in {in_bam}"
do.run(cmd.format(**locals()), message.format(**locals()))
return out_file
def priority_total_coverage(data):
"""
calculate coverage at 10 depth intervals in the priority regions
"""
bed_file = dd.get_svprioritize(data)
if not bed_file and not file_exists(bed_file):
return data
work_dir = os.path.join(dd.get_work_dir(data), "report", "coverage")
sample = dd.get_sample_name(data)
out_file = os.path.join(work_dir, sample + "_priority_total_coverage.bed")
if file_exists(out_file):
data['priority_total_coverage'] = os.path.abspath(out_file)
return data
nthreads = dd.get_num_cores(data)
in_bam = dd.get_align_bam(data) or dd.get_work_bam(data)
sambamba = config_utils.get_program("sambamba", data, default="sambamba")
with tx_tmpdir(data, work_dir) as tmp_dir:
cleaned_bed = os.path.join(tmp_dir, os.path.basename(bed_file))
cleaned_bed = bed.decomment(bed_file, cleaned_bed)
with file_transaction(out_file) as tx_out_file:
cmd = (
"{sambamba} depth region -t {nthreads} -L {cleaned_bed} "
"-F \"not unmapped\" "
"-T 10 -T 20 -T 30 -T 40 -T 50 -T 60 -T 70 -T 80 -T 90 -T 100 "
"{in_bam} -o {tx_out_file}")
message = "Calculating coverage of {bed_file} regions in {in_bam}"
do.run(cmd.format(**locals()), message.format(**locals()))
data['priority_total_coverage'] = os.path.abspath(out_file)
return data
def _handle_multiple_svcallers(data, stage):
"""Retrieve configured structural variation caller, handling multiple.
data is one sample
"""
svs = get_svcallers(data)
# special cases -- prioritization
if stage == "ensemble" and dd.get_svprioritize(data):
svs.append("prioritize")
out = []
for svcaller in svs:
if svcaller in _get_callers([data], stage):
base = copy.deepcopy(data)
# clean SV callers present in multiple rounds and not this caller
final_svs = []
for sv in data.get("sv", []):
if (stage == "ensemble" or sv["variantcaller"] == svcaller
or sv["variantcaller"] not in svs
or svcaller not in _get_callers(
[data], stage, special_cases=True)):
final_svs.append(sv)
base["sv"] = final_svs
base["config"]["algorithm"]["svcaller"] = svcaller
base["config"]["algorithm"]["svcaller_orig"] = svs
out.append(base)
return out
def priority_total_coverage(data):
"""
calculate coverage at 10 depth intervals in the priority regions
"""
bed_file = dd.get_svprioritize(data)
if not bed_file and not file_exists(bed_file):
return data
work_dir = os.path.join(dd.get_work_dir(data), "report", "coverage")
sample = dd.get_sample_name(data)
out_file = os.path.join(work_dir, sample + "_priority_total_coverage.bed")
if file_exists(out_file):
data['priority_total_coverage'] = os.path.abspath(out_file)
return data
nthreads = dd.get_num_cores(data)
in_bam = dd.get_align_bam(data) or dd.get_work_bam(data)
sambamba = config_utils.get_program("sambamba", data, default="sambamba")
with tx_tmpdir(data, work_dir) as tmp_dir:
cleaned_bed = os.path.join(tmp_dir, os.path.basename(bed_file))
cleaned_bed = bed.decomment(bed_file, cleaned_bed)
with file_transaction(out_file) as tx_out_file:
cmd = ("{sambamba} depth region -t {nthreads} -L {cleaned_bed} "
"-F \"not unmapped\" "
"-T 10 -T 20 -T 30 -T 40 -T 50 -T 60 -T 70 -T 80 -T 90 -T 100 "
"{in_bam} -o {tx_out_file}")
message = "Calculating coverage of {bed_file} regions in {in_bam}"
do.run(cmd.format(**locals()), message.format(**locals()))
data['priority_total_coverage'] = os.path.abspath(out_file)
return data
def priority_total_coverage(data, out_dir):
"""
calculate coverage at 10 depth intervals in the priority regions
"""
from bcbio.structural import prioritize
bed_file = dd.get_svprioritize(data)
if not bed_file and not file_exists(bed_file) or prioritize.is_gene_list(bed_file):
return {}
work_dir = safe_makedir(out_dir)
sample = dd.get_sample_name(data)
out_file = os.path.join(work_dir, sample + "_priority_total_coverage.bed")
if file_exists(out_file):
# data['priority_total_coverage'] = os.path.abspath(out_file)
return out_file
nthreads = dd.get_num_cores(data)
in_bam = dd.get_align_bam(data) or dd.get_work_bam(data)
sambamba = config_utils.get_program("sambamba", data, default="sambamba")
with tx_tmpdir(data, work_dir) as tmp_dir:
cleaned_bed = clean_file(bed_file, data)
with file_transaction(out_file) as tx_out_file:
cmd = ("{sambamba} depth region -t {nthreads} -L {cleaned_bed} "
"-F \"not unmapped\" "
"-T 10 -T 20 -T 30 -T 40 -T 50 -T 60 -T 70 -T 80 -T 90 -T 100 "
"{in_bam} -o {tx_out_file}")
message = "Calculating coverage of {bed_file} regions in {in_bam}"
do.run(cmd.format(**locals()), message.format(**locals()))
# data['priority_total_coverage'] = os.path.abspath(out_file)
return out_file
def priority_total_coverage(data, out_dir):
"""
calculate coverage at 10 depth intervals in the priority regions
"""
from bcbio.structural import prioritize
bed_file = dd.get_svprioritize(data)
if not bed_file and not file_exists(bed_file) or prioritize.is_gene_list(
bed_file):
return {}
in_bam = dd.get_align_bam(data) or dd.get_work_bam(data)
cleaned_bed = clean_file(bed_file, data, prefix="svprioritize-")
work_dir = safe_makedir(out_dir)
sample = dd.get_sample_name(data)
out_file = os.path.join(work_dir, sample + "_priority_total_coverage.bed")
if utils.file_uptodate(out_file, cleaned_bed) and utils.file_uptodate(
out_file, in_bam):
return out_file
cmdl = sambamba.make_command(
data,
"depth region",
in_bam,
cleaned_bed,
depth_thresholds=[10, 20, 30, 40, 50, 60, 70, 80, 90, 100])
with file_transaction(out_file) as tx_out_file:
message = "Calculating region coverage of {bed_file} in {in_bam}"
do.run(cmdl + " -o " + tx_out_file, message.format(**locals()))
logger.debug("Saved svprioritize coverage into " + out_file)
return out_file
def priority_total_coverage(data, out_dir):
"""
calculate coverage at 10 depth intervals in the priority regions
"""
from bcbio.structural import prioritize
bed_file = dd.get_svprioritize(data)
if not bed_file and not file_exists(bed_file) or prioritize.is_gene_list(
bed_file):
return {}
work_dir = safe_makedir(out_dir)
sample = dd.get_sample_name(data)
out_file = os.path.join(work_dir, sample + "_priority_total_coverage.bed")
if file_exists(out_file):
# data['priority_total_coverage'] = os.path.abspath(out_file)
return out_file
nthreads = dd.get_num_cores(data)
in_bam = dd.get_align_bam(data) or dd.get_work_bam(data)
sambamba = config_utils.get_program("sambamba", data, default="sambamba")
with tx_tmpdir(data, work_dir) as tmp_dir:
cleaned_bed = clean_file(bed_file, data)
with file_transaction(out_file) as tx_out_file:
cmd = (
"{sambamba} depth region -t {nthreads} -L {cleaned_bed} "
"-F \"not unmapped\" "
"-T 10 -T 20 -T 30 -T 40 -T 50 -T 60 -T 70 -T 80 -T 90 -T 100 "
"{in_bam} -o {tx_out_file}")
message = "Calculating coverage of {bed_file} regions in {in_bam}"
do.run(cmd.format(**locals()), message.format(**locals()))
# data['priority_total_coverage'] = os.path.abspath(out_file)
return out_file
def run(items):
"""Perform detection of structural variations with lumpy.
"""
if not all(
utils.get_in(data, ("config", "algorithm", "aligner")) in
["bwa", "sentieon-bwa", "minimap2", False, None] for data in items):
raise ValueError(
"Require bwa or minimap2 alignment input for lumpy structural variation detection"
)
paired = vcfutils.get_paired(items)
work_dir = _sv_workdir(
paired.tumor_data if paired and paired.tumor_data else items[0])
previous_evidence = {}
full_bams, sr_bams, disc_bams = [], [], []
for data in items:
full_bams.append(dd.get_align_bam(data))
sr_bam, disc_bam = sshared.find_existing_split_discordants(data)
sr_bams.append(sr_bam)
disc_bams.append(disc_bam)
cur_dels, cur_dups = _bedpes_from_cnv_caller(data, work_dir)
previous_evidence[dd.get_sample_name(data)] = {}
if cur_dels and utils.file_exists(cur_dels):
previous_evidence[dd.get_sample_name(data)]["dels"] = cur_dels
if cur_dups and utils.file_exists(cur_dups):
previous_evidence[dd.get_sample_name(data)]["dups"] = cur_dups
lumpy_vcf, exclude_file = _run_smoove(full_bams, sr_bams, disc_bams,
work_dir, items)
gt_vcfs = {}
# Retain paired samples with tumor/normal genotyped in one file
if paired and paired.normal_name:
batches = [[paired.tumor_data, paired.normal_data]]
else:
batches = [[x] for x in items]
for batch_items in batches:
for data in batch_items:
gt_vcfs[dd.get_sample_name(data)] = _filter_by_support(
lumpy_vcf, data)
if paired and paired.normal_name:
gt_vcfs = _filter_by_background(paired.tumor_name,
[paired.normal_name], gt_vcfs,
paired.tumor_data)
out = []
for data in items:
if "sv" not in data:
data["sv"] = []
vcf_file = gt_vcfs.get(dd.get_sample_name(data))
if vcf_file:
if dd.get_svprioritize(data):
effects_vcf, _ = effects.add_to_vcf(vcf_file, data, "snpeff")
else:
effects_vcf = None
data["sv"].append({
"variantcaller": "lumpy",
"vrn_file": effects_vcf or vcf_file,
"exclude_file": exclude_file
})
out.append(data)
return out
def get_coords(data):
for category, vtypes in [("LOH", {"LOSS", "HETEROZYGOSITY"}),
("amplification", {"AMPLIFICATION"})]:
out = tz.get_in([category, dd.get_genome_build(data)], _COORDS, {})
priority_file = dd.get_svprioritize(data)
if priority_file and os.path.basename(priority_file).find("civic") >= 0:
for chrom, start, end, gene in _civic_regions(priority_file, vtypes, dd.get_disease(data)):
out[gene] = (chrom, start, end)
yield category, out
def run(items):
"""Perform detection of structural variations with lumpy, using bwa-mem alignment.
"""
if not all(utils.get_in(data, ("config", "algorithm", "aligner"))
in ["bwa", "sentieon-bwa", False, None] for data in items):
raise ValueError("Require bwa-mem alignment input for lumpy structural variation detection")
paired = vcfutils.get_paired_bams([x["align_bam"] for x in items], items)
work_dir = _sv_workdir(paired.tumor_data if paired and paired.tumor_data else items[0])
previous_evidence = {}
full_bams, sr_bams, disc_bams = [], [], []
for data in items:
sr_bam, disc_bam = sshared.get_split_discordants(data, work_dir)
full_bams.append(dd.get_align_bam(data))
sr_bams.append(sr_bam)
disc_bams.append(disc_bam)
cur_dels, cur_dups = _bedpes_from_cnv_caller(data, work_dir)
previous_evidence[dd.get_sample_name(data)] = {}
if cur_dels and utils.file_exists(cur_dels):
previous_evidence[dd.get_sample_name(data)]["dels"] = cur_dels
if cur_dups and utils.file_exists(cur_dups):
previous_evidence[dd.get_sample_name(data)]["dups"] = cur_dups
lumpy_vcf, exclude_file = _run_lumpy(full_bams, sr_bams, disc_bams, previous_evidence,
work_dir, items)
gt_vcfs = {}
for data in items:
sample = dd.get_sample_name(data)
sample_vcf = vcfutils.select_sample(lumpy_vcf, sample,
utils.append_stem(lumpy_vcf, "-%s" % sample),
data["config"])
if "bnd-genotype" in dd.get_tools_on(data):
gt_vcf = _run_svtyper(sample_vcf, dd.get_align_bam(data), exclude_file, data)
elif "lumpy-genotype" in dd.get_tools_off(data):
gt_vcf = sample_vcf
else:
std_vcf, bnd_vcf = _split_breakends(sample_vcf, data)
std_gt_vcf = _run_svtyper(std_vcf, dd.get_align_bam(data), exclude_file, data)
gt_vcf = vcfutils.concat_variant_files_bcftools(
orig_files=[std_gt_vcf, bnd_vcf],
out_file="%s-combined.vcf.gz" % utils.splitext_plus(std_gt_vcf)[0],
config=data["config"])
gt_vcfs[dd.get_sample_name(data)] = _filter_by_support(gt_vcf, data)
if paired and paired.normal_name:
gt_vcfs = _filter_by_background([paired.tumor_name], [paired.normal_name], gt_vcfs, paired.tumor_data)
out = []
for data in items:
if "sv" not in data:
data["sv"] = []
vcf_file = gt_vcfs[dd.get_sample_name(data)]
if dd.get_svprioritize(data):
effects_vcf, _ = effects.add_to_vcf(vcf_file, data, "snpeff")
else:
effects_vcf = None
data["sv"].append({"variantcaller": "lumpy",
"vrn_file": effects_vcf or vcf_file,
"exclude_file": exclude_file})
out.append(data)
return out
def run(items):
"""Perform detection of structural variations with lumpy, using bwa-mem alignment.
"""
if not all(utils.get_in(data, ("config", "algorithm", "aligner"))
in ["bwa", "sentieon-bwa", False, None] for data in items):
raise ValueError("Require bwa-mem alignment input for lumpy structural variation detection")
paired = vcfutils.get_paired_bams([x["align_bam"] for x in items], items)
work_dir = _sv_workdir(paired.tumor_data if paired and paired.tumor_data else items[0])
previous_evidence = {}
full_bams, sr_bams, disc_bams = [], [], []
for data in items:
sr_bam, disc_bam = sshared.get_split_discordants(data, work_dir)
full_bams.append(dd.get_align_bam(data))
sr_bams.append(sr_bam)
disc_bams.append(disc_bam)
cur_dels, cur_dups = _bedpes_from_cnv_caller(data, work_dir)
previous_evidence[dd.get_sample_name(data)] = {}
if cur_dels and utils.file_exists(cur_dels):
previous_evidence[dd.get_sample_name(data)]["dels"] = cur_dels
if cur_dups and utils.file_exists(cur_dups):
previous_evidence[dd.get_sample_name(data)]["dups"] = cur_dups
lumpy_vcf, exclude_file = _run_lumpy(full_bams, sr_bams, disc_bams, previous_evidence,
work_dir, items)
gt_vcfs = {}
for data in items:
sample = dd.get_sample_name(data)
sample_vcf = vcfutils.select_sample(lumpy_vcf, sample,
utils.append_stem(lumpy_vcf, "-%s" % sample),
data["config"])
if "bnd-genotype" in dd.get_tools_on(data):
gt_vcf = _run_svtyper(sample_vcf, dd.get_align_bam(data), exclude_file, data)
else:
std_vcf, bnd_vcf = _split_breakends(sample_vcf, data)
std_gt_vcf = _run_svtyper(std_vcf, dd.get_align_bam(data), exclude_file, data)
gt_vcf = vcfutils.concat_variant_files_bcftools(
orig_files=[std_gt_vcf, bnd_vcf],
out_file="%s-combined.vcf.gz" % utils.splitext_plus(std_gt_vcf)[0],
config=data["config"])
gt_vcfs[dd.get_sample_name(data)] = _filter_by_support(gt_vcf, data)
if paired and paired.normal_name:
gt_vcfs = _filter_by_background([paired.tumor_name], [paired.normal_name], gt_vcfs, paired.tumor_data)
out = []
for data in items:
if "sv" not in data:
data["sv"] = []
vcf_file = gt_vcfs[dd.get_sample_name(data)]
if dd.get_svprioritize(data):
effects_vcf, _ = effects.add_to_vcf(vcf_file, data, "snpeff")
else:
effects_vcf = None
data["sv"].append({"variantcaller": "lumpy",
"vrn_file": effects_vcf or vcf_file,
"exclude_file": exclude_file})
out.append(data)
return out
def _handle_multiple_svcallers(data, stage):
"""Retrieve configured structural variation caller, handling multiple.
"""
svs = get_svcallers(data)
# special cases -- prioritization
if stage == "ensemble" and dd.get_svprioritize(data):
svs.append("prioritize")
out = []
for svcaller in svs:
if svcaller in _CALLERS[stage]:
base = copy.deepcopy(data)
base["config"]["algorithm"]["svcaller"] = svcaller
base["config"]["algorithm"]["svcaller_orig"] = svs
out.append(base)
return out
def _add_scatter_plot(out, data):
out_file = "%s-scatter.pdf" % os.path.splitext(out["cnr"])[0]
priority_bed = dd.get_svprioritize(data)
if not priority_bed:
return None
priority_bed = plot._prioritize_plot_regions(pybedtools.BedTool(priority_bed), data, os.path.dirname(out_file))
if utils.file_exists(out_file):
return out_file
cnr = _remove_haplotype_chroms(out["cnr"], data)
cns = _remove_haplotype_chroms(out["cns"], data)
with file_transaction(data, out_file) as tx_out_file:
cmd = [_get_cmd(), "scatter", "-s", cns, "-o", tx_out_file, "-l",
priority_bed, cnr]
do.run(cmd, "CNVkit scatter plot")
return out_file
def _add_scatter_plot(out, data):
out_file = "%s-scatter.pdf" % os.path.splitext(out["cnr"])[0]
priority_bed = dd.get_svprioritize(data)
if not priority_bed:
return None
priority_bed = plot._prioritize_plot_regions(pybedtools.BedTool(priority_bed), data, os.path.dirname(out_file))
if utils.file_exists(out_file):
return out_file
cnr = _remove_haplotype_chroms(out["cnr"], data)
cns = _remove_haplotype_chroms(out["cns"], data)
with file_transaction(data, out_file) as tx_out_file:
cmd = [_get_cmd(), "scatter", "-s", cns, "-o", tx_out_file, "-l",
priority_bed, cnr]
do.run(_prep_cmd(cmd, tx_out_file), "CNVkit scatter plot")
return out_file
def priority_coverage(data):
AVERAGE_REGION_STRING_LENGTH = 100
bed_file = dd.get_svprioritize(data)
if not bed_file or not file_exists(bed_file):
return data
work_dir = os.path.join(dd.get_work_dir(data), "report", "coverage")
batch_size = max_command_length() / AVERAGE_REGION_STRING_LENGTH
sample = dd.get_sample_name(data)
out_file = os.path.join(work_dir, sample + "_priority_depth.bed")
if file_exists(out_file):
data['priority_coverage'] = os.path.abspath(out_file)
return data
with chdir(work_dir):
in_bam = dd.get_align_bam(data) or dd.get_work_bam(data)
logger.debug("Calculating priority coverage for %s" % sample)
region_bed = pybedtools.BedTool(bed_file)
with file_transaction(out_file) as tx_out_file:
lcount = 0
for chunk in robust_partition_all(batch_size, region_bed):
coord_batch = []
line_batch = ""
for line in chunk:
lcount += 1
chrom = line.chrom
start = max(line.start, 0)
end = line.end
coords = "%s:%s-%s" % (chrom, start, end)
coord_batch.append(coords)
line_batch += "%s\t%s\t%s\n" % (chrom, start, end)
if not coord_batch:
continue
region_file = pybedtools.BedTool(line_batch,
from_string=True).saveas().fn
coord_string = " ".join(coord_batch)
awk_string = r"""'BEGIN {OFS="\t"} {print $1,$2+$5,$2+$5,$4,$6"\t%s"}'""" % sample
samtools = config_utils.get_program("samtools", data["config"])
bedtools = config_utils.get_program("bedtools", data["config"])
cmd = (
"{samtools} view -b {in_bam} {coord_string} | "
"{bedtools} coverage -sorted -d -a {region_file} -b - | "
"awk {awk_string} >> {tx_out_file}")
_silence_run(cmd.format(**locals()))
data['priority_coverage'] = os.path.abspath(out_file)
return data
def priority_coverage(data):
AVERAGE_REGION_STRING_LENGTH = 100
bed_file = dd.get_svprioritize(data)
if not bed_file or not file_exists(bed_file):
return data
work_dir = os.path.join(dd.get_work_dir(data), "report", "coverage")
batch_size = max_command_length() / AVERAGE_REGION_STRING_LENGTH
sample = dd.get_sample_name(data)
out_file = os.path.join(work_dir, sample + "_priority_depth.bed")
if file_exists(out_file):
data['priority_coverage'] = os.path.abspath(out_file)
return data
with chdir(work_dir):
in_bam = dd.get_align_bam(data) or dd.get_work_bam(data)
logger.debug("Calculating priority coverage for %s" % sample)
region_bed = pybedtools.BedTool(bed_file)
with file_transaction(out_file) as tx_out_file:
lcount = 0
for chunk in robust_partition_all(batch_size, region_bed):
coord_batch = []
line_batch = ""
for line in chunk:
lcount += 1
chrom = line.chrom
start = max(line.start, 0)
end = line.end
coords = "%s:%s-%s" % (chrom, start, end)
coord_batch.append(coords)
line_batch += "%s\t%s\t%s\n" % (chrom, start, end)
if not coord_batch:
continue
region_file = pybedtools.BedTool(line_batch,
from_string=True).saveas().fn
coord_string = " ".join(coord_batch)
awk_string = r"""'BEGIN {OFS="\t"} {print $1,$2+$5,$2+$5,$4,$6"\t%s"}'""" % sample
samtools = config_utils.get_program("samtools", data["config"])
bedtools = config_utils.get_program("bedtools", data["config"])
cmd = ("{samtools} view -b {in_bam} {coord_string} | "
"{bedtools} coverage -sorted -d -a {region_file} -b - | "
"awk {awk_string} >> {tx_out_file}")
_silence_run(cmd.format(**locals()))
data['priority_coverage'] = os.path.abspath(out_file)
return data
def priority_coverage(data, out_dir):
from bcbio.structural import prioritize
bed_file = dd.get_svprioritize(data)
if not bed_file or not file_exists(bed_file) or prioritize.is_gene_list(bed_file):
return data
work_dir = safe_makedir(out_dir)
sample = dd.get_sample_name(data)
cleaned_bed = clean_file(bed_file, data, prefix="cov-", simple=True)
out_file = os.path.join(work_dir, sample + "_priority_depth.bed")
in_bam = dd.get_align_bam(data) or dd.get_work_bam(data)
if utils.file_uptodate(out_file, cleaned_bed) and utils.file_uptodate(out_file, in_bam):
return out_file
with file_transaction(out_file) as tx_out_file:
cmdl = sambamba.make_command(data, "depth base", in_bam, cleaned_bed)
parse_cmd = "awk '{print $1\"\t\"$2\"\t\"$2\"\t\"$3\"\t\"$10}' | sed '1d'"
cmdl += " | {parse_cmd} > {tx_out_file}"
message = "Calculating base coverage of {bed_file} in {in_bam}"
do.run(cmdl.format(**locals()), message.format(**locals()))
return out_file
def priority_coverage(data, out_dir):
from bcbio.structural import prioritize
bed_file = dd.get_svprioritize(data)
if not bed_file or not file_exists(bed_file) or prioritize.is_gene_list(bed_file):
return data
work_dir = safe_makedir(out_dir)
sample = dd.get_sample_name(data)
cleaned_bed = clean_file(bed_file, data, prefix="cov-", simple=True)
out_file = os.path.join(work_dir, sample + "_priority_depth.bed")
in_bam = dd.get_align_bam(data) or dd.get_work_bam(data)
if utils.file_uptodate(out_file, cleaned_bed) and utils.file_uptodate(out_file, in_bam):
return out_file
with file_transaction(data, out_file) as tx_out_file:
cmdl = sambamba.make_command(data, "depth base", in_bam, cleaned_bed)
parse_cmd = "awk '{print $1\"\t\"$2\"\t\"$2\"\t\"$3\"\t\"$10}' | sed '1d'"
cmdl += " | {parse_cmd} > {tx_out_file}"
message = "Calculating base coverage of {bed_file} in {in_bam}"
do.run(cmdl.format(**locals()), message.format(**locals()))
return out_file
def get_coords(data):
"""Retrieve coordinates of genes of interest for prioritization.
Can read from CIViC input data or a supplied BED file of chrom, start, end
and gene information.
"""
for category, vtypes in [("LOH", {"LOSS", "HETEROZYGOSITY"}),
("amplification", {"AMPLIFICATION"})]:
out = tz.get_in([category, dd.get_genome_build(data)], _COORDS, {})
priority_file = dd.get_svprioritize(data)
if priority_file:
if os.path.basename(priority_file).find("civic") >= 0:
for chrom, start, end, gene in _civic_regions(priority_file, vtypes, dd.get_disease(data)):
out[gene] = (chrom, start, end)
elif os.path.basename(priority_file).find(".bed") >= 0:
for line in utils.open_gzipsafe(priority_file):
parts = line.strip().split("\t")
if len(parts) >= 4:
chrom, start, end, gene = parts[:4]
out[gene] = (chrom, int(start), int(end))
yield category, out
def _handle_multiple_svcallers(data, stage):
"""Retrieve configured structural variation caller, handling multiple.
"""
svs = get_svcallers(data)
# special cases -- prioritization
if stage == "ensemble" and dd.get_svprioritize(data):
svs.append("prioritize")
out = []
for svcaller in svs:
if svcaller in _get_callers([data], stage):
base = copy.deepcopy(data)
# clean SV callers present in multiple rounds and not this caller
final_svs = []
for sv in data.get("sv", []):
if stage == "ensemble" or sv["variantcaller"] == svcaller or sv["variantcaller"] not in svs:
final_svs.append(sv)
base["sv"] = final_svs
base["config"]["algorithm"]["svcaller"] = svcaller
base["config"]["algorithm"]["svcaller_orig"] = svs
out.append(base)
return out
def priority_total_coverage(data, out_dir):
"""
calculate coverage at 10 depth intervals in the priority regions
"""
from bcbio.structural import prioritize
bed_file = dd.get_svprioritize(data)
if not bed_file and not file_exists(bed_file) or prioritize.is_gene_list(bed_file):
return {}
in_bam = dd.get_align_bam(data) or dd.get_work_bam(data)
cleaned_bed = clean_file(bed_file, data, prefix="svprioritize-")
work_dir = safe_makedir(out_dir)
sample = dd.get_sample_name(data)
out_file = os.path.join(work_dir, sample + "_priority_total_coverage.bed")
if utils.file_uptodate(out_file, cleaned_bed) and utils.file_uptodate(out_file, in_bam):
return out_file
cmdl = sambamba.make_command(data, "depth region", in_bam, cleaned_bed,
depth_thresholds=[10, 20, 30, 40, 50, 60, 70, 80, 90, 100])
with file_transaction(out_file) as tx_out_file:
message = "Calculating region coverage of {bed_file} in {in_bam}"
do.run(cmdl + " -o " + tx_out_file, message.format(**locals()))
logger.debug("Saved svprioritize coverage into " + out_file)
return out_file
def get_coords(data):
"""Retrieve coordinates of genes of interest for prioritization.
Can read from CIViC input data or a supplied BED file of chrom, start, end
and gene information.
"""
for category, vtypes in [("LOH", {"LOSS", "HETEROZYGOSITY"}),
("amplification", {"AMPLIFICATION"})]:
out = tz.get_in([category, dd.get_genome_build(data)], _COORDS, {})
priority_file = dd.get_svprioritize(data)
if priority_file:
if os.path.basename(priority_file).find("civic") >= 0:
for chrom, start, end, gene in _civic_regions(
priority_file, vtypes, dd.get_disease(data)):
out[gene] = (chrom, start, end)
elif os.path.basename(priority_file).find(".bed") >= 0:
for line in utils.open_gzipsafe(priority_file):
parts = line.strip().split("\t")
if len(parts) >= 4:
chrom, start, end, gene = parts[:4]
out[gene] = (chrom, int(start), int(end))
yield category, out
def priority_coverage(data, out_dir):
bed_file = dd.get_svprioritize(data)
if not bed_file or not file_exists(bed_file):
return data
work_dir = safe_makedir(out_dir)
sample = dd.get_sample_name(data)
out_file = os.path.join(work_dir, sample + "_priority_depth.bed")
if file_exists(out_file):
return out_file
nthreads = dd.get_num_cores(data)
in_bam = dd.get_align_bam(data) or dd.get_work_bam(data)
sambamba = config_utils.get_program("sambamba", data, default="sambamba")
with tx_tmpdir(data, work_dir) as tmp_dir:
cleaned_bed = clean_file(bed_file, data)
with file_transaction(out_file) as tx_out_file:
parse_cmd = "awk '{print $1\"\t\"$2\"\t\"$2\"\t\"$3\"\t\"$10}' | sed '1d'"
cmd = ("{sambamba} depth base -t {nthreads} -L {cleaned_bed} "
"-F \"not unmapped\" "
"{in_bam} | {parse_cmd} > {tx_out_file}")
message = "Calculating coverage of {bed_file} regions in {in_bam}"
do.run(cmd.format(**locals()), message.format(**locals()))
return out_file