def run(call_file, ref_file, vrn_files, data):
"""Run filtering on the input call file, handling SNPs and indels separately.
"""
algs = [data["config"]["algorithm"]] * len(data.get("vrn_files", [1]))
if config_utils.use_vqsr(algs):
if "gvcf" in dd.get_tools_on(data) and not dd.get_jointcaller(data):
raise ValueError(
"Cannot force gVCF output with joint calling using tools_on: [gvcf] and use VQSR. "
"Try using cutoff-based soft filtering with tools_off: [vqsr]")
snp_file, indel_file = vcfutils.split_snps_indels(
call_file, ref_file, data["config"])
snp_filter_file = _variant_filtration(snp_file, ref_file, vrn_files,
data, "SNP",
vfilter.gatk_snp_cutoff)
indel_filter_file = _variant_filtration(indel_file, ref_file,
vrn_files, data, "INDEL",
vfilter.gatk_indel_cutoff)
orig_files = [snp_filter_file, indel_filter_file]
out_file = "%scombined.vcf.gz" % os.path.commonprefix(orig_files)
combined_file = vcfutils.combine_variant_files(orig_files, out_file,
ref_file,
data["config"])
return combined_file
else:
snp_filter = vfilter.gatk_snp_cutoff(call_file, data)
indel_filter = vfilter.gatk_indel_cutoff(snp_filter, data)
return indel_filter
def run_jointvc(items):
items = [utils.to_single_data(x) for x in items]
data = items[0]
if not dd.get_jointcaller(data):
data["config"]["algorithm"][
"jointcaller"] = "%s-joint" % dd.get_variantcaller(data)
# GenomicsDBImport uses 1-based coordinates. That's unexpected, convert over to these.
chrom, coords = data["region"].split(":")
start, end = coords.split("-")
ready_region = "%s:%s-%s" % (chrom, int(start) + 1, end)
str_region = ready_region.replace(":", "_")
batches = dd.get_batches(data) or dd.get_sample_name(data)
if not isinstance(batches, (list, tuple)):
batches = [batches]
out_file = os.path.join(
utils.safe_makedir(
os.path.join(dd.get_work_dir(data), "joint",
dd.get_variantcaller(data),
str_region)), "%s-%s-%s.vcf.gz" %
(batches[0], dd.get_variantcaller(data), str_region))
joint_out = square_batch_region(data, ready_region, [],
[d["vrn_file"] for d in items],
out_file)[0]
data["vrn_file_region"] = joint_out["vrn_file"]
return data
def _bcftools_stats(data, out_dir, vcf_file_key=None, germline=False):
"""Run bcftools stats.
"""
vcinfo = get_active_vcinfo(data)
if vcinfo:
out_dir = utils.safe_makedir(out_dir)
vcf_file = vcinfo[vcf_file_key or "vrn_file"]
if dd.get_jointcaller(data) or "gvcf" in dd.get_tools_on(data):
opts = ""
else:
opts = "-f PASS,."
name = dd.get_sample_name(data)
out_file = os.path.join(
out_dir,
"%s_bcftools_stats%s.txt" % (name,
("_germline" if germline else "")))
bcftools = config_utils.get_program("bcftools", data["config"])
if not utils.file_exists(out_file):
with file_transaction(data, out_file) as tx_out_file:
orig_out_file = os.path.join(
os.path.dirname(tx_out_file),
"orig_%s" % os.path.basename(tx_out_file))
cmd = (
"{bcftools} stats -s {name} {opts} {vcf_file} > {orig_out_file}"
)
do.run(cmd.format(**locals()), "bcftools stats %s" % name)
with open(orig_out_file) as in_handle:
with open(tx_out_file, "w") as out_handle:
for line in in_handle:
if line.startswith("ID\t"):
parts = line.split("\t")
parts[-1] = "%s\n" % name
line = "\t".join(parts)
out_handle.write(line)
return out_file
def rnaseq_variant_calling(samples, run_parallel):
"""
run RNA-seq variant calling using GATK
"""
samples = run_parallel("run_rnaseq_variant_calling", samples)
variantcaller = dd.get_variantcaller(to_single_data(samples[0]))
jointcaller = dd.get_jointcaller(to_single_data(samples[0]))
if jointcaller and 'gatk-haplotype-joint' in jointcaller:
out = []
for d in joint.square_off(samples, run_parallel):
out.extend(
[[to_single_data(xs)]
for xs in multi.split_variants_by_sample(to_single_data(d))])
samples = out
if variantcaller or jointcaller:
samples = run_parallel("run_rnaseq_ann_filter", samples)
if jointcaller and 'gatk-haplotype-joint' in jointcaller:
out = []
for data in (to_single_data(xs) for xs in samples):
if "variants" not in data:
data["variants"] = []
data["variants"].append({
"variantcaller": "gatk-haplotype",
"vcf": data["vrn_file_orig"],
"population": {
"vcf": data["vrn_file"]
}
})
data["vrn_file"] = data.pop("vrn_file_orig")
out.append([data])
samples = out
return samples
def _bcftools_stats(data, out_dir, vcf_file_key=None, germline=False):
"""Run bcftools stats.
"""
vcinfo = get_active_vcinfo(data)
if vcinfo:
out_dir = utils.safe_makedir(out_dir)
vcf_file = vcinfo[vcf_file_key or "vrn_file"]
if dd.get_jointcaller(data) or "gvcf" in dd.get_tools_on(data):
opts = ""
else:
opts = "-f PASS,."
name = dd.get_sample_name(data)
out_file = os.path.join(out_dir, "%s_bcftools_stats%s.txt" % (name, ("_germline" if germline else "")))
bcftools = config_utils.get_program("bcftools", data["config"])
if not utils.file_exists(out_file):
with file_transaction(data, out_file) as tx_out_file:
orig_out_file = os.path.join(os.path.dirname(tx_out_file), "orig_%s" % os.path.basename(tx_out_file))
cmd = ("{bcftools} stats -s {name} {opts} {vcf_file} > {orig_out_file}")
do.run(cmd.format(**locals()), "bcftools stats %s" % name)
with open(orig_out_file) as in_handle:
with open(tx_out_file, "w") as out_handle:
for line in in_handle:
if line.startswith("ID\t"):
parts = line.split("\t")
parts[-1] = "%s\n" % name
line = "\t".join(parts)
out_handle.write(line)
return out_file
def _variant_checkpoints(samples):
"""Check sample configuration to identify required steps in analysis.
"""
checkpoints = {}
checkpoints["vc"] = any([dd.get_variantcaller(d) for d in samples])
checkpoints["sv"] = any([dd.get_svcaller(d) for d in samples])
checkpoints["jointvc"] = any([dd.get_jointcaller(d) or ("gvcf" in dd.get_tools_on(d)) for d in samples])
checkpoints["hla"] = any([dd.get_hlacaller(d) for d in samples])
return checkpoints
def _variant_checkpoints(samples):
"""Check sample configuration to identify required steps in analysis.
"""
checkpoints = {}
checkpoints["vc"] = any([dd.get_variantcaller(d) for d in samples])
checkpoints["sv"] = any([dd.get_svcaller(d) for d in samples])
checkpoints["jointvc"] = any([dd.get_jointcaller(d) or ("gvcf" in dd.get_tools_on(d)) for d in samples])
checkpoints["hla"] = any([dd.get_hlacaller(d) for d in samples])
return checkpoints
def _variant_checkpoints(samples):
"""Check sample configuration to identify required steps in analysis.
"""
checkpoints = {}
checkpoints["vc"] = any([dd.get_variantcaller(d) for d in samples])
checkpoints["sv"] = any([dd.get_svcaller(d) for d in samples])
checkpoints["jointvc"] = any([(dd.get_jointcaller(d) or ("gvcf" in dd.get_tools_on(d))) and dd.get_batch(d)
for d in samples])
checkpoints["hla"] = any([dd.get_hlacaller(d) for d in samples])
checkpoints["align"] = any([(dd.get_aligner(d) or dd.get_bam_clean(d)) for d in samples])
checkpoints["align_split"] = not all([(dd.get_align_split_size(d) is False or
not dd.get_aligner(d))
for d in samples])
return checkpoints
def run_jointvc(items):
items = [utils.to_single_data(x) for x in items]
data = items[0]
if not dd.get_jointcaller(data):
data["config"]["algorithm"]["jointcaller"] = "%s-joint" % dd.get_variantcaller(data)
# GenomicsDBImport uses 1-based coordinates. That's unexpected, convert over to these.
chrom, coords = data["region"].split(":")
start, end = coords.split("-")
ready_region = "%s:%s-%s" % (chrom, int(start) + 1, end)
str_region = ready_region.replace(":", "_")
out_file = os.path.join(utils.safe_makedir(os.path.join(dd.get_work_dir(data), "joint",
dd.get_variantcaller(data), str_region)),
"%s-%s-%s.vcf.gz" % (dd.get_batches(data)[0], dd.get_variantcaller(data), str_region))
joint_out = square_batch_region(data, ready_region, [], [d["vrn_file"] for d in items], out_file)[0]
data["vrn_file_region"] = joint_out["vrn_file"]
return data
def _variant_checkpoints(samples):
"""Check sample configuration to identify required steps in analysis.
"""
checkpoints = {}
checkpoints["vc"] = any([dd.get_variantcaller(d) or d.get("vrn_file") for d in samples])
checkpoints["sv"] = any([dd.get_svcaller(d) for d in samples])
checkpoints["jointvc"] = any([(dd.get_jointcaller(d) or "gvcf" in dd.get_tools_on(d))
for d in samples])
checkpoints["hla"] = any([dd.get_hlacaller(d) for d in samples])
checkpoints["align"] = any([(dd.get_aligner(d) or dd.get_bam_clean(d)) for d in samples])
checkpoints["align_split"] = not all([(dd.get_align_split_size(d) is False or
not dd.get_aligner(d))
for d in samples])
checkpoints["umi"] = any([dd.get_umi_consensus(d) for d in samples])
checkpoints["ensemble"] = any([dd.get_ensemble(d) for d in samples])
checkpoints["cancer"] = any(dd.get_phenotype(d) in ["tumor"] for d in samples)
return checkpoints
def _variant_checkpoints(samples):
"""Check sample configuration to identify required steps in analysis.
"""
checkpoints = {}
checkpoints["vc"] = any([dd.get_variantcaller(d) or d.get("vrn_file") for d in samples])
checkpoints["sv"] = any([dd.get_svcaller(d) for d in samples])
checkpoints["jointvc"] = any([(dd.get_jointcaller(d) or "gvcf" in dd.get_tools_on(d))
for d in samples])
checkpoints["hla"] = any([dd.get_hlacaller(d) for d in samples])
checkpoints["align"] = any([(dd.get_aligner(d) or dd.get_bam_clean(d)) for d in samples])
checkpoints["align_split"] = not all([(dd.get_align_split_size(d) is False or
not dd.get_aligner(d))
for d in samples])
checkpoints["archive"] = any([dd.get_archive(d) for d in samples])
checkpoints["umi"] = any([dd.get_umi_consensus(d) for d in samples])
checkpoints["ensemble"] = any([dd.get_ensemble(d) for d in samples])
checkpoints["cancer"] = any(dd.get_phenotype(d) in ["tumor"] for d in samples)
return checkpoints
def run_rnaseq_ann_filter(data):
"""Run RNA-seq annotation and filtering.
"""
data = to_single_data(data)
if dd.get_vrn_file(data):
eff_file = effects.add_to_vcf(dd.get_vrn_file(data), data)[0]
if eff_file:
data = dd.set_vrn_file(data, eff_file)
ann_file = population.run_vcfanno(dd.get_vrn_file(data), data)
if ann_file:
data = dd.set_vrn_file(data, ann_file)
jointcaller = dd.get_jointcaller(data)
if jointcaller and 'gatk-haplotype-joint' in jointcaller:
filter_file = variation.gatk_filter_rnaseq(dd.get_vrn_file(data), data)
data = dd.set_vrn_file(data, filter_file)
# remove variants close to splice junctions
vrn_file = dd.get_vrn_file(data)
vrn_file = variation.filter_junction_variants(vrn_file, data)
data = dd.set_vrn_file(data, vrn_file)
return [[data]]
def is_joint(data):
return "gvcf" in dd.get_tools_on(data) or dd.get_jointcaller(data)
def run_peddy(samples, out_dir=None):
data = samples[0]
batch = dd.get_batch(data) or dd.get_sample_name(data)
if isinstance(batch, (list, tuple)):
batch = batch[0]
if out_dir:
peddy_dir = safe_makedir(out_dir)
else:
peddy_dir = safe_makedir(
os.path.join(dd.get_work_dir(data), "qc", batch, "peddy"))
peddy_prefix = os.path.join(peddy_dir, batch)
peddy_report = peddy_prefix + ".html"
vcf_file = None
for d in samples:
vcinfo = None
if dd.get_jointcaller(d):
vcinfo = variant.extract_population_vcinfo(d)
elif dd.get_phenotype(d) == "germline" or dd.get_phenotype(d) not in [
"tumor"
]:
vcinfo = variant.get_active_vcinfo(d, use_ensemble=False)
if not vcinfo and dd.get_phenotype(d) in ["tumor"]:
vcinfo = variant.extract_germline_vcinfo(d, peddy_dir)
if vcinfo:
for key in ["germline", "vrn_file"]:
if vcinfo and vcinfo.get(key) and utils.file_exists(
vcinfo[key]):
if vcinfo[key] and dd.get_sample_name(
d) in vcfutils.get_samples(vcinfo[key]):
if vcinfo[
key] and vcfutils.vcf_has_nonfiltered_variants(
vcinfo[key]):
vcf_file = vcinfo[key]
break
peddy = config_utils.get_program("peddy",
data) if config_utils.program_installed(
"peddy", data) else None
config_skips = any(["peddy" in dd.get_tools_off(d) for d in samples])
if not peddy or not vcf_file or not vcfanno.is_human(data) or config_skips:
if not peddy:
reason = "peddy executable not found"
elif config_skips:
reason = "peddy in tools_off configuration"
elif not vcfanno.is_human(data):
reason = "sample is not human"
else:
assert not vcf_file
reason = "no suitable VCF files found with the sample and non-filtered variants"
msg = "Skipping peddy QC, %s: %s" % (
reason, [dd.get_sample_name(d) for d in samples])
with open(peddy_prefix + "-failed.log", "w") as out_handle:
out_handle.write(msg)
logger.info(msg)
return samples
if file_exists(peddy_prefix + "-failed.log"):
return samples
if not file_exists(peddy_report):
ped_file = create_ped_file(samples, vcf_file, out_dir=out_dir)
num_cores = dd.get_num_cores(data)
with tx_tmpdir(data) as tx_dir:
peddy_prefix_tx = os.path.join(tx_dir,
os.path.basename(peddy_prefix))
# Redirects stderr because incredibly noisy with no intervals found messages from cyvcf2
stderr_log = os.path.join(tx_dir, "run-stderr.log")
sites_str = "--sites hg38" if dd.get_genome_build(
data) == "hg38" else ""
locale = utils.locale_export()
cmd = (
"{locale} {peddy} -p {num_cores} {sites_str} --plot --prefix {peddy_prefix_tx} "
"{vcf_file} {ped_file} 2> {stderr_log}")
message = "Running peddy on {vcf_file} against {ped_file}."
try:
do.run(cmd.format(**locals()), message.format(**locals()))
except:
to_show = collections.deque(maxlen=100)
with open(stderr_log) as in_handle:
for line in in_handle:
to_show.append(line)
def allowed_errors(l):
return (
(l.find("IndexError") >= 0
and l.find("is out of bounds for axis") >= 0) or
(l.find("n_components=") >= 0
and l.find("must be between 1 and n_features=") >= 0)
or (l.find("n_components=") >= 0
and l.find("must be between 1 and min") >= 0)
or (l.find(
"Input contains NaN, infinity or a value too large for dtype"
) >= 0)
or (l.find("peddy: no hets found for sample") >= 0)
or (l.find(
"ValueError: need at least one array to concatenate"
) >= 0))
def all_line_errors(l):
return (l.find("no intervals found for") >= 0)
if any([allowed_errors(l) for l in to_show]) or all(
[all_line_errors(l) for l in to_show]):
logger.info(
"Skipping peddy because no variants overlap with checks: %s"
% batch)
with open(peddy_prefix + "-failed.log", "w") as out_handle:
out_handle.write(
"peddy did not find overlaps with 1kg sites in VCF, skipping"
)
return samples
else:
logger.warning("".join(to_show))
raise
for ext in PEDDY_OUT_EXTENSIONS:
if os.path.exists(peddy_prefix_tx + ext):
shutil.move(peddy_prefix_tx + ext, peddy_prefix + ext)
peddyfiles = expected_peddy_files(peddy_report, batch)
return dd.set_in_samples(samples, dd.set_summary_qc, peddyfiles)
def is_joint(data):
return "gvcf" in dd.get_tools_on(data) or dd.get_jointcaller(data)
