def run_gvcfgenotyper(data, orig_region, vrn_files, out_file):
"""Merge strelka2 and Illumina compatible gVCFs with gvcfgenotyper.
https://github.com/Illumina/gvcfgenotyper
Also need to explore GLnexus (https://github.com/dnanexus-rnd/GLnexus)
"""
if not utils.file_exists(out_file):
with file_transaction(data, out_file) as tx_out_file:
regions = _find_gvcf_blocks(vrn_files[0],
bamprep.region_to_gatk(orig_region),
os.path.dirname(tx_out_file))
if len(regions) == 1:
_run_gvcfgenotyper(data, regions[0], vrn_files, tx_out_file)
else:
split_outs = [
_run_gvcfgenotyper(
data, r, vrn_files, "%s-%s.vcf.gz" %
(utils.splitext_plus(out_file)[0], r.replace(
":", "_").replace("-", "_"))) for r in regions
]
vcfutils.concat_variant_files(split_outs, tx_out_file, regions,
dd.get_ref_file(data),
data["config"])
return vcfutils.bgzip_and_index(out_file, data["config"])
def gatk_rnaseq_calling(data):
"""Use GATK to perform gVCF variant calling on RNA-seq data
"""
from bcbio.bam import callable
data = utils.deepish_copy(data)
tools_on = dd.get_tools_on(data)
if not tools_on:
tools_on = []
tools_on.append("gvcf")
data = dd.set_tools_on(data, tools_on)
data = dd.set_jointcaller(data, ["%s-joint" % v for v in dd.get_variantcaller(data)])
out_dir = utils.safe_makedir(os.path.join(dd.get_work_dir(data),
"variation", "rnaseq", "gatk-haplotype"))
data = _setup_variant_regions(data, out_dir)
out_file = os.path.join(out_dir, "%s-gatk-haplotype.vcf.gz" % dd.get_sample_name(data))
if not utils.file_exists(out_file):
region_files = []
regions = []
for cur_region in callable.get_split_regions(dd.get_variant_regions(data), data):
str_region = "_".join([str(x) for x in cur_region])
region_file = os.path.join(utils.safe_makedir(os.path.join(dd.get_work_dir(data),
"variation", "rnaseq", "gatk-haplotype",
"regions")),
"%s-%s-gatk-haplotype.vcf.gz" % (dd.get_sample_name(data), str_region))
region_file = gatk.haplotype_caller([dd.get_split_bam(data)], [data], dd.get_ref_file(data), {},
region=cur_region, out_file=region_file)
region_files.append(region_file)
regions.append(cur_region)
out_file = vcfutils.concat_variant_files(region_files, out_file, regions,
dd.get_ref_file(data), data["config"])
return dd.set_vrn_file(data, 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.gz" % dd.get_sample_name(inputs[0]))
if not utils.file_exists(out_file):
with file_transaction(inputs[0], out_file) as tx_out_file:
coords = chromhacks.autosomal_or_x_coords(dd.get_ref_file(inputs[0]))
parallel = {"type": "local", "cores": dd.get_cores(inputs[0]), "progs": []}
rs = run_multicore(_run_wham_coords,
[(inputs, background_bams, coord, out_file)
for coord in coords],
inputs[0]["config"], parallel)
rs = {coord: fname for (coord, fname) in rs}
vcfutils.concat_variant_files([rs[c] for c in coords], tx_out_file, coords,
dd.get_ref_file(inputs[0]), inputs[0]["config"])
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.gz" % dd.get_sample_name(inputs[0]))
if not utils.file_exists(out_file):
with file_transaction(inputs[0], out_file) as tx_out_file:
coords = chromhacks.autosomal_or_x_coords(dd.get_ref_file(inputs[0]))
parallel = {"type": "local", "cores": dd.get_cores(inputs[0]), "progs": []}
rs = run_multicore(_run_wham_coords,
[(inputs, background_bams, coord, out_file)
for coord in coords],
inputs[0]["config"], parallel)
rs = {coord: fname for (coord, fname) in rs}
vcfutils.concat_variant_files([rs[c] for c in coords], tx_out_file, coords,
dd.get_ref_file(inputs[0]), inputs[0]["config"])
return out_file
def gatk_rnaseq_calling(data):
"""Use GATK to perform gVCF variant calling on RNA-seq data
"""
from bcbio.bam import callable
data = utils.deepish_copy(data)
tools_on = dd.get_tools_on(data)
if not tools_on:
tools_on = []
tools_on.append("gvcf")
data = dd.set_tools_on(data, tools_on)
data = dd.set_jointcaller(data, ["%s-joint" % v for v in dd.get_variantcaller(data)])
out_dir = utils.safe_makedir(os.path.join(dd.get_work_dir(data),
"variation", "rnaseq", "gatk-haplotype"))
data = _setup_variant_regions(data, out_dir)
out_file = os.path.join(out_dir, "%s-gatk-haplotype.vcf.gz" % dd.get_sample_name(data))
if not utils.file_exists(out_file):
region_files = []
regions = []
for cur_region in callable.get_split_regions(dd.get_variant_regions(data), data):
str_region = "_".join([str(x) for x in cur_region])
region_file = os.path.join(utils.safe_makedir(os.path.join(dd.get_work_dir(data),
"variation", "rnaseq", "gatk-haplotype",
"regions")),
"%s-%s-gatk-haplotype.vcf.gz" % (dd.get_sample_name(data), str_region))
region_file = gatk.haplotype_caller([dd.get_split_bam(data)], [data], dd.get_ref_file(data), {},
region=cur_region, out_file=region_file)
region_files.append(region_file)
regions.append(cur_region)
out_file = vcfutils.concat_variant_files(region_files, out_file, regions,
dd.get_ref_file(data), data["config"])
return dd.set_vrn_file(data, out_file)
def run_gvcfgenotyper(data, orig_region, vrn_files, out_file):
"""Merge strelka2 and Illumina compatible gVCFs with gvcfgenotyper.
https://github.com/Illumina/gvcfgenotyper
Also need to explore GLnexus (https://github.com/dnanexus-rnd/GLnexus)
"""
if not utils.file_exists(out_file):
with file_transaction(data, out_file) as tx_out_file:
regions = _find_gvcf_blocks(vrn_files[0], bamprep.region_to_gatk(orig_region),
os.path.dirname(tx_out_file))
if len(regions) == 1:
_run_gvcfgenotyper(data, regions[0], vrn_files, tx_out_file)
else:
split_outs = [_run_gvcfgenotyper(data, r, vrn_files,
"%s-%s.vcf.gz" % (utils.splitext_plus(out_file)[0],
r.replace(":", "_").replace("-", "_")))
for r in regions]
vcfutils.concat_variant_files(split_outs, tx_out_file, regions,
dd.get_ref_file(data), data["config"])
return vcfutils.bgzip_and_index(out_file, data["config"])
def concat_batch_variantcalls(items):
"""CWL entry point: combine variant calls from regions into single VCF.
"""
items, cwl_extras = split_data_cwl_items(items)
batch_name = _get_batch_name(items)
variantcaller = _get_batch_variantcaller(items)
out_file = os.path.join(dd.get_work_dir(items[0]), variantcaller, "%s.vcf.gz" % (batch_name))
utils.safe_makedir(os.path.dirname(out_file))
regions = [_region_to_coords(r) for r in cwl_extras["region"]]
out_file = vcfutils.concat_variant_files(cwl_extras["vrn_file_region"], out_file, regions,
dd.get_ref_file(items[0]), items[0]["config"])
return {"vrn_file": out_file}
def concat_batch_variantcalls(items):
"""CWL entry point: combine variant calls from regions into single VCF.
"""
items = [utils.to_single_data(x) for x in items]
batch_name = _get_batch_name(items)
variantcaller = _get_batch_variantcaller(items)
out_file = os.path.join(dd.get_work_dir(items[0]), variantcaller, "%s.vcf.gz" % (batch_name))
utils.safe_makedir(os.path.dirname(out_file))
regions = [_region_to_coords(r) for r in items[0]["region"]]
vrn_file_regions = items[0]["vrn_file_region"]
out_file = vcfutils.concat_variant_files(vrn_file_regions, out_file, regions,
dd.get_ref_file(items[0]), items[0]["config"])
return {"vrn_file": out_file}
def concat_batch_variantcalls(items, region_block=True, skip_jointcheck=False):
"""CWL entry point: combine variant calls from regions into single VCF.
"""
items = [utils.to_single_data(x) for x in items]
batch_name = _get_batch_name(items, skip_jointcheck)
variantcaller = _get_batch_variantcaller(items)
out_file = os.path.join(dd.get_work_dir(items[0]), variantcaller, "%s.vcf.gz" % (batch_name))
utils.safe_makedir(os.path.dirname(out_file))
if region_block:
regions = [_region_to_coords(rs[0]) for rs in items[0]["region_block"]]
else:
regions = [_region_to_coords(r) for r in items[0]["region"]]
vrn_file_regions = items[0]["vrn_file_region"]
out_file = vcfutils.concat_variant_files(vrn_file_regions, out_file, regions,
dd.get_ref_file(items[0]), items[0]["config"])
return {"vrn_file": out_file}
def concat_batch_variantcalls(items):
"""CWL entry point: combine variant calls from regions into single VCF.
"""
items, cwl_extras = split_data_cwl_items(items)
batch_name = _get_batch_name(items)
variantcaller = _get_batch_variantcaller(items)
out_file = os.path.join(dd.get_work_dir(items[0]), variantcaller, "%s.vcf.gz" % (batch_name))
utils.safe_makedir(os.path.dirname(out_file))
if "region" in cwl_extras and "vrn_file_region" in cwl_extras:
regions = cwl_extras["region"]
vrn_file_regions = cwl_extras["vrn_file_region"]
else:
regions = [x["region"] for x in items]
vrn_file_regions = [x["vrn_file_region"] for x in items]
regions = [_region_to_coords(r) for r in regions]
out_file = vcfutils.concat_variant_files(vrn_file_regions, out_file, regions,
dd.get_ref_file(items[0]), items[0]["config"])
return {"vrn_file": out_file}
def concat_batch_variantcalls(items, region_block=True, skip_jointcheck=False):
"""CWL entry point: combine variant calls from regions into single VCF.
"""
items = [utils.to_single_data(x) for x in items]
batch_name = _get_batch_name(items, skip_jointcheck)
variantcaller = _get_batch_variantcaller(items)
# Pre-called input variant files
if not variantcaller and all(d.get("vrn_file") for d in items):
return {"vrn_file": items[0]["vrn_file"]}
out_file = os.path.join(dd.get_work_dir(items[0]), variantcaller, "%s.vcf.gz" % (batch_name))
utils.safe_makedir(os.path.dirname(out_file))
if region_block:
regions = [_region_to_coords(rs[0]) for rs in items[0]["region_block"]]
else:
regions = [_region_to_coords(r) for r in items[0]["region"]]
vrn_file_regions = items[0]["vrn_file_region"]
out_file = vcfutils.concat_variant_files(vrn_file_regions, out_file, regions,
dd.get_ref_file(items[0]), items[0]["config"])
return {"vrn_file": out_file}
def concat_variant_files(*args):
return vcfutils.concat_variant_files(*args)
def concat_variant_files(*args):
return vcfutils.concat_variant_files(*args)
