def split_somatic(items):
"""Split somatic batches, adding a germline target.
Enables separate germline calling of samples using shared alignments.
"""
somatic_groups, somatic, non_somatic = vcfutils.somatic_batches(items)
# extract germline samples to run from normals in tumor/normal pairs
germline_added = set([])
germline = []
for somatic_group in somatic_groups:
paired = vcfutils.get_paired(somatic_group)
if paired and paired.normal_data:
cur = utils.deepish_copy(paired.normal_data)
vc = dd.get_variantcaller(cur)
if isinstance(vc, dict) and "germline" in vc:
cur["description"] = "%s-germline" % cur["description"]
if cur["description"] not in germline_added:
germline_added.add(cur["description"])
cur["rgnames"]["sample"] = cur["description"]
del cur["metadata"]["batch"]
cur["metadata"]["phenotype"] = "germline"
cur = remove_align_qc_tools(cur)
cur["config"]["algorithm"]["variantcaller"] = vc[
"germline"]
germline.append(cur)
# Fix variantcalling specification for only somatic targets
somatic_out = []
for data in somatic:
vc = dd.get_variantcaller(data)
if isinstance(vc, dict) and "somatic" in vc:
data["config"]["algorithm"]["variantcaller"] = vc["somatic"]
somatic_out.append(data)
return non_somatic + somatic_out + germline
def split_somatic(items):
"""Split somatic batches, adding a germline target.
Enables separate germline calling of samples using shared alignments.
"""
items = [_clean_flat_variantcaller(x) for x in items]
somatic_groups, somatic, non_somatic = vcfutils.somatic_batches(items)
# extract germline samples to run from normals in tumor/normal pairs
germline_added = set([])
germline = []
for somatic_group in somatic_groups:
paired = vcfutils.get_paired(somatic_group)
if paired and paired.normal_data:
cur = utils.deepish_copy(paired.normal_data)
vc = dd.get_variantcaller(cur)
if isinstance(vc, dict) and "germline" in vc:
if cur["description"] not in germline_added:
germline_added.add(cur["description"])
cur["rgnames"]["sample"] = cur["description"]
cur["metadata"]["batch"] = "%s-germline" % cur["description"]
cur["metadata"]["phenotype"] = "germline"
cur = remove_align_qc_tools(cur)
cur["config"]["algorithm"]["variantcaller"] = vc["germline"]
germline.append(cur)
# Fix variantcalling specification for only somatic targets
somatic_out = []
for data in somatic:
vc = dd.get_variantcaller(data)
if isinstance(vc, dict) and "somatic" in vc:
data["config"]["algorithm"]["variantcaller"] = vc["somatic"]
somatic_out.append(data)
return non_somatic + somatic_out + germline
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 summarize_vc(items):
"""CWL target: summarize variant calls and validation for multiple samples.
"""
items = [utils.to_single_data(x) for x in utils.flatten(items)]
items = [_normalize_vc_input(x) for x in items]
items = validate.summarize_grading(items)
items = [utils.to_single_data(x) for x in items]
out = {
"validate": validate.combine_validations(items),
"variants": {
"calls": [],
"gvcf": [],
"samples": []
}
}
added = set([])
variants_by_sample = collections.defaultdict(list)
sample_order = []
for data in items:
batch_samples = data.get("batch_samples", [dd.get_sample_name(data)])
for s in batch_samples:
if s not in sample_order:
sample_order.append(s)
if data.get("vrn_file"):
# Only get batches if we're actually doing variantcalling in bcbio
# otherwise we'll be using the original files
names = dd.get_batches(data) if dd.get_variantcaller(
data) else None
if not names:
names = [dd.get_sample_name(data)]
batch_name = names[0]
if data.get("vrn_file_joint") is not None:
to_add = [("vrn_file", "gvcf", dd.get_sample_name(data)),
("vrn_file_joint", "calls", batch_name)]
else:
to_add = [("vrn_file", "calls", batch_name)]
for vrn_key, out_key, name in to_add:
cur_name = "%s-%s" % (name, dd.get_variantcaller(data))
out_file = os.path.join(
utils.safe_makedir(
os.path.join(dd.get_work_dir(data), "variants",
out_key)), "%s.vcf.gz" % cur_name)
for s in batch_samples:
variants_by_sample[s].append(out_file)
if cur_name not in added:
added.add(cur_name)
# Ideally could symlink here but doesn't appear to work with
# Docker container runs on Toil where PATHs don't get remapped
utils.copy_plus(os.path.realpath(data[vrn_key]), out_file)
vcfutils.bgzip_and_index(out_file, data["config"])
out["variants"][out_key].append(out_file)
for sample in sample_order:
out["variants"]["samples"].append(variants_by_sample[sample])
return [out]
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 batch(samples):
"""CWL: batch together per sample, joint and germline calls for ensemble combination.
Sets up groups of same sample/batch variant calls for ensemble calling, as
long as we have more than one caller per group.
"""
samples = [utils.to_single_data(x) for x in samples]
sample_order = [dd.get_sample_name(x) for x in samples]
batch_groups = collections.defaultdict(list)
for data in samples:
batch_samples = tuple(data.get("batch_samples", [dd.get_sample_name(data)]))
batch_groups[(batch_samples, dd.get_phenotype(data))].append(data)
out = []
for (batch_samples, phenotype), gsamples in batch_groups.items():
if len(gsamples) > 1:
batches = set([])
for d in gsamples:
batches |= set(dd.get_batches(d))
cur = copy.deepcopy(gsamples[0])
cur.update({"batch_id": sorted(list(batches))[0] if batches else "_".join(batch_samples),
"batch_samples": batch_samples,
"variants": {"variantcallers": [dd.get_variantcaller(d) for d in gsamples],
"calls": [d.get("vrn_file") for d in gsamples]}})
out.append(cur)
def by_original_order(d):
return min([sample_order.index(s) for s in d["batch_samples"] if s in sample_order])
return sorted(out, key=by_original_order)
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["hla"] = any([dd.get_hlacaller(d) for d in samples])
return checkpoints
def _check_for_problem_somatic_batches(items, config):
"""Identify problem batch setups for somatic calling.
We do not support multiple tumors in a single batch and VarDict(Java) does not
handle pooled calling, only tumor/normal.
"""
to_check = []
for data in items:
data = copy.deepcopy(data)
data["config"] = config_utils.update_w_custom(config, data)
to_check.append(data)
data_by_batches = collections.defaultdict(list)
for data in to_check:
batches = dd.get_batches(data)
if batches:
for batch in batches:
data_by_batches[batch].append(data)
for batch, items in data_by_batches.items():
if vcfutils.get_paired(items):
vcfutils.check_paired_problems(items)
elif len(items) > 1:
vcs = list(set(tz.concat([dd.get_variantcaller(data) or [] for data in items])))
if any(x.lower().startswith("vardict") for x in vcs):
raise ValueError("VarDict does not support pooled non-tumor/normal calling, in batch %s: %s"
% (batch, [dd.get_sample_name(data) for data in items]))
elif any(x.lower() == "mutect" for x in vcs):
raise ValueError("Mutect requires a 'phenotype: tumor' sample for calling, in batch %s: %s"
% (batch, [dd.get_sample_name(data) for data in items]))
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 _needs_java(data):
"""Check if a caller needs external java for MuTect.
No longer check for older GATK (<3.6) versions because of time cost; this
won't be relevant to most runs so we skip the sanity check.
"""
vc = dd.get_variantcaller(data)
if isinstance(vc, dict):
out = {}
for k, v in vc.items():
if not isinstance(v, (list, tuple)):
v = [v]
out[k] = v
vc = out
elif not isinstance(vc, (list, tuple)):
vc = [vc]
if "mutect" in vc or ("somatic" in vc and "mutect" in vc["somatic"]):
return True
if "gatk" in vc or "gatk-haplotype" in vc or (
"germline" in vc and "gatk-haplotype" in vc["germline"]):
pass
# runner = broad.runner_from_config(data["config"])
# version = runner.get_gatk_version()
# if LooseVersion(version) < LooseVersion("3.6"):
# return True
return False
def _needs_java(data):
"""Check if a caller needs external java for MuTect.
No longer check for older GATK (<3.6) versions because of time cost; this
won't be relevant to most runs so we skip the sanity check.
"""
vc = dd.get_variantcaller(data)
if isinstance(vc, dict):
out = {}
for k, v in vc.items():
if not isinstance(v, (list, tuple)):
v = [v]
out[k] = v
vc = out
elif not isinstance(vc, (list, tuple)):
vc = [vc]
if "mutect" in vc or ("somatic" in vc and "mutect" in vc["somatic"]):
return True
if "gatk" in vc or "gatk-haplotype" in vc or ("germline" in vc and "gatk-haplotype" in vc["germline"]):
pass
# runner = broad.runner_from_config(data["config"])
# version = runner.get_gatk_version()
# if LooseVersion(version) < LooseVersion("3.6"):
# return True
return False
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]))
if variantcaller and ("gatk-haplotype" in variantcaller):
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:
samples = run_parallel("run_rnaseq_ann_filter", samples)
if variantcaller and ("gatk-haplotype" in variantcaller):
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 _rnaseq_checkpoints(samples):
"""Check sample configuration to identify required steps in analysis.
"""
checkpoints = {}
checkpoints["rnaseq"] = True
checkpoints["vc"] = any([dd.get_variantcaller(d) for d in samples])
return checkpoints
def summarize_vc(items):
"""CWL target: summarize variant calls and validation for multiple samples.
"""
items = [
utils.to_single_data(x) for x in validate.summarize_grading(items)
]
out = {"validate": items[0]["validate"], "variants": {"calls": []}}
added = set([])
for data in items:
if data.get("vrn_file"):
names = dd.get_batches(data)
if not names:
names = [dd.get_sample_name(data)]
cur_name = "%s-%s" % (names[0], dd.get_variantcaller(data))
if cur_name not in added:
out_file = os.path.join(
utils.safe_makedir(
os.path.join(dd.get_work_dir(data), "variants",
"calls")), "%s.vcf.gz" % cur_name)
added.add(cur_name)
# Ideally could symlink here but doesn't appear to work with
# Docker container runs on Toil where PATHs don't get remapped
utils.copy_plus(os.path.realpath(data["vrn_file"]), out_file)
vcfutils.bgzip_and_index(out_file, data["config"])
out["variants"]["calls"].append(out_file)
return [out]
def _check_for_problem_somatic_batches(items, config):
"""Identify problem batch setups for somatic calling.
We do not support multiple tumors in a single batch and VarDict(Java) does not
handle pooled calling, only tumor/normal.
"""
to_check = []
for data in items:
data = copy.deepcopy(data)
data["config"] = config_utils.update_w_custom(config, data)
to_check.append(data)
data_by_batches = collections.defaultdict(list)
for data in to_check:
batches = dd.get_batches(data)
if batches:
for batch in batches:
data_by_batches[batch].append(data)
for batch, items in data_by_batches.items():
if vcfutils.get_paired(items):
vcfutils.check_paired_problems(items)
elif len(items) > 1:
vcs = list(set(tz.concat([dd.get_variantcaller(data) or [] for data in items])))
if any(x.lower().startswith("vardict") for x in vcs):
raise ValueError("VarDict does not support pooled non-tumor/normal calling, in batch %s: %s"
% (batch, [dd.get_sample_name(data) for data in items]))
elif any(x.lower() == "mutect" for x in vcs):
raise ValueError("Mutect requires a 'phenotype: tumor' sample for calling, in batch %s: %s"
% (batch, [dd.get_sample_name(data) for data in items]))
def run_rnaseq_variant_calling(data):
"""
run RNA-seq variant calling, variation file is stored in `vrn_file`
in the datadict
"""
variantcaller = dd.get_variantcaller(data)
if isinstance(variantcaller, list) and len(variantcaller) > 1:
logger.error("Only one variantcaller can be run for RNA-seq at "
"this time. Post an issue here "
"(https://github.com/bcbio/bcbio-nextgen/issues) "
"if this is something you need to do.")
sys.exit(1)
if variantcaller:
if "gatk-haplotype" in variantcaller:
data = variation.rnaseq_gatk_variant_calling(data)
if vardict.get_vardict_command(data):
data = variation.rnaseq_vardict_variant_calling(data)
if dd.get_vrn_file(data):
ann_file = vcfanno.run_vcfanno(dd.get_vrn_file(data), ["rnaedit"],
data)
if ann_file:
data = dd.set_vrn_file(data, ann_file)
ann_file = population.run_vcfanno(dd.get_vrn_file(data), data,
population.do_db_build([data]))
if ann_file:
data = dd.set_vrn_file(data, ann_file)
return [[data]]
def summarize_vc(items):
"""CWL target: summarize variant calls and validation for multiple samples.
"""
items = [utils.to_single_data(x) for x in validate.summarize_grading(items)]
out = {"validate": items[0]["validate"],
"variants": {"calls": [], "gvcf": []}}
added = set([])
for data in items:
if data.get("vrn_file"):
names = dd.get_batches(data)
if not names:
names = [dd.get_sample_name(data)]
batch_name = names[0]
if data.get("vrn_file_joint") is not None:
to_add = [("vrn_file", "gvcf", dd.get_sample_name(data)),
("vrn_file_joint", "calls", batch_name)]
else:
to_add = [("vrn_file", "calls", batch_name)]
for vrn_key, out_key, name in to_add:
cur_name = "%s-%s" % (name, dd.get_variantcaller(data))
if cur_name not in added:
out_file = os.path.join(utils.safe_makedir(os.path.join(dd.get_work_dir(data),
"variants", out_key)),
"%s.vcf.gz" % cur_name)
added.add(cur_name)
# Ideally could symlink here but doesn't appear to work with
# Docker container runs on Toil where PATHs don't get remapped
utils.copy_plus(os.path.realpath(data[vrn_key]), out_file)
vcfutils.bgzip_and_index(out_file, data["config"])
out["variants"][out_key].append(out_file)
return [out]
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 summarize_vc(items):
"""CWL target: summarize variant calls and validation for multiple samples.
"""
items = [utils.to_single_data(x) for x in utils.flatten(items)]
items = [_normalize_vc_input(x) for x in items]
items = validate.summarize_grading(items)
items = [utils.to_single_data(x) for x in items]
out = {"validate": validate.combine_validations(items),
"variants": {"calls": [], "gvcf": [], "samples": []}}
added = set([])
variants_by_sample = collections.defaultdict(list)
sample_order = []
for data in items:
batch_samples = data.get("batch_samples", [dd.get_sample_name(data)])
for s in batch_samples:
if s not in sample_order:
sample_order.append(s)
if data.get("vrn_file"):
# Only get batches if we're actually doing variantcalling in bcbio
# otherwise we'll be using the original files
names = dd.get_batches(data) if dd.get_variantcaller(data) else None
if not names:
names = [dd.get_sample_name(data)]
batch_name = names[0]
if data.get("vrn_file_joint") is not None:
to_add = [("vrn_file", "gvcf", dd.get_sample_name(data)),
("vrn_file_joint", "calls", batch_name)]
else:
to_add = [("vrn_file", "calls", batch_name)]
for vrn_key, out_key, name in to_add:
cur_name = "%s-%s" % (name, dd.get_variantcaller(data))
out_file = os.path.join(utils.safe_makedir(os.path.join(dd.get_work_dir(data),
"variants", out_key)),
"%s.vcf.gz" % cur_name)
for s in batch_samples:
variants_by_sample[s].append(out_file)
if cur_name not in added:
added.add(cur_name)
# Ideally could symlink here but doesn't appear to work with
# Docker container runs on Toil where PATHs don't get remapped
utils.copy_plus(os.path.realpath(data[vrn_key]), out_file)
vcfutils.bgzip_and_index(out_file, data["config"])
out["variants"][out_key].append(out_file)
for sample in sample_order:
out["variants"]["samples"].append(variants_by_sample[sample])
return [out]
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 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]))
if variantcaller and ("gatk-haplotype" in variantcaller):
samples = joint.square_off(samples, run_parallel)
samples = run_parallel("run_rnaseq_ann_filter", samples)
return samples
def _get_jvm_opts(data, out_file):
"""Retrieve JVM options when running the Java version of VarDict.
"""
if dd.get_variantcaller(data).endswith("-java"):
resources = config_utils.get_resources("vardict", data["config"])
jvm_opts = resources.get("jvm_opts", ["-Xms750m", "-Xmx4g"])
jvm_opts += broad.get_default_jvm_opts(os.path.dirname(out_file))
return "export VAR_DICT_OPTS='%s' && " % " ".join(jvm_opts)
else:
return ""
def _default_conf_files(data, retriever):
conf_files = []
if dd.get_variantcaller(data) or dd.get_vrn_file(data):
if annotate_gemini(data, retriever):
conf_files.append("gemini")
if _annotate_somatic(data, retriever):
conf_files.append("somatic")
if dd.get_analysis(data).lower().find("rna-seq") >= 0:
conf_files.append("rnaedit")
return conf_files
def _get_jvm_opts(data, out_file):
"""Retrieve JVM options when running the Java version of VarDict.
"""
if not dd.get_variantcaller(data).endswith("-perl"):
resources = config_utils.get_resources("vardict", data["config"])
jvm_opts = resources.get("jvm_opts", ["-Xms750m", "-Xmx4g"])
jvm_opts += broad.get_default_jvm_opts(os.path.dirname(out_file))
return "export VAR_DICT_OPTS='%s' && " % " ".join(jvm_opts)
else:
return ""
def _default_conf_files(data, retriever):
conf_files = []
if dd.get_variantcaller(data) or dd.get_vrn_file(data):
if annotate_gemini(data, retriever):
conf_files.append("gemini")
if _annotate_somatic(data, retriever):
conf_files.append("somatic")
if dd.get_analysis(data).lower().find("rna-seq") >= 0:
conf_files.append("rnaedit")
return conf_files
def get_somatic_variantcallers(items):
"""Retrieve all variant callers for somatic calling, handling somatic/germline.
"""
out = []
for data in items:
vcs = dd.get_variantcaller(data)
if isinstance(vcs, dict) and "somatic" in vcs:
vcs = vcs["somatic"]
if not isinstance(vcs, (list, tuple)):
vcs = [vcs]
out += vcs
return set(vcs)
def get_somatic_variantcallers(items):
"""Retrieve all variant callers for somatic calling, handling somatic/germline.
"""
out = []
for data in items:
vcs = dd.get_variantcaller(data)
if isinstance(vcs, dict) and "somatic" in vcs:
vcs = vcs["somatic"]
if not isinstance(vcs, (list, tuple)):
vcs = [vcs]
out += vcs
return set(vcs)
def get_type(data):
"""Retrieve the type of effects calculation to do.
"""
if data["analysis"].lower().startswith("var") or dd.get_variantcaller(data):
etype = tz.get_in(("config", "algorithm", "effects"), data, "snpeff")
if isinstance(etype, (list, tuple)):
if len(etype) == 1:
return etype[0]
else:
raise ValueError("Unexpected variant effect type for %s: %s" % (dd.get_sample_name(data), etype))
else:
return etype
def run_rnaseq_ann_filter(data):
"""Run RNA-seq annotation and filtering.
"""
data = to_single_data(data)
if dd.get_vrn_file(data):
ann_file = population.run_vcfanno(dd.get_vrn_file(data), data)
if ann_file:
data = dd.set_vrn_file(data, ann_file)
variantcaller = dd.get_variantcaller(data)
if variantcaller and ("gatk-haplotype" in variantcaller):
filter_file = variation.gatk_filter_rnaseq(dd.get_vrn_file(data), data)
data = dd.set_vrn_file(data, filter_file)
return [[data]]
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]))
if variantcaller and ("gatk-haplotype" in variantcaller):
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
samples = run_parallel("run_rnaseq_ann_filter", samples)
return samples
def _run_vardict_caller(align_bams, items, ref_file, assoc_files,
region=None, out_file=None):
"""Detect SNPs and indels with VarDict.
"""
config = items[0]["config"]
if out_file is None:
out_file = "%s-variants.vcf.gz" % os.path.splitext(align_bams[0])[0]
if not utils.file_exists(out_file):
with file_transaction(items[0], out_file) as tx_out_file:
for align_bam in align_bams:
bam.index(align_bam, config)
num_bams = len(align_bams)
sample_vcf_names = [] # for individual sample names, given batch calling may be required
for bamfile, item in itertools.izip(align_bams, items):
# prepare commands
vardict = dd.get_variantcaller(items[0])
strandbias = "teststrandbias.R"
var2vcf = "var2vcf_valid.pl"
opts = " ".join(_vardict_options_from_config(items, config, out_file, region))
vcfstreamsort = config_utils.get_program("vcfstreamsort", config)
compress_cmd = "| bgzip -c" if out_file.endswith("gz") else ""
freq = float(utils.get_in(config, ("algorithm", "min_allele_fraction"), 10)) / 100.0
coverage_interval = utils.get_in(config, ("algorithm", "coverage_interval"), "exome")
# for deep targeted panels, require 50 worth of coverage
var2vcf_opts = " -v 50 " if highdepth.get_median_coverage(items[0]) > 5000 else ""
fix_ambig = vcfutils.fix_ambiguous_cl()
sample = item["name"][1]
jvm_opts = _get_jvm_opts(items[0], tx_out_file)
cmd = ("{jvm_opts}{vardict} -G {ref_file} -f {freq} "
"-N {sample} -b {bamfile} {opts} "
"| {strandbias}"
"| {var2vcf} -N {sample} -E -f {freq} {var2vcf_opts} "
"| {fix_ambig} | {vcfstreamsort} {compress_cmd}")
if num_bams > 1:
temp_file_prefix = out_file.replace(".gz", "").replace(".vcf", "") + item["name"][1]
tmp_out = temp_file_prefix + ".temp.vcf"
tmp_out += ".gz" if out_file.endswith("gz") else ""
sample_vcf_names.append(tmp_out)
with file_transaction(item, tmp_out) as tx_tmp_file:
cmd += " > {tx_tmp_file}"
do.run(cmd.format(**locals()), "Genotyping with VarDict: Inference", {})
else:
cmd += " > {tx_out_file}"
do.run(cmd.format(**locals()), "Genotyping with VarDict: Inference", {})
if num_bams > 1:
# N.B. merge_variant_files wants region in 1-based end-inclusive
# coordinates. Thus use bamprep.region_to_gatk
vcfutils.merge_variant_files(orig_files=sample_vcf_names,
out_file=tx_out_file, ref_file=ref_file,
config=config, region=bamprep.region_to_gatk(region))
return out_file
def run_rnaseq_variant_calling(data):
variantcaller = dd.get_variantcaller(data)
if isinstance(variantcaller, list) and len(variantcaller) > 1:
logger.error("Only one variantcaller can be run for RNA-seq at "
"this time. Post an issue here "
"(https://github.com/chapmanb/bcbio-nextgen/issues) "
"if this is something you need to do.")
sys.exit(1)
if variantcaller and "gatk" in variantcaller:
data = variation.rnaseq_gatk_variant_calling(data)
if vardict.get_vardict_command(data):
data = variation.rnaseq_vardict_variant_calling(data)
return [[data]]
def get_type(data):
"""Retrieve the type of effects calculation to do.
"""
if data["analysis"].lower().startswith("var") or dd.get_variantcaller(
data):
etype = tz.get_in(("config", "algorithm", "effects"), data, "snpeff")
if isinstance(etype, (list, tuple)):
if len(etype) == 1:
return etype[0]
else:
raise ValueError("Unexpected variant effect type for %s: %s" %
(dd.get_sample_name(data), etype))
else:
return etype
def _needs_java(data):
"""Check if a caller needs external java for MuTect or older GATK 3.6.
"""
vc = dd.get_variantcaller(data)
if not isinstance(vc, (list, tuple)):
vc = [vc]
if "mutect" in vc:
return True
if "gatk" in vc or "gatk-haplotype" in vc:
runner = broad.runner_from_config(data["config"])
version = runner.get_gatk_version()
if LooseVersion(version) < LooseVersion("3.6"):
return True
return False
def _needs_java(data):
"""Check if a caller needs external java for MuTect or older GATK 3.6.
"""
vc = dd.get_variantcaller(data)
if not isinstance(vc, (list, tuple)):
vc = [vc]
if "mutect" in vc:
return True
if "gatk" in vc or "gatk-haplotype" in vc:
runner = broad.runner_from_config(data["config"])
version = runner.get_gatk_version()
if LooseVersion(version) < LooseVersion("3.6"):
return True
return False
def run_rnaseq_joint_genotyping(*samples):
data = samples[0][0]
variantcaller = dd.get_variantcaller(data)
ref_file = dd.get_ref_file(data)
out_file = os.path.join(dd.get_work_dir(data, "."), "variation", "combined.vcf")
if variantcaller and "gatk" in variantcaller:
vrn_files = [dd.get_vrn_file(d) for d in dd.sample_data_iterator(samples)]
out_file = variation.gatk_joint_calling(data, vrn_files, ref_file, out_file)
updated_samples = []
for data in dd.sample_data_iterator(samples):
data = dd.set_square_vcf(data, out_file)
updated_samples.append([data])
return updated_samples
return samples
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_rnaseq_variant_calling(data):
variantcaller = dd.get_variantcaller(data)
if isinstance(variantcaller, list) and len(variantcaller) > 1:
logger.error("Only one variantcaller can be run for RNA-seq at "
"this time. Post an issue here "
"(https://github.com/chapmanb/bcbio-nextgen/issues) "
"if this is something you need to do.")
sys.exit(1)
if variantcaller and "gatk" in variantcaller:
data = variation.rnaseq_gatk_variant_calling(data)
if vardict.get_vardict_command(data):
data = variation.rnaseq_vardict_variant_calling(data)
return [[data]]
def run_rnaseq_joint_genotyping(*samples):
data = samples[0][0]
variantcaller = dd.get_variantcaller(data)
ref_file = dd.get_ref_file(data)
out_file = os.path.join(dd.get_work_dir(data, "."), "variation", "combined.vcf")
if variantcaller and "gatk" in variantcaller:
vrn_files = [dd.get_vrn_file(d) for d in dd.sample_data_iterator(samples)]
out_file = variation.gatk_joint_calling(data, vrn_files, ref_file, out_file)
updated_samples = []
for data in dd.sample_data_iterator(samples):
data = dd.set_square_vcf(data, out_file)
updated_samples.append([data])
return updated_samples
return samples
def batch_for_jointvc(items):
batch_groups = collections.defaultdict(list)
for data in [utils.to_single_data(x) for x in items]:
vc = dd.get_variantcaller(data)
if genotype.is_joint(data):
batches = dd.get_batches(data) or dd.get_sample_name(data)
if not isinstance(batches, (list, tuple)):
batches = [batches]
else:
batches = [dd.get_sample_name(data)]
for b in batches:
data = utils.deepish_copy(data)
data["vrn_file_gvcf"] = data["vrn_file"]
batch_groups[(b, vc)].append(data)
return batch_groups.values()
def gatk_rnaseq_calling(data):
"""Use GATK to perform gVCF variant calling on RNA-seq data
"""
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_file = os.path.join(utils.safe_makedir(os.path.join("variation", "rnaseq", "gatk-haplotype")),
"%s-gatk-haplotype.vcf.gz" % dd.get_sample_name(data))
out_file = gatk.haplotype_caller([dd.get_split_bam(data)], [data], dd.get_ref_file(data), {},
out_file=out_file)
return dd.set_vrn_file(data, out_file)
def batch_for_jointvc(items):
batch_groups = collections.defaultdict(list)
for data in [utils.to_single_data(x) for x in items]:
vc = dd.get_variantcaller(data)
if genotype.is_joint(data):
batches = dd.get_batches(data) or dd.get_sample_name(data)
if not isinstance(batches, (list, tuple)):
batches = [batches]
else:
batches = [dd.get_sample_name(data)]
for b in batches:
data = utils.deepish_copy(data)
data["vrn_file_gvcf"] = data["vrn_file"]
batch_groups[(b, vc)].append(data)
return list(batch_groups.values())
def _run_vardict_paired(align_bams, items, ref_file, assoc_files,
region=None, out_file=None):
"""Detect variants with Vardict.
This is used for paired tumor / normal samples.
"""
config = items[0]["config"]
if out_file is None:
out_file = "%s-paired-variants.vcf.gz" % os.path.splitext(align_bams[0])[0]
if not utils.file_exists(out_file):
with file_transaction(items[0], out_file) as tx_out_file:
paired = vcfutils.get_paired_bams(align_bams, items)
if not paired.normal_bam:
ann_file = _run_vardict_caller(align_bams, items, ref_file,
assoc_files, region, out_file)
return ann_file
vcffilter = config_utils.get_program("vcffilter", config)
vardict = dd.get_variantcaller(items[0])
vcfstreamsort = config_utils.get_program("vcfstreamsort", config)
strandbias = "testsomatic.R"
var2vcf = "var2vcf_paired.pl"
compress_cmd = "| bgzip -c" if out_file.endswith("gz") else ""
freq = float(utils.get_in(config, ("algorithm", "min_allele_fraction"), 10)) / 100.0
# merge bed file regions as amplicon VarDict is only supported in single sample mode
opts = " ".join(_vardict_options_from_config(items, config, out_file, region, do_merge=True))
coverage_interval = utils.get_in(config, ("algorithm", "coverage_interval"), "exome")
# for deep targeted panels, require 50 worth of coverage
var2vcf_opts = " -v 50 " if highdepth.get_median_coverage(items[0]) > 5000 else ""
fix_ambig = vcfutils.fix_ambiguous_cl()
if any("vardict_somatic_filter" in tz.get_in(("config", "algorithm", "tools_off"), data, [])
for data in items):
somatic_filter = ""
else:
somatic_filter = ("| %s -x 'bcbio.variation.freebayes.call_somatic(x)'" %
os.path.join(os.path.dirname(sys.executable), "py"))
jvm_opts = _get_jvm_opts(items[0], tx_out_file)
cmd = ("{jvm_opts}{vardict} -G {ref_file} -f {freq} "
"-N {paired.tumor_name} -b \"{paired.tumor_bam}|{paired.normal_bam}\" {opts} "
"| {strandbias} "
"| {var2vcf} -N \"{paired.tumor_name}|{paired.normal_name}\" -f {freq} {var2vcf_opts} "
"| bcftools filter -m '+' -s 'REJECT' -e 'STATUS !~ \".*Somatic\"' 2> /dev/null "
"| sed 's/\\\\.*Somatic\\\\/Somatic/' "
"| sed 's/REJECT,Description=\".*\">/REJECT,Description=\"Not Somatic via VarDict\">/' "
"{somatic_filter} | {fix_ambig} | {vcfstreamsort} {compress_cmd} > {tx_out_file}")
bam.index(paired.tumor_bam, config)
bam.index(paired.normal_bam, config)
do.run(cmd.format(**locals()), "Genotyping with VarDict: Inference", {})
return out_file
def get_active_vcinfo(data):
"""Use first caller if ensemble is not active
"""
callers = dd.get_variantcaller(data)
if not callers:
return None
if isinstance(callers, basestring):
callers = [callers]
active_vs = []
if "variants" in data:
for v in data["variants"]:
if v.get("variantcaller") == "ensemble":
return v
if v.get("vrn_file"):
active_vs.append(v)
if len(active_vs) > 0:
return active_vs[0]
def get_vardict_command(data):
"""
convert variantcaller specification to proper vardict command, handling
string or list specification
"""
vcaller = dd.get_variantcaller(data)
if isinstance(vcaller, list):
vardict = [x for x in vcaller if "vardict" in x]
if not vardict:
return None
vardict = vardict[0]
elif not vcaller:
return None
else:
vardict = vcaller
vardict = "vardict-java" if not vardict.endswith("-perl") else "vardict"
return vardict
def _callable_from_gvcf(data, vrn_file, out_dir):
"""Retrieve callable regions based on ref call regions in gVCF.
Uses https://github.com/lijiayong/gvcf_regions
"""
methods = {"freebayes": "freebayes", "platypus": "platypus",
"gatk-haplotype": "gatk"}
gvcf_type = methods.get(dd.get_variantcaller(data))
if gvcf_type:
out_file = os.path.join(out_dir, "%s-gcvf-coverage.bed" %
utils.splitext_plus(os.path.basename(vrn_file))[0])
if not utils.file_uptodate(out_file, vrn_file):
with file_transaction(data, out_file) as tx_out_file:
cmd = ("gvcf_regions.py --gvcf_type {gvcf_type} {vrn_file} "
"| bedtools merge > {tx_out_file}")
do.run(cmd.format(**locals()), "Convert gVCF to BED file of callable regions")
return out_file
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 _clean_flat_variantcaller(data):
"""Convert flattened dictionary from CWL representation into dictionary.
CWL flattens somatic/germline tags into a set of strings, which we
reconstitute as a dictionary.
"""
vc = dd.get_variantcaller(data)
if isinstance(vc, (list, tuple)) and all([x.count(":") == 1 for x in vc]):
out = {}
for v in vc:
k, v = v.split(":")
if k in out:
out[k].append(v)
else:
out[k] = [v]
data = dd.set_variantcaller(data, out)
return data
def _callable_from_gvcf(data, vrn_file, out_dir):
"""Retrieve callable regions based on ref call regions in gVCF.
Uses https://github.com/lijiayong/gvcf_regions
"""
methods = {"freebayes": "freebayes", "platypus": "platypus",
"gatk-haplotype": "gatk"}
gvcf_type = methods.get(dd.get_variantcaller(data))
if gvcf_type:
out_file = os.path.join(out_dir, "%s-gcvf-coverage.bed" %
utils.splitext_plus(os.path.basename(vrn_file))[0])
if not utils.file_uptodate(out_file, vrn_file):
with file_transaction(data, out_file) as tx_out_file:
cmd = ("gvcf_regions.py --gvcf_type {gvcf_type} {vrn_file} "
"| bedtools merge > {tx_out_file}")
do.run(cmd.format(**locals()), "Convert gVCF to BED file of callable regions")
return out_file
def get_vardict_command(data):
"""
convert variantcaller specification to proper vardict command, handling
string or list specification
"""
vcaller = dd.get_variantcaller(data)
if isinstance(vcaller, list):
vardict = [x for x in vcaller if "vardict" in x]
if not vardict:
return None
vardict = vardict[0]
elif not vcaller:
return None
else:
vardict = vcaller
vardict = "vardict-java" if not vardict.endswith("-perl") else "vardict"
return vardict
def _get_active_vcinfo(data):
"""Use first caller if ensemble is not active
"""
callers = dd.get_variantcaller(data)
if not callers:
return None
if isinstance(callers, basestring):
callers = [callers]
active_vs = []
if "variants" in data:
for v in data["variants"]:
if v.get("variantcaller") == "ensemble":
return v
if v.get("vrn_file"):
active_vs.append(v)
if len(active_vs) > 0:
return active_vs[0]
def _clean_flat_variantcaller(data):
"""Convert flattened dictionary from CWL representation into dictionary.
CWL flattens somatic/germline tags into a set of strings, which we
reconstitute as a dictionary.
"""
vc = dd.get_variantcaller(data)
if isinstance(vc, (list, tuple)) and all([x.count(":") == 1 for x in vc]):
out = {}
for v in vc:
k, v = v.split(":")
if k in out:
out[k].append(v)
else:
out[k] = [v]
data = dd.set_variantcaller(data, out)
return data
def run_rnaseq_joint_genotyping(*samples):
data = samples[0][0]
variantcaller = dd.get_variantcaller(data)
if not variantcaller:
return samples
if "gatk" not in variantcaller:
return samples
ref_file = dd.get_ref_file(data)
if variantcaller and "gatk" in variantcaller:
vrn_files = [dd.get_vrn_file(d) for d in dd.sample_data_iterator(samples)]
out_file = variation.gatk_joint_calling(data, vrn_files, ref_file)
vrn_file = vcfanno.run_vcfanno(out_file, ["rnaedit"], data)
updated_samples = []
for data in dd.sample_data_iterator(samples):
data = dd.set_square_vcf(data, vrn_file)
updated_samples.append([data])
return updated_samples
return samples
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 parallel_prep_region(samples, run_parallel):
"""Perform full pre-variant calling BAM prep work on regions.
"""
file_key = "work_bam"
split_fn = _split_by_regions("bamprep", "-prep.bam", file_key)
# identify samples that do not need preparation -- no recalibration or realignment
extras = []
torun = []
for data in [x[0] for x in samples]:
if data.get("work_bam"):
data["align_bam"] = data["work_bam"]
if (not dd.get_recalibrate(data) and not dd.get_realign(data) and not dd.get_variantcaller(data)):
extras.append([data])
elif not data.get(file_key):
extras.append([data])
else:
torun.append([data])
return extras + parallel_split_combine(torun, split_fn, run_parallel,
"piped_bamprep", _add_combine_info, file_key, ["config"])
def _get_variant_callers(data):
"""Use first caller if ensemble is not active"""
callers = dd.get_variantcaller(data)
if not callers:
return None
if isinstance(callers, basestring):
callers = [callers]
active_callers = [c.get("variantcaller") for c in data.get("variants", [{}])]
active_vcf = [c.get("vrn_file") for c in data.get("variants", [{}])]
active_germline = [c.get("germline") for c in data.get("variants", [{}])]
vcf = dict(zip(active_callers, active_vcf))
germline = dict(zip(active_callers, active_germline))
if "ensemble" in active_callers:
vcf_fn = vcf["ensemble"]
else:
vcf_fn = vcf[callers[0]]
if not vcf_fn:
vcf_fn = germline[callers[0]]
return vcf_fn
def run_rnaseq_variant_calling(data):
"""
run RNA-seq variant calling, variation file is stored in `vrn_file`
in the datadict
"""
variantcaller = dd.get_variantcaller(data)
if isinstance(variantcaller, list) and len(variantcaller) > 1:
logger.error("Only one variantcaller can be run for RNA-seq at "
"this time. Post an issue here "
"(https://github.com/bcbio/bcbio-nextgen/issues) "
"if this is something you need to do.")
sys.exit(1)
if variantcaller:
if "gatk-haplotype" in variantcaller:
data = variation.rnaseq_gatk_variant_calling(data)
if vardict.get_vardict_command(data):
data = variation.rnaseq_vardict_variant_calling(data)
vrn_file = dd.get_vrn_file(data)
return [[data]]
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)
variantcaller = dd.get_variantcaller(data)
if variantcaller and ("gatk-haplotype" in variantcaller):
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]]