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 summarize_sv(items):
"""CWL target: summarize structural variants for multiple samples.
XXX Need to support non-VCF output as tabix indexed output
"""
items = [
utils.to_single_data(x)
for x in vcvalidate.summarize_grading(items, "svvalidate")
]
out = {
"sv": {
"calls": [],
"prioritize": {
"tsv": [],
"raw": []
}
},
"svvalidate": vcvalidate.combine_validations(items, "svvalidate")
}
added = set([])
# Standard callers
for data in items:
if data.get("sv"):
names = dd.get_batches(data)
if not names:
names = [dd.get_sample_name(data)]
batch_name = names[0]
cur_name = "%s-%s" % (batch_name, data["sv"]["variantcaller"])
if data["sv"].get("vrn_file"):
ext = utils.splitext_plus(data["sv"]["vrn_file"])[-1]
if cur_name not in added and ext.startswith(".vcf"):
added.add(cur_name)
out_file = os.path.join(
utils.safe_makedir(
os.path.join(dd.get_work_dir(data), "sv",
"calls")), "%s%s" % (cur_name, ext))
utils.copy_plus(data["sv"]["vrn_file"], out_file)
out_file = vcfutils.bgzip_and_index(
out_file, data["config"])
out["sv"]["calls"].append(out_file)
# prioritization
for pdata in _group_by_sample(items):
prioritysv = [
x for x in prioritize.run([utils.deepish_copy(pdata)])[0].get(
"sv", []) if x["variantcaller"] == "sv-prioritize"
]
if prioritysv:
out["sv"]["prioritize"]["tsv"].append(prioritysv[0]["vrn_file"])
out["sv"]["prioritize"]["raw"].extend(
prioritysv[0]["raw_files"].values())
return [out]
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 summarize_sv(items):
"""CWL target: summarize structural variants for multiple samples.
XXX Need to support non-VCF output as tabix indexed output
"""
items = [
utils.to_single_data(x)
for x in vcvalidate.summarize_grading(items, "svvalidate")
]
out = {
"sv": {
"calls": []
},
"svvalidate": vcvalidate.combine_validations(items, "svvalidate")
}
added = set([])
for data in items:
if data.get("sv"):
names = dd.get_batches(data)
if not names:
names = [dd.get_sample_name(data)]
batch_name = names[0]
cur_name = "%s-%s" % (batch_name, data["sv"]["variantcaller"])
if data["sv"].get("vrn_file"):
ext = utils.splitext_plus(data["sv"]["vrn_file"])[-1]
if cur_name not in added and ext.startswith(".vcf"):
added.add(cur_name)
out_file = os.path.join(
utils.safe_makedir(
os.path.join(dd.get_work_dir(data), "sv",
"calls")), "%s%s" % (cur_name, ext))
utils.copy_plus(data["sv"]["vrn_file"], out_file)
out_file = vcfutils.bgzip_and_index(
out_file, data["config"])
out["sv"]["calls"].append(out_file)
return [out]
def summarize_sv(items):
"""CWL target: summarize structural variants for multiple samples.
XXX Need to support non-VCF output as tabix indexed output
"""
items = [utils.to_single_data(x) for x in vcvalidate.summarize_grading(items, "svvalidate")]
out = {"sv": {"calls": [],
"supplemental": [],
"prioritize": {"tsv": [],
"raw": []}},
"svvalidate": vcvalidate.combine_validations(items, "svvalidate")}
added = set([])
# Standard callers
for data in items:
if data.get("sv"):
if data["sv"].get("vrn_file"):
ext = utils.splitext_plus(data["sv"]["vrn_file"])[-1]
cur_name = _useful_basename(data)
if cur_name not in added and ext.startswith(".vcf"):
added.add(cur_name)
out_file = os.path.join(utils.safe_makedir(os.path.join(dd.get_work_dir(data),
"sv", "calls")),
"%s%s" % (cur_name, ext))
utils.copy_plus(data["sv"]["vrn_file"], out_file)
out_file = vcfutils.bgzip_and_index(out_file, data["config"])
out["sv"]["calls"].append(out_file)
if data["sv"].get("supplemental"):
out["sv"]["supplemental"].extend([x for x in data["sv"]["supplemental"] if x])
# prioritization
for pdata in _group_by_sample(items):
prioritysv = [x for x in prioritize.run([utils.deepish_copy(pdata)])[0].get("sv", [])
if x["variantcaller"] == "sv-prioritize"]
if prioritysv:
out["sv"]["prioritize"]["tsv"].append(prioritysv[0]["vrn_file"])
out["sv"]["prioritize"]["raw"].extend(prioritysv[0]["raw_files"].values())
return [out]
