def _load_single_sample_variants(self, sample_idx, file_format_funcs, variant_type, merge_type):
sample_id = self.sample_ids[sample_idx]
normal_bam_id = None if self.normal_bam_ids is None else self.normal_bam_ids[sample_idx]
tumor_bam_id = None if self.tumor_bam_ids is None else self.tumor_bam_ids[sample_idx]
cached_file_name = "%s-%s-variants.pkl" % (variant_type, merge_type)
cached = self.load_from_cache(self.cache_names["variant"], sample_id, cached_file_name)
if cached is not None:
return cached
combined_variants = []
for file_format_func in file_format_funcs:
file_name = file_format_func(
sample_id, normal_bam_id, tumor_bam_id)
variants = varcode.load_vcf_fast(path.join(self.data_dir, file_name))
combined_variants.append(set(variants.elements))
if len(combined_variants) == 1:
# There is nothing to merge
merged_variants = VariantCollection(combined_variants[0])
else:
assert merge_type in ["union", "intersection"], "Unknown merge type: %s" % merge_type
if merge_type == "union":
merged_variants = VariantCollection(set.union(*combined_variants))
elif merge_type == "intersection":
merged_variants = VariantCollection(set.intersection(*combined_variants))
self.save_to_cache(merged_variants, self.cache_names["variant"], sample_id, cached_file_name)
return merged_variants
def do_test(kwargs):
vcf_pandas = load_vcf_fast(**kwargs)
vcf_pyvcf = load_vcf(**kwargs)
eq_(vcf_pandas, vcf_pyvcf)
eq_(len(vcf_pandas), len(vcf_pyvcf))
eq_(vcf_pandas.elements, vcf_pyvcf.elements)
eq_(vcf_pandas.metadata, vcf_pyvcf.metadata)
assert len(vcf_pandas) > 1
assert len(vcf_pyvcf) > 1
def do_test(kwargs):
vcf_pandas = load_vcf_fast(**kwargs)
vcf_pyvcf = load_vcf(**kwargs)
eq_(vcf_pandas, vcf_pyvcf)
eq_(len(vcf_pandas), len(vcf_pyvcf))
eq_(vcf_pandas.elements, vcf_pyvcf.elements)
eq_(vcf_pandas.metadata, vcf_pyvcf.metadata)
assert len(vcf_pandas) > 1
assert len(vcf_pyvcf) > 1
def loader(filename):
collection = varcode.load_vcf_fast(
filename,
genome=genome,
max_variants=max_variants,
only_passing=only_passing,
allow_extended_nucleotides=True)
return variants_to_dataframe(
collection,
collection.metadata,
metadata_column_prefix=metadata_column_prefix)
def loader(filename):
collection = varcode.load_vcf_fast(
filename,
genome=genome,
max_variants=max_variants,
only_passing=only_passing,
allow_extended_nucleotides=True)
return variants_to_dataframe(
collection,
collection.metadata,
metadata_column_prefix=metadata_column_prefix)
def run():
args = parser.parse_args()
extra_args = {}
if not args.info_field:
extra_args["include_info"] = False
start = time.time()
if args.pyvcf:
result = varcode.load_vcf(args.path, allow_extended_nucleotides=True)
else:
result = varcode.load_vcf_fast(args.path,
allow_extended_nucleotides=True,
**extra_args)
print("Loaded %d variants in %0.3f sec. " %
(len(result), time.time() - start))
print(result.to_string(limit=5))
def __init__(self,
ranked_variants_with_vaccine_peptides,
patient_info,
final_review,
reviewers,
args_for_report,
input_json_file,
cosmic_vcf_filename=None):
"""
Construct a TemplateDataCreator object, from the output of the vaxrank pipeline.
"""
self.ranked_variants_with_vaccine_peptides = ranked_variants_with_vaccine_peptides
self.patient_info = patient_info
# filter output-related command-line args: we want to display everything else
args_to_display_in_report = {
k: v
for k, v in args_for_report.items() if not k.startswith("output")
}
self.template_data = {
'args': sorted(args_to_display_in_report.items()),
'reviewers': reviewers.split(',') if reviewers else [],
'final_review': final_review,
'input_json_file': input_json_file,
# these report sections are optional
'include_manufacturability': args_for_report['manufacturability'],
'include_wt_epitopes': args_for_report['wt_epitopes'],
}
# map from peptide objects to their COSMIC IDs if they exist
if cosmic_vcf_filename:
logger.info('Loading COSMIC data...')
self.cosmic_variant_collection = load_vcf_fast(
cosmic_vcf_filename,
allow_extended_nucleotides=True,
include_info=False)
logger.info('COSMIC data loaded.')
else:
self.cosmic_variant_collection = None
def run():
args = parser.parse_args()
extra_args = {}
if not args.info_field:
extra_args["include_info"] = False
start = time.time()
if args.pyvcf:
result = varcode.load_vcf(
args.path,
allow_extended_nucleotides=True)
else:
result = varcode.load_vcf_fast(
args.path,
allow_extended_nucleotides=True,
**extra_args)
print("Loaded %d variants in %0.3f sec. " % (
len(result), time.time() - start))
print(result.to_string(limit=5))
def __init__(
self,
ranked_variants_with_vaccine_peptides,
patient_info,
final_review,
reviewers,
args_for_report,
input_json_file,
cosmic_vcf_filename=None):
"""
Construct a TemplateDataCreator object, from the output of the vaxrank pipeline.
"""
self.ranked_variants_with_vaccine_peptides = ranked_variants_with_vaccine_peptides
self.patient_info = patient_info
# filter output-related command-line args: we want to display everything else
args_to_display_in_report = {
k: v for k, v in args_for_report.items() if not k.startswith("output")
}
self.template_data = {
'args': sorted(args_to_display_in_report.items()),
'reviewers': reviewers.split(',') if reviewers else [],
'final_review': final_review,
'input_json_file': input_json_file,
# these report sections are optional
'include_manufacturability': args_for_report['manufacturability'],
'include_wt_epitopes': args_for_report['wt_epitopes'],
}
# map from peptide objects to their COSMIC IDs if they exist
if cosmic_vcf_filename:
logger.info('Loading COSMIC data...')
self.cosmic_variant_collection = load_vcf_fast(
cosmic_vcf_filename, allow_extended_nucleotides=True, include_info=False)
logger.info('COSMIC data loaded.')
else:
self.cosmic_variant_collection = None
def generate_vcfs(id_to_mutation_count, file_format, template_name):
"""
Generate cropped VCFs from a template, for each sample.
Parameters
----------
id_to_mutation_count : dict
sample ID to number of mutations we want to generate for that sample
Returns
-------
str
Path to the generated VCF directory
"""
for sample_id in id_to_mutation_count.keys():
template_path = data_path(template_name)
vcf_reader = vcf.Reader(filename=template_path)
file_path = generated_data_path(
path.join("vcfs", file_format % sample_id))
file_dir = path.dirname(file_path)
if not path.exists(file_dir):
makedirs(file_dir)
with open(file_path, "w") as f:
vcf_writer = vcf.Writer(f, vcf_reader)
i = 0
num_records_in_template = len(load_vcf_fast(template_path))
num_records_to_generate = id_to_mutation_count[sample_id]
assert num_records_in_template >= num_records_to_generate, (
"Cannot generate more records than exist in the template: %d is less than %d" % (
num_records_in_template, num_records_to_generate))
for record in vcf_reader:
if i < id_to_mutation_count[sample_id]:
vcf_writer.write_record(record)
i += 1
else:
break
return path.dirname(f.name)
def generate_vcfs(id_to_mutation_count, file_format_func, template_name):
"""
Generate cropped VCFs from a template, for each sample.
Parameters
----------
id_to_mutation_count : dict
sample ID to number of mutations we want to generate for that sample
Returns
-------
str
Path to the generated VCF directory
"""
for sample_id in id_to_mutation_count.keys():
template_path = data_path(template_name)
vcf_reader = vcf.Reader(filename=template_path)
file_path = generated_data_path(
path.join("vcfs", file_format_func(sample_id, None, None)))
file_dir = path.dirname(file_path)
if not path.exists(file_dir):
makedirs(file_dir)
with open(file_path, "w") as f:
vcf_writer = vcf.Writer(f, vcf_reader)
i = 0
num_records_in_template = len(load_vcf_fast(template_path))
num_records_to_generate = id_to_mutation_count[sample_id]
assert num_records_in_template >= num_records_to_generate, (
"Cannot generate more records than exist in the template: %d is less than %d"
% (num_records_in_template, num_records_to_generate))
for record in vcf_reader:
if i < id_to_mutation_count[sample_id]:
vcf_writer.write_record(record)
i += 1
else:
break
return path.dirname(f.name)
def _load_single_sample_variants(self, sample_idx, file_format_funcs,
variant_type, merge_type):
sample_id = self.sample_ids[sample_idx]
normal_bam_id = None if self.normal_bam_ids is None else self.normal_bam_ids[
sample_idx]
tumor_bam_id = None if self.tumor_bam_ids is None else self.tumor_bam_ids[
sample_idx]
cached_file_name = "%s-%s-variants.pkl" % (variant_type, merge_type)
cached = self.load_from_cache(self.cache_names["variant"], sample_id,
cached_file_name)
if cached is not None:
return cached
combined_variants = []
for file_format_func in file_format_funcs:
file_name = file_format_func(sample_id, normal_bam_id,
tumor_bam_id)
variants = varcode.load_vcf_fast(
path.join(self.data_dir, file_name))
combined_variants.append(set(variants.elements))
if len(combined_variants) == 1:
# There is nothing to merge
merged_variants = VariantCollection(combined_variants[0])
else:
assert merge_type in ["union", "intersection"
], "Unknown merge type: %s" % merge_type
if merge_type == "union":
merged_variants = VariantCollection(
set.union(*combined_variants))
elif merge_type == "intersection":
merged_variants = VariantCollection(
set.intersection(*combined_variants))
self.save_to_cache(merged_variants, self.cache_names["variant"],
sample_id, cached_file_name)
return merged_variants
def test_load_vcf_mouse_with_explicit_urls():
variants = load_vcf(MOUSE_VCF, genome=explicit_url_genome)
eq_(len(variants), 217)
variants = load_vcf_fast(MOUSE_VCF, genome=explicit_url_genome)
eq_(len(variants), 217)
def test_load_vcf_mouse_with_ensembl_release():
variants = load_vcf(MOUSE_VCF, genome=ensembl_mouse_genome)
eq_(len(variants), 217)
variants = load_vcf_fast(MOUSE_VCF, genome=ensembl_mouse_genome)
eq_(len(variants), 217)
def test_load_vcf_mouse_with_inferred_genome():
variants = load_vcf(MOUSE_VCF)
eq_(len(variants), 217)
variants = load_vcf_fast(MOUSE_VCF)
eq_(len(variants), 217)
def test_load_vcf_mouse_with_ensembl_release():
variants = load_vcf(MOUSE_VCF, genome=ensembl_mouse_genome)
eq_(len(variants), 217)
variants = load_vcf_fast(MOUSE_VCF, genome=ensembl_mouse_genome)
eq_(len(variants), 217)
def test_load_vcf_mouse_with_explicit_urls():
variants = load_vcf(MOUSE_VCF, genome=explicit_url_genome)
eq_(len(variants), 217)
variants = load_vcf_fast(MOUSE_VCF, genome=explicit_url_genome)
eq_(len(variants), 217)
def test_load_vcf_mouse_with_inferred_genome():
variants = load_vcf(MOUSE_VCF)
eq_(len(variants), 217)
variants = load_vcf_fast(MOUSE_VCF)
eq_(len(variants), 217)
