def test_mutant_amino_acids_in_mm10_chr9_82927102_refGT_altTG_pT441H():
# In the Isovar repository this test is weird because the VCF only
# mentions the G>T variant but doesn't include the subsequent nucleotide
# change T>G. To avoid having to think about phasing of variants I changed
# the VCF in vaxrank to contain a GT>TG variant.
arg_parser = make_variant_sequences_arg_parser()
args = arg_parser.parse_args([
"--vcf", data_path("b16.f10/b16.f10.Phip.vcf"),
"--bam", data_path("b16.f10/b16.combined.sorted.bam"),
])
reads_generator = allele_reads_generator_from_args(args)
ranked_list, _ = ranked_vaccine_peptides(
reads_generator=reads_generator,
mhc_predictor=RandomBindingPredictor(["H-2-Kb", "H-2-Db"]),
vaccine_peptide_length=15,
padding_around_mutation=5,
min_alt_rna_reads=1,
min_variant_sequence_coverage=1,
variant_sequence_assembly=True,
max_vaccine_peptides_per_variant=1)
for variant, vaccine_peptides in ranked_list:
vaccine_peptide = vaccine_peptides[0]
mutant_protein_fragment = vaccine_peptide.mutant_protein_fragment
check_mutant_amino_acids(
variant,
mutant_protein_fragment)
def test_keep_top_k_epitopes():
arg_parser = make_variant_sequences_arg_parser()
args = arg_parser.parse_args([
"--vcf", data_path("b16.f10/b16.f10.Phip.vcf"),
"--bam", data_path("b16.f10/b16.combined.sorted.bam"),
])
reads_generator = allele_reads_generator_from_args(args)
keep_k_epitopes = 3
ranked_list, _ = ranked_vaccine_peptides(
reads_generator=reads_generator,
mhc_predictor=RandomBindingPredictor(["H-2-Kb", "H-2-Db"]),
vaccine_peptide_length=15,
padding_around_mutation=5,
min_alt_rna_reads=1,
min_variant_sequence_coverage=1,
variant_sequence_assembly=True,
max_vaccine_peptides_per_variant=1,
num_mutant_epitopes_to_keep=keep_k_epitopes)
for variant, vaccine_peptides in ranked_list:
vaccine_peptide = vaccine_peptides[0]
eq_(keep_k_epitopes, len(vaccine_peptide.mutant_epitope_predictions))
# recompute the expected score, make sure the top-k argument from ranked_vaccine_peptides()
# propagated as expected
mutant_epitope_score = sum(
p.logistic_epitope_score() for p in vaccine_peptide.mutant_epitope_predictions)
assert_almost_equal(mutant_epitope_score, vaccine_peptide.mutant_epitope_score)
def test_mutant_amino_acids_in_mm10_chrX_8125624_refC_altA_pS460I():
# there are two co-occurring variants in the RNAseq data but since
# they don't happen in the same codon then we're considering the Varcode
# annotation to be correct
# TODO: deal with phasing of variants explicitly so that both
# variant positions are considered mutated
arg_parser = make_variant_sequences_arg_parser()
args = arg_parser.parse_args([
"--vcf", data_path("b16.f10/b16.f10.Wdr13.vcf"),
"--bam", data_path("b16.f10/b16.combined.sorted.bam"),
])
reads_generator = allele_reads_generator_from_args(args)
ranked_list, _ = ranked_vaccine_peptides(
reads_generator=reads_generator,
mhc_predictor=RandomBindingPredictor(["H-2-Kb", "H-2-Db"]),
vaccine_peptide_length=15,
padding_around_mutation=5,
max_vaccine_peptides_per_variant=1,
min_alt_rna_reads=1,
min_variant_sequence_coverage=1,
variant_sequence_assembly=True)
for variant, vaccine_peptides in ranked_list:
eq_(
1,
len(vaccine_peptides),
"Expected 1 vaccine peptide for variant '%s' but got %d" % (
variant, len(vaccine_peptides)))
vaccine_peptide = vaccine_peptides[0]
mutant_protein_fragment = vaccine_peptide.mutant_protein_fragment
check_mutant_amino_acids(variant, mutant_protein_fragment)
def test_mutant_amino_acids_in_mm10_chr9_82927102_refGT_altTG_pT441H():
# In the Isovar repository this test is weird because the VCF only
# mentions the G>T variant but doesn't include the subsequent nucleotide
# change T>G. To avoid having to think about phasing of variants I changed
# the VCF in vaxrank to contain a GT>TG variant.
arg_parser = make_variant_sequences_arg_parser()
args = arg_parser.parse_args([
"--vcf",
data_path("b16.f10/b16.f10.Phip.vcf"),
"--bam",
data_path("b16.f10/b16.combined.sorted.bam"),
])
reads_generator = allele_reads_generator_from_args(args)
ranked_list = ranked_vaccine_peptides(reads_generator=reads_generator,
mhc_predictor=RandomBindingPredictor(
["H-2-Kb", "H-2-Db"]),
vaccine_peptide_length=15,
padding_around_mutation=5,
min_alt_rna_reads=1,
min_variant_sequence_coverage=1,
variant_sequence_assembly=True,
max_vaccine_peptides_per_variant=1)
for variant, vaccine_peptides in ranked_list:
vaccine_peptide = vaccine_peptides[0]
mutant_protein_fragment = vaccine_peptide.mutant_protein_fragment
check_mutant_amino_acids(variant, mutant_protein_fragment)
def test_mutant_amino_acids_in_mm10_chrX_8125624_refC_altA_pS460I():
# there are two co-occurring variants in the RNAseq data but since
# they don't happen in the same codon then we're considering the Varcode
# annotation to be correct
# TODO: deal with phasing of variants explicitly so that both
# variant positions are considered mutated
arg_parser = make_variant_sequences_arg_parser()
args = arg_parser.parse_args([
"--vcf",
data_path("b16.f10/b16.f10.Wdr13.vcf"),
"--bam",
data_path("b16.f10/b16.combined.sorted.bam"),
])
reads_generator = allele_reads_generator_from_args(args)
ranked_list = ranked_vaccine_peptides(reads_generator=reads_generator,
mhc_predictor=RandomBindingPredictor(
["H-2-Kb", "H-2-Db"]),
vaccine_peptide_length=15,
padding_around_mutation=5,
max_vaccine_peptides_per_variant=1,
min_alt_rna_reads=1,
min_variant_sequence_coverage=1,
variant_sequence_assembly=True)
for variant, vaccine_peptides in ranked_list:
eq_(
1, len(vaccine_peptides),
"Expected 1 vaccine peptide for variant '%s' but got %d" %
(variant, len(vaccine_peptides)))
vaccine_peptide = vaccine_peptides[0]
mutant_protein_fragment = vaccine_peptide.mutant_protein_fragment
check_mutant_amino_acids(variant, mutant_protein_fragment)
def test_keep_top_k_epitopes():
arg_parser = make_variant_sequences_arg_parser()
args = arg_parser.parse_args([
"--vcf",
data_path("b16.f10/b16.f10.Phip.vcf"),
"--bam",
data_path("b16.f10/b16.combined.sorted.bam"),
])
reads_generator = allele_reads_generator_from_args(args)
keep_k_epitopes = 3
ranked_list, _ = ranked_vaccine_peptides(
reads_generator=reads_generator,
mhc_predictor=RandomBindingPredictor(["H-2-Kb", "H-2-Db"]),
vaccine_peptide_length=15,
padding_around_mutation=5,
min_alt_rna_reads=1,
min_variant_sequence_coverage=1,
variant_sequence_assembly=True,
max_vaccine_peptides_per_variant=1,
num_mutant_epitopes_to_keep=keep_k_epitopes)
for variant, vaccine_peptides in ranked_list:
vaccine_peptide = vaccine_peptides[0]
eq_(keep_k_epitopes, len(vaccine_peptide.mutant_epitope_predictions))
# recompute the expected score, make sure the top-k argument from ranked_vaccine_peptides()
# propagated as expected
mutant_epitope_score = sum(
p.logistic_epitope_score()
for p in vaccine_peptide.mutant_epitope_predictions)
assert_almost_equal(mutant_epitope_score,
vaccine_peptide.mutant_epitope_score)
Prints number of reads supporting ref, alt, and other alleles at variant loci.
"""
from __future__ import division, absolute_import
import logging
import logging.config
import pkg_resources
from isovar.cli.rna_reads import (make_rna_reads_arg_parser,
allele_reads_generator_from_args)
from isovar.allele_counts import allele_counts_dataframe
logging.config.fileConfig(
pkg_resources.resource_filename('isovar.cli', 'logging.conf'))
logger = logging.getLogger(__name__)
parser = make_rna_reads_arg_parser()
parser.add_argument("--output",
default="isovar-allele-counts-result.csv",
help="Name of CSV file which contains read sequences")
if __name__ == "__main__":
args = parser.parse_args()
logger.info(args)
variants_and_allele_reads_generator = allele_reads_generator_from_args(
args)
allele_counts_df = allele_counts_dataframe(
variants_and_allele_reads_generator)
logger.info(allele_counts_df)
allele_counts_df.to_csv(args.output)
def ranked_variant_list_with_metadata(args):
"""
Computes all the data needed for report generation.
Parameters
----------
args : Namespace
Parsed user args from this run
Returns a dictionary containing 3 items:
- ranked variant/vaccine peptide list
- a dictionary of command-line arguments used to generate it
- patient info object
"""
if hasattr(args, 'input_json_file'):
with open(args.input_json_file) as f:
data = serializable.from_json(f.read())
# the JSON data from the previous run will have the older args saved, which may need to
# be overridden with args from this run (which all be output related)
data['args'].update(vars(args))
# if we need to truncate the variant list based on max_mutations_in_report, do that here
if len(data['variants']) > args.max_mutations_in_report:
data['variants'] = data['variants'][:args.
max_mutations_in_report]
return data
# get various things from user args
mhc_alleles = mhc_alleles_from_args(args)
logger.info("MHC alleles: %s", mhc_alleles)
variants = variant_collection_from_args(args)
logger.info("Variants: %s", variants)
# generator that for each variant gathers all RNA reads, both those
# supporting the variant and reference alleles
reads_generator = allele_reads_generator_from_args(args)
mhc_predictor = mhc_binding_predictor_from_args(args)
ranked_list, variants_count_dict = ranked_vaccine_peptides(
reads_generator=reads_generator,
mhc_predictor=mhc_predictor,
vaccine_peptide_length=args.vaccine_peptide_length,
padding_around_mutation=args.padding_around_mutation,
max_vaccine_peptides_per_variant=args.
max_vaccine_peptides_per_mutation,
min_alt_rna_reads=args.min_alt_rna_reads,
min_variant_sequence_coverage=args.min_variant_sequence_coverage,
min_epitope_score=args.min_epitope_score,
num_mutant_epitopes_to_keep=args.num_epitopes_per_peptide,
variant_sequence_assembly=args.variant_sequence_assembly)
ranked_list_for_report = ranked_list[:args.max_mutations_in_report]
patient_info = PatientInfo(
patient_id=args.output_patient_id,
vcf_paths=variants.sources,
bam_path=args.bam,
mhc_alleles=mhc_alleles,
num_somatic_variants=len(variants),
num_coding_effect_variants=variants_count_dict[
'num_coding_effect_variants'],
num_variants_with_rna_support=variants_count_dict[
'num_variants_with_rna_support'],
num_variants_with_vaccine_peptides=variants_count_dict[
'num_variants_with_vaccine_peptides'])
# return variants, patient info, and command-line args
data = {
'variants': ranked_list_for_report,
'patient_info': patient_info,
'args': vars(args),
}
logger.info('About to save args: %s', data['args'])
# save JSON data if necessary. as of time of writing, vaxrank takes ~25 min to run,
# most of which is core logic. the formatting is super fast, and it can
# be useful to save the data to be able to iterate just on the formatting
if args.output_json_file:
with open(args.output_json_file, 'w') as f:
f.write(serializable.to_json(data))
logger.info('Wrote JSON report data to %s', args.output_json_file)
return data
def ranked_variant_list_with_metadata(args):
"""
Computes all the data needed for report generation.
Parameters
----------
args : Namespace
Parsed user args from this run
Returns a dictionary containing 3 items:
- ranked variant/vaccine peptide list
- a dictionary of command-line arguments used to generate it
- patient info object
"""
if hasattr(args, 'input_json_file'):
with open(args.input_json_file) as f:
data = serializable.from_json(f.read())
# the JSON data from the previous run will have the older args saved, which may need to
# be overridden with args from this run (which all be output related)
data['args'].update(vars(args))
# if we need to truncate the variant list based on max_mutations_in_report, do that here
if len(data['variants']) > args.max_mutations_in_report:
data['variants'] = data['variants'][:args.max_mutations_in_report]
return data
# get various things from user args
mhc_alleles = mhc_alleles_from_args(args)
logger.info("MHC alleles: %s", mhc_alleles)
variants = variant_collection_from_args(args)
logger.info("Variants: %s", variants)
# generator that for each variant gathers all RNA reads, both those
# supporting the variant and reference alleles
reads_generator = allele_reads_generator_from_args(args)
mhc_predictor = mhc_binding_predictor_from_args(args)
ranked_list, variants_count_dict = ranked_vaccine_peptides(
reads_generator=reads_generator,
mhc_predictor=mhc_predictor,
vaccine_peptide_length=args.vaccine_peptide_length,
padding_around_mutation=args.padding_around_mutation,
max_vaccine_peptides_per_variant=args.max_vaccine_peptides_per_mutation,
min_alt_rna_reads=args.min_alt_rna_reads,
min_variant_sequence_coverage=args.min_variant_sequence_coverage,
min_epitope_score=args.min_epitope_score,
num_mutant_epitopes_to_keep=args.num_epitopes_per_peptide,
variant_sequence_assembly=args.variant_sequence_assembly)
ranked_list_for_report = ranked_list[:args.max_mutations_in_report]
patient_info = PatientInfo(
patient_id=args.output_patient_id,
vcf_paths=variants.sources,
bam_path=args.bam,
mhc_alleles=mhc_alleles,
num_somatic_variants=len(variants),
num_coding_effect_variants=variants_count_dict['num_coding_effect_variants'],
num_variants_with_rna_support=variants_count_dict['num_variants_with_rna_support'],
num_variants_with_vaccine_peptides=variants_count_dict['num_variants_with_vaccine_peptides']
)
# return variants, patient info, and command-line args
data = {
'variants': ranked_list_for_report,
'patient_info': patient_info,
'args': vars(args),
}
logger.info('About to save args: %s', data['args'])
# save JSON data if necessary. as of time of writing, vaxrank takes ~25 min to run,
# most of which is core logic. the formatting is super fast, and it can
# be useful to save the data to be able to iterate just on the formatting
if args.output_json_file:
with open(args.output_json_file, 'w') as f:
f.write(serializable.to_json(data))
logger.info('Wrote JSON report data to %s', args.output_json_file)
return data
"""
from __future__ import division, absolute_import
import logging
import logging.config
import pkg_resources
from isovar.cli.rna_reads import (
make_rna_reads_arg_parser,
allele_reads_generator_from_args
)
from isovar.allele_counts import allele_counts_dataframe
logging.config.fileConfig(pkg_resources.resource_filename('isovar.cli', 'logging.conf'))
logger = logging.getLogger(__name__)
parser = make_rna_reads_arg_parser()
parser.add_argument(
"--output",
default="isovar-allele-counts-result.csv",
help="Name of CSV file which contains read sequences")
if __name__ == "__main__":
args = parser.parse_args()
logger.info(args)
variants_and_allele_reads_generator = allele_reads_generator_from_args(args)
allele_counts_df = allele_counts_dataframe(variants_and_allele_reads_generator)
logger.info(allele_counts_df)
allele_counts_df.to_csv(args.output)
