def run_pipeline(patient_id, score_epitopes):
"""Run the pipeline for this patient, and save the output to the DB as a
Run."""
hla_types = HLAType.query.with_entities(HLAType.allele,
HLAType.mhc_class).filter_by(patient_id=patient_id).all()
peptide_length = 31
alleles = [normalize_hla_allele_name(
allele) for allele, mhc_class in hla_types]
vcf_df = get_vcf_df(patient_id)
transcripts_df, vcf_df, variant_report = expand_transcripts(
vcf_df,
patient_id,
min_peptide_length = peptide_length,
max_peptide_length = peptide_length)
scored_epitopes = score_epitopes(transcripts_df, alleles)
imm = ImmunogenicityPredictor(alleles=alleles)
scored_epitopes = imm.predict(scored_epitopes)
# TODO(tavi) Make this expansion more robust. It breaks the IEDB predictor,
# for example.
short_transcripts_df = transcripts_df[['chr', 'pos', 'ref',
'alt', 'TranscriptId']]
scored_epitopes = merge(scored_epitopes, short_transcripts_df,
on='TranscriptId', how='left')
peptides = group_epitopes_dataframe(
scored_epitopes, use_transcript_name = True)
run = Run(patient_id=patient_id, output=dumps(peptides))
db.session.add(run)
scored_epitopes = mhc_binding_prediction(mutated_regions, alleles)
if args.skip_thymic_deletion:
scored_epitopes[THYMIC_DELETION_FIELD_NAME] = False
else:
imm = ImmunogenicityPredictor(alleles = alleles)
scored_epitopes = imm.predict(scored_epitopes)
if PERCENTILE_RANK_FIELD_NAME in scored_epitopes:
scored_epitopes = scored_epitopes.sort([PERCENTILE_RANK_FIELD_NAME])
if args.output_epitopes_file:
scored_epitopes.to_csv(args.output_epitopes_file, index=False)
source_sequences = group_epitopes_dataframe(scored_epitopes)
if args.print_epitopes:
print_epitopes(source_sequences)
if args.print_vaccine_peptides or args.vaccine_peptide_file:
padding = args.vaccine_peptide_padding
if args.vaccine_peptide_logistic_epitope_scoring:
epitope_scorer = logistic_ic50_epitope_scorer
else:
epitope_scorer = simple_ic50_epitope_scorer
vaccine_peptide_records = select_vaccine_peptides(
source_sequences,
epitope_scorer=epitope_scorer,
vaccine_peptide_length=peptide_length,
