Bio Workflows Neoantigen Pipeline

Somatic VCF (annotated) + Tumor RNA-seq (optional)
        |
        v
[1. HLA Typing] --> arcasHLA / OptiType (if types not provided)
        |
        v
[2. MHC Binding Prediction] --> MHCflurry / NetMHCpan
        |
        v
[3. Neoantigen Calling] --> pVACseq
        |
        v
[4. Immunogenicity Scoring] --> Multi-factor ranking
        |
        v
Ranked Vaccine Candidates (TSV + visualizations)

pip install pvactools mhcflurry vatools

mhcflurry-downloads fetch

conda install -c bioconda ensembl-vep arcas-hla optitype

# From tumor RNA-seq BAM
arcasHLA extract tumor.bam -t 8 -o hla_output/
arcasHLA genotype hla_output/tumor.extracted.1.fq.gz hla_output/tumor.extracted.2.fq.gz \
    -g A,B,C,DRB1,DQB1,DQA1,DPB1,DPA1 -t 8 -o hla_output/   # type the DQA1/DPA1 alpha chains too: NetMHCIIpan needs PAIRED DQ/DP alleles

# Parse results
cat hla_output/tumor.genotype.json

import json

with open('hla_output/tumor.genotype.json') as f:
    hla_data = json.load(f)

hla_alleles = []
for gene, alleles in hla_data.items():
    for allele in alleles:
        # arcasHLA emits 3-field alleles (A*01:01:01); pVACseq/IEDB validate 2-field (HLA-A*01:01)
        hla_alleles.append('HLA-' + ':'.join(allele.split(':')[:2]))

# Format for pVACseq: HLA-A*02:01,HLA-A*24:02,HLA-B*07:02,...
hla_string = ','.join(hla_alleles)
print(f'HLA alleles: {hla_string}')

# Annotate somatic VCF
vep --input_file somatic.vcf \
    --output_file somatic.vep.vcf \
    --format vcf --vcf --symbol --terms SO \
    --plugin Frameshift --plugin Wildtype \
    --offline --cache \
    --pick --fork 4

# Add expression data (optional but recommended)
# Positionals: <vcf> <expression_file> {kallisto,stringtie,cufflinks,custom} {gene,transcript}
vcf-expression-annotator somatic.vep.vcf \
    expression.tsv custom gene \
    -s tumor_sample --id-column gene_id --expression-column tpm \
    -o somatic.vep.expression.vcf

# PHASE proximal variants (the review-sinker). Merge somatic + germline, phase with WhatsHap,
# and pass the result to pVACseq via --phased-proximal-variants-vcf so a second variant in the
# same codon-window (esp. a germline SNP in cis) yields the peptide the tumor ACTUALLY makes.
whatshap phase -o phased.vcf.gz --reference reference.fa somatic_plus_germline.vcf.gz tumor.bam
tabix -p vcf phased.vcf.gz

# Basic run with MHC Class I
pvacseq run \
    somatic.vep.vcf \
    tumor_sample \
    "HLA-A*02:01,HLA-A*24:02,HLA-B*07:02,HLA-B*44:02,HLA-C*07:02,HLA-C*05:01" \
    MHCflurry MHCnuggetsI NetMHCpan \
    pvacseq_output/ \
    -e1 8,9,10,11 \
    --iedb-install-directory /path/to/iedb \
    -t 8

# With expression filtering
pvacseq run \
    somatic.vep.expression.vcf \
    tumor_sample \
    "HLA-A*02:01,HLA-A*24:02,HLA-B*07:02,HLA-B*44:02" \
    MHCflurry NetMHCpan \
    pvacseq_output/ \
    -e1 8,9,10,11 \
    --phased-proximal-variants-vcf phased.vcf.gz \
    --tumor-purity 0.7 \
    --tdna-vaf 0.1 \
    --expn-val 1 \
    -t 8

import pandas as pd
import numpy as np

results = pd.read_csv('pvacseq_output/MHC_Class_I/tumor_sample.filtered.tsv', sep='\t')

# Binding affinity filter (IC50 <500nM considered strong binder)
# IC50 <500nM: strong binder; 500-5000nM: weak binder
strong_binders = results[results['Median MT IC50 Score'] < 500].copy()

# Differential agretopicity index (DAI): WT/MT IC50 ratio (== pVACtools Fold Change), matching the
# WT/MT ratio definition. DAI > 1 = MT binds better than WT (mutation created/improved binding); higher = more tumor-specific.
strong_binders['DAI'] = strong_binders['Median WT IC50 Score'] / strong_binders['Median MT IC50 Score']

# Expression filter (if available)
if 'Gene Expression' in strong_binders.columns:
    # TPM >1 ensures detectable expression
    strong_binders = strong_binders[strong_binders['Gene Expression'] > 1]

# VAF filter: prioritize clonal mutations
# VAF >0.1 ensures mutation present in substantial tumor fraction
strong_binders = strong_binders[strong_binders['Tumor DNA VAF'] > 0.1]

# Multi-factor scoring
def immunogenicity_score(row):
    score = 0
    # Strong binding (IC50 <150nM is very strong)
    if row['Median MT IC50 Score'] < 150:
        score += 3
    elif row['Median MT IC50 Score'] < 500:
        score += 2

    # High DAI (tumor-specificity). DAI is the WT/MT IC50 ratio: >1 = MT binds better than WT.
    if row['DAI'] > 10:
        score += 2
    elif row['DAI'] > 2:
        score += 1

    # Clonal mutation (high VAF)
    if row['Tumor DNA VAF'] > 0.3:
        score += 2
    elif row['Tumor DNA VAF'] > 0.15:
        score += 1

    # Expressed (if available)
    if 'Gene Expression' in row.index and row['Gene Expression'] > 10:
        score += 1

    return score

strong_binders['Immunogenicity Score'] = strong_binders.apply(immunogenicity_score, axis=1)

# Rank by composite score
ranked = strong_binders.sort_values('Immunogenicity Score', ascending=False)

# Top candidates for vaccine
top_candidates = ranked.head(20)
top_candidates.to_csv('top_neoantigen_candidates.tsv', sep='\t', index=False)

print(f'Total strong binders: {len(strong_binders)}')
print(f'Top 20 candidates exported')
print(ranked[['Gene Name', 'MT Epitope Seq', 'HLA Allele', 'Median MT IC50 Score', 'DAI', 'Immunogenicity Score']].head(10))

pvacseq run \
    somatic.vep.vcf \
    tumor_sample \
    "DRB1*01:01,DRB1*07:01,DQA1*05:01-DQB1*02:01,DQA1*03:01-DQB1*03:01" \
    MHCnuggetsII NetMHCIIpan \
    pvacseq_class2_output/ \
    -e2 15 \
    --iedb-install-directory /path/to/iedb \
    -t 8