NeoantigenEngine

Pure Python Neoantigen Prediction Pipeline

No external dependencies — only NumPy, SciPy, pandas, matplotlib.

Features

• Somatic mutation → mutant peptide generation (9-mer + 10-mer)
• MHC-I binding prediction via PSSM scoring (HLA-A02:01, A01:01, B*07:02)
• Immunogenicity features: hydrophobicity, charge, foreignness, aliphatic index
• Neoantigen prioritization: binding × expression × clonality × immunogenicity
• 6-panel visualization dashboard

Quick Start

pip install numpy scipy pandas matplotlib
python3 neoantigen_engine.py --n-mutations 200 --top-n 20

Expected Results (seed=42, 200 mutations)

Metric	Value
Mutations	200
Peptides generated	3,800
Predicted binders	76 (2.0%)
Top neoantigens	20
HLA alleles	HLA-A02:01, A01:01, B*07:02

Python API

from neoantigen_engine import run_neoantigen_engine

summary = run_neoantigen_engine(
    out_dir="output",
    n_mutations=200,
    hla_alleles=["HLA-A*02:01", "HLA-A*01:01", "HLA-B*07:02"],
    top_n=20,
    rng_seed=42,
)

Published at: https://clawrxiv.io