neoantigen

pTuneos: prioritizing Tumor neoantigen from next-generation sequencing data

Multi-Omics Peptide Generator

A neoantigen calling pipeline begins from variants record file (MAF) (Not maintain now)

IRIS: Isoform peptides from RNA splicing for Immunotherapy target Screening

neoantigen depletion checking and detection

PREP: Prioritizing of RNA Editing-based Peptides

Calculate and explore property indices of peptides for cancer immunotherapy study

Neoantigen Discovery pipeline

Measuring peptide–MHC generalization to unseen alleles across both HLA classes — leakage-controlled benchmark + factorized predictor. Open 4.66M / research-use 5.8M measurements over 421 / 507 HLA alleles. Companion paper submitted to PLOS Computational Biology, 2026.

Shared missense neoepitopes across 29 DNA-repair genes in TCGA BRCA, COAD and OV - pipeline, analysis and figures. Accepted in Computational Biology and Chemistry (2026).

HLA-A*02:01 nine-mer peptide binding prediction from sequence, with grouped validation and fully traceable metrics.

Core Question of Focus: For a specific cancer, which antigens would make the best vaccine targets?

How a personalized cancer vaccine is designed, and what the evidence for one actually shows. A reproducible pipeline + an honest re-analysis of the KEYNOTE-942 trial. Educational.

Specificity-first protein binder design: every design is scored against its target and its decoys, and ranked on the margin. Pre-registered thresholds, a measured false-accept rate, and failures reported as results.

Chapter 6 of Machine Learning for Biology. Sequence-only immunogenicity prediction on 1,200 HLA-A*02:01 IEDB binders, cluster-split and pre-registered. Network 0.610 AUPRC, binding-only baseline 0.591, chance 0.485.

Leakage-aware, patient-level, reproducible benchmark resource for public MHC-I neoantigen predictors

Private, on-premise AI workstation that turns a tumour variant file into an explainable, structure-guided shortlist of neoantigen research candidates. Runs fully offline on an HP ZGX Nano (NVIDIA GB10). Validated against 2,555 lab-tested peptides.

Clinical-grade in silico neoantigen discovery, HLA Class I presentation modeling, and personalized cancer vaccine prioritization pipeline.

Ultrafast MHC binding prediction and epitope's mimic search. Immunogenicity scorer. Designing personalised cancer vaccine cassettes