Genesis: A modular protein language modelling approach to immunogenicity prediction
Preprint
Abstract
Neoantigen immunogenicity prediction is a highly challenging problem in the development of personalised medicines. Low reactivity rates in called neoantigens result in a difficult prediction scenario with limited training datasets. Here we describe Genesis, a modular protein language modelling approach to immunogenicity prediction for CD8+ reactive epitopes. Genesis comprises of a pMHC encoding module trained on three pMHC prediction tasks, an optional TCR encoding module and a set of context specific immunogenicity prediction head modules. Compared with state-of-the-art models for each task, Genesis’ encoding module performs comparably or better on pMHC binding affinity, eluted ligand prediction and stability tasks. Genesis outperforms all compared models on pMHC immunogenicity prediction (Area under the receiver operating characteristic curve=0.619, average precision: 0.514), with a 7% increase in average precision compared to the next best model. Genesis shows further improved performance on immunogenicity prediction with the integration of TCR context information. Genesis performance is further analysed for interpretability, which locates areas of weakness found across existing immunogenicity models and highlight possible biases in public datasets.Keywords
This publication has 32 references indexed in Scilit:
- Interpretable deep learning to uncover the molecular binding patterns determining TCR–epitope interaction predictionsImmunoInformatics, 2023
- Adoptive cell transfer immunotherapy for patients with solid epithelial cancersCancer Cell, 2023
- Benchmarking solutions to the T-cell receptor epitope prediction problem: IMMREP22 workshop reportImmunoInformatics, 2023
- Neoantigen-specific CD8 T cell responses in the peripheral blood following PD-L1 blockade might predict therapy outcome in metastatic urothelial carcinomaNature Communications, 2022
- A machine learning model for ranking candidate HLA class I neoantigens based on known neoepitopes from multiple human tumor typesNature Cancer, 2021
- Current challenges for unseen-epitope TCR interaction prediction and a new perspective derived from image classificationBriefings in Bioinformatics, 2020
- Key Parameters of Tumor Epitope Immunogenicity Revealed Through a Consortium Approach Improve Neoantigen PredictionCell, 2020
- UVB-Induced Tumor Heterogeneity Diminishes Immune Response in MelanomaCell, 2019
- MHCflurry: Open-Source Class I MHC Binding Affinity PredictionCell Systems, 2018
- NetCTLpan: pan-specific MHC class I pathway epitope predictionsImmunogenetics, 2010