Assessing data size requirements for training generalizable sequence-based TCR specificity models via pan-allelic MHC-I non-self ligandome evaluation
Preprint
- 8 August 2025
- preprint
- Published by Springer Nature in Research Square
Abstract
Quickly identifying which T cell receptors (TCRs) specifically bind patient-unique neoepitopes is a critical challenge for personalized TCR cell therapy in oncology. Due to enormous diversity of both TCR and neoepitope repertoires, a machine learning predictor of TCR-pMHC specificity for personalized therapy must generalize to TCRs and epitopes not seen in the training data. For the first time, we estimate the necessary size of such training data. We first show that published models fail to generalize beyond a single-residue dissimilarity to the epitope training set distribution. We then impute the possible mutated ligandome across the 34 most prevalent human MHC alleles and represent it as a graph based on our established dissimilarity cutoff. By finding the dominating set of this graph, we estimate that between one and 100 million epitopes are required to train a generalizable sequence-based TCR specificity prediction model - 1000 times the size of current public data.Keywords
All Related Versions
This publication has 34 references indexed in Scilit:
- Lessons learned from the IMMREP23 TCR-epitope prediction challengeImmunoInformatics, 2024
- Structure of a fully assembled tumor-specific T cell receptor ligated by pMHCCell, 2022
- Fast track to personalized TCR T cell therapiesCancer Cell, 2022
- MHCflurry 2.0: Improved Pan-Allele Prediction of MHC Class I-Presented Peptides by Incorporating Antigen ProcessingCell Systems, 2020
- Six-locus high resolution HLA haplotype frequencies derived from mixed-resolution DNA typing for the entire US donor registryHuman Immunology, 2013
- Multi-sorting algorithm for finding pairs of similar short substrings from large-scale string dataKnowledge and Information Systems, 2009
- How T cells 'see' antigenNature Immunology, 2005
- Random ForestsMachine Learning, 2001
- Structural analysis of MHC class I molecules with bound peptide antigensSeminars in Immunology, 1993
- T-cell antigen receptor genes and T-cell recognitionNature, 1988