Computational Antibody Papers
Filter by tags
epitope prediction
Filter by published year
2026
TitleKey points
2026-10-09
Computational identification of B- and T-cell epitopes: a unified task taxonomy and review of databases, datasets, predictive pipelines, and gaps
- epitope prediction
- Review of B and T cell epitope predictors
- The review unifies AI-driven B- and T-cell epitope identification by establishing a novel 12-task taxonomy mapped across a shared five-stage predictive pipeline, systematically evaluating 155 studies (2015–2026) to address severe methodological fragmentation, database underutilization, and benchmark overfitting in computational immunoinformatics.
- The proposed taxonomy organizes the field into linear and conformational B-cell prediction alongside ten sequential T-cell sub-tasks (T1–T10; spanning upstream HLA typing, antigen processing, MHC class I/II binding, immunogenicity, TCR specificity, and structural modeling to downstream neoantigen, tumor antigen, and vaccine design applications) while providing a multidimensional landscape analysis of 43 dedicated immunology databases and 144 benchmark datasets.
- Methodological synthesis across 272 representation learning encodings and 148 classifiers indicates that deep learning and protein language models (PLMs) such as ESM and BERT have become the dominant paradigm in structural, MHC binding, and TCR specificity tasks, whereas classical machine learning remains heavily over-represented in translational applications like tumor T-cell antigen classification (T9) and multi-epitope vaccine construct design (T10).
- The analysis exposes critical field-wide bottlenecks, including steep prediction accuracy collapse on unseen epitopes/TCRs, an immunogenicity (T5) accuracy ceiling that severely degrades neoantigen prioritization, an absence of uncertainty quantification, and poor practical deployment practices where only 12.5% of audited B/T-cell predictors offer dual code repository and operational web server availability.