PREpiBind: Protein Representation-integrated Epitope--MHC Class II Binding Prediction
- 1Seoul National University
Abstract
Motivation: Accurate peptide-MHC class II (pMHC-II) binding prediction is complicated by MHC polymorphism and context-dependent peptide recognition. Protein representations are usually evaluated in different pipelines, obscuring their contribution to predictive performance. Results: We present PREpiBind, a joint-attention framework comparing ten protein representations under a fixed architecture and identical data splits across qualitative binding, mass spectrometry, and thresholded IC50 datasets. PLMs generally achieved the strongest pooled performance; ESM3 Large reached a ROC-AUC of 0.927 +/- 0.002 on the qualitative dataset. PREpiBind PLM variants exceeded evaluated reference methods on qualitative and mass-spectrometry benchmarks, whereas NetMHCIIpan-4.3 was higher on thresholded IC50 using its binding-affinity head. PLM advantages narrowed in allele-wise and held-out MHC-molecule evaluations, and H2-out rankings depended on aggregation, indicating scenario-dependent representation performance. Availability and implementation: Source code and the training and evaluation datasets are available at https://github.com/daylight-00/PREpiBind and archived at https://doi.org/10.5281/zenodo.22934281; trained model checkpoints are available at https://huggingface.co/daylight-00/prepibind. Implemented in Python and released under the MIT License. Contact: [email protected] Supplementary information: Supplementary data are available online.
Related
- FedEpitope: Parameter-Efficient Federated Protein Language Models for Linear B-Cell Epitope Prediction
- Computational prediction of a multi-epitope Human Metapneumovirus vaccine candidate through integrated reverse vaccinology and pan-genomic approaches
- EpiRank: partner-agnostic surface-patch retrieval for epitope prediction of protein binding interfaces
- Toward a Transferable Representation of Protein Dynamics for Functional Prediction and Mechanistic Discovery
- BCell-Epitope-Prediction: A local, reproducible pipeline for multi-epitope vaccine design: integration and structural validation against a panel of PDB antigen-antibody complexes
BibTeX
@misc{jang2026prepibind,
title = {{PREpiBind: Protein Representation-integrated Epitope--MHC Class II Binding Prediction}},
author = {D. H. Jang and D. Kim and B. Park and U. Hwang and Y. Choi and J. Lee},
howpublished = {bioRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.15.751749},
url = {https://www.biorxiv.org/content/10.64898/2026.09.15.751749v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - PREpiBind: Protein Representation-integrated Epitope--MHC Class II Binding Prediction
AU - D. H. Jang
AU - D. Kim
AU - B. Park
AU - U. Hwang
AU - Y. Choi
AU - J. Lee
PY - 2026
DA - 2026/09/15
PB - bioRxiv
DO - 10.64898/2026.09.15.751749
UR - https://www.biorxiv.org/content/10.64898/2026.09.15.751749v1
AB - Motivation: Accurate peptide-MHC class II (pMHC-II) binding prediction is complicated by MHC polymorphism and context-dependent peptide recognition. Protein representations are usually evaluated in different pipelines, obscuring their contribution to predictive performance. Results: We present PREpiBind, a joint-attention framework comparing ten protein representations under a fixed architecture and identical data splits across qualitative binding, mass spectrometry, and thresholded IC50 datasets. PLMs generally achieved the strongest pooled performance; ESM3 Large reached a ROC-AUC of 0.927 +/- 0.002 on the qualitative dataset. PREpiBind PLM variants exceeded evaluated reference methods on qualitative and mass-spectrometry benchmarks, whereas NetMHCIIpan-4.3 was higher on thresholded IC50 using its binding-affinity head. PLM advantages narrowed in allele-wise and held-out MHC-molecule evaluations, and H2-out rankings depended on aggregation, indicating scenario-dependent representation performance. Availability and implementation: Source code and the training and evaluation datasets are available at https://github.com/daylight-00/PREpiBind and archived at https://doi.org/10.5281/zenodo.22934281; trained model checkpoints are available at https://huggingface.co/daylight-00/prepibind. Implemented in Python and released under the MIT License. Contact: [email protected] Supplementary information: Supplementary data are available online.
ER -