What question did this study set out to answer?

The aim is to develop a BERT-based model that accurately predicts linear and structural epitopes from protein sequences.

March 2, 202224 citationsOpen Access

EpiBERTope: a sequence-based pre-trained BERT model improves linear and structural epitope prediction by learning long-distance protein interactions effectively

MPMinjun ParkNYU Langone Health SSSeung‐Woo SeoSeoul National University EPEunyoung ParkUniversity of British Columbia

Key Points

The aim is to develop a BERT-based model that accurately predicts linear and structural epitopes from protein sequences.
Developed EpiBERTope, a BERT-based epitope prediction model pre-trained on the Swiss-Prot protein database.
Evaluated the model's performance on linear and structural epitope datasets using AUC as a metric.
Compared EpiBERTope against benchmark models such as random forest and support vector machines.
Achieved an AUC of 0.922 for linear epitopes and 0.667 for structural epitopes.
Outperformed existing classification models including random forest and gradient boosting.
Demonstrated that EpiBERTope effectively captures long-distance interactions within antigen sequences.

Abstract

Abstract Motivation Epitopes are the immunogenic regions of antigen that are recognized by antibodies in a highly specific manner to trigger an immune response. Predicting such regions is extremely difficult yet contains profound implications for complex mechanisms of humoral immunogenicity. Results Here, we present a BERT-based epitope prediction model called EpiBERTope, a pre-trained model on the Swiss-Prot protein database, which can predict both linear and structural epitopes using protein sequences only. The model achieves an AUC of 0.922 and 0.667 for linear and structural epitope datasets respectively, outperforming all benchmark classification models including random forest, gradient boosting, naive Bayesian, and support vector machine models. In conclusion, EpiBERTope is a sequence-based model that captures content-based global interactions of antigen sequences, which will be transformative in epitope discovery with high specificity. Contact minjun.park@standigm.com

KI fragen

Bookmark

View Full Paper