AUTHOR=Shashkova Tatiana I. , Umerenkov Dmitriy , Salnikov Mikhail , Strashnov Pavel V. , Konstantinova Alina V. , Lebed Ivan , Shcherbinin Dmitriy N. , Asatryan Marina N. , Kardymon Olga L. , Ivanisenko Nikita V. 

TITLE=SEMA: Antigen B-cell conformational epitope prediction using deep transfer learning

JOURNAL=Frontiers in Immunology

VOLUME=13

YEAR=2022

URL=https://www.frontiersin.org/journals/immunology/articles/10.3389/fimmu.2022.960985

DOI=10.3389/fimmu.2022.960985

ISSN=1664-3224

ABSTRACT=<p>One of the primary tasks in vaccine design and development of immunotherapeutic drugs is to predict conformational B-cell epitopes corresponding to primary antibody binding sites within the antigen tertiary structure. To date, multiple approaches have been developed to address this issue. However, for a wide range of antigens their accuracy is limited. In this paper, we applied the transfer learning approach using pretrained deep learning models to develop a model that predicts conformational B-cell epitopes based on the primary antigen sequence and tertiary structure. A pretrained protein language model, ESM-1v, and an inverse folding model, ESM-IF1, were fine-tuned to quantitatively predict antibody-antigen interaction features and distinguish between epitope and non-epitope residues. The resulting model called SEMA demonstrated the best performance on an independent test set with ROC AUC of 0.76 compared to peer-reviewed tools. We show that SEMA can quantitatively rank the immunodominant regions within the SARS-CoV-2 RBD domain. SEMA is available at <uri xlink:href="https://github.com/AIRI-Institute/SEMAi" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/AIRI-Institute/SEMAi</uri> and the web-interface <uri xlink:href="http://sema.airi.net" xmlns:xlink="http://www.w3.org/1999/xlink">http://sema.airi.net</uri>.</p>