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

Autor:	Shashkova TI; Artificial Intelligence Research Institute, Moscow, Russia., Umerenkov D; Sber AI Lab, Moscow, Russia., Salnikov M; Artificial Intelligence Research Institute, Moscow, Russia., Strashnov PV; Artificial Intelligence Research Institute, Moscow, Russia., Konstantinova AV; Artificial Intelligence Research Institute, Moscow, Russia., Lebed I; AI Center Block Services, Sber, Moscow, Russia., Shcherbinin DN; Federal Research Centre of Epidemiology and Microbiology named after Honorary Academician N. F. Gamaleya, Ministry of Health, Moscow, Russia., Asatryan MN; Federal Research Centre of Epidemiology and Microbiology named after Honorary Academician N. F. Gamaleya, Ministry of Health, Moscow, Russia., Kardymon OL; Artificial Intelligence Research Institute, Moscow, Russia., Ivanisenko NV; Artificial Intelligence Research Institute, Moscow, Russia.; Laboratory of Computational Proteomics, Institute of Cytology and Genetics Siberian Branch of the Russian Academy of Sciences, Novosibirsk, Russia.
Jazyk:	angličtina
Zdroj:	Frontiers in immunology [Front Immunol] 2022 Sep 15; Vol. 13, pp. 960985. Date of Electronic Publication: 2022 Sep 15 (Print Publication: 2022).
DOI:	10.3389/fimmu.2022.960985
Abstrakt:	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 https://github.com/AIRI-Institute/SEMAi and the web-interface http://sema.airi.net. Competing Interests: Author’s DU and IL were employed by Sber. The remaining authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest. (Copyright © 2022 Shashkova, Umerenkov, Salnikov, Strashnov, Konstantinova, Lebed, Shcherbinin, Asatryan, Kardymon and Ivanisenko.)
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu