TY - JOUR

T1 - DiscoTope-3.0

T2 - improved B-cell epitope prediction using inverse folding latent representations

AU - Høie, Magnus Haraldson

AU - Gade, Frederik Steensgaard

AU - Johansen, Julie Maria

AU - Würtzen, Charlotte

AU - Winther, Ole

AU - Nielsen, Morten

AU - Marcatili, Paolo

N1 - Publisher Copyright: Copyright © 2024 Høie, Gade, Johansen, Würtzen, Winther, Nielsen and Marcatili.

PY - 2024

Y1 - 2024

N2 - Accurate computational identification of B-cell epitopes is crucial for the development of vaccines, therapies, and diagnostic tools. However, current structure-based prediction methods face limitations due to the dependency on experimentally solved structures. Here, we introduce DiscoTope-3.0, a markedly improved B-cell epitope prediction tool that innovatively employs inverse folding structure representations and a positive-unlabelled learning strategy, and is adapted for both solved and predicted structures. Our tool demonstrates a considerable improvement in performance over existing methods, accurately predicting linear and conformational epitopes across multiple independent datasets. Most notably, DiscoTope-3.0 maintains high predictive performance across solved, relaxed and predicted structures, alleviating the need for experimental structures and extending the general applicability of accurate B-cell epitope prediction by 3 orders of magnitude. DiscoTope-3.0 is made widely accessible on two web servers, processing over 100 structures per submission, and as a downloadable package. In addition, the servers interface with RCSB and AlphaFoldDB, facilitating large-scale prediction across over 200 million cataloged proteins. DiscoTope-3.0 is available at: https://services.healthtech.dtu.dk/service.php?DiscoTope-3.0.

AB - Accurate computational identification of B-cell epitopes is crucial for the development of vaccines, therapies, and diagnostic tools. However, current structure-based prediction methods face limitations due to the dependency on experimentally solved structures. Here, we introduce DiscoTope-3.0, a markedly improved B-cell epitope prediction tool that innovatively employs inverse folding structure representations and a positive-unlabelled learning strategy, and is adapted for both solved and predicted structures. Our tool demonstrates a considerable improvement in performance over existing methods, accurately predicting linear and conformational epitopes across multiple independent datasets. Most notably, DiscoTope-3.0 maintains high predictive performance across solved, relaxed and predicted structures, alleviating the need for experimental structures and extending the general applicability of accurate B-cell epitope prediction by 3 orders of magnitude. DiscoTope-3.0 is made widely accessible on two web servers, processing over 100 structures per submission, and as a downloadable package. In addition, the servers interface with RCSB and AlphaFoldDB, facilitating large-scale prediction across over 200 million cataloged proteins. DiscoTope-3.0 is available at: https://services.healthtech.dtu.dk/service.php?DiscoTope-3.0.

KW - antibody epitope prediction

KW - B cell epitope prediction

KW - ESM-IF1

KW - immunogenicity prediction

KW - inverse-folding

KW - structure-based

KW - vaccine design

U2 - 10.3389/fimmu.2024.1322712

DO - 10.3389/fimmu.2024.1322712

M3 - Journal article

C2 - 38390326

AN - SCOPUS:85185854796

VL - 15

JO - Frontiers in Immunology

JF - Frontiers in Immunology

SN - 1664-3224

M1 - 1322712

ER -