Paragraph-antibody Paratope Prediction Using Graph Neural Networks with Minimal Feature Vectors
Overview
Affiliations
Summary: The development of new vaccines and antibody therapeutics typically takes several years and requires over $1bn in investment. Accurate knowledge of the paratope (antibody binding site) can speed up and reduce the cost of this process by improving our understanding of antibody-antigen binding. We present Paragraph, a structure-based paratope prediction tool that outperforms current state-of-the-art tools using simpler feature vectors and no antigen information.
Availability And Implementation: Source code is freely available at www.github.com/oxpig/Paragraph.
Supplementary Information: Supplementary data are available at Bioinformatics online.
Contrastive Learning Enables Epitope Overlap Predictions for Targeted Antibody Discovery.
Holt C, Janke A, Amlashi P, Jamieson P, Marinov T, Georgiev I bioRxiv. 2025; .
PMID: 40060439 PMC: 11888244. DOI: 10.1101/2025.02.25.640114.
Occlusion of TCR binding to HLA-A*11:01 by a non-pathogenic human alloantibody.
Hamidinia M, Gu Y, Ser Z, Brzostek J, Tay N, Yap J Cell Mol Life Sci. 2025; 82(1):94.
PMID: 40009199 PMC: 11865395. DOI: 10.1007/s00018-025-05614-y.
ParaSurf: a surface-based deep learning approach for paratope-antigen interaction prediction.
Papadopoulos A, Axenopoulos A, Iatrou A, Stamatopoulos K, Alvarez F, Daras P Bioinformatics. 2025; 41(2).
PMID: 39921885 PMC: 11855283. DOI: 10.1093/bioinformatics/btaf062.
ParaAntiProt provides paratope prediction using antibody and protein language models.
Kalemati M, Noroozi A, Shahbakhsh A, Koohi S Sci Rep. 2024; 14(1):29141.
PMID: 39587231 PMC: 11589832. DOI: 10.1038/s41598-024-80940-y.
Integrating machine learning to advance epitope mapping.
Grewal S, Hegde N, Yanow S Front Immunol. 2024; 15:1463931.
PMID: 39403389 PMC: 11471525. DOI: 10.3389/fimmu.2024.1463931.