![]() ![]() The structures predicted by DeepSCAb and alternative methods for benchmarking have been deposited at Zenodo: 10.5281/zenodo.6371490.įunding: This work was supported by National Science Foundation Research Experience for Undergraduates grant DBI-1659649 (D.A.), AstraZeneca (J.A.R.), National Institutes of Health grants T32-GM008403 (J.A.R.), R35- GM141881 (J.A.R.), R35-GM141881 (J.A.R.), and R01-GM078221(S.P.M., J.J.G.). This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.ĭata Availability: The source code to train and run DeepSCAb, as well as pretrained models, are available at. Received: SeptemAccepted: Published: June 15, 2022Ĭopyright: © 2022 Akpinaroglu et al. PLoS ONE 17(6):Ĭincinnati Children’s Hospital Medical Center, UNITED STATES Our findings suggest that DeepSCAb improves antibody structure prediction with accurate side-chain modeling and is adaptable to applications in docking of antibody-antigen complexes and design of new therapeutic antibody sequences.Ĭitation: Akpinaroglu D, Ruffolo JA, Mahajan SP, Gray JJ (2022) Simultaneous prediction of antibody backbone and side-chain conformations with deep learning. When compared to alternative rotamer repacking methods, which require an input backbone structure, DeepSCAb predicts side-chain conformations competitively. We evaluate the performance of the model for discriminating near-native structures from sets of decoys and find that DeepSCAb outperforms similar methods lacking side-chain context. Rotamer predictions use an interpretable self-attention layer, which learns to identify structurally conserved anchor positions across several species. The network requires only sequence as input, rendering it particularly useful for antibodies without any known backbone conformations. To address this shortcoming, we created DeepSCAb: a deep learning method that predicts inter-residue geometries as well as side-chain dihedrals of the antibody variable fragment. However, antigen binding is also dependent on the specific conformations of surface side-chains. Deep learning methods have previously been shown to effectively predict antibody backbone structures described as a set of inter-residue distances and orientations. Hence, accurate high-resolution modeling of these loops is essential for effective antibody engineering and design. Antibody function relies largely on the recognition and binding of antigenic epitopes via the loops in the complementarity determining regions. Antibody engineering is becoming increasingly popular in medicine for the development of diagnostics and immunotherapies. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |