Simultaneous prediction of antibody backbone and side-chain conformations with deep learning.

Antibody engineering is becoming increasingly popular in medicine for the development of diagnostics and immunotherapies. Antibody function relies largely on the recognition and binding of antigenic epitopes via the loops in the complementarity determining regions. Hence, accurate high-resolution mo...

Full description

Bibliographic Details
Main Authors: Deniz Akpinaroglu, Jeffrey A Ruffolo, Sai Pooja Mahajan, Jeffrey J Gray
Format: Article
Language:English
Published: Public Library of Science (PLoS) 2022-01-01
Series:PLoS ONE
Online Access:https://doi.org/10.1371/journal.pone.0258173
_version_ 1818513009844158464
author Deniz Akpinaroglu
Jeffrey A Ruffolo
Sai Pooja Mahajan
Jeffrey J Gray
author_facet Deniz Akpinaroglu
Jeffrey A Ruffolo
Sai Pooja Mahajan
Jeffrey J Gray
author_sort Deniz Akpinaroglu
collection DOAJ
description Antibody engineering is becoming increasingly popular in medicine for the development of diagnostics and immunotherapies. Antibody function relies largely on the recognition and binding of antigenic epitopes via the loops in the complementarity determining regions. Hence, accurate high-resolution modeling of these loops is essential for effective antibody engineering and design. Deep learning methods have previously been shown to effectively predict antibody backbone structures described as a set of inter-residue distances and orientations. However, antigen binding is also dependent on the specific conformations of surface side-chains. 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. The network requires only sequence as input, rendering it particularly useful for antibodies without any known backbone conformations. Rotamer predictions use an interpretable self-attention layer, which learns to identify structurally conserved anchor positions across several species. 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. When compared to alternative rotamer repacking methods, which require an input backbone structure, DeepSCAb predicts side-chain conformations competitively. 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.
first_indexed 2024-12-10T23:55:01Z
format Article
id doaj.art-6b9490e294de4e8c8a668e1ea4fa049d
institution Directory Open Access Journal
issn 1932-6203
language English
last_indexed 2024-12-10T23:55:01Z
publishDate 2022-01-01
publisher Public Library of Science (PLoS)
record_format Article
series PLoS ONE
spelling doaj.art-6b9490e294de4e8c8a668e1ea4fa049d2022-12-22T01:28:37ZengPublic Library of Science (PLoS)PLoS ONE1932-62032022-01-01176e025817310.1371/journal.pone.0258173Simultaneous prediction of antibody backbone and side-chain conformations with deep learning.Deniz AkpinarogluJeffrey A RuffoloSai Pooja MahajanJeffrey J GrayAntibody engineering is becoming increasingly popular in medicine for the development of diagnostics and immunotherapies. Antibody function relies largely on the recognition and binding of antigenic epitopes via the loops in the complementarity determining regions. Hence, accurate high-resolution modeling of these loops is essential for effective antibody engineering and design. Deep learning methods have previously been shown to effectively predict antibody backbone structures described as a set of inter-residue distances and orientations. However, antigen binding is also dependent on the specific conformations of surface side-chains. 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. The network requires only sequence as input, rendering it particularly useful for antibodies without any known backbone conformations. Rotamer predictions use an interpretable self-attention layer, which learns to identify structurally conserved anchor positions across several species. 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. When compared to alternative rotamer repacking methods, which require an input backbone structure, DeepSCAb predicts side-chain conformations competitively. 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.https://doi.org/10.1371/journal.pone.0258173
spellingShingle Deniz Akpinaroglu
Jeffrey A Ruffolo
Sai Pooja Mahajan
Jeffrey J Gray
Simultaneous prediction of antibody backbone and side-chain conformations with deep learning.
PLoS ONE
title Simultaneous prediction of antibody backbone and side-chain conformations with deep learning.
title_full Simultaneous prediction of antibody backbone and side-chain conformations with deep learning.
title_fullStr Simultaneous prediction of antibody backbone and side-chain conformations with deep learning.
title_full_unstemmed Simultaneous prediction of antibody backbone and side-chain conformations with deep learning.
title_short Simultaneous prediction of antibody backbone and side-chain conformations with deep learning.
title_sort simultaneous prediction of antibody backbone and side chain conformations with deep learning
url https://doi.org/10.1371/journal.pone.0258173
work_keys_str_mv AT denizakpinaroglu simultaneouspredictionofantibodybackboneandsidechainconformationswithdeeplearning
AT jeffreyaruffolo simultaneouspredictionofantibodybackboneandsidechainconformationswithdeeplearning
AT saipoojamahajan simultaneouspredictionofantibodybackboneandsidechainconformationswithdeeplearning
AT jeffreyjgray simultaneouspredictionofantibodybackboneandsidechainconformationswithdeeplearning