Predicting Antibody Affinity Changes upon Mutation Based on Unbound Protein Structures.

Publisher: MDPI Country of Publication: Switzerland NLM ID: 101092791 Publication Model: Electronic Cited Medium: Internet ISSN: 1422-0067 (Electronic) Linking ISSN: 14220067 NLM ISO Abbreviation: Int J Mol Sci Subsets: MEDLINE

Original Publication: Basel, Switzerland : MDPI, [2000-

Mutation* ; Antibody Affinity*/genetics ; Antibodies, Viral*/genetics ; Antibodies, Viral*/immunology ; Antibodies, Viral*/chemistry; Humans ; SARS-CoV-2/immunology ; Protein Conformation ; COVID-19/immunology ; Antibodies, Monoclonal/genetics ; Antibodies, Monoclonal/chemistry ; Antibodies, Monoclonal/immunology ; Antigen-Antibody Complex/chemistry ; Antigen-Antibody Complex/immunology ; Antigen-Antibody Complex/genetics ; Spike Glycoprotein, Coronavirus/immunology ; Spike Glycoprotein, Coronavirus/genetics ; Spike Glycoprotein, Coronavirus/chemistry

Antibodies are key proteins in the immune system that can reversibly and non-covalently bind specifically to their corresponding antigens, forming antigen-antibody complexes. They play a crucial role in recognizing foreign or self-antigens during the adaptive immune response. Monoclonal antibodies have emerged as a promising class of biological macromolecule therapeutics with broad market prospects. In the process of antibody drug development, a key engineering challenge is to improve the affinity of candidate antibodies, without experimentally resolved structures of the antigen-antibody complexes as input for computer-aided predictive methods. In this work, we present an approach for predicting the effect of residue mutations on antibody affinity without the structures of the antigen-antibody complexes. The method involves the graph representation of proteins and utilizes a pre-trained encoder. The encoder captures the residue-level microenvironment of the target residue on the antibody along with the antigen context pre- and post-mutation. The encoder inherently possesses the potential to identify paratope residues. In addition, we curated a benchmark dataset specifically for mutations of the antibody. Compared to baseline methods based on complex structures and sequences, our approach achieves superior or comparable average accuracy on benchmark datasets. Additionally, we validate its advantage of not requiring antigen-antibody complex structures as input for predicting the effects of mutations in antibodies against SARS-CoV-2, influenza, and human cytomegalovirus. Our method shows its potential for identifying mutations that improve antibody affinity in practical antibody engineering applications.

Nucleic Acids Res. 2020 Jul 2;48(W1):W125-W131. (PMID: 32432715)
Nucleic Acids Res. 2016 Jul 8;44(W1):W469-73. (PMID: 27216816)
J Chem Inf Model. 2022 Sep 12;62(17):3961-3969. (PMID: 36040839)
Methods Enzymol. 2011;487:545-74. (PMID: 21187238)
Protein Sci. 2022 Jan;31(1):141-146. (PMID: 34655133)
Protein Eng. 1998 Jan;11(1):65-74. (PMID: 9579662)
iScience. 2020 Mar 27;23(3):100939. (PMID: 32169820)
Bioinformatics. 2020 Feb 15;36(4):1114-1120. (PMID: 31593229)
Nucleic Acids Res. 2022 Jan 7;50(D1):D1368-D1372. (PMID: 34986602)
Protein Sci. 2022 Aug;31(8):e4379. (PMID: 35900023)
Cell Biosci. 2022 May 17;12(1):63. (PMID: 35581593)
Bioinformatics. 2020 Jul 1;36(13):3996-4003. (PMID: 32321157)
Nat Biomed Eng. 2021 Jun;5(6):600-612. (PMID: 33859386)
Bioinformatics. 2019 Oct 15;35(20):4168-4169. (PMID: 30874800)
Nat Commun. 2015 Sep 14;6:8176. (PMID: 26365435)
Nucleic Acids Res. 2004 Jul 1;32(Web Server issue):W500-2. (PMID: 15215436)
Biochemistry. 1998 Jul 28;37(30):10660-70. (PMID: 9692956)
Proteins. 2014 Jul;82(7):1142-55. (PMID: 24243399)
Nucleic Acids Res. 2019 Jul 2;47(W1):W338-W344. (PMID: 31114883)
Bioinformatics. 2020 Feb 15;36(4):1135-1142. (PMID: 31588495)
Nature. 2024 Jun;630(8016):493-500. (PMID: 38718835)
J Mol Biol. 2014 Nov 11;426(22):3729-3743. (PMID: 25174334)
Bioinformatics. 2020 Mar 1;36(5):1453-1459. (PMID: 31665262)
Sci Rep. 2020 Nov 11;10(1):19533. (PMID: 33177627)
Nat Rev Immunol. 2023 Nov;23(11):720-734. (PMID: 37069260)
PLoS Comput Biol. 2021 Aug 4;17(8):e1009284. (PMID: 34347784)
Nat Mach Intell. 2020;2(2):116-123. (PMID: 34170981)
Int J Mol Sci. 2020 Apr 07;21(7):. (PMID: 32272725)
Bioinformatics. 2012 Oct 15;28(20):2608-14. (PMID: 23053206)
J Chem Theory Comput. 2023 Aug 22;19(16):5315-5333. (PMID: 37527403)
Proc Natl Acad Sci U S A. 2014 Jul 1;111(26):E2656-65. (PMID: 24938786)
Nucleic Acids Res. 1997 Sep 1;25(17):3389-402. (PMID: 9254694)
Proc Natl Acad Sci U S A. 2022 Mar 15;119(11):e2122954119. (PMID: 35238654)
J Mol Biol. 2019 Jun 14;431(13):2467-2476. (PMID: 30851277)
Nat Med. 2023 Aug;29(8):2007-2018. (PMID: 37524952)
Front Immunol. 2013 Oct 08;4:302. (PMID: 24115948)
Nat Protoc. 2017 Feb;12(2):255-278. (PMID: 28079879)
J Mol Recognit. 2018 May;31(5):e2693. (PMID: 29218757)
Bioinformatics. 2024 Oct 1;40(10):. (PMID: 39348158)
Nat Commun. 2024 Sep 6;15(1):7785. (PMID: 39242604)
Adv Biol. 2014;2014:. (PMID: 27099867)
J Mol Biol. 2017 Feb 3;429(3):426-434. (PMID: 27899282)
Bioinformatics. 2014 Feb 01;30(3):335-42. (PMID: 24281696)

20240484733 Beijing Nova Program; 2023YFC2604400 National Key R&D Program of China

Keywords: antibody affinity changes; antibody mutation; antigen–antibody complex; deep learning; structure representation

0 (Antibodies, Monoclonal)
0 (Antigen-Antibody Complex)
0 (Spike Glycoprotein, Coronavirus)
0 (Antibodies, Viral)

Date Created: 20250213 Date Completed: 20250507 Latest Revision: 20250507

20250508

PMC11818220

10.3390/ijms26031343

39941111