AI Models for Protein Design Are Driving Antibody Engineering

Overview

Journal Curr Opin Biomed Eng

Specialty Biomedical Engineering

Date 2023 Jul 24

PMID 37484815

Authors

Michael Chungyoun

Jeffrey J Gray

Affiliations

Soon will be listed here.

Abstract

Therapeutic antibody engineering seeks to identify antibody sequences with specific binding to a target and optimized drug-like properties. When guided by deep learning, antibody generation methods can draw on prior knowledge and experimental efforts to improve this process. By leveraging the increasing quantity and quality of predicted structures of antibodies and target antigens, powerful structure-based generative models are emerging. In this review, we tie the advancements in deep learning-based protein structure prediction and design to the study of antibody therapeutics.

Citing Articles

What does AlphaFold3 learn about antigen and nanobody docking, and what remains unsolved?.

Hitawala F, Gray J bioRxiv. 2025; .

PMID: 39975279 PMC: 11838198. DOI: 10.1101/2024.09.21.614257.

ProteinReDiff: Complex-based ligand-binding proteins redesign by equivariant diffusion-based generative models.

Nguyen V, Nguyen N, Hy T Struct Dyn. 2024; 11(6):064102.

PMID: 39629167 PMC: 11614476. DOI: 10.1063/4.0000271.

ABodyBuilder3: improved and scalable antibody structure predictions.

Kenlay H, Dreyer F, Cutting D, Nissley D, Deane C Bioinformatics. 2024; 40(10).

PMID: 39363504 PMC: 11474105. DOI: 10.1093/bioinformatics/btae576.

AI-driven antibody design with generative diffusion models: current insights and future directions.

He X, Li J, Xu J, Shan H, Shen S, Gao S Acta Pharmacol Sin. 2024; 46(3):565-574.

PMID: 39349764 PMC: 11845702. DOI: 10.1038/s41401-024-01380-y.

A survey of generative AI for de novo drug design: new frontiers in molecule and protein generation.

Tang X, Dai H, Knight E, Wu F, Li Y, Li T Brief Bioinform. 2024; 25(4).

PMID: 39007594 PMC: 11247410. DOI: 10.1093/bib/bbae338.

References

Leem J, Mitchell L, Farmery J, Barton J, Galson J . Deciphering the language of antibodies using self-supervised learning. Patterns (N Y). 2022; 3(7):100513. PMC: 9278498. DOI: 10.1016/j.patter.2022.100513. View

Anand N, Eguchi R, Mathews I, Perez C, Derry A, Altman R . Protein sequence design with a learned potential. Nat Commun. 2022; 13(1):746. PMC: 8826426. DOI: 10.1038/s41467-022-28313-9. View

Ruffolo J, Sulam J, Gray J . Antibody structure prediction using interpretable deep learning. Patterns (N Y). 2022; 3(2):100406. PMC: 8848015. DOI: 10.1016/j.patter.2021.100406. View

Mahajan S, Ruffolo J, Frick R, Gray J . Hallucinating structure-conditioned antibody libraries for target-specific binders. Front Immunol. 2022; 13:999034. PMC: 9635398. DOI: 10.3389/fimmu.2022.999034. View

Nijkamp E, Ruffolo J, Weinstein E, Naik N, Madani A . ProGen2: Exploring the boundaries of protein language models. Cell Syst. 2023; 14(11):968-978.e3. DOI: 10.1016/j.cels.2023.10.002. View

Dauparas J, Anishchenko I, Bennett N, Bai H, Ragotte R, Milles L . Robust deep learning-based protein sequence design using ProteinMPNN. Science. 2022; 378(6615):49-56. PMC: 9997061. DOI: 10.1126/science.add2187. View

Strebhardt K, Ullrich A . Paul Ehrlich's magic bullet concept: 100 years of progress. Nat Rev Cancer. 2008; 8(6):473-80. DOI: 10.1038/nrc2394. View

Vu M, Robert P, Akbar R, Swiatczak B, Sandve G, Haug D . Linguistics-based formalization of the antibody language as a basis for antibody language models. Nat Comput Sci. 2024; 4(6):412-422. DOI: 10.1038/s43588-024-00642-3. View

Jing X, Wu F, Luo X, Xu J . Single-sequence protein structure prediction by integrating protein language models. Proc Natl Acad Sci U S A. 2024; 121(13):e2308788121. PMC: 10990103. DOI: 10.1073/pnas.2308788121. View

10.

Ferruz N, Schmidt S, Hocker B . ProtGPT2 is a deep unsupervised language model for protein design. Nat Commun. 2022; 13(1):4348. PMC: 9329459. DOI: 10.1038/s41467-022-32007-7. View

11.

Kozakov D, Hall D, Xia B, Porter K, Padhorny D, Yueh C . The ClusPro web server for protein-protein docking. Nat Protoc. 2017; 12(2):255-278. PMC: 5540229. DOI: 10.1038/nprot.2016.169. View

12.

Dunbar J, Krawczyk K, Leem J, Baker T, Fuchs A, Georges G . SAbDab: the structural antibody database. Nucleic Acids Res. 2013; 42(Database issue):D1140-6. PMC: 3965125. DOI: 10.1093/nar/gkt1043. View

13.

Olsen T, Moal I, Deane C . AbLang: an antibody language model for completing antibody sequences. Bioinform Adv. 2023; 2(1):vbac046. PMC: 9710568. DOI: 10.1093/bioadv/vbac046. View

14.

Huang P, Boyken S, Baker D . The coming of age of de novo protein design. Nature. 2016; 537(7620):320-7. DOI: 10.1038/nature19946. View

15.

Ruffolo J, Chu L, Mahajan S, Gray J . Fast, accurate antibody structure prediction from deep learning on massive set of natural antibodies. Nat Commun. 2023; 14(1):2389. PMC: 10129313. DOI: 10.1038/s41467-023-38063-x. View

16.

Abanades B, Wong W, Boyles F, Georges G, Bujotzek A, Deane C . ImmuneBuilder: Deep-Learning models for predicting the structures of immune proteins. Commun Biol. 2023; 6(1):575. PMC: 10227038. DOI: 10.1038/s42003-023-04927-7. View

17.

Shuai R, Ruffolo J, Gray J . IgLM: Infilling language modeling for antibody sequence design. Cell Syst. 2023; 14(11):979-989.e4. PMC: 11018345. DOI: 10.1016/j.cels.2023.10.001. View

18.

Robert P, Akbar R, Frank R, Pavlovic M, Widrich M, Snapkov I . Unconstrained generation of synthetic antibody-antigen structures to guide machine learning methodology for antibody specificity prediction. Nat Comput Sci. 2024; 2(12):845-865. DOI: 10.1038/s43588-022-00372-4. View

19.

Ruffolo J, Guerra C, Mahajan S, Sulam J, Gray J . Geometric potentials from deep learning improve prediction of CDR H3 loop structures. Bioinformatics. 2020; 36(Suppl_1):i268-i275. PMC: 7355305. DOI: 10.1093/bioinformatics/btaa457. View

20.

Makowski E, Kinnunen P, Huang J, Wu L, Smith M, Wang T . Co-optimization of therapeutic antibody affinity and specificity using machine learning models that generalize to novel mutational space. Nat Commun. 2022; 13(1):3788. PMC: 9249733. DOI: 10.1038/s41467-022-31457-3. View