We introduce IgDiff, an antibody variable domain diffusion model based on a general protein backbone diffusion framework, which was extended to handle multiple chains. Assessing the designability and novelty of the structures generated with our model, we find that IgDiff produces highly designable antibodies that can contain novel binding regions. The backbone dihedral angles of sampled structures show good agreement with a reference antibody distribution. We verify these designed antibodies experimentally and find that all express with high yield. Finally, we compare our model with a state-of-the-art generative backbone diffusion model on a range of antibody design tasks, such as the design of the complementarity determining regions or the pairing of a light chain to an existing heavy chain, and show improved properties and designability.
Get full access to this article
View all access options for this article.
References
1.
AbanadesB, WongWK, BoylesF, et al.Immunebuilder: Deep-learning models for predicting the structures of immune proteins. bioRxiv, 2022; doi: 10.1101/2022.11.04.514231
2.
Adolf-BryfogleJ, KalyuzhniyO, KubitzM, et al.Rosettaantibodydesign (rabd): A general framework for computational antibody design. PLOS Computational Biology, 2018; 14(4):e1006112–e38; doi: 10.1371/journal.pcbi, 1006112
3.
AkbarR, RobertPA, PavlovićM, et al.A compact vocabulary of paratope-epitope interactions enables predictability of antibody-antigen binding. Cell Rep, 2021; 34(11):108856; doi: 10.1016/j.celrep.2021.108856
4.
AlfordR, Leaver-FayA, JeliazkovJ, et al.The rosetta all-atom energy function for macromolecular modeling and design. J Chem Theory Comput, 2017; 13(6):3031–3048; doi: 10.1021/acs.jctc.7b00125
5.
BaekM, DiMaioF, AnishchenkoI, et al.Accurate prediction of protein structures and interactions using a three-track neural network. Science, 2021; 373(6557):871–876; doi: 10.1126/science.abj8754
6.
BennettNR, WatsonJL, RagotteRJ, et al.Atomically accurate de novo design of single-domain antibodies. bioRxiv, 2024; doi: 10.1101/2024.03.14.585103
7.
BortoliVD, MathieuE, HutchinsonM, et al.Riemannian score-based generative modelling, 2022.
8.
ChengJ, LiangT, XieX-Q, et al.A new era of antibody discovery: An in-depth review of ai-driven approaches. Drug Discovery Today, 2024; 29(6):103984; doi: 10.1016/j.drudis.2024.103984
9.
ChiuML, GouletDR, TeplyakovA, et al.Antibody structure and function: The basis for engineering therapeutics. Antibodies, 2019; 8(4):55.
10.
ChothiaC, LeskAM. Canonical structures for the hypervariable regions of immunoglobulins. J Mol Biol, 1987; 196(4):901–917; doi: 10.1016/0022-2836(87)90412-8
11.
ChuAE, ChengL, NesrGE, et al.An all-atom protein generative model. bioRxiv, 2023; doi: 10.1101/2023.05.24.542194
12.
CrescioliS, KaplonH, ChenowethA, et al.Antibodies to watch in 2024. MAbs, 2024; 16(1):2297450; doi: 10.1080/19420862.2023.2297450
13.
DauparasJ, AnishchenkoI, BennettN, et al.Robust deep learning based protein sequence design using proteinmpnn. bioRxiv, 2022; doi: 10.1101/2022.06.03.494563
14.
DeKoskyBJ, KojimaT, RodinA, et al.In-depth determination and analysis of the human paired heavy- and light-chain antibody repertoire. Nat Med, 2015; 21(1):86–91; doi: 10.1038/nm.3743
15.
DidiK, VargasF, MathisSV, et al.framework for conditional diffusion modelling with applications in motif scaffolding for protein design, 2024. Available from: https://arxiv.org/abs/2312.09236
16.
DreyerFA, CuttingD, SchneiderC, et al.Inverse folding for antibody sequence design using deep learning. In 2023 ICML Workshop on Computational Biology, 2023. Available from: https://arxiv.org/abs/2310.19513
17.
DreyerFA, SchneiderC, KovaltsukA, et al.Computational design of developable therapeutic antibodies: Efficient traversal of binder landscapes and rescue of escape mutations. bioRxiv, 2024; doi: 10.1101/2024.10.03.616038
EnghRA, HuberR. Structure quality and target parameters, chapter 18.3, pages 474–484. John Wiley & Sons, Ltd, 2012. ISBN 9780470685754; doi: 10.1107/97809553602060000857
21.
EvansR, O’NeillM, PritzelA, et al.Protein complex prediction with alphafold-multimer. bioRxiv, 2022; doi: 10.1101/2021.10.04.463034
22.
FuL, NiuB, ZhuZ, et al.CD-HIT: Accelerated for clustering the next-generation sequencing data. Bioinformatics, 2012; 28(23):3150–3152; doi: 10.1093/bioinformatics/bts565
23.
FuchsFB, WorrallDE, FischerV, et al.Se(3)-transformers: 3d roto-translation equivariant attention networks. In Advances in Neural Information Processing Systems. 34 (NeurIPS), 2020.
24.
GruverN, StantonS, FreyNC, et al.Protein design with guided discrete diffusion, 2023.
JinW, BarzilayD, JaakkolaT. Antibody-antigen docking and design via hierarchical structure refinement. In ChaudhuriK, JegelkaS, SongL, SzepesvariC, NiuG, and SabatoS., editors, Proceedings of the 39th International Conference on Machine Learning, volume 162 of Proceedings of Machine Learning Research, pages 10217–10227. PMLR, 2022a. https://proceedings.mlr.press/v162/jin22a.html
29.
JinW, WohlwendJ, BarzilayR, et al.Iterative refinement graph neural network for antibody sequence-structure co-design. In International Conference on Learning Representations, 2022b. https://openreview.net/forum?id=LI2bhrE_2A
30.
JørgensenE. The central limit problem for geodesic random walks. Zeitschrift Für Wahrscheinlichkeitstheorie Und Verwandte Gebiete, 1975; 32(1):1–64; doi: 10.1007/BF00533088
31.
JumperJ, EvansR, PritzelA, et al.Highly accurate protein structure prediction with alphafold. Nature, 2021; 596(7873):583–589; doi: 10.1038/s41586-021-03819-2
32.
KimJ, McFeeM, FangQ, et al.Computational and artificial intelligence-based methods for antibody development. Trends Pharmacol Sci, 2023; 44(3):175–189; doi: 10.1016/j.tips.2022.12.005
33.
KingmaDP, BaJA. A method for stochastic optimization, 2017.
KongX, HuangW, LiuY. Conditional antibody design as 3d equivariant graph translation. In The Eleventh International Conference on Learning Representations, 2023b. https://openreview.net/forum?id=LFHFQbjxIiP
36.
KovaltsukA, LeemJ, KelmS, et al.Observed antibody space: A resource for data mining next-generation sequencing of antibody repertoires. J Immunol, 2018; 201(8):2502–2509; doi: 10.4049/jimmunol.1800708
37.
Leaver-FayA, TykaM, LewisSM, et al.Chapter nineteen - rosetta3: An object-oriented software suite for the simulation and design of macromolecules. In Computer Methods, Part C, volume 487 of Methods in Enzymology (JohnsonM. L and BrandL, eds) Academic Press, 2011; pp 545–574, doi: 10.1016/B978-0-12-381270-4.00019-6
38.
LefrancM-P, PommiéC, RuizM, et al.Imgt unique numbering for immunoglobulin and t cell receptor variable domains and ig superfamily v-like domains. Dev Comp Immunol, 2003; 27(1):55–77; doi: 10.1016/S0145-305X(02)00039-3
39.
LiT, PantazesRJ, MaranasCD. Optmaven – a new framework for the de novo design of antibody variable region models targeting specific antigen epitopes. Plos ONE, 2014; 9(8):e105954–e17; doi: 10.1371/journal.pone.0105954
40.
LinY, AlQuraishiM. Generating novel, designable, and diverse protein structures by equivariantly diffusing oriented residue clouds, 2023.
41.
LisanzaSL, GershonJM, TippsS, et al.Joint generation of protein sequence and structure with rosettafold sequence space diffusion. bioRxiv, 2023; doi: 10.1101/2023.05.08.539766
42.
LiuG, ZengH, MuellerJ, et al.Antibody complementarity determining region design using high-capacity machine learning. Bioinformatics, 2020; 36(7):2126–2133; doi: 10.1093/bioinformatics/btz895
43.
LuoS, SuY, PengX, et al.Antigen-specific antibody design and optimization with diffusion-based generative models for protein structures. In Advances in Neural Information Processing Systems (OhA. H, AgarwalA, BelgraveD, and ChoKeds). 2022. https://openreview.net/forum?id=jSorGn2Tjg
44.
MartinkusK, LudwiczakJ, ChoK, et al.Abdiffuser: Full-atom generation of in-vitro functioning antibodies, 2023.
45.
NarcisoJE, UyI, CabangA, et al.Analysis of the antibody structure based on high-resolution crystallographic studies. N Biotechnol, 2011; 28(5):435–447; doi: 10.1016/j.nbt.2011.03.012
46.
NorthB, LehmannA, DunbrackRL. A new clustering of antibody cdr loop conformations. J Mol Biol, 2011; 406(2):228–256; doi: 10.1016/j.jmb.2010.10.030
47.
OlsenTH, BoylesF, DeaneCM. Observed antibody space: A diverse database of cleaned, annotated, and translated unpaired and paired antibody sequences. Protein Sci, 2022; 31(1):141–146; doi: 10.1002/pro.4205
48.
SakaK, KakuzakiT, MetsugiS, et al.Antibody design using lstm based deep generative model from phage display library for affinity maturation. Sci Rep, 2021; 11(1):5852; doi: 10.1038/s41598-021-85274-7
49.
ShanehsazzadehA, AlverioJ, KasunG, et al.In vitro validated antibody design against multiple therapeutic antigens using generative inverse folding. bioRxiv, 2023; doi: 10.1101/2023.12.08.570889
50.
ShanehsazzadehA, McPartlonM, KasunG, et al.Unlocking de novo antibody design with generative artificial intelligence. bioRxiv, 2024; doi: 10.1101/2023.01.08.523187
51.
Sohl-DicksteinJ, WeissE, MaheswaranathanN, et al.Deep unsupervised learning using nonequilibrium thermodynamics. In Proceedings of the 32nd International Conference on Machine Learning, volume 37 of Proceedings of Machine Learning Research, (BachF and BleiD, eds) PMLR: Lille: France; 2015; pp. 2256–2265. https://proceedings.mlr.press/v37/sohl-dickstein15.html
52.
SongY, Sohl-DicksteinJ, KingmaDP, et al.Score-based generative modeling through stochastic differential equations, 2021.
53.
SvilenovHL, ArosioP, MenzenT, et al.Approaches to expand the conventional toolbox for discovery and selection of antibodies with drug-like physicochemical properties. MAbs, 2023; 15(1):2164459.
54.
TrippeBL, YimJ, TischerD, et al.Diffusion probabilistic modeling of protein backbones in 3d for the motif-scaffolding problem. In The Eleventh International Conference on Learning Representations, 2023. https://openreview.net/forum?id=6TxBxqNME1Y
55.
TsuchiyaY, MizuguchiK. The diversity of h3 loops determines the antigen-binding tendencies of antibody cdr loops. Protein Sci, 2016; 25(4):815–825; doi: 10.1002/pro.2874
56.
VaswaniA, ShazeerN, ParmarN, et al.Attention is all you need, 2017.
57.
WatsonJL, JuergensD, BennettNR, et al.Broadly applicable and accurate protein design by integrating structure prediction networks and diffusion generative models. bioRxiv, 2022; doi: 10.1101/2022.12.09.519842
58.
WuL, TrippeBL, NaessethCA, et al.Practical and asymptotically exact conditional sampling in diffusion models, 2023. Available from: https://arxiv.org/abs/2306.17775
59.
WuZ, JohnstonKE, ArnoldFH, et al.Protein sequence design with deep generative models. Curr Opin Chem Biol, 2021; 65:18–27; doi: 10.1016/j.cbpa.2021.04.004
60.
YimJ, TrippeBL, De BortoliV, et al.Se(3) diffusion model with application to protein backbone generation. arXiv Preprint arXiv, 20232302.02277.
61.
ZhanY, ZhangZ, ZhongB, et al.Diffpack: A torsional diffusion model for autoregressive protein side-chain packing, 2023.
62.
ZhangC, LeachA, MakkinkT, et al.Framedipt: Se(3) diffusion model for protein structure inpainting. bioRxiv, 2023; doi: 10.1101/2023.11.21.568057
63.
ZhangY, SkolnickJ. Scoring function for automated assessment of protein structure template quality. Proteins, 2004; 57(4):702–710; doi: 10.1002/prot.20264
Supplementary Material
Please find the following supplemental material available below.
For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.
For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.
