1
|
Abramson J, Adler J, Dunger J, Evans R, Green T, Pritzel A, Ronneberger O, Willmore L, Ballard AJ, Bambrick J, Bodenstein SW, Evans DA, Hung CC, O'Neill M, Reiman D, Tunyasuvunakool K, Wu Z, Žemgulytė A, Arvaniti E, Beattie C, Bertolli O, Bridgland A, Cherepanov A, Congreve M, Cowen-Rivers AI, Cowie A, Figurnov M, Fuchs FB, Gladman H, Jain R, Khan YA, Low CMR, Perlin K, Potapenko A, Savy P, Singh S, Stecula A, Thillaisundaram A, Tong C, Yakneen S, Zhong ED, Zielinski M, Žídek A, Bapst V, Kohli P, Jaderberg M, Hassabis D, Jumper JM. Accurate structure prediction of biomolecular interactions with AlphaFold 3. Nature 2024; 630:493-500. [PMID: 38718835 PMCID: PMC11168924 DOI: 10.1038/s41586-024-07487-w] [Citation(s) in RCA: 10] [Impact Index Per Article: 10.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/19/2023] [Accepted: 04/29/2024] [Indexed: 06/13/2024]
Abstract
The introduction of AlphaFold 21 has spurred a revolution in modelling the structure of proteins and their interactions, enabling a huge range of applications in protein modelling and design2-6. Here we describe our AlphaFold 3 model with a substantially updated diffusion-based architecture that is capable of predicting the joint structure of complexes including proteins, nucleic acids, small molecules, ions and modified residues. The new AlphaFold model demonstrates substantially improved accuracy over many previous specialized tools: far greater accuracy for protein-ligand interactions compared with state-of-the-art docking tools, much higher accuracy for protein-nucleic acid interactions compared with nucleic-acid-specific predictors and substantially higher antibody-antigen prediction accuracy compared with AlphaFold-Multimer v.2.37,8. Together, these results show that high-accuracy modelling across biomolecular space is possible within a single unified deep-learning framework.
Collapse
Affiliation(s)
| | - Jonas Adler
- Core Contributor, Google DeepMind, London, UK
| | - Jack Dunger
- Core Contributor, Google DeepMind, London, UK
| | | | - Tim Green
- Core Contributor, Google DeepMind, London, UK
| | | | | | | | | | | | | | | | | | | | | | | | - Zachary Wu
- Core Contributor, Google DeepMind, London, UK
| | | | | | | | | | | | | | | | | | | | | | | | | | | | - Yousuf A Khan
- Google DeepMind, London, UK
- Department of Molecular and Cellular Physiology, Stanford University, Stanford, CA, USA
| | | | | | | | | | | | | | | | | | | | - Ellen D Zhong
- Google DeepMind, London, UK
- Department of Computer Science, Princeton University, Princeton, NJ, USA
| | | | | | | | | | | | - Demis Hassabis
- Core Contributor, Google DeepMind, London, UK.
- Core Contributor, Isomorphic Labs, London, UK.
| | | |
Collapse
|
2
|
Kim DN, McNaughton AD, Kumar N. Leveraging Artificial Intelligence to Expedite Antibody Design and Enhance Antibody-Antigen Interactions. Bioengineering (Basel) 2024; 11:185. [PMID: 38391671 PMCID: PMC10886287 DOI: 10.3390/bioengineering11020185] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/30/2023] [Revised: 01/30/2024] [Accepted: 02/06/2024] [Indexed: 02/24/2024] Open
Abstract
This perspective sheds light on the transformative impact of recent computational advancements in the field of protein therapeutics, with a particular focus on the design and development of antibodies. Cutting-edge computational methods have revolutionized our understanding of protein-protein interactions (PPIs), enhancing the efficacy of protein therapeutics in preclinical and clinical settings. Central to these advancements is the application of machine learning and deep learning, which offers unprecedented insights into the intricate mechanisms of PPIs and facilitates precise control over protein functions. Despite these advancements, the complex structural nuances of antibodies pose ongoing challenges in their design and optimization. Our review provides a comprehensive exploration of the latest deep learning approaches, including language models and diffusion techniques, and their role in surmounting these challenges. We also present a critical analysis of these methods, offering insights to drive further progress in this rapidly evolving field. The paper includes practical recommendations for the application of these computational techniques, supplemented with independent benchmark studies. These studies focus on key performance metrics such as accuracy and the ease of program execution, providing a valuable resource for researchers engaged in antibody design and development. Through this detailed perspective, we aim to contribute to the advancement of antibody design, equipping researchers with the tools and knowledge to navigate the complexities of this field.
Collapse
Affiliation(s)
- Doo Nam Kim
- Pacific Northwest National Laboratory, 902 Battelle Blvd., Richland, WA 99352, USA
| | - Andrew D McNaughton
- Pacific Northwest National Laboratory, 902 Battelle Blvd., Richland, WA 99352, USA
| | - Neeraj Kumar
- Pacific Northwest National Laboratory, 902 Battelle Blvd., Richland, WA 99352, USA
| |
Collapse
|
3
|
Lu W, Zhang J, Huang W, Zhang Z, Jia X, Wang Z, Shi L, Li C, Wolynes PG, Zheng S. DynamicBind: predicting ligand-specific protein-ligand complex structure with a deep equivariant generative model. Nat Commun 2024; 15:1071. [PMID: 38316797 PMCID: PMC10844226 DOI: 10.1038/s41467-024-45461-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/24/2023] [Accepted: 01/24/2024] [Indexed: 02/07/2024] Open
Abstract
While significant advances have been made in predicting static protein structures, the inherent dynamics of proteins, modulated by ligands, are crucial for understanding protein function and facilitating drug discovery. Traditional docking methods, frequently used in studying protein-ligand interactions, typically treat proteins as rigid. While molecular dynamics simulations can propose appropriate protein conformations, they're computationally demanding due to rare transitions between biologically relevant equilibrium states. In this study, we present DynamicBind, a deep learning method that employs equivariant geometric diffusion networks to construct a smooth energy landscape, promoting efficient transitions between different equilibrium states. DynamicBind accurately recovers ligand-specific conformations from unbound protein structures without the need for holo-structures or extensive sampling. Remarkably, it demonstrates state-of-the-art performance in docking and virtual screening benchmarks. Our experiments reveal that DynamicBind can accommodate a wide range of large protein conformational changes and identify cryptic pockets in unseen protein targets. As a result, DynamicBind shows potential in accelerating the development of small molecules for previously undruggable targets and expanding the horizons of computational drug discovery.
Collapse
Affiliation(s)
- Wei Lu
- Galixir Technologies, 200100, Shanghai, China.
| | | | - Weifeng Huang
- School of Pharmaceutical Science, Sun Yat-sen University, 510006, Guangzhou, China
| | | | - Xiangyu Jia
- Galixir Technologies, 200100, Shanghai, China
| | - Zhenyu Wang
- Galixir Technologies, 200100, Shanghai, China
| | - Leilei Shi
- Galixir Technologies, 200100, Shanghai, China
| | - Chengtao Li
- Galixir Technologies, 200100, Shanghai, China
| | - Peter G Wolynes
- Center for Theoretical Biological Physics and Department of Chemistry, Rice University, Houston, TX, 77005, USA
| | - Shuangjia Zheng
- Global Institute of Future Technology, Shanghai Jiao Tong University, 200240, Shanghai, China.
| |
Collapse
|
4
|
Liu B, Jiang Y, Yang Y, Chen JX. OmeDDG: Improved Protein Mutation Stability Prediction Based on Predicted 3D Structures. J Phys Chem B 2024; 128:67-76. [PMID: 38130113 DOI: 10.1021/acs.jpcb.3c05601] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/23/2023]
Abstract
Determining changes in the protein's thermal stability following mutations is critical in protein engineering and understanding pathogenic missense mutations. Despite the development of various computational methods to predict the effects of single-point mutations, their accuracy remains limited. In this study, we propose a new computational method, OmeDDG, that more accurately predicts mutation-induced Gibbs free energy changes in protein folding (ΔΔG). OmeDDG takes the sequences of wild-type and mutant proteins as input, utilizes OmegaFold to obtain the 3D structure, employs a convolutional neural network to extract structural features, and combines them with protein mutation features and pretraining features to predict the stability of single-point mutations in proteins. We performed a comprehensive comparison between OmeDDG and other available prediction methods on four blind test datasets, confirming that OmeDDG can effectively enhance protein mutation prediction performance. Notably, on the antisymmetric dataset Ssym, OmeDDG achieves the best performance, demonstrating favorable antisymmetry with PCC = 0.79 and RMSE = 0.96 for forward mutations and PCC = 0.77 and RMSE = 0.97 for reverse mutant types.
Collapse
Affiliation(s)
- Baoying Liu
- School of Computing and Artificial Intelligence, Southwest Jiaotong University, Chengdu 611756, Sichuan, China
| | - Yongquan Jiang
- School of Computing and Artificial Intelligence, Southwest Jiaotong University, Chengdu 611756, Sichuan, China
- Artificial Intelligence Research Institute, Southwest Jiaotong University, Chengdu 611756, Sichuan, China
| | - Yan Yang
- School of Computing and Artificial Intelligence, Southwest Jiaotong University, Chengdu 611756, Sichuan, China
- Artificial Intelligence Research Institute, Southwest Jiaotong University, Chengdu 611756, Sichuan, China
| | - Jim X Chen
- Department of Computer Science, George Mason University, Fairfax, Virginia 22030-4444, United States
| |
Collapse
|
5
|
Baillif B, Cole J, Giangreco I, McCabe P, Bender A. Applying atomistic neural networks to bias conformer ensembles towards bioactive-like conformations. J Cheminform 2023; 15:124. [PMID: 38129933 PMCID: PMC10740246 DOI: 10.1186/s13321-023-00794-w] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/11/2023] [Accepted: 12/10/2023] [Indexed: 12/23/2023] Open
Abstract
Identifying bioactive conformations of small molecules is an essential process for virtual screening applications relying on three-dimensional structure such as molecular docking. For most small molecules, conformer generators retrieve at least one bioactive-like conformation, with an atomic root-mean-square deviation (ARMSD) lower than 1 Å, among the set of low-energy conformers generated. However, there is currently no general method to prioritise these likely target-bound conformations in the ensemble. In this work, we trained atomistic neural networks (AtNNs) on 3D information of generated conformers of a curated subset of PDBbind ligands to predict the ARMSD to their closest bioactive conformation, and evaluated the early enrichment of bioactive-like conformations when ranking conformers by AtNN prediction. AtNN ranking was compared with bioactivity-unaware baselines such as ascending Sage force field energy ranking, and a slower bioactivity-based baseline ranking by ascending Torsion Fingerprint Deviation to the Maximum Common Substructure to the most similar molecule in the training set (TFD2SimRefMCS). On test sets from random ligand splits of PDBbind, ranking conformers using ComENet, the AtNN encoding the most 3D information, leads to early enrichment of bioactive-like conformations with a median BEDROC of 0.29 ± 0.02, outperforming the best bioactivity-unaware Sage energy ranking baseline (median BEDROC of 0.18 ± 0.02), and performing on a par with the bioactivity-based TFD2SimRefMCS baseline (median BEDROC of 0.31 ± 0.02). The improved performance of the AtNN and TFD2SimRefMCS baseline is mostly observed on test set ligands that bind proteins similar to proteins observed in the training set. On a more challenging subset of flexible molecules, the bioactivity-unaware baselines showed median BEDROCs up to 0.02, while AtNNs and TFD2SimRefMCS showed median BEDROCs between 0.09 and 0.13. When performing rigid ligand re-docking of PDBbind ligands with GOLD using the 1% top-ranked conformers, ComENet ranked conformers showed a higher successful docking rate than bioactivity-unaware baselines, with a rate of 0.48 ± 0.02 compared to CSD probability baseline with a rate of 0.39 ± 0.02. Similarly, on a pharmacophore searching experiment, selecting the 20% top-ranked conformers ranked by ComENet showed higher hit rate compared to baselines. Hence, the approach presented here uses AtNNs successfully to focus conformer ensembles towards bioactive-like conformations, representing an opportunity to reduce computational expense in virtual screening applications on known targets that require input conformations.
Collapse
Affiliation(s)
- Benoit Baillif
- Yusuf Hamied Department of Chemistry, University of Cambridge, Lensfield Rd, Cambridge, CB2 1EW, UK
| | - Jason Cole
- Cambridge Crystallographic Data Centre, 12 Union Road, Cambridge, CB2 1EZ, UK
| | - Ilenia Giangreco
- Cambridge Crystallographic Data Centre, 12 Union Road, Cambridge, CB2 1EZ, UK
- Exscientia plc, The Schrödinger Building, Oxford Science Park, Oxford, OX4 4GE, UK
| | - Patrick McCabe
- Cambridge Crystallographic Data Centre, 12 Union Road, Cambridge, CB2 1EZ, UK
| | - Andreas Bender
- Yusuf Hamied Department of Chemistry, University of Cambridge, Lensfield Rd, Cambridge, CB2 1EW, UK.
| |
Collapse
|