1
|
Min Y, Wei Y, Wang P, Wang X, Li H, Wu N, Bauer S, Zheng S, Shi Y, Wang Y, Wu J, Zhao D, Zeng J. From Static to Dynamic Structures: Improving Binding Affinity Prediction with Graph-Based Deep Learning. ADVANCED SCIENCE (WEINHEIM, BADEN-WURTTEMBERG, GERMANY) 2024:e2405404. [PMID: 39206846 DOI: 10.1002/advs.202405404] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 05/17/2024] [Revised: 07/29/2024] [Indexed: 09/04/2024]
Abstract
Accurate prediction of protein-ligand binding affinities is an essential challenge in structure-based drug design. Despite recent advances in data-driven methods for affinity prediction, their accuracy is still limited, partially because they only take advantage of static crystal structures while the actual binding affinities are generally determined by the thermodynamic ensembles between proteins and ligands. One effective way to approximate such a thermodynamic ensemble is to use molecular dynamics (MD) simulation. Here, an MD dataset containing 3,218 different protein-ligand complexes is curated, and Dynaformer, a graph-based deep learning model is further developed to predict the binding affinities by learning the geometric characteristics of the protein-ligand interactions from the MD trajectories. In silico experiments demonstrated that the model exhibits state-of-the-art scoring and ranking power on the CASF-2016 benchmark dataset, outperforming the methods hitherto reported. Moreover, in a virtual screening on heat shock protein 90 (HSP90) using Dynaformer, 20 candidates are identified and their binding affinities are further experimentally validated. Dynaformer displayed promising results in virtual drug screening, revealing 12 hit compounds (two are in the submicromolar range), including several novel scaffolds. Overall, these results demonstrated that the approach offer a promising avenue for accelerating the early drug discovery process.
Collapse
Affiliation(s)
- Yaosen Min
- Institute for Interdisciplinary Information Sciences, Tsinghua University, Beijing, 100084, China
| | - Ye Wei
- Institute for Interdisciplinary Information Sciences, Tsinghua University, Beijing, 100084, China
| | - Peizhuo Wang
- Institute for Interdisciplinary Information Sciences, Tsinghua University, Beijing, 100084, China
- School of Life Science and Technology, Xidian University, Xi'an, 710071, Shaanxi, China
| | - Xiaoting Wang
- School of Medicine, Tsinghua University, Beijing, 100084, China
| | - Han Li
- Institute for Interdisciplinary Information Sciences, Tsinghua University, Beijing, 100084, China
| | - Nian Wu
- Institute for Interdisciplinary Information Sciences, Tsinghua University, Beijing, 100084, China
| | - Stefan Bauer
- Department of Intelligent Systems, KTH, Stockholm, 10044, Sweden
| | | | - Yu Shi
- Microsoft Research Asia, Beijing, 100080, China
| | - Yingheng Wang
- Department of Electrical Engineering, Tsinghua University, Beijing, 100084, China
| | - Ji Wu
- Department of Electrical Engineering, Tsinghua University, Beijing, 100084, China
| | - Dan Zhao
- Institute for Interdisciplinary Information Sciences, Tsinghua University, Beijing, 100084, China
| | - Jianyang Zeng
- School of Engineering, Westlake University, Hangzhou, 310030, China
- Research Center for Industries of the Future, Westlake University, Hangzhou, 310030, China
| |
Collapse
|
2
|
Durairaj J, de Ridder D, van Dijk AD. Beyond sequence: Structure-based machine learning. Comput Struct Biotechnol J 2022; 21:630-643. [PMID: 36659927 PMCID: PMC9826903 DOI: 10.1016/j.csbj.2022.12.039] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/26/2022] [Revised: 12/21/2022] [Accepted: 12/21/2022] [Indexed: 12/31/2022] Open
Abstract
Recent breakthroughs in protein structure prediction demarcate the start of a new era in structural bioinformatics. Combined with various advances in experimental structure determination and the uninterrupted pace at which new structures are published, this promises an age in which protein structure information is as prevalent and ubiquitous as sequence. Machine learning in protein bioinformatics has been dominated by sequence-based methods, but this is now changing to make use of the deluge of rich structural information as input. Machine learning methods making use of structures are scattered across literature and cover a number of different applications and scopes; while some try to address questions and tasks within a single protein family, others aim to capture characteristics across all available proteins. In this review, we look at the variety of structure-based machine learning approaches, how structures can be used as input, and typical applications of these approaches in protein biology. We also discuss current challenges and opportunities in this all-important and increasingly popular field.
Collapse
Affiliation(s)
- Janani Durairaj
- Biozentrum, University of Basel, Basel, Switzerland
- Bioinformatics Group, Department of Plant Sciences, Wageningen University and Research, Wageningen, the Netherlands
| | - Dick de Ridder
- Bioinformatics Group, Department of Plant Sciences, Wageningen University and Research, Wageningen, the Netherlands
| | - Aalt D.J. van Dijk
- Bioinformatics Group, Department of Plant Sciences, Wageningen University and Research, Wageningen, the Netherlands
| |
Collapse
|
3
|
DFT calculations of electronic structure evaluation and intermolecular interactions of p53-derived peptides with cytotoxic effect on breast cancer. Theor Chem Acc 2021. [DOI: 10.1007/s00214-021-02822-0] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/20/2022]
|
4
|
Fernández A. Artificial Intelligence Deconstructs Drug Targeting In Vivo by Leveraging a Transformer Platform. ACS Med Chem Lett 2021; 12:1052-1055. [PMID: 34267868 DOI: 10.1021/acsmedchemlett.1c00237] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/29/2022] Open
Abstract
Lead optimization in structure-based drug design ultimately requires that the therapeutic agent be evaluated in the cellular context. However, the in vivo control of the target structure remains unyielding to computational modeling. This situation may change as transformer technologies enable a deconstruction of in vivo cooperativity steering drug-induced protein folding.
Collapse
Affiliation(s)
- Ariel Fernández
- Daruma Institute for AI in Pharmaceutical Research, AF Innovation Pharma Consultancy, GmbH, 4000 Pemberton Court, Winston-Salem, North Carolina 27106, United States
- CONICET/INQUISUR, National Research Council for Science and Technology, Buenos Aires 1033, Argentina
| |
Collapse
|
5
|
Fernández A. Artificial Intelligence Set to Reverse Engineer Drug Targeting in the Cell. ACS Pharmacol Transl Sci 2021; 4:1256-1259. [PMID: 34151218 DOI: 10.1021/acsptsci.1c00107] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/13/2021] [Indexed: 11/28/2022]
Abstract
Therapeutic drugs are required to target proteins in the cell, not in vitro. Yet, drug-induced protein folding in vivo is off limits to computational modeling efforts. This situation may change as artificial intelligence empowers molecular dynamics and enables the deconstruction of in vivo cooperativity for structural adaptation.
Collapse
Affiliation(s)
- Ariel Fernández
- Daruma Institute for AI in Pharmaceutical Research, AF Innovation Pharma Consultancy, GmbH, 4000 Pemberton Court, Winston-Salem, North Carolina 27106, United States.,CONICET, Argentine National Research Council, Buenos Aires 1033, Argentina
| |
Collapse
|
6
|
Liu PR, Lu L, Zhang JY, Huo TT, Liu SX, Ye ZW. Application of Artificial Intelligence in Medicine: An Overview. Curr Med Sci 2021; 41:1105-1115. [PMID: 34874486 PMCID: PMC8648557 DOI: 10.1007/s11596-021-2474-3] [Citation(s) in RCA: 64] [Impact Index Per Article: 21.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/04/2020] [Accepted: 12/01/2020] [Indexed: 02/06/2023]
Abstract
Artificial intelligence (AI) is a new technical discipline that uses computer technology to research and develop the theory, method, technique, and application system for the simulation, extension, and expansion of human intelligence. With the assistance of new AI technology, the traditional medical environment has changed a lot. For example, a patient's diagnosis based on radiological, pathological, endoscopic, ultrasonographic, and biochemical examinations has been effectively promoted with a higher accuracy and a lower human workload. The medical treatments during the perioperative period, including the preoperative preparation, surgical period, and postoperative recovery period, have been significantly enhanced with better surgical effects. In addition, AI technology has also played a crucial role in medical drug production, medical management, and medical education, taking them into a new direction. The purpose of this review is to introduce the application of AI in medicine and to provide an outlook of future trends.
Collapse
Affiliation(s)
- Peng-ran Liu
- Department of Orthopedics, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, 430022 China
| | - Lin Lu
- Department of Orthopedics, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, 430022 China
| | - Jia-yao Zhang
- Department of Orthopedics, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, 430022 China
| | - Tong-tong Huo
- Department of Orthopedics, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, 430022 China
| | - Song-xiang Liu
- Department of Orthopedics, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, 430022 China
| | - Zhe-wei Ye
- Department of Orthopedics, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, 430022 China
| |
Collapse
|
7
|
Fernández A. Targeted Disassembling of SARS-CoV-2 as It Gets Ready for Cell Penetration. ACS Med Chem Lett 2020; 11:2055-2057. [PMID: 33214807 DOI: 10.1021/acsmedchemlett.0c00548] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/21/2020] [Accepted: 10/26/2020] [Indexed: 01/17/2023] Open
Affiliation(s)
- Ariel Fernández
- Daruma Institute for AI in Pharmaceutical Research, AF Innovation Pharma Consultancy, 4000 Pemberton Court, Winston-Salem, North Carolina 27106, United States
| |
Collapse
|