1
|
Wang C, Ong HH, Chiba S, Rajapakse JC. GLDM: hit molecule generation with constrained graph latent diffusion model. Brief Bioinform 2024; 25:bbae142. [PMID: 38581415 PMCID: PMC10998532 DOI: 10.1093/bib/bbae142] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/19/2023] [Revised: 03/08/2024] [Accepted: 03/03/2024] [Indexed: 04/08/2024] Open
Abstract
Discovering hit molecules with desired biological activity in a directed manner is a promising but profound task in computer-aided drug discovery. Inspired by recent generative AI approaches, particularly Diffusion Models (DM), we propose Graph Latent Diffusion Model (GLDM)-a latent DM that preserves both the effectiveness of autoencoders of compressing complex chemical data and the DM's capabilities of generating novel molecules. Specifically, we first develop an autoencoder to encode the molecular data into low-dimensional latent representations and then train the DM on the latent space to generate molecules inducing targeted biological activity defined by gene expression profiles. Manipulating DM in the latent space rather than the input space avoids complicated operations to map molecule decomposition and reconstruction to diffusion processes, and thus improves training efficiency. Experiments show that GLDM not only achieves outstanding performances on molecular generation benchmarks, but also generates samples with optimal chemical properties and potentials to induce desired biological activity.
Collapse
Affiliation(s)
- Conghao Wang
- School of Computer Science and Engineering, Nanyang Technological University, 50 Nanyang Ave, 639798, Singapore
| | - Hiok Hian Ong
- School of Computer Science and Engineering, Nanyang Technological University, 50 Nanyang Ave, 639798, Singapore
| | - Shunsuke Chiba
- School of Chemistry, Chemical Engineering and Biotechnology, Nanyang Technological University, 21 Nanyang Link, 637371, Singapore
| | - Jagath C Rajapakse
- School of Computer Science and Engineering, Nanyang Technological University, 50 Nanyang Ave, 639798, Singapore
| |
Collapse
|
2
|
Li M, Lan X, Lu X, Zhang J. A Structure-Based Allosteric Modulator Design Paradigm. HEALTH DATA SCIENCE 2023; 3:0094. [PMID: 38487194 PMCID: PMC10904074 DOI: 10.34133/hds.0094] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 07/02/2023] [Accepted: 10/11/2023] [Indexed: 03/17/2024]
Abstract
Importance: Allosteric drugs bound to topologically distal allosteric sites hold a substantial promise in modulating therapeutic targets deemed undruggable at their orthosteric sites. Traditionally, allosteric modulator discovery has predominantly relied on serendipitous high-throughput screening. Nevertheless, the landscape has undergone a transformative shift due to recent advancements in our understanding of allosteric modulation mechanisms, coupled with a significant increase in the accessibility of allosteric structural data. These factors have extensively promoted the development of various computational methodologies, especially for machine-learning approaches, to guide the rational design of structure-based allosteric modulators. Highlights: We here presented a comprehensive structure-based allosteric modulator design paradigm encompassing 3 critical stages: drug target acquisition, allosteric binding site, and modulator discovery. The recent advances in computational methods in each stage are encapsulated. Furthermore, we delve into analyzing the successes and obstacles encountered in the rational design of allosteric modulators. Conclusion: The structure-based allosteric modulator design paradigm holds immense potential for the rational design of allosteric modulators. We hope that this review would heighten awareness of the use of structure-based computational methodologies in advancing the field of allosteric drug discovery.
Collapse
Affiliation(s)
- Mingyu Li
- College of Pharmacy,
Ningxia Medical University, Yinchuan, NingxiaHui Autonomous Region, China
- State Key Laboratory of Medical Genomics, National Research Center for Translational Medicine at Shanghai, Ruijin Hospital,
Shanghai Jiao Tong University School of Medicine, Shanghai, China
- Medicinal Chemistry and Bioinformatics Center,
Shanghai Jiao Tong University School of Medicine, Shanghai 200025, China
| | - Xiaobin Lan
- College of Pharmacy,
Ningxia Medical University, Yinchuan, NingxiaHui Autonomous Region, China
- Medicinal Chemistry and Bioinformatics Center,
Shanghai Jiao Tong University School of Medicine, Shanghai 200025, China
| | - Xun Lu
- College of Pharmacy,
Ningxia Medical University, Yinchuan, NingxiaHui Autonomous Region, China
- State Key Laboratory of Medical Genomics, National Research Center for Translational Medicine at Shanghai, Ruijin Hospital,
Shanghai Jiao Tong University School of Medicine, Shanghai, China
- Medicinal Chemistry and Bioinformatics Center,
Shanghai Jiao Tong University School of Medicine, Shanghai 200025, China
| | - Jian Zhang
- College of Pharmacy,
Ningxia Medical University, Yinchuan, NingxiaHui Autonomous Region, China
- State Key Laboratory of Medical Genomics, National Research Center for Translational Medicine at Shanghai, Ruijin Hospital,
Shanghai Jiao Tong University School of Medicine, Shanghai, China
- Medicinal Chemistry and Bioinformatics Center,
Shanghai Jiao Tong University School of Medicine, Shanghai 200025, China
| |
Collapse
|
3
|
Xiao S, Verkhivker GM, Tao P. Machine learning and protein allostery. Trends Biochem Sci 2023; 48:375-390. [PMID: 36564251 PMCID: PMC10023316 DOI: 10.1016/j.tibs.2022.12.001] [Citation(s) in RCA: 4] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/04/2022] [Revised: 11/16/2022] [Accepted: 12/02/2022] [Indexed: 12/23/2022]
Abstract
The fundamental biological importance and complexity of allosterically regulated proteins stem from their central role in signal transduction and cellular processes. Recently, machine-learning approaches have been developed and actively deployed to facilitate theoretical and experimental studies of protein dynamics and allosteric mechanisms. In this review, we survey recent developments in applications of machine-learning methods for studies of allosteric mechanisms, prediction of allosteric effects and allostery-related physicochemical properties, and allosteric protein engineering. We also review the applications of machine-learning strategies for characterization of allosteric mechanisms and drug design targeting SARS-CoV-2. Continuous development and task-specific adaptation of machine-learning methods for protein allosteric mechanisms will have an increasingly important role in bridging a wide spectrum of data-intensive experimental and theoretical technologies.
Collapse
Affiliation(s)
- Sian Xiao
- Department of Chemistry, Center for Research Computing, Center for Drug Discovery, Design, and Delivery (CD4), Southern Methodist University, Dallas, TX 75205, USA.
| | - Gennady M Verkhivker
- Graduate Program in Computational and Data Sciences, Schmid College of Science and Technology, Chapman University, Orange, CA 92866, USA; Department of Biomedical and Pharmaceutical Sciences, Chapman University School of Pharmacy, Irvine, CA 92618, USA
| | - Peng Tao
- Department of Chemistry, Center for Research Computing, Center for Drug Discovery, Design, and Delivery (CD4), Southern Methodist University, Dallas, TX 75205, USA.
| |
Collapse
|
4
|
Bian Y, Kwon JJ, Liu C, Margiotta E, Shekhar M, Gould AE. Target-driven machine learning-enabled virtual screening (TAME-VS) platform for early-stage hit identification. Front Mol Biosci 2023; 10:1163536. [PMID: 36994428 PMCID: PMC10040869 DOI: 10.3389/fmolb.2023.1163536] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/10/2023] [Accepted: 02/28/2023] [Indexed: 03/15/2023] Open
Abstract
High-throughput screening (HTS) methods enable the empirical evaluation of a large scale of compounds and can be augmented by virtual screening (VS) techniques to save time and money by using potential active compounds for experimental testing. Structure-based and ligand-based virtual screening approaches have been extensively studied and applied in drug discovery practice with proven outcomes in advancing candidate molecules. However, the experimental data required for VS are expensive, and hit identification in an effective and efficient manner is particularly challenging during early-stage drug discovery for novel protein targets. Herein, we present our TArget-driven Machine learning-Enabled VS (TAME-VS) platform, which leverages existing chemical databases of bioactive molecules to modularly facilitate hit finding. Our methodology enables bespoke hit identification campaigns through a user-defined protein target. The input target ID is used to perform a homology-based target expansion, followed by compound retrieval from a large compilation of molecules with experimentally validated activity. Compounds are subsequently vectorized and adopted for machine learning (ML) model training. These machine learning models are deployed to perform model-based inferential virtual screening, and compounds are nominated based on predicted activity. Our platform was retrospectively validated across ten diverse protein targets and demonstrated clear predictive power. The implemented methodology provides a flexible and efficient approach that is accessible to a wide range of users. The TAME-VS platform is publicly available at https://github.com/bymgood/Target-driven-ML-enabled-VS to facilitate early-stage hit identification.
Collapse
Affiliation(s)
- Yuemin Bian
- Center for the Development of Therapeutics, Broad Institute of MIT and Harvard, Cambridge, MA, United States
- *Correspondence: Yuemin Bian,
| | - Jason J. Kwon
- Cancer Program, Broad Institute of MIT and Harvard, Cambridge, MA, United States
- Department of Medical Oncology, Dana-Farber Cancer Institute, Boston, MA, United States
- Harvard Medical School, Boston, MA, United States
| | - Cong Liu
- Center for the Development of Therapeutics, Broad Institute of MIT and Harvard, Cambridge, MA, United States
| | - Enrico Margiotta
- Center for the Development of Therapeutics, Broad Institute of MIT and Harvard, Cambridge, MA, United States
| | - Mrinal Shekhar
- Center for the Development of Therapeutics, Broad Institute of MIT and Harvard, Cambridge, MA, United States
| | - Alexandra E. Gould
- Center for the Development of Therapeutics, Broad Institute of MIT and Harvard, Cambridge, MA, United States
| |
Collapse
|
5
|
Ferranti AS, Foster DJ. Cannabinoid type-2 receptors: An emerging target for regulating schizophrenia-relevant brain circuits. Front Neurosci 2022; 16:925792. [PMID: 36033626 PMCID: PMC9403189 DOI: 10.3389/fnins.2022.925792] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/21/2022] [Accepted: 07/27/2022] [Indexed: 11/17/2022] Open
Abstract
Although the cannabinoid type-2 receptor (CB2) is highly expressed in the immune system, emerging evidence points to CB2 playing a key role in regulating neuronal function in the central nervous system. Recent anatomical studies, combined with electrophysiological studies, indicate that CB2 receptors are expressed in specific dopaminergic and glutamatergic brain circuits that are hyperactive in schizophrenia patients. The ability of CB2 receptors to inhibit dopaminergic and hippocampal circuits, combined with the anti-inflammatory effects of CB2 receptor activation, make this receptor an intriguing target for treating schizophrenia, a disease where novel interventions that move beyond dopamine receptor antagonists are desperately needed. The development of new CB2-related pharmacological and genetic tools, including the first small molecule positive allosteric modulator of CB2 receptors, has greatly advanced our understanding of this receptor. While more work is needed to further elucidate the translational value of selectively targeting CB2 receptors with respect to schizophrenia, the studies discussed below could suggest that CB2 receptors are anatomically located in schizophrenia-relevant circuits, where the physiological consequence of CB2 receptor activation could correct circuit-based deficits commonly associated with positive and cognitive deficits.
Collapse
Affiliation(s)
- Anthony S. Ferranti
- Department of Pharmacology, Vanderbilt University, Nashville, TN, United States
- Warren Center for Neuroscience Drug Discovery, Vanderbilt University, Nashville, TN, United States
| | - Daniel J. Foster
- Department of Pharmacology, Physiology and Neuroscience, University of South Carolina School of Medicine, Columbia, SC, United States
| |
Collapse
|