1
|
Liu Y, Xia X, Gong Y, Song B, Zeng X. SSR-DTA: Substructure-aware multi-layer graph neural networks for drug-target binding affinity prediction. Artif Intell Med 2024; 157:102983. [PMID: 39321746 DOI: 10.1016/j.artmed.2024.102983] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/12/2023] [Revised: 09/10/2024] [Accepted: 09/13/2024] [Indexed: 09/27/2024]
Abstract
Accurate prediction of drug-target binding affinity (DTA) is essential in the field of drug discovery. Recently, scientists have been attempting to utilize artificial intelligence prediction to screen out a significant number of ineffective compounds, thereby mitigating labor and financial losses. While graph neural networks (GNNs) have been applied to DTA, existing GNNs have limitations in effectively extracting substructural features across various sizes. Functional groups play a crucial role in modulating molecular properties, but existing GNNs struggle with feature extraction from certain motifs due to scale mismatches. Additionally, sequence-based models for target proteins lack the integration of structural information. To address these limitations, we present SSR-DTA, a multi-layer graph network capable of adapting to diverse structural sizes, which can extract richer biological features, thereby improving the robustness and accuracy of predictions. Multi-layer GNNs enable the capture of molecular motifs across different scales, ranging from atomic to macrocyclic motifs. Furthermore, we introduce BiGNN to simultaneously learn sequence and structural information. Sequence information corresponds to the primary structure of proteins, while graph information represents the tertiary structure. BiGNN assimilates richer information compared to sequence-based methods while mitigating the impact of errors from predicted structures, resulting in more accurate predictions. Through rigorous experimental evaluations conducted on four benchmark datasets, we demonstrate the superiority of SSR-DTA over state-of-the-art models. Particularly, in comparison to state-of-the-art models, SSR-DTA demonstrates an impressive 20% reduction in mean squared error on the Davis dataset and a 5% reduction on the KIBA dataset, underscoring its potential as a valuable tool for advancing DTA prediction.
Collapse
Affiliation(s)
- Yuansheng Liu
- College of Computer Science and Electronic Engineering, Hunan University, Changsha, 410086, Hunan, China; Key Laboratory of Intelligent Computing & Signal Processing of Ministry of Education, Anhui University, Hefei, 230601, Anhui, China
| | - Xinyan Xia
- College of Computer Science and Electronic Engineering, Hunan University, Changsha, 410086, Hunan, China
| | - Yongshun Gong
- School of Software, Shandong University, Jinan, 250100, Shandong, China
| | - Bosheng Song
- College of Computer Science and Electronic Engineering, Hunan University, Changsha, 410086, Hunan, China
| | - Xiangxiang Zeng
- College of Computer Science and Electronic Engineering, Hunan University, Changsha, 410086, Hunan, China.
| |
Collapse
|
2
|
Nguyen VTD, Hy TS. Multimodal pretraining for unsupervised protein representation learning. Biol Methods Protoc 2024; 9:bpae043. [PMID: 38983679 PMCID: PMC11233121 DOI: 10.1093/biomethods/bpae043] [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: 04/15/2024] [Revised: 05/30/2024] [Accepted: 06/12/2024] [Indexed: 07/11/2024] Open
Abstract
Proteins are complex biomolecules essential for numerous biological processes, making them crucial targets for advancements in molecular biology, medical research, and drug design. Understanding their intricate, hierarchical structures, and functions is vital for progress in these fields. To capture this complexity, we introduce Multimodal Protein Representation Learning (MPRL), a novel framework for symmetry-preserving multimodal pretraining that learns unified, unsupervised protein representations by integrating primary and tertiary structures. MPRL employs Evolutionary Scale Modeling (ESM-2) for sequence analysis, Variational Graph Auto-Encoders (VGAE) for residue-level graphs, and PointNet Autoencoder (PAE) for 3D point clouds of atoms, each designed to capture the spatial and evolutionary intricacies of proteins while preserving critical symmetries. By leveraging Auto-Fusion to synthesize joint representations from these pretrained models, MPRL ensures robust and comprehensive protein representations. Our extensive evaluation demonstrates that MPRL significantly enhances performance in various tasks such as protein-ligand binding affinity prediction, protein fold classification, enzyme activity identification, and mutation stability prediction. This framework advances the understanding of protein dynamics and facilitates future research in the field. Our source code is publicly available at https://github.com/HySonLab/Protein_Pretrain.
Collapse
Affiliation(s)
| | - Truong Son Hy
- FPT Software AI Center, HCMC, Hanoi, Vietnam
- Department of Mathematics and Computer Science, Indiana State University, Terre Haute, IN, 47809, United States
| |
Collapse
|
3
|
Qiu X, Wang H, Tan X, Fang Z. G-K BertDTA: A graph representation learning and semantic embedding-based framework for drug-target affinity prediction. Comput Biol Med 2024; 173:108376. [PMID: 38552281 DOI: 10.1016/j.compbiomed.2024.108376] [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: 12/21/2023] [Revised: 03/21/2024] [Accepted: 03/24/2024] [Indexed: 04/17/2024]
Abstract
Developing new drugs is costly, time-consuming, and risky. Drug-target affinity (DTA), indicating the binding capability between drugs and target proteins, is a crucial indicator for drug development. Accurately predicting interaction strength between new drug-target pairs by analyzing previous experiments aids in screening potential drug molecules, repurposing them, and developing safe and effective medicines. Existing computational models for DTA prediction rely on strings or single-graph neural networks, lacking consideration of protein structure and molecular semantic information, leading to limited accuracy. Our experiments demonstrate that string-based methods may overlook protein conformations, causing a high root mean square error (RMSE) of 3.584 in affinity due to a lack of spatial context. Single graph networks also underperform on topology features, with a 6% lower confidence interval (CI) for activity classification. Absent semantic information also limits generalization across diverse compounds, resulting in 18% increment in RMSE and 5% in misclassifications within quantifications study, restricting potential drug discovery. To address these limitations, we propose G-K BertDTA, a novel framework for accurate DTA prediction incorporating protein features, molecular semantic features, and molecular structural information. In this proposed model, we represent drugs as graphs, with a GIN employed to learn the molecular topological information. For the extraction of protein structural features, we utilize a DenseNet architecture. A knowledge-based BERT semantic model is incorporated to obtain rich pre-trained semantic embeddings, thereby enhancing the feature information. We extensively evaluated our proposed approach on the publicly available benchmark datasets (i.e., KIBA and Davis), and experimental results demonstrate the promising performance of our method, which consistently outperforms previous state-of-the-art approaches. Code is available at https://github.com/AmbitYuki/G-K-BertDTA.
Collapse
Affiliation(s)
- Xihe Qiu
- School of Electronic and Electrical Engineering, Shanghai University of Engineering Science, Shanghai, China
| | - Haoyu Wang
- School of Electronic and Electrical Engineering, Shanghai University of Engineering Science, Shanghai, China
| | - Xiaoyu Tan
- INF Technology (Shanghai) Co., Ltd., Shanghai, China
| | - Zhijun Fang
- School of Computer Science and Technology, Donghua University, Shanghai, China.
| |
Collapse
|
4
|
Oliveira PF, Guedes RC, Falcao AO. Inferring molecular inhibition potency with AlphaFold predicted structures. Sci Rep 2024; 14:8252. [PMID: 38589418 PMCID: PMC11001998 DOI: 10.1038/s41598-024-58394-z] [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: 12/03/2023] [Accepted: 03/28/2024] [Indexed: 04/10/2024] Open
Abstract
Even though in silico drug ligand-based methods have been successful in predicting interactions with known target proteins, they struggle with new, unassessed targets. To address this challenge, we propose an approach that integrates structural data from AlphaFold 2 predicted protein structures into machine learning models. Our method extracts 3D structural protein fingerprints and combines them with ligand structural data to train a single machine learning model. This model captures the relationship between ligand properties and the unique structural features of various target proteins, enabling predictions for never before tested molecules and protein targets. To assess our model, we used a dataset of 144 Human G-protein Coupled Receptors (GPCRs) with over 140,000 measured inhibition constants (Ki) values. Results strongly suggest that our approach performs as well as state-of-the-art ligand-based methods. In a second modeling approach that used 129 targets for training and a separate test set of 15 different protein targets, our model correctly predicted interactions for 73% of targets, with explained variances exceeding 0.50 in 22% of cases. Our findings further verified that the usage of experimentally determined protein structures produced models that were statistically indistinct from the Alphafold synthetic structures. This study presents a proteo-chemometric drug screening approach that uses a simple and scalable method for extracting protein structural information for usage in machine learning models capable of predicting protein-molecule interactions even for orphan targets.
Collapse
Affiliation(s)
- Pedro F Oliveira
- Lasige, Faculdade de Ciências, Universidade de Lisboa, 1749-016 Lisboa, Portugal
| | - Rita C Guedes
- Research Institute for Medicines (iMed.ULisboa), Faculdade de Farmácia, Universidade de Lisboa, Av. Prof. Gama Pinto, 1649-003 Lisboa, Portugal
| | - Andre O Falcao
- Departamento de Informática, Faculdade de Ciências, Universidade de Lisboa, 1749-016, Lisboa, Portugal.
| |
Collapse
|
5
|
Huang J, Fang Y, Wu R, Xia T, Wang X, Jia J, Wang G. All-trans retinoic acid acts as a dual-purpose inhibitor of SARS-CoV-2 infection and inflammation. Comput Biol Med 2024; 169:107942. [PMID: 38183702 DOI: 10.1016/j.compbiomed.2024.107942] [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: 11/17/2023] [Revised: 12/16/2023] [Accepted: 01/01/2024] [Indexed: 01/08/2024]
Abstract
Coronavirus disease 2019 (COVID-19) was an epidemic that effected human health caused by SARS-CoV-2 infection. All-trans retinoic acid (ATRA) has anti-inflammatory capability. In this article, we evaluated the effectiveness and revealed the molecular mechanism of ATRA for treating SARS-CoV-2 using deep learning, in vitro studies, multi-scale molecular modeling, and network pharmacology. The DeepDTA model suggested that ATRA would be effective against COVID-19. In vitro studies confirmed the antiviral activity of ATRA. Subsequently, multi-scale molecular modeling indicated that ATRA could binding to angiotensin converting enzyme 2 (ACE2), 3C-like protease (3CLpro), RNA dependent RNA polymerase (RdRp), helicase, and 3'-to-5' exonuclease by non-covalent interactions. Additionally, network pharmacology suggested that ATRA alleviated inflammatory response by regulating the IL-17 signaling pathway and binding with TNF, PTGS2, and MAPK1 directly. In summary, our findings provide the first evidence that ATRA suppresses the entry and replication of SARS-CoV-2, and regulates inflammatory response of host cells.
Collapse
Affiliation(s)
- Juanjuan Huang
- Department of Pathogen Biology, The Key Laboratory of Zoonosis, Chinese Ministry of Education, College of Basic Medicine, Jilin University, Changchun, 130021, China; Department of Computational Mathematics, School of Mathematics, Jilin University, Changchun, 130012, China
| | - Yabo Fang
- Department of Computational Mathematics, School of Mathematics, Jilin University, Changchun, 130012, China
| | - Runze Wu
- Department of Probability Statistics and Data Science, School of Mathematics, Jilin University, Changchun, 130012, China
| | - Tingzheng Xia
- Department of Pathogen Biology, The Key Laboratory of Zoonosis, Chinese Ministry of Education, College of Basic Medicine, Jilin University, Changchun, 130021, China
| | - Xuan Wang
- Department of Pathogen Biology, The Key Laboratory of Zoonosis, Chinese Ministry of Education, College of Basic Medicine, Jilin University, Changchun, 130021, China
| | - Jiwei Jia
- Department of Computational Mathematics, School of Mathematics, Jilin University, Changchun, 130012, China; Jilin National Applied Mathematical Center, Jilin University, Changchun, 130012, China.
| | - Guoqing Wang
- Department of Pathogen Biology, The Key Laboratory of Zoonosis, Chinese Ministry of Education, College of Basic Medicine, Jilin University, Changchun, 130021, China.
| |
Collapse
|
6
|
Zhu Z, Yao Z, Zheng X, Qi G, Li Y, Mazur N, Gao X, Gong Y, Cong B. Drug-target affinity prediction method based on multi-scale information interaction and graph optimization. Comput Biol Med 2023; 167:107621. [PMID: 37907030 DOI: 10.1016/j.compbiomed.2023.107621] [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: 07/18/2023] [Revised: 10/16/2023] [Accepted: 10/23/2023] [Indexed: 11/02/2023]
Abstract
Drug-target affinity (DTA) prediction as an emerging and effective method is widely applied to explore the strength of drug-target interactions in drug development research. By predicting these interactions, researchers can assess the potential efficacy and safety of candidate drugs at an early stage, narrowing down the search space for therapeutic targets and accelerating the discovery and development of new drugs. However, existing DTA prediction models mainly use graphical representations of drug molecules, which lack information on interactions between individual substructures, thus affecting prediction accuracy and model interpretability. Therefore, transformer and diffusion on drug graphs in DTA prediction (TDGraphDTA) are introduced to predict drug-target interactions using multi-scale information interaction and graph optimization. An interactive module is integrated into feature extraction of drug and target features at different granularity levels. A diffusion model-based graph optimization module is proposed to improve the representation of molecular graph structures and enhance the interpretability of graph representations while obtaining optimal feature representations. In addition, TDGraphDTA improves the accuracy and reliability of predictions by capturing relationships and contextual information between molecular substructures. The performance of the proposed TDGraphDTA in DTA prediction was verified on three publicly available benchmark datasets (Davis, Metz, and KIBA). Compared with state-of-the-art baseline models, it achieved better results in terms of consistency index, R-squared, etc. Furthermore, compared with some existing methods, the proposed TDGraphDTA is demonstrated to have better structure capturing capabilities by visualizing the feature capturing capabilities of the model using Grad-AAM toxicity labels in the ToxCast dataset. The corresponding source codes are available at https://github.com/Lamouryz/TDGraph.
Collapse
Affiliation(s)
- Zhiqin Zhu
- College of Automation, Chongqing University of Posts and Telecommunications, Chongqing, 400065, China.
| | - Zheng Yao
- College of Automation, Chongqing University of Posts and Telecommunications, Chongqing, 400065, China.
| | - Xin Zheng
- College of Automation, Chongqing University of Posts and Telecommunications, Chongqing, 400065, China.
| | - Guanqiu Qi
- Computer Information Systems Department, State University of New York at Buffalo State, Buffalo, NY 14222, USA.
| | - Yuanyuan Li
- College of Automation, Chongqing University of Posts and Telecommunications, Chongqing, 400065, China.
| | - Neal Mazur
- Computer Information Systems Department, State University of New York at Buffalo State, Buffalo, NY 14222, USA.
| | - Xinbo Gao
- College of Automation, Chongqing University of Posts and Telecommunications, Chongqing, 400065, China.
| | - Yifei Gong
- Faculty of applied science & engineering, the Edward S. Rogers Sr. Department of Electrical & Computer Engineering (ECE), University of Toronto at Toronto, ON M5S, Canada.
| | - Baisen Cong
- Diagnostics Digital, DH(Shanghai) Diagnostics Co, Ltd, a Danaher company, Shanghai, 200335, China.
| |
Collapse
|