1
|
Sadeghi S, Bui A, Forooghi A, Lu J, Ngom A. Can large language models understand molecules? BMC Bioinformatics 2024; 25:225. [PMID: 38926641 DOI: 10.1186/s12859-024-05847-x] [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: 12/31/2023] [Accepted: 06/18/2024] [Indexed: 06/28/2024] Open
Abstract
PURPOSE Large Language Models (LLMs) like Generative Pre-trained Transformer (GPT) from OpenAI and LLaMA (Large Language Model Meta AI) from Meta AI are increasingly recognized for their potential in the field of cheminformatics, particularly in understanding Simplified Molecular Input Line Entry System (SMILES), a standard method for representing chemical structures. These LLMs also have the ability to decode SMILES strings into vector representations. METHOD We investigate the performance of GPT and LLaMA compared to pre-trained models on SMILES in embedding SMILES strings on downstream tasks, focusing on two key applications: molecular property prediction and drug-drug interaction prediction. RESULTS We find that SMILES embeddings generated using LLaMA outperform those from GPT in both molecular property and DDI prediction tasks. Notably, LLaMA-based SMILES embeddings show results comparable to pre-trained models on SMILES in molecular prediction tasks and outperform the pre-trained models for the DDI prediction tasks. CONCLUSION The performance of LLMs in generating SMILES embeddings shows great potential for further investigation of these models for molecular embedding. We hope our study bridges the gap between LLMs and molecular embedding, motivating additional research into the potential of LLMs in the molecular representation field. GitHub: https://github.com/sshaghayeghs/LLaMA-VS-GPT .
Collapse
Affiliation(s)
- Shaghayegh Sadeghi
- School of Computer Science, Univeristy of Windsor, Sunset Ave, Windsor, ON, N9B 3P4, Canada.
| | - Alan Bui
- School of Computer Science, Univeristy of Windsor, Sunset Ave, Windsor, ON, N9B 3P4, Canada
| | - Ali Forooghi
- School of Computer Science, Univeristy of Windsor, Sunset Ave, Windsor, ON, N9B 3P4, Canada
| | - Jianguo Lu
- School of Computer Science, Univeristy of Windsor, Sunset Ave, Windsor, ON, N9B 3P4, Canada
| | - Alioune Ngom
- School of Computer Science, Univeristy of Windsor, Sunset Ave, Windsor, ON, N9B 3P4, Canada
| |
Collapse
|
2
|
Zhang H, Liu X, Cheng W, Wang T, Chen Y. Prediction of drug-target binding affinity based on deep learning models. Comput Biol Med 2024; 174:108435. [PMID: 38608327 DOI: 10.1016/j.compbiomed.2024.108435] [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: 01/29/2024] [Revised: 04/05/2024] [Accepted: 04/07/2024] [Indexed: 04/14/2024]
Abstract
The prediction of drug-target binding affinity (DTA) plays an important role in drug discovery. Computerized virtual screening techniques have been used for DTA prediction, greatly reducing the time and economic costs of drug discovery. However, these techniques have not succeeded in reversing the low success rate of new drug development. In recent years, the continuous development of deep learning (DL) technology has brought new opportunities for drug discovery through the DTA prediction. This shift has moved the prediction of DTA from traditional machine learning methods to DL. The DL frameworks used for DTA prediction include convolutional neural networks (CNN), graph convolutional neural networks (GCN), and recurrent neural networks (RNN), and reinforcement learning (RL), among others. This review article summarizes the available literature on DTA prediction using DL models, including DTA quantification metrics and datasets, and DL algorithms used for DTA prediction (including input representation of models, neural network frameworks, valuation indicators, and model interpretability). In addition, the opportunities, challenges, and prospects of the application of DL frameworks for DTA prediction in the field of drug discovery are discussed.
Collapse
Affiliation(s)
- Hao Zhang
- College of Science, Nanjing Agricultural University, Nanjing, 210095, China
| | - Xiaoqian Liu
- College of Science, Nanjing Agricultural University, Nanjing, 210095, China
| | - Wenya Cheng
- College of Science, Nanjing Agricultural University, Nanjing, 210095, China
| | - Tianshi Wang
- College of Science, Nanjing Agricultural University, Nanjing, 210095, China
| | - Yuanyuan Chen
- College of Science, Nanjing Agricultural University, Nanjing, 210095, China.
| |
Collapse
|
3
|
Kengkanna A, Ohue M. Enhancing property and activity prediction and interpretation using multiple molecular graph representations with MMGX. Commun Chem 2024; 7:74. [PMID: 38580841 PMCID: PMC10997661 DOI: 10.1038/s42004-024-01155-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: 12/08/2023] [Accepted: 03/18/2024] [Indexed: 04/07/2024] Open
Abstract
Graph Neural Networks (GNNs) excel in compound property and activity prediction, but the choice of molecular graph representations significantly influences model learning and interpretation. While atom-level molecular graphs resemble natural topology, they overlook key substructures or functional groups and their interpretation partially aligns with chemical intuition. Recent research suggests alternative representations using reduced molecular graphs to integrate higher-level chemical information and leverages both representations for model. However, there is a lack of studies about applicability and impact of different molecular graphs on model learning and interpretation. Here, we introduce MMGX (Multiple Molecular Graph eXplainable discovery), investigating the effects of multiple molecular graphs, including Atom, Pharmacophore, JunctionTree, and FunctionalGroup, on model learning and interpretation with various perspectives. Our findings indicate that multiple graphs relatively improve model performance, but in varying degrees depending on datasets. Interpretation from multiple graphs in different views provides more comprehensive features and potential substructures consistent with background knowledge. These results help to understand model decisions and offer valuable insights for subsequent tasks. The concept of multiple molecular graph representations and diverse interpretation perspectives has broad applicability across tasks, architectures, and explanation techniques, enhancing model learning and interpretation for relevant applications in drug discovery.
Collapse
Affiliation(s)
- Apakorn Kengkanna
- Department of Computer Science, School of Computing, Tokyo Institute of Technology, Kanagawa, 226-8501, Japan
| | - Masahito Ohue
- Department of Computer Science, School of Computing, Tokyo Institute of Technology, Kanagawa, 226-8501, Japan.
| |
Collapse
|
4
|
Ghandikota SK, Jegga AG. Application of artificial intelligence and machine learning in drug repurposing. PROGRESS IN MOLECULAR BIOLOGY AND TRANSLATIONAL SCIENCE 2024; 205:171-211. [PMID: 38789178 DOI: 10.1016/bs.pmbts.2024.03.030] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/26/2024]
Abstract
The purpose of drug repurposing is to leverage previously approved drugs for a particular disease indication and apply them to another disease. It can be seen as a faster and more cost-effective approach to drug discovery and a powerful tool for achieving precision medicine. In addition, drug repurposing can be used to identify therapeutic candidates for rare diseases and phenotypic conditions with limited information on disease biology. Machine learning and artificial intelligence (AI) methodologies have enabled the construction of effective, data-driven repurposing pipelines by integrating and analyzing large-scale biomedical data. Recent technological advances, especially in heterogeneous network mining and natural language processing, have opened up exciting new opportunities and analytical strategies for drug repurposing. In this review, we first introduce the challenges in repurposing approaches and highlight some success stories, including those during the COVID-19 pandemic. Next, we review some existing computational frameworks in the literature, organized on the basis of the type of biomedical input data analyzed and the computational algorithms involved. In conclusion, we outline some exciting new directions that drug repurposing research may take, as pioneered by the generative AI revolution.
Collapse
Affiliation(s)
- Sudhir K Ghandikota
- Division of Biomedical Informatics, Cincinnati Children's Hospital Medical Center, Cincinnati, OH, United States
| | - Anil G Jegga
- Division of Biomedical Informatics, Cincinnati Children's Hospital Medical Center, Cincinnati, OH, United States; Department of Pediatrics, University of Cincinnati College of Medicine, Cincinnati, OH, United States.
| |
Collapse
|
5
|
Zhao W, Yu Y, Liu G, Liang Y, Xu D, Feng X, Guan R. MSI-DTI: predicting drug-target interaction based on multi-source information and multi-head self-attention. Brief Bioinform 2024; 25:bbae238. [PMID: 38762789 PMCID: PMC11102638 DOI: 10.1093/bib/bbae238] [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: 01/29/2024] [Revised: 04/09/2024] [Accepted: 05/03/2024] [Indexed: 05/20/2024] Open
Abstract
Identifying drug-target interactions (DTIs) holds significant importance in drug discovery and development, playing a crucial role in various areas such as virtual screening, drug repurposing and identification of potential drug side effects. However, existing methods commonly exploit only a single type of feature from drugs and targets, suffering from miscellaneous challenges such as high sparsity and cold-start problems. We propose a novel framework called MSI-DTI (Multi-Source Information-based Drug-Target Interaction Prediction) to enhance prediction performance, which obtains feature representations from different views by integrating biometric features and knowledge graph representations from multi-source information. Our approach involves constructing a Drug-Target Knowledge Graph (DTKG), obtaining multiple feature representations from diverse information sources for SMILES sequences and amino acid sequences, incorporating network features from DTKG and performing an effective multi-source information fusion. Subsequently, we employ a multi-head self-attention mechanism coupled with residual connections to capture higher-order interaction information between sparse features while preserving lower-order information. Experimental results on DTKG and two benchmark datasets demonstrate that our MSI-DTI outperforms several state-of-the-art DTIs prediction methods, yielding more accurate and robust predictions. The source codes and datasets are publicly accessible at https://github.com/KEAML-JLU/MSI-DTI.
Collapse
Affiliation(s)
- Wenchuan Zhao
- Key Laboratory of Symbolic Computation and Knowledge Engineering of the Ministry of Education, College of Computer Science and Technology, Jilin University, Changchun 130012, Jilin, China
| | - Yufeng Yu
- Key Laboratory of Symbolic Computation and Knowledge Engineering of the Ministry of Education, College of Computer Science and Technology, Jilin University, Changchun 130012, Jilin, China
| | - Guosheng Liu
- Key Laboratory of Symbolic Computation and Knowledge Engineering of the Ministry of Education, College of Computer Science and Technology, Jilin University, Changchun 130012, Jilin, China
| | - Yanchun Liang
- Zhuhai Laboratory of the Key Laboratory of Symbolic Computation and Knowledge Engineering of the Ministry of Education, Zhuhai College of Science and Technology, Zhuhai 519041, China
| | - Dong Xu
- Department of Computer Science, Informatics Institute, and Christopher S. Bond Life Sciences Center, University of Missouri, Columbia, MO 65211, USA
| | - Xiaoyue Feng
- Key Laboratory of Symbolic Computation and Knowledge Engineering of the Ministry of Education, College of Computer Science and Technology, Jilin University, Changchun 130012, Jilin, China
| | - Renchu Guan
- Key Laboratory of Symbolic Computation and Knowledge Engineering of the Ministry of Education, College of Computer Science and Technology, Jilin University, Changchun 130012, Jilin, China
| |
Collapse
|
6
|
Zhang Y, Li S, Meng K, Sun S. Machine Learning for Sequence and Structure-Based Protein-Ligand Interaction Prediction. J Chem Inf Model 2024; 64:1456-1472. [PMID: 38385768 DOI: 10.1021/acs.jcim.3c01841] [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] [Indexed: 02/23/2024]
Abstract
Developing new drugs is too expensive and time -consuming. Accurately predicting the interaction between drugs and targets will likely change how the drug is discovered. Machine learning-based protein-ligand interaction prediction has demonstrated significant potential. In this paper, computational methods, focusing on sequence and structure to study protein-ligand interactions, are examined. Therefore, this paper starts by presenting an overview of the data sets applied in this area, as well as the various approaches applied for representing proteins and ligands. Then, sequence-based and structure-based classification criteria are subsequently utilized to categorize and summarize both the classical machine learning models and deep learning models employed in protein-ligand interaction studies. Moreover, the evaluation methods and interpretability of these models are proposed. Furthermore, delving into the diverse applications of protein-ligand interaction models in drug research is presented. Lastly, the current challenges and future directions in this field are addressed.
Collapse
Affiliation(s)
- Yunjiang Zhang
- Beijing Key Laboratory for Green Catalysis and Separation, The Faculty of Environment and Life, Beijing University of Technology, Beijing 100124, P. R. China
| | - Shuyuan Li
- Beijing Key Laboratory for Green Catalysis and Separation, The Faculty of Environment and Life, Beijing University of Technology, Beijing 100124, P. R. China
| | - Kong Meng
- Beijing Key Laboratory for Green Catalysis and Separation, The Faculty of Environment and Life, Beijing University of Technology, Beijing 100124, P. R. China
| | - Shaorui Sun
- Beijing Key Laboratory for Green Catalysis and Separation, The Faculty of Environment and Life, Beijing University of Technology, Beijing 100124, P. R. China
| |
Collapse
|
7
|
Molecular Property Prediction by Combining LSTM and GAT. Biomolecules 2023; 13:biom13030503. [PMID: 36979438 PMCID: PMC10046625 DOI: 10.3390/biom13030503] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/06/2023] [Revised: 02/10/2023] [Accepted: 03/06/2023] [Indexed: 03/12/2023] Open
Abstract
Molecular property prediction is an important direction in computer-aided drug design. In this paper, to fully explore the information from SMILE stings and graph data of molecules, we combined the SALSTM and GAT methods in order to mine the feature information of molecules from sequences and graphs. The embedding atoms are obtained through SALSTM, firstly using SMILES strings, and they are combined with graph node features and fed into the GAT to extract the global molecular representation. At the same time, data augmentation is added to enlarge the training dataset and improve the performance of the model. Finally, to enhance the interpretability of the model, the attention layers of both models are fused together to highlight the key atoms. Comparison with other graph-based and sequence-based methods, for multiple datasets, shows that our method can achieve high prediction accuracy with good generalizability.
Collapse
|
8
|
Wei D, Peslherbe GH, Selvaraj G, Wang Y. Advances in Drug Design and Development for Human Therapeutics Using Artificial Intelligence-I. Biomolecules 2022; 12:biom12121846. [PMID: 36551273 PMCID: PMC9775020 DOI: 10.3390/biom12121846] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/06/2022] [Accepted: 12/08/2022] [Indexed: 12/14/2022] Open
Abstract
Artificial intelligence (AI) has emerged as a key player in modern healthcare, especially in the pharmaceutical industry for the development of new drugs and vaccine candidates [...].
Collapse
Affiliation(s)
- Dongqing Wei
- Department of Bioinformatics, The State Key Laboratory of Microbial Metabolism, College of Life Sciences and Biotechnology, Shanghai Jiao Tong University, Shanghai 200240, China
- Correspondence: (D.W.); (G.H.P.); (G.S.); (Y.W.)
| | - Gilles H. Peslherbe
- Centre for Research in Molecular Modeling (CERMM) & Department of Chemistry and Biochemistry, Concordia University, Montreal, QC H4B 1R6, Canada
- Correspondence: (D.W.); (G.H.P.); (G.S.); (Y.W.)
| | - Gurudeeban Selvaraj
- Centre for Research in Molecular Modeling (CERMM) & Department of Chemistry and Biochemistry, Concordia University, Montreal, QC H4B 1R6, Canada
- Correspondence: (D.W.); (G.H.P.); (G.S.); (Y.W.)
| | - Yanjing Wang
- Department of Bioinformatics, The State Key Laboratory of Microbial Metabolism, College of Life Sciences and Biotechnology, Shanghai Jiao Tong University, Shanghai 200240, China
- Correspondence: (D.W.); (G.H.P.); (G.S.); (Y.W.)
| |
Collapse
|
9
|
Ji Z, Shi R, Lu J, Li F, Yang Y. ReLMole: Molecular Representation Learning Based on Two-Level Graph Similarities. J Chem Inf Model 2022; 62:5361-5372. [PMID: 36302249 DOI: 10.1021/acs.jcim.2c00798] [Citation(s) in RCA: 8] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/13/2022]
Abstract
Molecular representation is a critical part of various prediction tasks for physicochemical properties of molecules and drug design. As graph notations are common in expressing the structural information of chemical compounds, graph neural networks (GNNs) have become the mainstream backbone model for learning molecular representation. However, the scarcity of task-specific labels in the biomedical domain limits the power of GNNs. Recently, self-supervised pretraining for GNNs has been leveraged to deal with this issue, while the existing pretraining methods are mainly designed for graph data in general domains without considering the specific data properties of molecules. In this paper, we propose a representation learning method for molecular graphs, called ReLMole, which is featured by a hierarchical graph modeling of molecules and a contrastive learning scheme based on two-level graph similarities. We assess the performance of ReLMole on two types of downstream tasks, namely, the prediction of molecular properties (MPs) and drug-drug interaction (DDIs). ReLMole achieves promising results for all the tasks. It outperforms the baseline models by over 2.6% on ROC-AUC averaged across six MP prediction tasks, and it improves the F1 value by 7-18% in DDI prediction for unseen drugs compared with other self-supervised models.
Collapse
Affiliation(s)
- Zewei Ji
- Department of Computer Science and Engineering, and Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering, Shanghai Jiao Tong University, Shanghai200240, China
| | - Runhan Shi
- Department of Computer Science and Engineering, and Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering, Shanghai Jiao Tong University, Shanghai200240, China
| | - Jiarui Lu
- Department of Computer Science and Engineering, and Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering, Shanghai Jiao Tong University, Shanghai200240, China
| | - Fang Li
- Department of Computer Science and Engineering, and Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering, Shanghai Jiao Tong University, Shanghai200240, China
| | - Yang Yang
- Department of Computer Science and Engineering, and Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering, Shanghai Jiao Tong University, Shanghai200240, China
| |
Collapse
|
10
|
Zhao L, Zhu Y, Wang J, Wen N, Wang C, Cheng L. A brief review of protein-ligand interaction prediction. Comput Struct Biotechnol J 2022; 20:2831-2838. [PMID: 35765652 PMCID: PMC9189993 DOI: 10.1016/j.csbj.2022.06.004] [Citation(s) in RCA: 15] [Impact Index Per Article: 7.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/14/2022] [Revised: 05/30/2022] [Accepted: 06/01/2022] [Indexed: 01/21/2023] Open
Abstract
The task of identifying protein–ligand interactions (PLIs) plays a prominent role in the field of drug discovery. However, it is infeasible to identify potential PLIs via costly and laborious in vitro experiments. There is a need to develop PLI computational prediction approaches to speed up the drug discovery process. In this review, we summarize a brief introduction to various computation-based PLIs. We discuss these approaches, in particular, machine learning-based methods, with illustrations of different emphases based on mainstream trends. Moreover, we analyzed three research dynamics that can be further explored in future studies.
Collapse
Affiliation(s)
- Lingling Zhao
- Faculty of Computing, Harbin Institute of Technology, Harbin, China
| | - Yan Zhu
- Faculty of Computing, Harbin Institute of Technology, Harbin, China
| | - Junjie Wang
- Department of Medical Informatics, School of Biomedical Engineering and Informatics, Nanjing Medical University, Nanjing, China
| | - Naifeng Wen
- School of Mechanical and Electrical Engineering, Dalian Minzu University, Dalian, China
| | - Chunyu Wang
- Faculty of Computing, Harbin Institute of Technology, Harbin, China
- Corresponding authors.
| | - Liang Cheng
- College of Bioinformatics Science and Technology, Harbin Medical University, Harbin, China
- NHC and CAMS Key Laboratory of Molecular Probe and Targeted Theranostics, Harbin Medical University, Harbin, China
- Corresponding authors.
| |
Collapse
|