1
|
Hu C, Li S, Yang C, Chen J, Xiong Y, Fan G, Liu H, Hong L. ScaffoldGVAE: scaffold generation and hopping of drug molecules via a variational autoencoder based on multi-view graph neural networks. J Cheminform 2023; 15:91. [PMID: 37794460 PMCID: PMC10548653 DOI: 10.1186/s13321-023-00766-0] [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: 08/11/2023] [Accepted: 09/25/2023] [Indexed: 10/06/2023] Open
Abstract
In recent years, drug design has been revolutionized by the application of deep learning techniques, and molecule generation is a crucial aspect of this transformation. However, most of the current deep learning approaches do not explicitly consider and apply scaffold hopping strategy when performing molecular generation. In this work, we propose ScaffoldGVAE, a variational autoencoder based on multi-view graph neural networks, for scaffold generation and scaffold hopping of drug molecules. The model integrates several important components, such as node-central and edge-central message passing, side-chain embedding, and Gaussian mixture distribution of scaffolds. To assess the efficacy of our model, we conduct a comprehensive evaluation and comparison with baseline models based on seven general generative model evaluation metrics and four scaffold hopping generative model evaluation metrics. The results demonstrate that ScaffoldGVAE can explore the unseen chemical space and generate novel molecules distinct from known compounds. Especially, the scaffold hopped molecules generated by our model are validated by the evaluation of GraphDTA, LeDock, and MM/GBSA. The case study of generating inhibitors of LRRK2 for the treatment of PD further demonstrates the effectiveness of ScaffoldGVAE in generating novel compounds through scaffold hopping. This novel approach can also be applied to other protein targets of various diseases, thereby contributing to the future development of new drugs. Source codes and data are available at https://github.com/ecust-hc/ScaffoldGVAE .
Collapse
Affiliation(s)
- Chao Hu
- Shanghai Matwings Technology Co., Ltd., Shanghai, 200240, China
- School of Information Science and Engineering, East China University of Science and Technology, Shanghai, 200237, China
| | - Song Li
- School of Physics and Astronomy and Institute of Natural Sciences, Shanghai Jiao Tong University, Shanghai, 200240, China
- Shanghai Matwings Technology Co., Ltd., Shanghai, 200240, China
| | - Chenxing Yang
- Shanghai Matwings Technology Co., Ltd., Shanghai, 200240, China
| | - Jun Chen
- Shanghai Matwings Technology Co., Ltd., Shanghai, 200240, China
| | - Yi Xiong
- School of Life Sciences and Biotechnology, Shanghai Jiao Tong University, Shanghai, 200240, China
- Zhangjiang Institute for Advanced Study, Shanghai Jiao Tong University, Shanghai, 201203, China
| | - Guisheng Fan
- School of Information Science and Engineering, East China University of Science and Technology, Shanghai, 200237, China
| | - Hao Liu
- Shanghai Matwings Technology Co., Ltd., Shanghai, 200240, China.
| | - Liang Hong
- School of Physics and Astronomy and Institute of Natural Sciences, Shanghai Jiao Tong University, Shanghai, 200240, China.
- School of Life Sciences and Biotechnology, Shanghai Jiao Tong University, Shanghai, 200240, China.
- Zhangjiang Institute for Advanced Study, Shanghai Jiao Tong University, Shanghai, 201203, China.
| |
Collapse
|
2
|
Jin J, Wang D, Shi G, Bao J, Wang J, Zhang H, Pan P, Li D, Yao X, Liu H, Hou T, Kang Y. FFLOM: A Flow-Based Autoregressive Model for Fragment-to-Lead Optimization. J Med Chem 2023; 66:10808-10823. [PMID: 37471134 DOI: 10.1021/acs.jmedchem.3c01009] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 07/21/2023]
Abstract
Recently, deep generative models have been regarded as promising tools in fragment-based drug design (FBDD). Despite the growing interest in these models, they still face challenges in generating molecules with desired properties in low data regimes. In this study, we propose a novel flow-based autoregressive model named FFLOM for linker and R-group design. In a large-scale benchmark evaluation on ZINC, CASF, and PDBbind test sets, FFLOM achieves state-of-the-art performance in terms of validity, uniqueness, novelty, and recovery of the generated molecules and can recover over 92% of the original molecules in the PDBbind test set (with at least five atoms). FFLOM also exhibits excellent potential applicability in several practical scenarios encompassing fragment linking, PROTAC design, R-group growing, and R-group optimization. In all four cases, FFLOM can perfectly reconstruct the ground-truth compounds and generate over 74% of molecules with novel fragments, some of which have higher binding affinity than the ground truth.
Collapse
Affiliation(s)
- Jieyu Jin
- Innovation Institute for Artificial Intelligence in Medicine of Zhejiang University, College of Pharmaceutical Sciences, Zhejiang University, Hangzhou 310058, Zhejiang, China
| | - Dong Wang
- Innovation Institute for Artificial Intelligence in Medicine of Zhejiang University, College of Pharmaceutical Sciences, Zhejiang University, Hangzhou 310058, Zhejiang, China
| | - Guqin Shi
- Shanghai Qilu Pharmaceutical R&D Center, 576 Libing Road, Pudong New Area District, Shanghai 310115, China
| | - Jingxiao Bao
- Shanghai Qilu Pharmaceutical R&D Center, 576 Libing Road, Pudong New Area District, Shanghai 310115, China
| | - Jike Wang
- Innovation Institute for Artificial Intelligence in Medicine of Zhejiang University, College of Pharmaceutical Sciences, Zhejiang University, Hangzhou 310058, Zhejiang, China
| | - Haotian Zhang
- Innovation Institute for Artificial Intelligence in Medicine of Zhejiang University, College of Pharmaceutical Sciences, Zhejiang University, Hangzhou 310058, Zhejiang, China
| | - Peichen Pan
- Innovation Institute for Artificial Intelligence in Medicine of Zhejiang University, College of Pharmaceutical Sciences, Zhejiang University, Hangzhou 310058, Zhejiang, China
| | - Dan Li
- Innovation Institute for Artificial Intelligence in Medicine of Zhejiang University, College of Pharmaceutical Sciences, Zhejiang University, Hangzhou 310058, Zhejiang, China
| | - Xiaojun Yao
- State Key Laboratory of Quality Research in Chinese Medicines, Macau University of Science and Technology, Macau 999078, China
| | - Huanxiang Liu
- Faculty of Applied Science, Macao Polytechnic University, Macau 999078, China
| | - Tingjun Hou
- Innovation Institute for Artificial Intelligence in Medicine of Zhejiang University, College of Pharmaceutical Sciences, Zhejiang University, Hangzhou 310058, Zhejiang, China
| | - Yu Kang
- Innovation Institute for Artificial Intelligence in Medicine of Zhejiang University, College of Pharmaceutical Sciences, Zhejiang University, Hangzhou 310058, Zhejiang, China
| |
Collapse
|
3
|
Chowdhury I, Dashi G, Keskitalo S. CMGC Kinases in Health and Cancer. Cancers (Basel) 2023; 15:3838. [PMID: 37568654 PMCID: PMC10417348 DOI: 10.3390/cancers15153838] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/21/2023] [Revised: 07/18/2023] [Accepted: 07/26/2023] [Indexed: 08/13/2023] Open
Abstract
CMGC kinases, encompassing cyclin-dependent kinases (CDKs), mitogen-activated protein kinases (MAPKs), glycogen synthase kinases (GSKs), and CDC-like kinases (CLKs), play pivotal roles in cellular signaling pathways, including cell cycle regulation, proliferation, differentiation, apoptosis, and gene expression regulation. The dysregulation and aberrant activation of these kinases have been implicated in cancer development and progression, making them attractive therapeutic targets. In recent years, kinase inhibitors targeting CMGC kinases, such as CDK4/6 inhibitors and BRAF/MEK inhibitors, have demonstrated clinical success in treating specific cancer types. However, challenges remain, including resistance to kinase inhibitors, off-target effects, and the need for better patient stratification. This review provides a comprehensive overview of the importance of CMGC kinases in cancer biology, their involvement in cellular signaling pathways, protein-protein interactions, and the current state of kinase inhibitors targeting these kinases. Furthermore, we discuss the challenges and future perspectives in targeting CMGC kinases for cancer therapy, including potential strategies to overcome resistance, the development of more selective inhibitors, and novel therapeutic approaches, such as targeting protein-protein interactions, exploiting synthetic lethality, and the evolution of omics in the study of the human kinome. As our understanding of the molecular mechanisms and protein-protein interactions involving CMGC kinases expands, so too will the opportunities for the development of more selective and effective therapeutic strategies for cancer treatment.
Collapse
Affiliation(s)
- Iftekhar Chowdhury
- Institute of Biotechnology, University of Helsinki, 00014 Helsinki, Finland; (I.C.)
- Helsinki Institute of Life Science, University of Helsinki, 00014 Helsinki, Finland
| | - Giovanna Dashi
- Institute of Biotechnology, University of Helsinki, 00014 Helsinki, Finland; (I.C.)
- Helsinki Institute of Life Science, University of Helsinki, 00014 Helsinki, Finland
| | - Salla Keskitalo
- Institute of Biotechnology, University of Helsinki, 00014 Helsinki, Finland; (I.C.)
- Helsinki Institute of Life Science, University of Helsinki, 00014 Helsinki, Finland
| |
Collapse
|
4
|
Nitulescu GM, Stancov G, Seremet OC, Nitulescu G, Mihai DP, Duta-Bratu CG, Barbuceanu SF, Olaru OT. The Importance of the Pyrazole Scaffold in the Design of Protein Kinases Inhibitors as Targeted Anticancer Therapies. Molecules 2023; 28:5359. [PMID: 37513232 PMCID: PMC10385367 DOI: 10.3390/molecules28145359] [Citation(s) in RCA: 5] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/18/2023] [Revised: 07/08/2023] [Accepted: 07/10/2023] [Indexed: 07/30/2023] Open
Abstract
The altered activation or overexpression of protein kinases (PKs) is a major subject of research in oncology and their inhibition using small molecules, protein kinases inhibitors (PKI) is the best available option for the cure of cancer. The pyrazole ring is extensively employed in the field of medicinal chemistry and drug development strategies, playing a vital role as a fundamental framework in the structure of various PKIs. This scaffold holds major importance and is considered a privileged structure based on its synthetic accessibility, drug-like properties, and its versatile bioisosteric replacement function. It has proven to play a key role in many PKI, such as the inhibitors of Akt, Aurora kinases, MAPK, B-raf, JAK, Bcr-Abl, c-Met, PDGFR, FGFRT, and RET. Of the 74 small molecule PKI approved by the US FDA, 8 contain a pyrazole ring: Avapritinib, Asciminib, Crizotinib, Encorafenib, Erdafitinib, Pralsetinib, Pirtobrutinib, and Ruxolitinib. The focus of this review is on the importance of the unfused pyrazole ring within the clinically tested PKI and on the additional required elements of their chemical structures. Related important pyrazole fused scaffolds like indazole, pyrrolo[1,2-b]pyrazole, pyrazolo[4,3-b]pyridine, pyrazolo[1,5-a]pyrimidine, or pyrazolo[3,4-d]pyrimidine are beyond the subject of this work.
Collapse
Affiliation(s)
| | | | | | - Georgiana Nitulescu
- Faculty of Pharmacy, Carol Davila University of Medicine and Pharmacy, Traian Vuia 6, 020956 Bucharest, Romania; (G.M.N.)
| | | | | | | | | |
Collapse
|
5
|
Song S, Tang H, Ran T, Fang F, Tong L, Chen H, Xie H, Lu X. Application of deep generative model for design of Pyrrolo[2,3-d] pyrimidine derivatives as new selective TANK binding kinase 1 (TBK1) inhibitors. Eur J Med Chem 2023; 247:115034. [PMID: 36603506 DOI: 10.1016/j.ejmech.2022.115034] [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: 10/31/2022] [Revised: 12/08/2022] [Accepted: 12/17/2022] [Indexed: 12/24/2022]
Abstract
The deep conditional transformer neural network SyntaLinker was applied to identify compounds with pyrrolo[2,3-d]pyrimidine scaffold as potent selective TBK1 inhibitor. Further medicinal chemistry optimization campaign led to the discovery of the most potent compound 7l, which exhibited strong enzymatic inhibitory activity against TBK1 with an IC50 value of 22.4 nM 7l had a superior inhibitory activity in human monocytic THP1-Blue cells reporter gene assay than MRT67307. Furthermore, 7l significantly inhibited TBK1 downstream target genes cxcl10 and ifnβ expression in THP1 and RAW264.7 cells induced by poly (I:C) and lipopolysaccharide, respectively. This study suggested that combination of deep conditional transformer neural network SyntaLinker and transfer learning could be a powerful tool for scaffold hopping in drug discovery.
Collapse
Affiliation(s)
- Shukai Song
- School of Pharmacy, Jinan University, #855 Xingye Avenue, Guangzhou, 510632, China
| | - Haotian Tang
- Division of Antitumor Pharmacology, State Key Laboratory of Drug Research, Shanghai Institute of Materia Medica, Chinese Academy of Sciences, #555 Zuchongzhi Road, Shanghai, 201203, China; University of Chinese Academy of Sciences, No.19(A) Yuquan Road, Shijingshan District, Beijing, 100049, China
| | - Ting Ran
- Division of Drug and Vaccine Research, Guangzhou Laboratory, Guangzhou, 510530, China
| | - Feng Fang
- Division of Antitumor Pharmacology, State Key Laboratory of Drug Research, Shanghai Institute of Materia Medica, Chinese Academy of Sciences, #555 Zuchongzhi Road, Shanghai, 201203, China
| | - Linjiang Tong
- Division of Antitumor Pharmacology, State Key Laboratory of Drug Research, Shanghai Institute of Materia Medica, Chinese Academy of Sciences, #555 Zuchongzhi Road, Shanghai, 201203, China
| | - Hongming Chen
- Division of Drug and Vaccine Research, Guangzhou Laboratory, Guangzhou, 510530, China.
| | - Hua Xie
- Division of Antitumor Pharmacology, State Key Laboratory of Drug Research, Shanghai Institute of Materia Medica, Chinese Academy of Sciences, #555 Zuchongzhi Road, Shanghai, 201203, China; Zhongshan Institute for Drug Discovery, Shanghai Institute of Materia Medica, Chinese Academy of Sciences, Cuiheng New District, Zhongshan City, China.
| | - Xiaoyun Lu
- School of Pharmacy, Jinan University, #855 Xingye Avenue, Guangzhou, 510632, China.
| |
Collapse
|