Scaffold and SAR studies on c-MET inhibitors using machine learning approaches

Jing Zhang; Mingming Zhang; Weiran Huang; Changjie Liang; Wei Xu; Jinghua Zhang; Jun Tu; Innocent Okohi Agida; Jinke Cheng; Dong-Qing Wei; Buyong Ma; Yanjing Wang; Hongsheng Tan

doi:10.1016/j.jpha.2025.101303

Volume 15 Issue 6

Jun. 2025

Turn off MathJax

Article Contents

Article Navigation > Journal of Pharmaceutical Analysis > 2025 > 15(6): 101303

Jing Zhang, Mingming Zhang, Weiran Huang, Changjie Liang, Wei Xu, Jinghua Zhang, Jun Tu, Innocent Okohi Agida, Jinke Cheng, Dong-Qing Wei, Buyong Ma, Yanjing Wang, Hongsheng Tan. Scaffold and SAR studies on c-MET inhibitors using machine learning approaches[J]. Journal of Pharmaceutical Analysis, 2025, 15(6): 101303. doi: 10.1016/j.jpha.2025.101303

Citation:

Jing Zhang, Mingming Zhang, Weiran Huang, Changjie Liang, Wei Xu, Jinghua Zhang, Jun Tu, Innocent Okohi Agida, Jinke Cheng, Dong-Qing Wei, Buyong Ma, Yanjing Wang, Hongsheng Tan. Scaffold and SAR studies on c-MET inhibitors using machine learning approaches[J]. Journal of Pharmaceutical Analysis, 2025, 15(6): 101303. doi: 10.1016/j.jpha.2025.101303

Citation:

Jing Zhang, Mingming Zhang, Weiran Huang, Changjie Liang, Wei Xu, Jinghua Zhang, Jun Tu, Innocent Okohi Agida, Jinke Cheng, Dong-Qing Wei, Buyong Ma, Yanjing Wang, Hongsheng Tan. Scaffold and SAR studies on c-MET inhibitors using machine learning approaches[J]. Journal of Pharmaceutical Analysis, 2025, 15(6): 101303. doi: 10.1016/j.jpha.2025.101303

PDF( 3598 KB)

Scaffold and SAR studies on c-MET inhibitors using machine learning approaches

doi: 10.1016/j.jpha.2025.101303

a. Clinical Research Institute & School of Public Health, Shanghai Jiao Tong University School of Medicine, Shanghai, 200025, China;
b. Department of Biochemistry and Molecular Cell Biology, Shanghai Key Laboratory for Tumor Microenvironment and Inflammation, Shanghai Jiao Tong University School of Medicine, Shanghai, 200025, China;
c. Academy of Integrative Medicine, Shanghai University of Traditional Chinese Medicine, Shanghai, 201203, China;
d. Engineering Research Center of Cell & Therapeutic Antibody, School of Pharmacy, Shanghai Jiao Tong University, Shanghai, 200240, China;
e. Core Facility of Basic Medical Sciences, Shanghai Jiao Tong University School of Medicine, Shanghai, 200025, China;
f. School of Life Sciences and Biotechnology, Shanghai Jiao Tong University, Shanghai, 200030, China

Funds:

This study was supported by the National Natural Science Foundation of China (Grant Nos.: 82173699 and 32200531), Shanghai Jiao Tong University Trans-Med Awards Research, China (STAR Project No.: 20230101), and Shanghai Science and Technology Commission, China (Grant No.: 23DZ2290600).

Received Date: Oct. 28, 2024
Accepted Date: Apr. 04, 2025
Rev Recd Date: Mar. 19, 2025
Publish Date: Apr. 10, 2025

Abstract

Abstract

Numerous c-mesenchymal-epithelial transition (c-MET) inhibitors have been reported as potential anticancer agents. However, most fail to enter clinical trials owing to poor efficacy or drug resistance. To date, the scaffold-based chemical space of small-molecule c-MET inhibitors has not been analyzed. In this study, we constructed the largest c-MET dataset, which included 2,278 molecules with different structures, by inhibiting the half maximal inhibitory concentration (IC₅₀) of kinase activity. No significant differences in drug-like properties were observed between active molecules (1,228) and inactive molecules (1,050), including chemical space coverage, physicochemical properties, and absorption, distribution, metabolism, excretion, and toxicity (ADMET) profiles. The higher chemical diversity of the active molecules was downscaled using t-distributed stochastic neighbor embedding (t-SNE) high-dimensional data. Further clustering and chemical space networks (CSNs) analyses revealed commonly used scaffolds for c-MET inhibitors, such as M5, M7, and M8. Activity cliffs and structural alerts were used to reveal “dead ends” and “safe bets” for c-MET, as well as dominant structural fragments consisting of pyridazinones, triazoles, and pyrazines. Finally, the decision tree model precisely indicated the key structural features required to constitute active c-MET inhibitor molecules, including at least three aromatic heterocycles, five aromatic nitrogen atoms, and eight nitrogen–oxygen atoms. Overall, our analyses revealed potential structure-activity relationship (SAR) patterns for c-MET inhibitors, which can inform the screening of new compounds and guide future optimization efforts.
- c-MET inhibitors,
- Machine learning,
- Structure-activity relationship,
- Hierarchical clustering,
- Scaffold based chemical space,
- Active cliff

FullText(HTML)

References(55)

References

[1]	E.C. Scott, A.C. Baines, Y. Gong, et al., Trends in the approval of cancer therapies by the FDA in the twenty-first century, Nat. Rev. Drug Discov. 22 (2023) 625-640.
[2]	R.L. Siegel, K.D. Miller, N.S. Wagle, et al., Cancer statistics, 2023, CA A Cancer J. Clin. 73 (2023) 17-48.
[3]	C. Birchmeier, W. Birchmeier, E. Gherardi, et al., Met, metastasis, motility and more, Nat. Rev. Mol. Cell Biol. 4 (2003) 915-925.
[4]	C. Ponzetto, A. Bardelli, Z. Zhen, et al., A multifunctional docking site mediates signaling and transformation by the hepatocyte growth factor/scatter factor receptor family, Cell 77 (1994) 261-271.
[5]	J. Fu, X. Su, Z. Li, et al., HGF/c-MET pathway in cancer: From molecular characterization to clinical evidence, Oncogene 40 (2021) 4625-4651.
[6]	F. Jin, Y. Lin, W. Yuan, et al., Recent advances in c-Met-based dual inhibitors in the treatment of cancers, Eur. J. Med. Chem. 272 (2024), 116477.
[7]	G.E. Wood, H. Hockings, D.M. Hilton, et al., The role of MET in chemotherapy resistance, Oncogene 40 (2021) 1927-1941.
[8]	Z. Sun, Y. Yang, Z. Zhang, et al., Optimization techniques for novel c-Met kinase inhibitors, Expert Opin. Drug Discov. 14 (2019) 59-69.
[9]	S. Takiguchi, K. Inoue, K. Matsusue, et al., Crizotinib, a MET inhibitor, prevents peritoneal dissemination in pancreatic cancer, Int. J. Oncol. 51 (2017) 184-192.
[10]	T. Fujino, Y. Kobayashi, K. Suda, et al., Sensitivity and resistance of MET exon 14 mutations in lung cancer to eight MET tyrosine kinase inhibitors in vitro, J. Thorac. Oncol. 14 (2019) 1753-1765.
[11]	A. Puccini, N.I. Marin-Ramos, F. Bergamo, et al., Safety and tolerability of c-MET inhibitors in cancer, Drug Saf. 42 (2019) 211-233.
[12]	D. Dimova, D. Stumpfe, J. Bajorath, Systematic assessment of coordinated activity cliffs formed by kinase inhibitors and detailed characterization of activity cliff clusters and associated SAR information, Eur. J. Med. Chem. 90 (2015) 414-427.
[13]	S. Daoud, M. Taha, Protein characteristics substantially influence the propensity of activity cliffs among kinase inhibitors, Sci. Rep. 14 (2024), 9058.
[14]	K.Z. Myint, X.Q. Xie, Recent advances in fragment-based QSAR and multi-dimensional QSAR methods, Int. J. Mol. Sci. 11 (2010) 3846-3866.
[15]	A. Raafat, S. Mowafy, S.M. Abouseri, et al., Lead generation of cysteine based mesenchymal epithelial transition (c-Met) kinase inhibitors: Using structure-based scaffold hopping, 3D-QSAR pharmacophore modeling, virtual screening, molecular docking, and molecular dynamics simulation, Comput. Biol. Med. 146 (2022), 105526.
[16]	H. Yuan, Q. Liu, L. Zhang, et al., Discovery, optimization and biological evaluation for novel c-Met kinase inhibitors, Eur. J. Med. Chem. 143 (2018) 491-502.
[17]	D. Boldini, F. Grisoni, D. Kuhn, et al., Practical guidelines for the use of gradient boosting for molecular property prediction, J. Cheminform. 15 (2023), 73.
[18]	A.L. Teixeira, J.P. Leal, A.O. Falcao, Random forests for feature selection in QSPR Models - an application for predicting standard enthalpy of formation of hydrocarbons, J. Cheminform. 5 (2013), 9.
[19]	X. Li, Y. Xu, H. Yao, et al., Chemical space exploration based on recurrent neural networks: Applications in discovering kinase inhibitors, J. Cheminform. 12 (2020), 42.
[20]	F. Li, J. Yin, M. Lu, et al., DrugMAP: Molecular atlas and pharma-information of all drugs, Nucleic Acids Res. 51 (2023) D1288-D1299.
[21]	J. Porter, Small molecule c-Met kinase inhibitors: A review of recent patents, Expert Opin. Ther. Pat. 20 (2010) 159-177.
[22]	B.K. Albrecht, J.C. Harmange, D. Bauer, et al., Discovery and optimization of triazolopyridazines as potent and selective inhibitors of the c-Met kinase, J. Med. Chem. 51 (2008) 2879-2882.
[23]	F. Chen, Y. Wang, J. Ai, et al., O-linked triazolotriazines: Potent and selective c-Met inhibitors, ChemMedChem 7 (2012) 1276-1285.
[24]	M.H. Norman, L. Liu, M. Lee, et al., Structure-based design of novel class II c-Met inhibitors: 1. Identification of pyrazolone-based derivatives, J. Med. Chem. 55 (2012) 1858-1867.
[25]	L. Ye, X. Ou, Y. Tian, et al., Indazoles as potential c-Met inhibitors: Design, synthesis and molecular docking studies, Eur. J. Med. Chem. 65 (2013) 112-118.
[26]	J.J. Cui, H. Shen, M. Tran-Dube, et al., Lessons from (S)-6-(1-(6-(1-Methyl-1H-pyrazol-4-yl)-[1, 2, 4] triazolo [4, 3-b] pyridazin-3-yl)ethyl)quinoline (PF-04254644), an inhibitor of receptor tyrosine kinase c-Met with high protein kinase selectivity but broad phosphodiesterase family inhibition leading to myocardial degeneration in rats, J. Med. Chem. 56 (2013) 6651-6665.
[27]	J.D. Katz, J.P. Jewell, D.J. Guerin, et al., Discovery of a 5H-benzo [4,5] cyclohepta [1,2-b] pyridin-5-one (MK-2461) inhibitor of c-Met kinase for the treatment of cancer, J. Med. Chem. 54 (2011) 4092-4108.
[28]	C.A. Zificsak, J.P. Theroff, L.D. Aimone, et al., 2, 4-Diaminopyrimidine inhibitors of c-Met kinase bearing benzoxazepine anilines, Bioorg. Med. Chem. Lett. 21 (2011) 660-663.
[29]	Z. Liang, X. Ding, J. Ai, et al., Discovering potent inhibitors against c-Met kinase: Molecular design, organic synthesis and bioassay, Org. Biomol. Chem. 10 (2012) 421-430.
[30]	J. Porter, S. Lumb, F. Lecomte, et al., Discovery of a novel series of quinoxalines as inhibitors of c-Met kinase, Bioorg. Med. Chem. Lett. 19 (2009) 397-400.
[31]	G. Xiong, Z. Wu, J. Yi, et al., ADMETlab 2.0: An integrated online platform for accurate and comprehensive predictions of ADMET properties, Nucleic Acids Res. 49 (2021) W5-W14.
[32]	S. Ji, Z. Zhang, S. Ying, et al., Kullback-leibler divergence metric learning, IEEE Trans. Cybern. 52 (2022) 2047-2058.
[33]	N. Pezzotti, B.P.F. Lelieveldt, L. van der Maaten, et al., Approximated and user steerable tSNE for progressive visual analytics, IEEE Trans. Vis. Comput. Graph. 23 (2017) 1739-1752.
[34]	V.F. Scalfani, V.D. Patel, A.M. Fernandez, Visualizing chemical space networks with RDKit and NetworkX, J. Cheminform. 14 (2022), 87.
[35]	E. Ahlberg, L. Carlsson, S. Boyer, Computational derivation of structural alerts from large toxicology data sets, J. Chem. Inf. Model. 54 (2014) 2945-2952.
[36]	T. Yu, C. Nantasenamat, S. Kachenton, et al., Cheminformatic analysis and machine learning modeling to investigate androgen receptor antagonists to combat prostate cancer, ACS Omega 8 (2023) 6729-6742.
[37]	R.P. Sheridan, J.C. Culberson, E. Joshi, et al., Prediction accuracy of production ADMET models as a function of version: Activity cliffs rule, J. Chem. Inf. Model. 62 (2022) 3275-3280.
[38]	R.P. Sheridan, P. Karnachi, M. Tudor, et al., Experimental error, kurtosis, activity cliffs, and methodology: What limits the predictivity of quantitative structure-activity relationship models? J. Chem. Inf. Model. 60 (2020) 1969-1982.
[39]	O.F. Hamim, S.V. Ukkusuri, Towards safer streets: A framework for unveiling pedestrians’ perceived road safety using street view imagery, Accid. Anal. Prev. 195 (2024), 107400.
[40]	D. Marutho, S. Hendra Handaka, E. Wijaya, et al., The determination of cluster number at k-mean using elbow method and purity evaluation on headline news, 2018 International Seminar on Application for Technology of Information and Communication. September 21-22, 2018, Semarang, Indonesia, pp. 533-538.
[41]	F. Zhao, L. Zhang, Y. Hao, et al., Identification of 3-substituted-6-(1-(1H-[1,2,3] triazolo [4,5-b] pyrazin-1-yl)ethyl)quinoline derivatives as highly potent and selective mesenchymal-epithelial transition factor (c-Met) inhibitors via metabolite profiling-based structural optimization, Eur. J. Med. Chem. 134 (2017) 147-158.
[42]	M. Wang, L. Zhuo, F. Yang, et al., Synthesis and biological evaluation of new MET inhibitors with 1,6-naphthyridinone scaffold, Eur. J. Med. Chem. 185 (2020), 111803.
[43]	L. Zhuo, H. Xu, M. Wang, et al., 2,7-naphthyridinone-based MET kinase inhibitors: A promising novel scaffold for antitumor drug development, Eur. J. Med. Chem. 178 (2019) 705-714.
[44]	A. Martorana, G.L. Monica, A. Lauria, Quinoline-based molecules targeting c-met, EGF, and VEGF receptors and the proteins involved in related carcinogenic pathways, Molecules 25 (2020), 4279.
[45]	S. Eathiraj, R. Palma, E. Volckova, et al., Discovery of a novel mode of protein kinase inhibition characterized by the mechanism of inhibition of human mesenchymal-epithelial transition factor (c-Met) protein autophosphorylation by ARQ 197, J. Biol. Chem. 286 (2011) 20666-20676.
[46]	I. Cortes-Ciriano, Bioalerts: A Python library for the derivation of structural alerts from bioactivity and toxicity data sets, J. Cheminform. 8 (2016), 13.
[47]	W. Xing, J. Ai, S. Jin, et al., Enhancing the cellular anti-proliferation activity of pyridazinones as c-Met inhibitors using docking analysis, Eur. J. Med. Chem. 95 (2015) 302-312.
[48]	D. Lu, J. Yan, L. Wang, et al., Design, synthesis, and biological evaluation of the first c-met/HDAC inhibitors based on pyridazinone derivatives, ACS Med. Chem. Lett. 8 (2017) 830-834.
[49]	Y. Liu, S. Jin, X. Peng, et al., Pyridazinone derivatives displaying highly potent and selective inhibitory activities against c-Met tyrosine kinase, Eur. J. Med. Chem. 108 (2016) 322-333.
[50]	E.Y. Kim, S.T. Kang, H. Jung, et al., Discovery of substituted pyrazol-4-yl pyridazinone derivatives as novel c-Met kinase inhibitors, Arch. Pharm. Res. 39 (2016) 453-464.
[51]	X. Nan, H. Li, S. Fang, et al., Structure-based discovery of novel 4-(2-fluorophenoxy)quinoline derivatives as c-Met inhibitors using isocyanide-involved multicomponent reactions, Eur. J. Med. Chem. 193 (2020), 112241.
[52]	Z. Zhan, X. Peng, Q. Liu, et al., Discovery of 6-(difluoro(6-(4-fluorophenyl)-[1,2,4] triazolo[4,3-b][1,2,4]triazin-3-yl)methyl)quinoline as a highly potent and selective c-Met inhibitor, Eur. J. Med. Chem. 116 (2016) 239-251.
[53]	J.W. Zhang, W. Xiao, Z.T. Gao, et al., Metabolism of c-met kinase inhibitors containing quinoline by aldehyde oxidase, electron donating, and steric hindrance effect, Drug Metab. Dispos. 46 (2018) 1847-1855.
[54]	G.R. Hoffman, A.M. Schoffstall, Syntheses and applications of 1,2,3-triazole-fused pyrazines and pyridazines, Molecules 27 (2022), 4681.
[55]	L. Wang, S. Xu, X. Liu, et al., Discovery of thinopyrimidine-triazole conjugates as c-Met targeting and apoptosis inducing agents, Bioorg. Chem. 77 (2018) 370-380.