We have developed a deep generative model, generative tensorial reinforcement learning (GENTRL), for de novo small-molecule design. GENTRL optimizes synthetic feasibility, novelty, and biological activity. We used GENTRL to discover potent inhibitors of discoidin domain receptor 1 (DDR1), a kinase target implicated in fibrosis and other diseases, in 21 days. Four compounds were active in biochemical assays, and two were validated in cell-based assays. One lead candidate was tested and demonstrated favorable pharmacokinetics in mice.
This is a preview of subscription content, access via your institution
Open Access articles citing this article.
Journal of Cheminformatics Open Access 19 January 2023
Journal of Cheminformatics Open Access 12 December 2022
High-confidence cancer patient stratification through multiomics investigation of DNA repair disorders
Cell Death & Disease Open Access 26 November 2022
Subscribe to Nature+
Get immediate online access to Nature and 55 other Nature journal
Subscribe to Journal
Get full journal access for 1 year
only $8.25 per issue
All prices are NET prices.
VAT will be added later in the checkout.
Tax calculation will be finalised during checkout.
Get time limited or full article access on ReadCube.
All prices are NET prices.
All data are available in the main text or the supplementary materials.
Paul, S. M. et al. Nat. Rev. Drug Discov. 9, 203–214 (2010).
Avorn, J. N. Engl. J. Med. 372, 1877–1879 (2015).
Goodfellow, I. et al. Generative adversarial nets. in Advances in Neural Information Processing Systems 2672–2680 (2014).
Mamoshina, P. et al. Mol. Pharm. 13, 1445–1454 (2016).
Sanchez-Lengeling, B. & Aspuru-Guzik, A. Science 361, 360–365 (2018).
Kadurin, A. et al. Oncotarget 8, 10883–10890 (2016).
Kadurin, A. et al. Mol. Pharm. 14, 3098–3104 (2017).
Gómez-Bombarelli, R. et al. ACS Cent. Sci. 4, 268–276 (2018).
Putin, E. et al. Mol. Pharm. 15, 4386–4397 (2018).
Putin, E. et al. J. Chem. Inf. Model. 58, 1194–1204 (2018).
Harel, S. & Radinsky, K. Mol. Pharm. 15, 4406–4416 (2018).
Polykovskiy, D. et al. Mol. Pharm. 15, 4398–4405 (2018).
Kuzminykh, D. et al. Mol. Pharm. 15, 4378–4385 (2018).
Segler, M. H. S. et al. Nature 555, 604–610 (2018).
Merk, D. et al. Mol. Inform. 37, 1–2 (2018).
Merk, D. et al. Commun. Chem. 1.1, 68 (2018).
Moll, S. et al. Biochim. Biophys. Acta Mol. Cell Res. https://doi.org/10.1016/j.bbamcr.2019.04.004 (2019).
Richter, H. et al. ACS Chem. Biol. 14, 37–49 (2019).
Elton, D. C. et al. Mol. Syst. Des. Eng. 4, 828–849 (2019).
Irwin, J. J. et al. J. Chem. Inf. Model. 52, 1757–1768 (2012).
Oseledets, I. V. SIAM J. Sci. Comput. 33, 2295–2317 (2011).
Williams, R. J. Mach. Learn. 8, 229–256 (1992).
Brown, N. et al. J. Chem. Inf. Model. 59, 1096–1108 (2018).
Guimaraes, G. L. et al. Objective-Reinforced Generative Adversarial Networks (ORGAN) for sequence generation models. Preprint at https://arxiv.org/abs/1705.10843 (2017).
Sanchez-Lengeling, B. et al. Optimizing distributions over molecular space. An Objective-Reinforced Generative Adversarial Network for Inverse-design Chemistry (ORGANIC). Preprint at https://chemrxiv.org/articles/ORGANIC_1_pdf/5309668 (2017).
Ritter, H. & Kohonen, T. Biol. Cybern. 61, 241–254 (1989).
Sammon, J. W. IEEE Trans. Comput. C-18, 401–409 (1969).
Rappe, A. K. J. Am. Chem. Soc. 114, 10024–10035 (1992).
The authors thank T. Oprea (University of New Mexico School of Medicine) for the valuable contributions, review, and assessment of the novelty of the intellectual property generated by GENTRL. The authors would like to thank NVIDIA Corporation and M. Berger for providing early access to the graphics processing equipment used for deep learning applications by Insilico Medicine. The authors acknowledge T. Lu, L. Duan, Y. Hu, and the WuXi AppTec chemistry team for providing chemical synthesis of the presented compounds. The authors thank S. Djuric, whose valuable comments informed further experiments.
A. Zhavoronkov, Y.A.I., A. Aliper, M.S.V., V.A.A., A.V.A., V.A.T., D.A.P., M.D.K., A. Zholus, A. Asadulaev, Y.V., A. Zhebrak, R.R.S., L.I.M., and B.A.Z. work for Insilico Medicine, a commercial artificial intelligence company. L.H.L., R.S., D.M., L.X., and T.G. work for WuXi AppTec, a commercial research organization. A.A.-G. is a cofounder and board member of, and consultant for, Kebotix, an artificial intelligence-driven molecular discovery company and a member of the science advisory board of Insilico Medicine.
Publisher’s note: Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Integrated supplementary information
Generative Tensorial Reinforcement Learning model.
(a) Representation of Trending SOM, a Kohonen-based reward function that discriminates “novel” compounds from “old” compounds considering the application priority date of lead compounds disclosed in patents by major pharmaceutical companies. (b) Representation of neurons populated with kinase inhibitors. (c) Representation of neurons populated by molecules with no experimental activity against kinases. (d) Neurons were selected based on PF (circles) and subsequently were used for reward. Within the Specific Kinase SOM (not depicted) we observed that DDR1 inhibitors were distributed in the ensemble of topographically proximal neurons. Finally, we selected those structures which were located in DDR1 associated neurons.
(a) 3-Centered pharmacophore hypothesis: Acc - hydrogen bond acceptor (r = 2Å), Hyd|Aro - hydrophobic or aromatic center (r = 2Å), Hyd - hydrophobic center (r = 2Å). (b) 4-Centered pharmacophore hypothesis: Acc - hydrogen bond acceptor (r = 2Å), Hyd|Aro - hydrophobic or aromatic center (r = 2Å), Hyd - hydrophobic center (r = 2Å), Acc|Specific - hydrogen bond acceptor or a fragment with similar spatial geometry (e.g. double or triple bond, planar cycle) (r = 1.7Å). Non-depicted distances are the same as for 3-centered pharmacophore. (c) 5-Centered pharmacophore hypothesis containing the same points that are highlighted in b above with an additional hydrophobic feature. Non-depicted distances are the same as for 3-centered and 4-centered pharmacophores. Yellow: the reported small-molecule DDR1 inhibitor (PDB code: 5BVN).
The selected 40 molecules are marked by orange triangles. Areas of the best pharmacophore matching are highlighted by circles.
(a) Six generated compounds were tested in a dose-dependent manner against DDR1 tyrosine kinase. Compounds 1 and 2 demonstrated the IC50 values in the low nanomolar range. (b) Compounds 2 and 4 were additionally rescreened towards DDR1 kinase using another biochemical assay (Thermo Fisher-PR6913A) and have demonstrated the IC50 values of 37.12 and 155.6 nM respectively (below). Measure of center is mean, error bars are s.d. (n=2 for each experiment).
The inhibition percent versus 44 non-target kinases was measured at 10μM concentration. The highest inhibition potency(%INH=37) within the panel was revealed against eEF-2K.
Supplementary Figure 7 Inhibition of DDR1 auto-phosphorylation in U2OS cells stimulated with collagen.
Representative blots of phosphorylated DDR1-Y513 in U2OS cells stimulated with collagen and treated with DDR1 inhibitors at different doses. Dasatinib was served as a positive control. Dasatinib, compounds 1 and 2 inhibited auto-phosphorylation in a dose-dependent manner. Experiments were repeated at least once and similar results were obtained.
Supplementary Figure 8 Effects of compounds 1 and 2 on cellular fibrosis markers α-actin and CCN2 (normalized to GAPDH) in MRC-5 cells.
Representative blots of produced α-actin and CCN2 in MRC-5 cells treated with TGF-b in the presence of DDR1 inhibitors at different doses. SB25334 and dasatinib were served as a positive control. Dasatinib and compound 1 suppressed α-actin and CCN2 production at the concentration of 10 μM. SB25334 inhibited α-actin production at the dose of 10 μM. Experiments were repeated at least once and similar results were obtained.
Supplementary Figure 9 Effects of compounds 1 and 2 on cellular fibrosis markers collagen I, α-actin and CCN2 (normalized to GAPDH) in LX-2 cells.
Representative blots of produced collagen I, α-actin and CCN2 in LX-2 cells treated with TGF-b in the presence of DDR1 inhibitors at different doses. SB25334 was served as a positive control. SB25334 and compound 1 suppressed collagen I production in a dose dependent manner. SB25334 inhibited α-actin production at the dose of 10 μM. Experiments were repeated at least once and similar results were obtained.
Examples of molecules that were rejected during the prioritization step.
About this article
Cite this article
Zhavoronkov, A., Ivanenkov, Y.A., Aliper, A. et al. Deep learning enables rapid identification of potent DDR1 kinase inhibitors. Nat Biotechnol 37, 1038–1040 (2019). https://doi.org/10.1038/s41587-019-0224-x
This article is cited by
Journal of Cheminformatics (2023)
Augmented Hill-Climb increases reinforcement learning efficiency for language-based de novo molecule generation
Journal of Cheminformatics (2022)
Integrating concept of pharmacophore with graph neural networks for chemical property prediction and interpretation
Journal of Cheminformatics (2022)
Journal of Cheminformatics (2022)
Identification of pan-kinase-family inhibitors using graph convolutional networks to reveal family-sensitive pre-moieties
BMC Bioinformatics (2022)