Skip to main content

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

  • Article
  • Published:

A deep learning approach for rational ligand generation with toxicity control via reactive building blocks

Nature Computational Science volume 4, pages 851–864 (2024)Cite this article

Subjects

Abstract

Deep generative models are gaining attention in the field of de novo drug design. However, the rational design of ligand molecules for novel targets remains challenging, particularly in controlling the properties of the generated molecules. Here, inspired by the DNA-encoded compound library technique, we introduce DeepBlock, a deep learning approach for block-based ligand generation tailored to target protein sequences while enabling precise property control. DeepBlock neatly divides the generation process into two steps: building blocks generation and molecule reconstruction, accomplished by a neural network and a rule-based reconstruction algorithm we proposed, respectively. Furthermore, DeepBlock synergizes the optimization algorithm and deep learning to regulate the properties of the generated molecules. Experiments show that DeepBlock outperforms existing methods in generating ligands with affinity, synthetic accessibility and drug likeness. Moreover, when integrated with simulated annealing or Bayesian optimization using toxicity as the optimization objective, DeepBlock successfully generates ligands with low toxicity while preserving affinity with the target.

Access through your institution
Buy or subscribe

This is a preview of subscription content, access via your institution

Access options

Access through your institution

Buy this article

  • Purchase on SpringerLink
  • Instant access to full article PDF
Buy now

Prices may be subject to local taxes which are calculated during checkout

Fig. 1: Overview of the DeepBlock framework.
Fig. 2: Comparison of the proposed method and baselines.
Fig. 3: Binding contribution of a residue.
Fig. 4: Case study of ligands generation for KIAA1363.
Fig. 5: Comparison of affinity before and after optimization.
Fig. 6: The optimization processes and results.

Similar content being viewed by others

Data availability

Source data for Figs. 2–6 are provided with this paper. All of the datasets used in this study are publicly available. The raw data of the CrossDocked 2020 dataset were obtained from https://github.com/gnina/models/tree/master/data/CrossDocked2020. The dataset for pretraining BGNet were obtained from ChEMBL dataset (https://ftp.ebi.ac.uk/pub/databases/chembl/ChEMBLdb/releases/chembl_31/). The processed datasets used to train the model are available via figshare56 at https://figshare.com/articles/dataset/crossdocked_pocket10_with_protein_tar_gz/25878871. The small-mouse intraperitoneal LD50 sub-dataset was obtained from TOXRIC (https://toxric.bioinforai.tech/home).

Code availability

The source code and weights of trained models are available on GitHub at https://github.com/BioChemAI/DeepBlock and deposited on Zenodo at https://doi.org/10.5281/zenodo.13852436 (ref. 57).

References

  1. Shoichet, B. K. Virtual screening of chemical libraries. Nature 432, 862–865 (2004).

    Article  Google Scholar 

  2. Meyers, J., Fabian, B. & Brown, N. De novo molecular design and generative models. Drug Discov. Today 26, 2707–2715 (2021).

    Article  Google Scholar 

  3. Wang, M. et al. Deep learning approaches for de novo drug design: an overview. Curr. Opin. Struc. Biol. 72, 135–144 (2022).

    Article  Google Scholar 

  4. Segler, M. H., Kogej, T., Tyrchan, C. & Waller, M. P. Generating focused molecule libraries for drug discovery with recurrent neural networks. ACS Cent. Sci. 4, 120–131 (2018).

    Article  Google Scholar 

  5. Moret, M., Friedrich, L., Grisoni, F., Merk, D. & Schneider, G. Generative molecular design in low data regimes. Nat. Mach. Intell. 2, 171–180 (2020).

    Article  Google Scholar 

  6. Gómez-Bombarelli, R. et al. Automatic chemical design using a data-driven continuous representation of molecules. ACS Cent. Sci. 4, 268–276 (2018).

    Article  Google Scholar 

  7. Jin, W., Barzilay, R. & Jaakkola, T. Junction tree variational autoencoder for molecular graph generation. In Proc. 35th International Conference on Machine Learning, Proc. Machine Learning Research Vol. 80 (eds Dy, J. & Krause, A.) 2323–2332 (PMLR, 2018).

  8. Li, Y., Zhang, L. & Liu, Z. Multi-objective de novo drug design with conditional graph generative model. J. Cheminform. 10, 33 (2018).

    Article  Google Scholar 

  9. Putin, E. et al. Reinforced adversarial neural computer for de novo molecular design. J. Chem. Inf. Model. 58, 1194–1204 (2018).

    Article  Google Scholar 

  10. Zang, C. & Wang, F. Moflow: an invertible flow model for generating molecular graphs. In Proc. 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining 617–626 (ACM, 2020).

  11. Kuznetsov, M. & Polykovskiy, D. MolGrow: a graph normalizing flow for hierarchical molecular generation. Proc. AAAI Conf. Artif. Intell. 35, 8226–8234 (2021).

    Google Scholar 

  12. Hoogeboom, E., Satorras, V. G., Vignac, C. & Welling, M. Equivariant diffusion for molecule generation in 3D. In Proc. 39th International Conference on Machine Learning, Proc. Machine Learning Research Vol. 162 (eds Chaudhuri, K. et al.) 8867–8887 (PMLR, 2022).

  13. Schneuing, A. et al. Structure-based drug design with equivariant diffusion models. Preprint at https://arxiv.org/abs/2210.13695 (2022).

  14. Li, J. et al. Mining for potent inhibitors through artificial intelligence and physics: a unified methodology for ligand based and structure based drug design. J. Chem. Inf. Model. https://doi.org/10.1021/acs.jcim.4c00634 (2024).

  15. Ragoza, M., Masuda, T. & Koes, D. R. Generating 3D molecules conditional on receptor binding sites with deep generative models. Chem. Sci. 13, 2701–2713 (2022).

    Article  Google Scholar 

  16. Luo, S., Guan, J., Ma, J. & Peng, J. A 3D generative model for structure-based drug design. Adv. Neural Inf. Process. Syst. 34, 6229–6239 (2021).

    Google Scholar 

  17. Gao, W. & Coley, C. W. The synthesizability of molecules proposed by generative models. J. Chem. Inf. Model. 60, 5714–5723 (2020).

    Article  Google Scholar 

  18. Brenner, S. & Lerner, R. A. Encoded combinatorial chemistry. Proc. Natl Acad. Sci. USA 89, 5381–5383 (1992).

    Article  Google Scholar 

  19. Liu, R., Li, X. & Lam, K. S. Combinatorial chemistry in drug discovery. Curr. Opin. Chem. Biol. 38, 117–126 (2017).

    Article  Google Scholar 

  20. Bertsimas, D. & Tsitsiklis, J. Simulated annealing. Stat. Sci. 8, 10–15 (1993).

    Article  Google Scholar 

  21. Lin, Z. et al. Evolutionary-scale prediction of atomic-level protein structure with a language model. Science 379, 1123–1130 (2023).

    Article  MathSciNet  Google Scholar 

  22. Degen, J., Wegscheid-Gerlach, C., Zaliani, A. & Rarey, M. On the art of compiling and using ‘drug-like’ chemical fragment spaces. ChemMedChem 3, 1503–1507 (2008).

    Article  Google Scholar 

  23. Mendez, D. et al. ChEMBL: towards direct deposition of bioassay data. Nucleic Acids Res. 47, D930–D940 (2019).

    Article  Google Scholar 

  24. Wang, R., Fang, X., Lu, Y. & Wang, S. The PDBbind database: collection of binding affinities for protein–ligand complexes with known three-dimensional structures. J. Med. Chem. 47, 2977–2980 (2004).

    Article  Google Scholar 

  25. Jessani, N., Liu, Y., Humphrey, M. & Cravatt, B. F. Enzyme activity profiles of the secreted and membrane proteome that depict cancer cell invasiveness. Proc. Natl Acad. Sci. USA 99, 10335–10340 (2002).

    Article  Google Scholar 

  26. Chiang, K. P., Niessen, S., Saghatelian, A. & Cravatt, B. F. An enzyme that regulates ether lipid signaling pathways in cancer annotated by multidimensional profiling. Chem. Biol. 13, 1041–1050 (2006).

    Article  Google Scholar 

  27. Chang, J. W., Nomura, D. K. & Cravatt, B. F. A potent and selective inhibitor of KIAA1363/AADACL1 that impairs prostate cancer pathogenesis. Chem. Biol. 18, 476–484 (2011).

    Article  Google Scholar 

  28. Francoeur, P. G. et al. Three-dimensional convolutional neural networks and a cross-docked data set for structure-based drug design. J. Chem. Inf. Model. 60, 4200–4215 (2020).

    Article  Google Scholar 

  29. Steinegger, M. & Söding, J. mmseqs2 enables sensitive protein sequence searching for the analysis of massive data sets. Nat. Biotechnol. 35, 1026–1028 (2017).

    Article  Google Scholar 

  30. Jänne, P. et al. KRYSTAL-1: activity and safety of adagrasib (MRTX849) in advanced/metastatic non-small cell lung cancer (NSCLC) harboring KRASG12C mutation. Eur. J. Cancer 138, S1–S2 (2020).

    Article  Google Scholar 

  31. Landrum, G. RDKit: open-source cheminformatics. RDKit http://www.rdkit.org (2006).

  32. Zhao, T., Zhao, R. & Eskenazi, M. Learning discourse-level diversity for neural dialog models using conditional variational autoencoders. In Proc. 55th Annual Meeting of the Association for Computational Linguistics Vol. 1 (eds Barzilay, R. & Kan, M.) 654–664 (ACL, 2017).

  33. Kingma, D. P. & Welling, M. Auto-encoding variational Bayes. Preprint at https://arxiv.org/abs/1312.6114 (2014).

  34. Chung, J., Gulcehre, C., Cho, K. & Bengio, Y. Empirical evaluation of gated recurrent neural networks on sequence modeling. Preprint at https://arxiv.org/abs/1412.3555 (2014).

  35. Devlin, J., Chang, M.-W., Lee, K. & Toutanova, K. BERT: pre-training of deep bidirectional transformers for language understanding. In Proc. North American Chapter of the Association for Computational Linguistics Vol. 1 (eds Burstein, J. et al.) 4171–4186 (ACL, 2019).

  36. Kingma, D. P. & Ba, J. Adam: a method for stochastic optimization. Preprint at https://arxiv.org/abs/1412.6980 (2015).

  37. Bowman, S. R. et al. Generating sentences from a continuous space. In Proc. 20th SIGNLL Conference on Computational Natural Language Learning (eds Riezler, S. & Goldberg, Y.) 10–21 (ACL, 2016).

  38. Riniker, S. & Landrum, G. A. Better informed distance geometry: using what we know to improve conformation generation. J. Chem. Inf. Model. 55, 2562–2574 (2015).

    Article  Google Scholar 

  39. Metropolis, N., Rosenbluth, A. W., Rosenbluth, M. N., Teller, A. H. & Teller, E. Equation of state calculations by fast computing machines. J. Chem. Phys. 21, 1087–1092 (1953).

    Article  Google Scholar 

  40. Kirkpatrick, S., Gelatt, C. D. & Vecchi, M. P. Optimization by simulated annealing. Science 220, 671–680 (1983).

    Article  MathSciNet  Google Scholar 

  41. Bajusz, D., Rácz, A. & Héberger, K. Why is Tanimoto index an appropriate choice for fingerprint-based similarity calculations? J. Cheminform. 7, 20 (2015).

    Article  Google Scholar 

  42. Jain, S. et al. Large-scale modeling of multispecies acute toxicity end points using consensus of multitask deep learning methods. J. Chem. Inf. Model. 61, 653–663 (2021).

    Article  Google Scholar 

  43. Liwanag, P. M., Hudson, V. W. & Hazard, G. F. Jr. ChemIDplus: a web-based chemical search system. NLM https://www.nlm.nih.gov/pubs/techbull/ma00/ma00_chemid.html (2000).

  44. Wu, L. et al. TOXRIC: a comprehensive database of toxicological data and benchmarks. Nucleic Acids Res. 51, D1432–D1445 (2023).

    Article  Google Scholar 

  45. Durant, J. L., Leland, B. A., Henry, D. R. & Nourse, J. G. Reoptimization of mdl keys for use in drug discovery. J. Chem. Inf. Comput. Sci. 42, 1273–1280 (2002).

    Article  Google Scholar 

  46. Le, T. T., Fu, W. & Moore, J. H. Scaling tree-based automated machine learning to biomedical big data with a feature set selector. Bioinformatics 36, 250–256 (2020).

    Article  Google Scholar 

  47. Cao, Y., Goodin, D. & Mcree, D. Probing the strength and character of an Asp-His-x hydrogen bond by introducing buried charges. PDB https://doi.org/10.2210/pdb1a2g/pdb (1998).

  48. Alhossary, A., Handoko, S. D., Mu, Y. & Kwoh, C.-K. Fast, accurate, and reliable molecular docking with QuickVina 2. Bioinformatics 31, 2214–2216 (2015).

    Article  Google Scholar 

  49. Trott, O. & Olson, A. J. AutoDock Vina: improving the speed and accuracy of docking with a new scoring function, efficient optimization, and multithreading. J. Comput. Chem. 31, 455–461 (2010).

    Article  Google Scholar 

  50. Eberhardt, J., Santos-Martins, D., Tillack, A. F. & Forli, S. AutoDock Vina 1.2. 0: new docking methods, expanded force field, and Python bindings. J. Chem. Inf. Model. 61, 3891–3898 (2021).

    Article  Google Scholar 

  51. Bickerton, G. R., Paolini, G. V., Besnard, J., Muresan, S. & Hopkins, A. L. Quantifying the chemical beauty of drugs. Nat. Chem. 4, 90–98 (2012).

    Article  Google Scholar 

  52. Ertl, P. & Schuffenhauer, A. Estimation of synthetic accessibility score of drug-like molecules based on molecular complexity and fragment contributions. J. Cheminform. 1, 8 (2009).

    Article  Google Scholar 

  53. Wildman, S. A. & Crippen, G. M. Prediction of physicochemical parameters by atomic contributions. J. Chem. Inf. Comput. Sci. 39, 868–873 (1999).

    Article  Google Scholar 

  54. Chen, B., Li, C., Dai, H. & Song, L. Retro*: learning retrosynthetic planning with neural guided A* search. In Proc. 37th International Conference on Machine Learning Vol. 119 (eds Daumé, H. III & Singh, A.) 1608–1616 (PMLR, 2020).

  55. Bemis, G. W. & Murcko, M. A. The properties of known drugs. 1. Molecular frameworks. J. Med. Chem. 39, 2887–2893 (1996).

    Article  Google Scholar 

  56. Zhang, K. & Li, P. crossdocked_pocket10_with_protein.tar.gz. figshare https://figshare.com/articles/dataset/crossdocked_pocket10_with_protein_tar_gz/25878871 (2024).

  57. Li, P. & Zhang, K. Biochemai/deepblock. Zenodo https://doi.org/10.5281/zenodo.13852436 (2024).

Download references

Acknowledgements

This work was supported by the National Science and Technology Major Project (2023ZD0120902 to X.Z.), the National Natural Science Foundation of China (62202353 to P.L.; U22A2037 to X.Z.; 62425204 to X.Z.; 62122025 to X.Z.; 62450002 to X.Z.; and 62432011 to X.Z.).

Author information

Authors and Affiliations

  1. School of Computer Science and Technology, Xidian University, Xi’an, China

    Pengyong Li, Tianxiao Liu & Lin Gao

  2. School of Computer Science and Technology, Xi’an Jiaotong University, Xi’an, China

    Kaihao Zhang

  3. Centre for Artificial Intelligence Driven Drug Discovery, Faculty of Applied Sciences, Macao Polytechnic University, Macao, China

    Ruiqiang Lu & Xiaojun Yao

  4. University of Tsukuba, Tsukuba, Japan

    Yangyang Chen

  5. College of Computer Science and Electronic Engineering, Hunan University, Changsha, China

    Xiangxiang Zeng

Authors
  1. Pengyong Li
    View author publications

    Search author on:PubMed Google Scholar

  2. Kaihao Zhang
    View author publications

    Search author on:PubMed Google Scholar

  3. Tianxiao Liu
    View author publications

    Search author on:PubMed Google Scholar

  4. Ruiqiang Lu
    View author publications

    Search author on:PubMed Google Scholar

  5. Yangyang Chen
    View author publications

    Search author on:PubMed Google Scholar

  6. Xiaojun Yao
    View author publications

    Search author on:PubMed Google Scholar

  7. Lin Gao
    View author publications

    Search author on:PubMed Google Scholar

  8. Xiangxiang Zeng
    View author publications

    Search author on:PubMed Google Scholar

Contributions

P.L. and X.Z. conceived the research project. P.L. and K.Z. designed and implemented the framework. P.L., X.Y., L.G. and X.Z. designed the experiments. P.L., K.Z., T.L., Y.C., X.Y., L.G. and X.Z. conducted the experiments and results analyses. R.L. conducted the molecular dynamics simulation. All the authors discussed the experimental results and commented on the paper.

Corresponding author

Correspondence to Xiangxiang Zeng.

Ethics declarations

Competing interests

The authors declare no competing interests.

Peer review

Peer review information

Nature Computational Science thanks Kil To Chong and the other, anonymous, reviewer(s) for their contribution to the peer review of this work. Primary Handling Editor: Kaitlin McCardle, in collaboration with the Nature Computational Science team.

Additional information

Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary information

Supplementary Information

Supplementary Figs. 1–20, Tables 1 and 2, and Algorithms 1–3.

Reporting Summary

Source data

Source Data Fig. 2

Source data for Fig. 2.

Source Data Fig. 3

Source data for Fig. 3.

Source Data Fig. 4

Source data for Fig. 4.

Source Data Fig. 5

Source data for Fig. 5.

Source Data Fig. 6

Source data for Fig. 6.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Li, P., Zhang, K., Liu, T. et al. A deep learning approach for rational ligand generation with toxicity control via reactive building blocks. Nat Comput Sci 4, 851–864 (2024). https://doi.org/10.1038/s43588-024-00718-0

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1038/s43588-024-00718-0

This article is cited by

Search

Advanced search

Quick links

Nature Briefing: Translational Research

Sign up for the Nature Briefing: Translational Research newsletter — top stories in biotechnology, drug discovery and pharma.

Get what matters in translational research, free to your inbox weekly. Sign up for Nature Briefing: Translational Research