ABSTRACT
In medicinal chemistry programs, it is key to design and make compounds that are efficacious and safe. In this study, we developed a new deep Reinforcement learning-based compounds molecular generation method. Because chemical space is impractically large, and many existing generation models generate molecules that lack effectiveness, novelty and unsatisfactory molecular properties. Our proposed method-DeepRLDS, which integrates transformer network, balanced binary tree search and docking simulation based on super large-scale supercomputing, can solve these problems well. Experiments show that more than 96 of the generated molecules are chemically valid, 99 of the generated molecules are chemically novelty, the generated molecules have satisfactory molecular properties and possess a broader chemical space distribution.
- [1]Jing Y, Bian Y, Hu Z, et al. Deep learning for drug design: an artificial intelligence paradigm for drug discovery in the big data era. AAPS J 2018; 20(3): 1–10.Google Scholar
- [2]Weininger D. SMILES, a chemical language and information system. 1. introduction to methodology and encoding rules. J Chem Inf Comput Sci 1988; 28(1): 31–6.Google Scholar
- [3]Xia X, Hu J, Wang Y, et al. Graph-based generative models for de novo drug design. Drug Discov Today Technol 2020.Google Scholar
- [4]Arús‑Pous J et al. Randomized SMILES strings improve the quality of molecular generative models. J Cheminform 11(1):71. https ://doi.org/10.1186/s1332 1‑019‑0393‑0Google ScholarCross Ref
- [5]Bjerrum EJ (2017) SMILES enumeration as data augmentation for neural network modeling of molecules. arXiv :1703.07076 [cs]. http://arxiv.org/abs/1703.07076. Accessed 19 Feb 2020Google Scholar
- [6] Weininger D, Weininger A, Weininger JL (1989) SMILES. 2. Algorithm for generation of unique SMILES notation. J Chem Inf Comput Sci 29(2):97–101. https ://doi.org/10.1021/ci000 62a008Google ScholarCross Ref
- [7]M. H. S. Segler, T. Kogej, C. Tyrchan, and M. P. Waller, “Generating focused molecule libraries for drug discovery with recurrent neural networks,” ACS Cent. Sci., vol. 4, no. 1, pp. 120–131, 2017.Google ScholarCross Ref
- [8]X. Yang, J. Zhang, K. Yoshizoe, K. Terayama, and K. Tsuda. ChemTS: An Efficient Python Library for de novo Molecular Generation. ArXiv e-prints, Sept. 2017.Google Scholar
- [9]M. Olivecrona, T. Blaschke, O. Engkvist, and H. Chen. Molecular de-novo design through deep reinforcement learning. Journal of Cheminformatics, 9(1):48, Sep 2017.Google ScholarCross Ref
- [10]Popova, M.; Isayev, O.; Tropsha, A. Deep reinforcement learning for de novo drug design. Science Advances 2018, 4, No. eaap7885.Google Scholar
- [11] G. Lima Guimaraes, B. Sanchez-Lengeling, C. Outeiral, P. L. Cunha Farias, and A. AspuruGuzik. Objective-Reinforced Generative Adversarial Networks (ORGAN) for Sequence Generation Models. ArXiv e-prints, May 2017Google Scholar
- [12]B. Sanchez-Lengeling, C. Outeiral, G. L. Guimaraes, and A. Aspuru-Guzik. Optimizing distributions over molecular space. An Objective-Reinforced Generative Adversarial Network for Inverse-design Chemistry (ORGANIC). ChemRxiv e-prints, 8 2017.Google Scholar
- [13] E. Putin et al., “Adversarial threshold neural computer for molecular de novo design,” Mol. Pharm., vol. 15, no. 10, pp. 4386–4397, 2018.Google ScholarCross Ref
- [14]M. J. Kusner, B. Paige, and J. M. Hernández-Lobato. Grammar Variational Autoencoder. arXiv e-prints:1703.01925, March 2017.Google Scholar
- [15]Arus-Pous, J.; Blaschke, T.; Ulander, S.; Reymond, J.-L.; Chen, H.; Engqvist, O. Exploring the GDB-13 chemical space using deep generative models. J. Cheminformatics 2019, 11, 20-34.Google Scholar
- [16] Olivecrona, M.; Blaschke, T.; Engquist, O.; Chen, H. Molecular de-novo design through deep reinforcement learning. J. Cheminformatics 2017, 9, 48.Google Scholar
- [17] Brooks, W. H.; Guida, W. C.; Daniel, K. G. The significance of chirality in drug design and development. Curr. Top Med. Chem. 2011,11, 760-70.Google ScholarCross Ref
- [18] O’Boyle, N.; Dalke, A. DeepSMILES: An adaptation of SMILES for use in machine-learning of chemical structures. DOI: 10.26434/chemrxiv.7097960.v1. (accessed: 2019-06-07).Google ScholarCross Ref
- [19] Stephen Heller, Alan McNaught, Stephen Stein, Dmitrii Tchekhovskoi, and Igor Pletnev. InChI - the worldwide chemical structure identifier standard. Journal of Cheminformatics, 5(1):7, 2013.Google ScholarCross Ref
- [20]Robin Winter, Floriane Montanari, Frank Noé, and DjorkArné Clevert. Learning continuous and data-driven molecular descriptors by translating equivalent chemical representations. Chemical Science, 10(6):1692–1701, 2019.Google ScholarCross Ref
- [21] De Cao N, Kipf T. MolGAN: An implicit generative model for small molecular graphs. In: ICML 2018 workshop on Theoretical Foundations and Applications of Deep Generative Models, 2018.Google Scholar
- [22]W. Jin, R. Barzilay, and T. Jaakkola. Junction tree variational autoencoder for molecular graph generation. arXiv preprint arXiv:1802.04364, 2018.Google Scholar
- [23]Gómez-Bombarelli R, Wei JN, Duvenaud D, et al. Automatic chemical design using a data-driven continuous representation of molecules. ACS Central Science 2018; 4(2): 268–76.Google Scholar
- [24]Kusner MJ, Paige B, Hernández-Lobato JM. Grammar variational autoencoder. In: International Conference on Machine Learning. PMLR, 2017, 1945–54.Google Scholar
- [25]Dai H, Tian Y, Dai B, et al. Syntax-directed variational autoencoder for molecule generation. In: International Conference on Learning Representations, 2018.Google Scholar
- [26]Simonovsky M, Komodakis N. Graphvae: T owards generation of small graphs using variational autoencoders. In: International Conference on Artificial Neural Networks. Springer, 2018,412–22.Google ScholarCross Ref
- [27]Li Y, Vinyals O, Dyer C, et al. Learning deep generative models of graphs. In: International Conference on Learning Representations, 2018.Google Scholar
- [28]Gilmer J, Schoenholz SS, Riley PF, et al. Neural message passing for quantum chemistry. In: International Conference on Machine Learning. PMLR, 2017, 1263–72.Google Scholar
- [29]You J, Ying R, Ren X, et al. GraphRNN: Generating realistic graphs with deep auto-regressive models. In: International Conference on Machine Learning. PMLR, 2018, 5708–17.Google Scholar
- [30]Popova M, Shvets M, Oliva J, et al. MolecularRNN: Generating realistic molecular graphs with optimized properties arXiv preprint arXiv:1905.13372. 2019.Google Scholar
- [31]Li, Y.; Zhang, L.; Liu, Z. Multi-objective de novo drug design with conditional graph generative model. J. Cheminformatics 2018, 10, 33-57.Google Scholar
- [32]Arjovsky, M.; Chintala, S.; Bottou, L. Wasserstein generative adversarial networks. International Conference on Machine Learning. 2017, 214-223.Google Scholar
- [33] Zhou, Z.; Kearnes, S.; Li, L.; Zare, R. N.; Riley, P. Optimization of molecules via deep reinforcement learning. arXiv preprint https://arxiv.org/abs/1810.08678 (accessed: 2019-06-07).Google Scholar
- [34]Ståhl N, Falkman G, Karlsson A, Mathiason G, Boström J. Deep Reinforcement Learning for Multiparameter Optimization in de novo Drug Design. J Chem Inf Model. 2019 Jul 22;59(7):3166-3176. doi: 10.1021/acs.jcim.9b00325. Epub 2019 Jul 5. PMID: 31273995.Google ScholarCross Ref
Index Terms
- Deep Reinforcement Learning and Docking Simulations for autonomous molecule generation in de novo Drug Design
Recommendations
A Reinforcement Learning-Based Reward Mechanism for Molecule Generation that Introduces Activity Information
MMAsia '21: Proceedings of the 3rd ACM International Conference on Multimedia in AsiaIn this paper, we propose an activity prediction method for molecule generation based on the framework of reinforcement learning. The method is used as a scoring module for the molecule generation process. By introducing information about known active ...
ILP-assisted de novo drug design
De novo design of drugs uses the three-dimensional structure of a target protein (often called the receptor) to design molecules (or ligands) that could bind to the receptor and hence inhibit its functioning. Thus, unlike a ligand-based approach, this ...
CDGCN: Conditional de novo Drug Generative Model Using Graph Convolution Networks
Research in Computational Molecular BiologyAbstractDe novo drug design is a crucial part of drug discovery which is a highly expensive and slow process. Many deep learning methods have been proposed to automate and accelerate it. However, most of the current state-of-the-art methods are limited to ...
Comments