Structure-Based de Novo Molecular Generator Combined with Artificial Intelligence and Docking SimulationsClick to copy article linkArticle link copied!
- Biao MaBiao MaCenter for Cluster Development and Coordination, Foundation for Biomedical Research and Innovation at Kobe, 1-5-2, Minatojima-minamimachi, Chuo-ku, Kobe, Hyogo 650-0047, JapanRIKEN Center for Computational Science, 7-1-26 Minatojima-minamimachi, Chuo-ku, Kobe, Hyogo 650-0047, JapanMore by Biao Ma
- Kei Terayama*Kei Terayama*Email: [email protected]Graduate School of Medicine, Kyoto University, 53 Shogoin-Kawaharacho, Sakyo-ku, Kyoto 606-8507, JapanGraduate School of Medical Life Science, Yokohama City University, 1-7-29, Suehiro-cho, Tsurumi-ku, Yohohama, Kanagawa 230-0045, JapanMore by Kei Terayama
- Shigeyuki MatsumotoShigeyuki MatsumotoGraduate School of Medicine, Kyoto University, 53 Shogoin-Kawaharacho, Sakyo-ku, Kyoto 606-8507, JapanMore by Shigeyuki Matsumoto
- Yuta IsakaYuta IsakaCenter for Cluster Development and Coordination, Foundation for Biomedical Research and Innovation at Kobe, 1-5-2, Minatojima-minamimachi, Chuo-ku, Kobe, Hyogo 650-0047, JapanRIKEN Center for Computational Science, 7-1-26 Minatojima-minamimachi, Chuo-ku, Kobe, Hyogo 650-0047, JapanMore by Yuta Isaka
- Yoko SasakuraYoko SasakuraCenter for Cluster Development and Coordination, Foundation for Biomedical Research and Innovation at Kobe, 1-5-2, Minatojima-minamimachi, Chuo-ku, Kobe, Hyogo 650-0047, JapanRIKEN Center for Computational Science, 7-1-26 Minatojima-minamimachi, Chuo-ku, Kobe, Hyogo 650-0047, JapanMore by Yoko Sasakura
- Hiroaki IwataHiroaki IwataGraduate School of Medicine, Kyoto University, 53 Shogoin-Kawaharacho, Sakyo-ku, Kyoto 606-8507, JapanMore by Hiroaki Iwata
- Mitsugu ArakiMitsugu ArakiGraduate School of Medicine, Kyoto University, 53 Shogoin-Kawaharacho, Sakyo-ku, Kyoto 606-8507, JapanMore by Mitsugu Araki
- Yasushi Okuno*Yasushi Okuno*Email: [email protected]Center for Cluster Development and Coordination, Foundation for Biomedical Research and Innovation at Kobe, 1-5-2, Minatojima-minamimachi, Chuo-ku, Kobe, Hyogo 650-0047, JapanRIKEN Center for Computational Science, 7-1-26 Minatojima-minamimachi, Chuo-ku, Kobe, Hyogo 650-0047, JapanGraduate School of Medicine, Kyoto University, 53 Shogoin-Kawaharacho, Sakyo-ku, Kyoto 606-8507, JapanMore by Yasushi Okuno
Abstract

Recently, molecular generation models based on deep learning have attracted significant attention in drug discovery. However, most existing molecular generation models have serious limitations in the context of drug design wherein they do not sufficiently consider the effect of the three-dimensional (3D) structure of the target protein in the generation process. In this study, we developed a new deep learning-based molecular generator, SBMolGen, that integrates a recurrent neural network, a Monte Carlo tree search, and docking simulations. The results of an evaluation using four target proteins (two kinases and two G protein-coupled receptors) showed that the generated molecules had a better binding affinity score (docking score) than the known active compounds, and the generated molecules possessed a broader chemical space distribution. SBMolGen not only generates novel binding active molecules but also presents 3D docking poses with target proteins, which will be useful in subsequent drug design. The code is available at https://github.com/clinfo/SBMolGen.
Cited By
Smart citations by scite.ai include citation statements extracted from the full text of the citing article. The number of the statements may be higher than the number of citations provided by ACS Publications if one paper cites another multiple times or lower if scite has not yet processed some of the citing articles.
This article is cited by 42 publications.
- Teresa Maria Creanza, Domenico Alberga, Cosimo Patruno, Giuseppe Felice Mangiatordi, Nicola Ancona. Transformer Decoder Learns from a Pretrained Protein Language Model to Generate Ligands with High Affinity. Journal of Chemical Information and Modeling 2025, 65
(3)
, 1258-1277. https://doi.org/10.1021/acs.jcim.4c02019
- Masami Sako, Nobuaki Yasuo, Masakazu Sekijima. DiffInt: A Diffusion Model for Structure-Based Drug Design with Explicit Hydrogen Bond Interaction Guidance. Journal of Chemical Information and Modeling 2025, 65
(1)
, 71-82. https://doi.org/10.1021/acs.jcim.4c01385
- Takamasa Suzuki, Dian Ma, Nobuaki Yasuo, Masakazu Sekijima. Mothra: Multiobjective de novo Molecular Generation Using Monte Carlo Tree Search. Journal of Chemical Information and Modeling 2024, 64
(19)
, 7291-7302. https://doi.org/10.1021/acs.jcim.4c00759
- Milo Roucairol, Alexios Georgiou, Tristan Cazenave, Filippo Prischi, Olivier E. Pardo. DrugSynthMC: An Atom-Based Generation of Drug-like Molecules with Monte Carlo Search. Journal of Chemical Information and Modeling 2024, 64
(18)
, 7097-7107. https://doi.org/10.1021/acs.jcim.4c01451
- Yuki Matsukiyo, Atsushi Tengeiji, Chen Li, Yoshihiro Yamanishi. Transcriptionally Conditional Recurrent Neural Network for De Novo Drug Design. Journal of Chemical Information and Modeling 2024, 64
(15)
, 5844-5852. https://doi.org/10.1021/acs.jcim.4c00531
- Yidan Tang, Rocco Moretti, Jens Meiler. Recent Advances in Automated Structure-Based De Novo Drug Design. Journal of Chemical Information and Modeling 2024, 64
(6)
, 1794-1805. https://doi.org/10.1021/acs.jcim.4c00247
- Hiroaki Iwata, Taichi Nakai, Takuto Koyama, Shigeyuki Matsumoto, Ryosuke Kojima, Yasushi Okuno. VGAE-MCTS: A New Molecular Generative Model Combining the Variational Graph Auto-Encoder and Monte Carlo Tree Search. Journal of Chemical Information and Modeling 2023, 63
(23)
, 7392-7400. https://doi.org/10.1021/acs.jcim.3c01220
- Miho Hatanaka, Hiromoto Kato, Minami Sakai, Kosuke Kariya, Shunsuke Nakatani, Takayoshi Yoshimura, Taichi Inagaki. Insights into the Luminescence Quantum Yields of Cyclometalated Iridium(III) Complexes: A Density Functional Theory and Machine Learning Approach. The Journal of Physical Chemistry A 2023, 127
(36)
, 7630-7637. https://doi.org/10.1021/acs.jpca.3c02179
- Song Li, Chao Hu, Song Ke, Chenxing Yang, Jun Chen, Yi Xiong, Hao Liu, Liang Hong. LS-MolGen: Ligand-and-Structure Dual-Driven Deep Reinforcement Learning for Target-Specific Molecular Generation Improves Binding Affinity and Novelty. Journal of Chemical Information and Modeling 2023, 63
(13)
, 4207-4215. https://doi.org/10.1021/acs.jcim.3c00587
- Wenyi Zhang, Kaiyue Zhang, Jing Huang. A Simple Way to Incorporate Target Structural Information in Molecular Generative Models. Journal of Chemical Information and Modeling 2023, 63
(12)
, 3719-3730. https://doi.org/10.1021/acs.jcim.3c00293
- Yuwei Yang, Chang-Yu Hsieh, Yu Kang, Tingjun Hou, Huanxiang Liu, Xiaojun Yao. Deep Generation Model Guided by the Docking Score for Active Molecular Design. Journal of Chemical Information and Modeling 2023, 63
(10)
, 2983-2991. https://doi.org/10.1021/acs.jcim.3c00572
- Xiao-Nan Jia, Wei-Jia Wang, Bo Yin, Lin-Jing Zhou, Yong-Qi Zhen, Lan Zhang, Xian-Li Zhou, Hai-Ning Song, Yong Tang, Feng Gao. Deep Learning Promotes the Screening of Natural Products with Potential Microtubule Inhibition Activity. ACS Omega 2022, 7
(32)
, 28334-28341. https://doi.org/10.1021/acsomega.2c02854
- Shen Wang, Tong Lin, Tianyi Peng, Enming Xing, Sijie Chen, Levent Burak Kara, Xiaolin Cheng. TopMT-GAN: a 3D topology-driven generative model for efficient and diverse structure-based ligand design. Chemical Science 2025, 16
(6)
, 2796-2809. https://doi.org/10.1039/D4SC05211K
- Kusum Gurung†, Saurav K. Mishra†, Tabsum Chhetri, Sneha Roy, Anagha Balakrishnan, John J. Georrge*. Recent Knowledge in Drug Design and Development: Automation and Advancement. 2025, 153-181. https://doi.org/10.1002/9781394280735.ch9
- Hanyang Qu, Shengpeng Wang, Mingyang He, Yuhui Wu, Fei Yan, Tiaotiao Liu, Meiling Zhang. Is it feasible to use AI-based drug design methods in the process of generating effective COVID-19 inhibitors? A validation study using molecular docking, molecular simulation, and pharmacophore methods. Journal of Biomolecular Structure and Dynamics 2024, 119 , 1-14. https://doi.org/10.1080/07391102.2024.2445169
- Yanlin Fei, Yurui Li, Zhiling Zhou, Haohan Wang. DiffSim: Aligning Diffusion Model and Molecular Dynamics Simulation for Blind Docking. 2024, 669-674. https://doi.org/10.1109/BIBM62325.2024.10822415
- Yaodong Yang, Guangyong Chen, Jinpeng Li, Junyou Li, Odin Zhang, Xujun Zhang, Lanqing Li, Jianye Hao, Ercheng Wang, Pheng-Ann Heng. Enabling target-aware molecule generation to follow multi objectives with Pareto MCTS. Communications Biology 2024, 7
(1)
https://doi.org/10.1038/s42003-024-06746-w
- Jianmin Wang, Jiashun Mao, Chunyan Li, Hongxin Xiang, Xun Wang, Shuang Wang, Zixu Wang, Yangyang Chen, Yuquan Li, Kyoung Tai No, Tao Song, Xiangxiang Zeng. Interface-aware molecular generative framework for protein–protein interaction modulators. Journal of Cheminformatics 2024, 16
(1)
https://doi.org/10.1186/s13321-024-00930-0
- Wen Sun, Cheng Li, Jingtian Yu, Xiaoyan Liang, Xiaochen Gao, Baoxing Shen, Yaqiong Yang. Signal-amplified detection of amyloid-β aggregates based on plasmon-enhanced fluorescence. Microchemical Journal 2024, 206 , 111541. https://doi.org/10.1016/j.microc.2024.111541
- Ifra Saifi, Basharat Ahmad Bhat, Syed Suhail Hamdani, Umar Yousuf Bhat, Carlos Alberto Lobato-Tapia, Mushtaq Ahmad Mir, Tanvir Ul Hasan Dar, Showkat Ahmad Ganie. Artificial intelligence and cheminformatics tools: a contribution to the drug development and chemical science. Journal of Biomolecular Structure and Dynamics 2024, 42
(12)
, 6523-6541. https://doi.org/10.1080/07391102.2023.2234039
- Solene Bechelli, Jerome Delhommelle. AI's role in pharmaceuticals: Assisting drug design from protein interactions to drug development. Artificial Intelligence Chemistry 2024, 2
(1)
, 100038. https://doi.org/10.1016/j.aichem.2023.100038
- Achyut Tiwari, Ashok Kumar Gupta, Tanmay Gupta. A robust approach to shear strength prediction of reinforced concrete deep beams using ensemble learning with SHAP interpretability. Soft Computing 2024, 28
(7-8)
, 6343-6365. https://doi.org/10.1007/s00500-023-09495-w
- Marco Kemmerling, Daniel Lütticke, Robert H. Schmitt. Beyond games: a systematic review of neural Monte Carlo tree search applications. Applied Intelligence 2024, 54
(1)
, 1020-1046. https://doi.org/10.1007/s10489-023-05240-w
- Yugo Shimizu, Masateru Ohta, Shoichi Ishida, Kei Terayama, Masanori Osawa, Teruki Honma, Kazuyoshi Ikeda. AI-driven molecular generation of not-patented pharmaceutical compounds using world open patent data. Journal of Cheminformatics 2023, 15
(1)
https://doi.org/10.1186/s13321-023-00791-z
- Shoichi Ishida, Tanuj Aasawat, Masato Sumita, Michio Katouda, Tatsuya Yoshizawa, Kazuki Yoshizoe, Koji Tsuda, Kei Terayama. ChemTSv2
: Functional molecular design using de novo molecule generator. WIREs Computational Molecular Science 2023, 13
(6)
https://doi.org/10.1002/wcms.1680
- Jianmin Wang, Jiashun Mao, Chunyan Li, Hongxin Xiang, Xun Wang, Shuang Wang, Zixu Wang, Yangyang Chen, Yuquan Li, Kyoung Tai No, Tao Song, Xiangxiang Zeng. Interface-aware molecular generative framework for protein-protein interaction modulators. 2023https://doi.org/10.1101/2023.10.10.557742
- Hanyang Qu, Shengpeng Wang, Mingyang He, Yuhui Wu, Fei Yan, Tiaotiao Liu, Meiling Zhang. A Novel de novo Design Study of Potent SARS-CoV-2 Main Protease Inhibitors Based on Reinforcement Learning and Molecular Docking. 2023https://doi.org/10.21203/rs.3.rs-3199639/v1
- Jiayue Hu, Wang Yu, Chao Pang, Junru Jin, Nhat Truong Pham, Balachandran Manavalan, Leyi Wei. DrugormerDTI: Drug Graphormer for drug–target interaction prediction. Computers in Biology and Medicine 2023, 161 , 106946. https://doi.org/10.1016/j.compbiomed.2023.106946
- Ana L. Chávez-Hernández, Edgar López-López, José L. Medina-Franco. Yin-yang in drug discovery: rethinking de novo design and development of predictive models. Frontiers in Drug Discovery 2023, 3 https://doi.org/10.3389/fddsv.2023.1222655
- Wenyi Zhang, Kaiyue Zhang, Jing Huang. A Simple Way to Incorporate Target Structural Information in Molecular Generative Models. 2023https://doi.org/10.1101/2023.02.17.529000
- Lijuan Yang, Chao Jin, Guanghui Yang, Zhitong Bing, Liang Huang, Yuzhen Niu, Lei Yang. Transformer-based deep learning method for optimizing ADMET properties of lead compounds. Physical Chemistry Chemical Physics 2023, 25
(3)
, 2377-2385. https://doi.org/10.1039/D2CP05332B
- Bandi Sai Kiran Reddy, R. Nithya. Comparative analysis of accuracy in image forensics for authentication using novel convolutional neural networks with artificial neural networks algorithm. 2023, 020188. https://doi.org/10.1063/5.0178983
- Xun Wang, Changnan Gao, Peifu Han, Xue Li, Wenqi Chen, Alfonso Rodríguez Patón, Shuang Wang, Pan Zheng. PETrans: De Novo Drug Design with Protein-Specific Encoding Based on Transfer Learning. International Journal of Molecular Sciences 2023, 24
(2)
, 1146. https://doi.org/10.3390/ijms24021146
- Yurim Lee, Kyudam Choi, Cheongwon Kim. Docking-based Multi-objective Molecular optimization Pipeline using Structure-constrained Genetic Algorithm. 2022, 3438-3445. https://doi.org/10.1109/BIBM55620.2022.9995456
- Chong Lu, Shien Liu, Weihua Shi, Jun Yu, Zhou Zhou, Xiaoxiao Zhang, Xiaoli Lu, Faji Cai, Ning Xia, Yikai Wang. Systemic evolutionary chemical space exploration for drug discovery. Journal of Cheminformatics 2022, 14
(1)
https://doi.org/10.1186/s13321-022-00598-4
- Morgan Thomas, Noel M. O’Boyle, Andreas Bender, Chris de Graaf. Augmented Hill-Climb increases reinforcement learning efficiency for language-based de novo molecule generation. Journal of Cheminformatics 2022, 14
(1)
https://doi.org/10.1186/s13321-022-00646-z
- Marta Bon, Alan Bilsland, Justin Bower, Kirsten McAulay. Fragment‐based drug discovery—the importance of high‐quality molecule libraries. Molecular Oncology 2022, 16
(21)
, 3761-3777. https://doi.org/10.1002/1878-0261.13277
- Susanne Sauer, Hans Matter, Gerhard Hessler, Christoph Grebner. Optimizing interactions to protein binding sites by integrating docking-scoring strategies into generative AI methods. Frontiers in Chemistry 2022, 10 https://doi.org/10.3389/fchem.2022.1012507
- Lijuan Yang, Guanghui Yang, Zhitong Bing, Yuan Tian, Liang Huang, Yuzhen Niu, Lei Yang. Accelerating the discovery of anticancer peptides targeting lung and breast cancers with the Wasserstein autoencoder model and PSO algorithm. Briefings in Bioinformatics 2022, 23
(5)
https://doi.org/10.1093/bib/bbac320
- Hao Qian, Cheng Lin, Dengwei Zhao, Shikui Tu, Lei Xu, . AlphaDrug: protein target specific de novo molecular generation. PNAS Nexus 2022, 1
(4)
https://doi.org/10.1093/pnasnexus/pgac227
- Haiping Zhang, Konda Mani Saravanan, Yang Yang, Yanjie Wei, Pan Yi, John Z H Zhang. Generating and screening
de novo
compounds against given targets using ultrafast deep learning models as core components. Briefings in Bioinformatics 2022, 23
(4)
https://doi.org/10.1093/bib/bbac226
- Jeff Guo, Vendy Fialková, Juan Diego Arango, Christian Margreitter, Jon Paul Janet, Kostas Papadopoulos, Ola Engkvist, Atanas Patronov. Improving de novo molecular design with curriculum learning. Nature Machine Intelligence 2022, 4
(6)
, 555-563. https://doi.org/10.1038/s42256-022-00494-4
- SM Bargeen Alam Turzo, Eric R. Hantz, Steffen Lindert. Applications of machine learning in computer-aided drug discovery. QRB Discovery 2022, 3 https://doi.org/10.1017/qrd.2022.12
- Shruti Goel, Mihir Khulbe, Reena Sharma, Abha Kathuria. Ai's Assistance in Amplifying the Competence of Chemists. SSRN Electronic Journal 2022, 524 https://doi.org/10.2139/ssrn.4055501
- Jieun Choi, Juyong Lee. V-Dock: Fast Generation of Novel Drug-like Molecules Using Machine-Learning-Based Docking Score and Molecular Optimization. International Journal of Molecular Sciences 2021, 22
(21)
, 11635. https://doi.org/10.3390/ijms222111635
Article Views are the COUNTER-compliant sum of full text article downloads since November 2008 (both PDF and HTML) across all institutions and individuals. These metrics are regularly updated to reflect usage leading up to the last few days.
Citations are the number of other articles citing this article, calculated by Crossref and updated daily. Find more information about Crossref citation counts.
The Altmetric Attention Score is a quantitative measure of the attention that a research article has received online. Clicking on the donut icon will load a page at altmetric.com with additional details about the score and the social media presence for the given article. Find more information on the Altmetric Attention Score and how the score is calculated.