AI for Chemistry · 合成规划 · 酶催化

王晓瑞

深圳理工大学合成生物学院教研助理教授、特聘副教授、博士生导师，主要从事计算酶科学、智能合成规划等交叉领域研究，重点关注酶催化功能预测、智能酶设计、酶促合成规划及专业化科研智能体等方向。

中国深圳 · 深圳理工大学

邮箱 ResearchGate Google Scholar GitHub
王晓瑞

个人简介

王晓瑞博士，深圳理工大学合成生物学院教研助理教授、特聘副教授、博士生导师，长期从事计算酶科学、智能合成规划等交叉领域研究，重点关注酶催化功能预测、智能酶设计、酶促合成规划及专业化科研智能体等方向。近年来开发了 RetroPrime、Parrot、EasIFA、ChemEnzyRetroPlanner 等原创算法与应用平台，相关成果发表于 Nature Communications、Chemical Reviews、Nature Machine Intelligence、Chem、Research、Chemical Engineering Journal 等国际学术期刊。累计发表 SCI 论文 44 篇，其中第一或共同第一作者论文 12 篇，相关成果累计被引 1500+ 次。主持国家自然科学基金青年科学基金项目、国家资助博士后研究人员计划 C 档项目，并获得教育部海外博士后引才专项资助。

科研与教育经历

2026.10-至今，深圳理工大学，合成生物学院，教研助理教授、特聘副教授、博士生导师

2024.09-2026.09，浙江大学，药学院，药学，博士后，合作导师：侯廷军教授

2022.06-2024.08，浙江大学，药学院，访问学生，联合培养导师：侯廷军教授

2021.09-2024.08，澳门科技大学，中医药学院，中药学，博士研究生，导师：姚小军教授

2019.11-2021.06，腾讯，量子实验室，研究实习生，导师：谢昌谕博士

2018.09-2021.06，兰州大学，化学化工学院，化学信息学，硕士研究生，导师：姚小军教授

2014.09-2018.06，兰州大学，化学化工学院，化学（基地班），本科

近期动态

  • 2026.04 获得深圳理工大学合成生物学院助理教授聘任意向。课题组面向 AI for Chemistry、酶催化与合成生物学交叉方向招收博士生、硕士生、研究助理教授以及科研助理，欢迎感兴趣的同学和青年学者通过邮箱 wangxiaorui@suat-sz.edu.cn 咨询交流。
  • 2026.01 主持青年科学基金项目：基于人工智能的混合酶促-有机合成规划算法研究与智能应用平台开发。
  • 2025.06 发明专利 CN116227485B 获得授权，专利名称为“一种反应条件预测模型训练方法及装置”。
  • 2025 混合酶促-有机合成规划平台相关论文发表于 Nature Communications。
  • 2024 多模态酶催化活性位点标注方法相关论文发表于 Nature Communications。

研究方向

人工智能辅助合成规划算法

拟围绕人工智能辅助合成规划方向开展研究，重点关注反应预测、条件推荐、多步合成路线设计和路径合理性评估等问题。研究希望将化学知识、实验数据与智能方法相结合，发展具有可解释性、通用性和实用价值的合成规划方法，为药物分子、功能分子及复杂有机分子的高效合成设计提供支持。相关工作也希望面向自动化、智能化合成平台建设，推动计算预测、实验决策与结果评估之间的协同衔接。

酶催化预测方法

拟围绕酶催化预测与智能酶设计方向开展研究，重点关注酶功能识别、催化位点解析、酶促反应匹配、酶-底物相互作用分析、催化机理解析以及酶设计与改造等问题。研究希望结合生物催化知识、蛋白质信息与数据驱动方法，探索高效、可解释的酶催化预测策略，为酶功能注释、底物筛选、酶分子设计和绿色合成应用提供方法支持，并为智能化合成平台中的生物催化模块建设奠定基础。

面向合成规划与酶催化的专业化智能体

拟探索面向合成规划与酶催化研究的专业化科研智能体，重点关注大语言模型在任务理解、知识整合、工具协同和结果评估中的作用。研究希望将领域算法、化学与生物催化知识、数据库资源及计算工具有机连接，提升复杂科研问题分析和实验决策支持的自动化水平。相关工作也将面向智能化合成平台建设，推动从算法预测到科研工作流辅助的进一步融合。

科研成果

# 表示共同第一作者，* 表示通讯作者。

第一及共同第一作者论文

  1. Wang, X., Yin, X., Jiang, D., Zhao, H., Wu, Z., Zhang, O., Wang, J., Li, Y., Deng, Y., Liu, H., Luo, P., Han, Y., Hou, T., Yao, X., & Hsieh, C.-Y.* (2024). Multi-modal deep learning enables efficient and accurate annotation of enzymatic active sites. Nature Communications, 15, 7348. (IF: 15.7，Nature 子刊，Nature Index，CAS 1 区 TOP，JCR Q1)
  2. Wang, X.#, Yin, X.#, Zhang, X., Zhao, H., Gu, S., Wu, Z., Zhang, O., Qian, W., Huang, Y., Li, Y., Jiang, D., Wang, M., Liu, H., Yao, X., Hsieh, C.-Y., & Hou, T.* (2025). A Virtual Platform for Automated Hybrid Organic-Enzymatic Synthesis Planning. Nature Communications, 16, 10929. (IF: 15.7，Nature 子刊，Nature Index，CAS 1 区 TOP，JCR Q1)
  3. Wang, X, Li Y., Qiu, J., Chen, G., Liu, H., Liao, B., Hsieh, C.-Y., & Yao, X.* (2021). RetroPrime: A diverse, plausible and transformer-based method for single-step retrosynthesis predictions. Chemical Engineering Journal, 420, 129845. (IF: 13.2，CAS 1 区 TOP，JCR Q1)
  4. Wang, X., Hsieh, C.-Y., Yin, X., Wang, J., Li, Y., Deng, Y., Jiang, D., Wu, Z., Du, H., Chen, H., Li, Y., Liu, H., Wang, Y., Luo, P., Hou, T., & Yao, X.* (2023). Generic interpretable reaction condition predictions with open reaction condition datasets and unsupervised learning of reaction center. Research, 6, 0231. (IF: 10.7，CAS 1 区 TOP，JCR Q1)
  5. Bian, Y.#; Wang, X.#; Ma, X.#; Zhong, H.#; Pardaev, A.; Sun, L.; Liu, S.; Wang, X.; Hou, T.; Yang, W. A triangle association strategy for de novo reaction discovery. Chem 2026. DOI: 10.1016/j.chempr.2026.103204.(共同第一作者，IF：19.1，CAS 1区 TOP，JCR Q1)
  6. Wang, J.#, Wang, X.#, Sun, H., Wang, M., Zeng, Y., Jiang, D., Wu, Z., Liu, Z., Liao, B., Yao, X., Hsieh, C.-Y., Cao, D., Chen, X., & Hou, T. (2022). ChemistGA: A chemical synthesizable accessible molecular generation algorithm for real-world drug discovery. Journal of Medicinal Chemistry, 65(18), 12482-12496. (共同第一作者，IF: 6.8，CAS 1 区 TOP，JCR Q1)
  7. Zhang, O.#, Lin, H.#, Zhang, X.#, Wang, X.#, Wu, Z., Ye, Q., Zhao, W., Wang, J., Ying, K., Kang, Y., Hsieh, C.-Y., & Hou, T. (2025). Graph Neural Networks in Modern AI-Aided Drug Discovery. Chemical Reviews, 125(20), 10001-10103. (共同第一作者，IF: 55.8，CAS 1 区 TOP，JCR Q1)
  8. Tian, Y.#, Wang, X.#, Yao, X., Liu, H., & Yang, Y. (2023). Predicting molecular properties based on the interpretable graph neural network with multistep focus mechanism. Briefings in Bioinformatics, 24(1), bbac534. (共同第一作者，IF: 7.7，CAS 1 区 TOP，JCR Q1)
  9. Yin, X.#, Wang, X.#, Li, Y., Wang, J., Wang, Y., Deng, Y., Hou, T., Liu, H., Luo, P., & Yao, X.* (2023). CODD-Pred: A web server for efficient target identification and bioactivity prediction of small molecules. Journal of Chemical Information and Modeling, 63(20), 6169-6176. (共同第一作者，IF: 5.3，CAS 2 区 TOP，JCR Q1)
  10. Qian, W., Wang, X.#, Huang, Y., Kang, Y., Pan, P., Hsieh, C., & Hou, T.* (2024). Deep learning-driven insights into enzyme-substrate interaction discovery. Journal of Chemical Information and Modeling, 65(1), 187-200. (共同第一作者，IF: 5.3，CAS 2 区 TOP，JCR Q1)
  11. Qian, W.#, Wang, X.#, Kang, Y., Pan, P., Hou, T., & Hsieh, C.-Y. (2024). A general model for predicting enzyme functions based on enzymatic reactions. Journal of Cheminformatics, 16(1). (共同第一作者，IF: 5.7，CAS 2 区，JCR Q1)
  12. Li, S.#, Wang, X.#, Zhu, Y., Ge, J., Zhao, D., Xu, H., Hou, T., & Hsieh, C.* (2025). PepBAN: A deep learning framework with bilinear attention and adversarial learning for peptide-protein interaction prediction. Journal of Chemical Information and Modeling, 65(17), 9061-9074. (共同第一作者，IF: 5.3，CAS 2 区，JCR Q1)
其他共同作者论文 (定时更新)
  1. Wu, Z., Zhang, O., Wang, X., Fu, L., Zhao, H., Wang, J., Du, H., Jiang, D., Deng, Y., Cao, D., Hsieh, C.-Y., & Hou, T.* (2024). Leveraging language model for advanced multiproperty molecular optimization via prompt engineering. Nature Machine Intelligence, 6(11). (IF: 23.9，Nature 子刊，Nature Index，CAS 1 区 TOP，JCR Q1)
  2. Wang, J., Hsieh, C.-Y., Wang, M., Wang, X., Wu, Z., Jiang, D., Liao, B., Zhang, X., Yang, B., He, Q., Cao, D., Chen, X., & Hou, T.* (2021). Multi-constraint molecular generation based on conditional transformer, knowledge distillation and reinforcement learning. Nature Machine Intelligence, 3(10), 914-922. (IF: 23.9，Nature 子刊，Nature Index，CAS 1 区 TOP，JCR Q1)
  3. Li, Y., Hsieh, C.-Y., Lu, R., Gong, X., Wang, X., Li, P., Liu, S., Tian, Y., Jiang, D., Yan, J., Bai, Q., Liu, H., Zhang, S., & Yao, X.* (2022). An adaptive graph learning method for automated molecular interactions and properties predictions. Nature Machine Intelligence, 4(7). (IF: 23.9，Nature 子刊，Nature Index，CAS 1 区 TOP，JCR Q1)
  4. Zhao, H., Zhang, O., Jiang, D., Wu, Z., Du, H., Wang, X., Zhao, Y., Huang, Y., Ge, J., Hou, T.* & Yu, K.* (2025). Protein-peptide docking with a rational and accurate diffusion generative model. Nature Machine Intelligence, 7, 1308-1321. (IF: 23.9，Nature 子刊，Nature Index，CAS 1 区 TOP，JCR Q1)
  5. Zhang, O., Wang, T., Weng, G., Jiang, D., Wang, N., Wang, X., Zhao, H., Wu, J., Wang, E., Chen, G., Deng, Y., Pan, P., Kang, Y., Hsieh, C.-Y., & Hou, T.* (2023). Learning on topological surface and geometric structure for 3D molecular generation. Nature Computational Science, 3(10), 849-859. (IF: 18.3，Nature 子刊，JCR Q1)
  6. Zhu, Y., Li, S., Chen, J., Zhao, D., Wang, X., Li, Y., Liu, Y., Kong, Y., Zhang, B., Liu, C., Hou, T.* & Hsieh, C.-Y.* (2025). SynGFN: learning across chemical space with generative flow-based molecular discovery. Nature Computational Science, doi: 10.1038/s43588-025-00902-w. (IF: 18.3，Nature 子刊，JCR Q1)
  7. Tian, Y., Lu, R., Gong, X., Zhao, W., Li, Y., Wang, X., Jia, X., Li, Q., Yang, Y., Tong, H. H. Y., Arrais, J. P., Yao, X., & Liu, H. (2025). Enhancing kinase-inhibitor activity and selectivity prediction through contrastive learning. Nature Communications, 16, 10860. (IF: 15.7，Nature 子刊，Nature Index，CAS 1 区 TOP，JCR Q1)
  8. Wang, M., Li, S., Wang, J., Zhang, O., Du, H., Jiang, D., Wu, Z., Deng, Y., Kang, Y., Pan, P., Li, D., Wang, X., Yao, X., Hou, T., & Hsieh, C.-Y. (2024). ClickGen: Directed exploration of synthesizable chemical space via modular reactions and reinforcement learning. Nature Communications, 15(1). (IF: 15.7，Nature 子刊，Nature Index，CAS 1 区 TOP，JCR Q1)
  9. Deng, Y., Zhao, X., Sun, H., Chen, Y., Wang, X., Xue, X., Li, L., Song, J., Hsieh, C.-Y., Hou, T., Pan, X., Alomar, T., Ji, X., & Wang, X. (2025). RSGPT: a generative transformer model for retrosynthesis planning pre-trained on ten billion datapoints. Nature Communications, 16(1), 7012. (IF: 15.7，Nature 子刊，Nature Index，CAS 1 区 TOP，JCR Q1)
  10. Chen, Z., Gu, C., Tan, S., Wang, X., Li, Y., He, M., Lu, R., Sun, S., Hsieh, C., Yao, X., Liu, H., & Heng P.-A. (2025). Interpretable PROTAC Degradation Prediction With Structure-Informed Deep Ternary Attention Framework. Advanced Science, e08138. (IF: 14.1，CAS 1 区 TOP，JCR Q1)
  11. Zhang, X., Jiang, L., Weng, G., Shen, C., Zhang, O., Liu, M., Zhang, C., Gu, S., Wang, J., Wang, X., Du, H., Zhang, H., Zhang, K., Wang, E.* & Hou, T.* (2025). HawkDock version 2: an updated web server to predict and analyze the structures of protein-protein complexes. Nucleic Acids Research, 53(W1), W306-W315. (IF: 13.1，CAS 1 区 TOP，JCR Q1)
  12. Li, Y., Li, P., Yang, X., Hsieh, C.-Y., Zhang, S., Wang, X., Lu, R., Liu, H., & Yao, X.* (2021). Introducing block design in graph neural networks for molecular properties prediction. Chemical Engineering Journal, 414, 128817. (IF: 13.3，CAS 1 区 TOP，JCR Q1)
  13. Yin, X., Hsieh, C.-Y., Wang, X., Wu, Z., Ye, Q., Bao, H., Deng, Y., Chen, H., Luo, P., Liu, H., Hou, T., & Yao, X.* (2024). Enhancing generic reaction yield prediction through reaction condition-based contrastive learning. Research, 7, 0292. (IF: 10.7，CAS 1 区，JCR Q1)
  14. Su, H., He, L., Yu, X., Wang, Y., Yang, L., Wang, X., Yao, X., Luo, P.* & Zhang, Z.* (2024). Structural characterization and mechanisms of macrophage immunomodulatory activity of a novel polysaccharide with a galactose backbone from the processed Polygonati Rhizoma. Journal of Pharmaceutical Analysis, 14(7), 100974. (IF: 8.9，CAS 1 区，JCR Q1)
  15. Wu, J., Zhu, Y., Wang, X., Li, Y., Yin, M., Wang, T., Han, Y., Kang, Y., Deng, Y., Wu, J., Hsieh, C. & Hou, T.* (2025). HiCLR: Knowledge-Induced Hierarchical Contrastive Learning with Retrosynthesis Prediction Yields a Reaction Foundation Model. JACS Au, 5(7), 3140-3155. (IF: 8.7，CAS 1 区 TOP，JCR Q1)
  16. Jiang, D., Zhao, H., Du, H., Kang, Y., Pan, P., Wu, Z., Zeng, Y., Zhang, O., Wang, X., Wang, J., Huang, Y., Zhao, Y., Hsieh, C.-Y., Cao, D., Sun, H., & Hou, T.* (2025). Harnessing deep statistical potential for biophysical scoring of protein-peptide interactions. Acta Pharmacologica Sinica, 1-15. (IF: 8.4，CAS 1 区，JCR Q1)
  17. Jiang, D., Ye, Z., Hsieh, C.-Y., Yang, Z., Zhang, X., Kang, Y., Du, H., Wu, Z., Wang, J., Zeng, Y., Zhang, H., Wang, X., Wang, M., Yao, X., Zhang, S., Wu, J., & Hou, T.* (2023). MetalProGNet: A structure-based deep graph model for metalloprotein-ligand interaction predictions. Chemical Science, 14(8), 2054-2069. (IF: 7.6，Nature Index，CAS 1 区 TOP，JCR Q1)
  18. Wang, T., Wang, L., Zhang, X., Shen, C., Zhang, O., Wang, J., Wu, J., Jin, R., Zhou, D., Chen, S., Liu, L., Wang, X., Hsieh, C.-Y., Chen, G., Pan, P., Kang, Y., & Hou, T.* (2023). Comprehensive assessment of protein loop modeling programs on large-scale datasets: prediction accuracy and efficiency. Briefings in Bioinformatics, 25(1). (IF: 7.7，CAS 1 区，JCR Q1)
  19. Du, H., Jiang, D., Zhang, O., Wu, Z., Gao, J., Zhang, X., Wang, X., Deng, Y., Kang, Y., Li, D., Pan, P., Hsieh, C.-Y., & Hou, T.* (2023). A flexible data-free framework for structure-based de novo drug design with reinforcement learning. Chemical Science, 14(43), 12166-12181. (IF: 7.6，Nature Index，CAS 1 区 TOP，JCR Q1)
  20. Yin, X., Wang, X., Wu, Z., Li, Q., Kang, Y., Deng, Y., Luo, P., Liu, H., Shi, G., Wang, Z., Yao, X., Hsieh, C.-Y., & Hou, T.* (2025). Syn-MolOpt: A synthesis planning-driven molecular optimization method using data-derived functional reaction templates. Journal of Cheminformatics, 17(1), 27. (IF: 7.1，CAS 2 区，JCR Q1)
  21. Gu, S., Yang, Y., Zhao, Y., Qiu, J., Wang, X., Tong, H. H. Y., Liu, L., Wan, X., Liu, H., Hou, T. & Kang, Y.* (2024). Evaluation of AlphaFold2 Structures for Hit Identification across Multiple Scenarios. Journal of Chemical Information and Modeling, 64(9), 3630-3639. (IF: 5.3，CAS 2 区，JCR Q1)
  22. Zhao, H., Jiang, D., Shen, C., Zhang, J., Zhang, X., Wang, X., Nie, D., Hou, T.* & Kang, Y.* (2024). Comprehensive Evaluation of 10 Docking Programs on a Diverse Set of Protein-Cyclic Peptide Complexes. Journal of Chemical Information and Modeling, 64(6), 2112-2124. (IF: 5.3，CAS 2 区，JCR Q1)
  23. Wang, J., Zeng, Y., Sun, H., Wang, J., Wang, X., Jin, R., Wang, M., Zhang, X., Cao, D., Chen, X., Hsieh, C. & Hou, T.* (2023). Molecular Generation with Reduced Labeling through Constraint Architecture. Journal of Chemical Information and Modeling, 63(11), 3319-3327. (IF: 5.3，CAS 2 区，JCR Q1)
  24. Jiang, D., Zhao, H., Du, H., Deng, Y., Wu, Z., Wang, J., Zeng, Y., Zhang, H., Wang, X., Wu, J., Hsieh, C. & Hou, T.* (2023). How Good Are Current Docking Programs at Nucleic Acid-Ligand Docking? A Comprehensive Evaluation. Journal of Chemical Theory and Computation, 19(16), 5633-5647. (IF: 5.5，CAS 1 区，JCR Q1)
  25. Zhang, W., Bai, H., Wang, Y., Wang, X., Jin, R., Guo, H., Lai, H., Tang, Y. & Wang, Y.* (2024). Identification of mIDH1 R132C/S280F Inhibitors from Natural Products by Integrated Molecular Docking, Pharmacophore Modeling and Molecular Dynamics Simulations. Pharmaceuticals, 17(3), 336. (IF: 4.8，CAS 2 区，JCR Q1)
  26. Bai, H., Cheng, Y., Jia, S., Wang, X., Jin, R., Guo, H., Tang, Y., & Wang, Y.* (2025). Machine learning-based QSAR and structure-based virtual screening guided discovery of novel mIDH1 inhibitors from natural products. Journal of Computer-Aided Molecular Design, 39(1), 44. (IF: 3.2，CAS 2 区，JCR Q2)
  27. Ge, H., Mao, L., Zhao, J., Wang, Y., Shi, D., Yang, X., Wang, X., Liu, H., & Yao, X.* (2021). Discovery of novel IDO1 inhibitors via structure-based virtual screening and biological assays. Journal of Computer-Aided Molecular Design, 35(5), 679-694. (IF: 3.2，CAS 2 区，JCR Q2)
  28. Jiang, D., Du, H., Zhao, H., Deng, Y., Wu, Z., Wang, J., Zeng, Y., Zhang, H., Wang, X., Wang, E., Hou, T., & Hsieh, C.-Y. (2024). Assessing the performance of MM/PBSA and MM/GBSA methods. 10. Prediction reliability of binding affinities and binding poses for RNA-ligand complexes. Physical Chemistry Chemical Physics, 26(13), 10323-10335. (IF: 2.9，CAS 3 区，JCR Q2)

主持基金项目

  • 2026.01-2028.12 青年科学基金项目，22503082，主持，30 万元。项目名称：基于人工智能的混合酶促-有机合成规划算法研究与智能应用平台开发。
  • 2024.10-2026.10 国家资助博士后研究人员计划 C 档，GZC20252369，主持，24 万元。

工具与平台

授权发明专利

  • 王晓瑞，康玉，侯廷军，谢昌谕，曹东升，邓亚峰，施慧。一种反应条件预测模型训练方法及装置（发明专利）。专利号：CN116227485B。授权公告日：2025.06.24。

个人荣誉

  • 2021-2024 澳门科技大学研究生参与学术全额奖学金。
  • 2018-2021 兰州大学研究生学业奖学金。
  • 2017.10 兰州大学本科生三等奖学金。
  • 2017.09 兰州大学优秀研究生培养奖学金。