تقرير
Optimization of binding affinities in chemical space with generative pretrained transformer and deep reinforcement learning
العنوان: | Optimization of binding affinities in chemical space with generative pretrained transformer and deep reinforcement learning |
---|---|
المؤلفون: | Xu, Xiaopeng, Zhou, Juexiao, Zhu, Chen, Zhan, Qing, Li, Zhongxiao, Zhang, Ruochi, Wang, Yu, Liao, Xingyu, Gao, Xin |
المساهمون: | Computer Science Program, Computer, Electrical and Mathematical Science and Engineering (CEMSE) Division, Computational Bioscience Research Center (CBRC), KAUST Catalysis Center (KCC), Syneron Technology, Guangzhou, China |
بيانات النشر: | American Chemical Society (ACS) |
سنة النشر: | 2023 |
المجموعة: | King Abdullah University of Science and Technology: KAUST Repository |
الوصف: | Background: The key challenge in drug discovery is to discover novel compounds with desirable properties. Among the properties, binding affinity to a target is one of the prerequisites and usually evaluated by molecular docking or quantitative structure activity relationship (QSAR) models. Methods: In this study, we developed Simplified molecular input line entry system Generative Pretrained Transformer with Reinforcement Learning (SGPT-RL), which uses a transformer decoder as the policy network of the reinforcement learning agent to optimize the binding affinity to a target. SGPT-RL was evaluated on the Moses distribution learning benchmark and two goal-directed generation tasks, with Dopamine Receptor D2 (DRD2) and Angiotensin-Converting Enzyme 2 (ACE2) as the targets. Both QSAR model and molecular docking were implemented as the optimization goals in the tasks. The popular Reinvent method was used as the baseline for comparison. Results: The results on Moses benchmark showed that SGPT-RL learned good property distributions and generated molecules with high validity and novelty. On the two goal-directed generation tasks, both SGPT-RL and Reinvent were able to generate valid molecules with improved target scores. The SGPT-RL method achieved better results than Reinvent on the ACE2 task, where molecular docking was used as the optimization goal. Further analysis shows that SGPT-RL learned conserved scaffold patterns during exploration. Conclusions: The superior performance of SGPT-RL in the ACE2 task indicates that it can be applied to the virtual screening process where molecular docking is widely used as the criteria. Besides, the scaffold patterns learned by SGPT-RL during the exploration process can assist chemists to better design and discover novel lead candidates. ; This work was supported by the grants assigned to Prof. Xin Gao from the King Abdullah University of Science and Technology (KAUST) Office of Research Administration (ORA) under Award No FCC/1/1976-44-01, FCC/1/1976-45-01, URF/1/4663-01-01, ... |
نوع الوثيقة: | report |
وصف الملف: | application/pdf |
اللغة: | unknown |
العلاقة: | github:charlesxu90/sgpt; https://chemrxiv.org/engage/chemrxiv/article-details/64272436a029a26b4cb49451Test; Xu, X., Zhou, J., Zhu, C., Zhan, Q., Li, Z., Zhang, R., Wang, Y., Liao, X., & Gao, X. (2023). Optimization of binding affinities in chemical space with generative pretrained transformer and deep reinforcement learning. https://doi.org/10.26434/chemrxiv-2023-7v4swTest; http://hdl.handle.net/10754/690881Test |
DOI: | 10.26434/chemrxiv-2023-7v4sw |
الإتاحة: | https://doi.org/10.26434/chemrxiv-2023-7v4swTest https://doi.org/10.5281/zenodo.7632731Test http://hdl.handle.net/10754/690881Test |
حقوق: | This is a preprint version of a paper and has not been peer reviewed. Archived with thanks to American Chemical Society (ACS) under a Creative Commons license, details at: https://creativecommons.org/licenses/by-nc/4.0Test/ ; https://creativecommons.org/licenses/by-nc/4.0Test/ |
رقم الانضمام: | edsbas.E2C9B0D4 |
قاعدة البيانات: | BASE |
DOI: | 10.26434/chemrxiv-2023-7v4sw |
---|