Quantum-inspired Reinforcement Learning for Synthesizable Drug Design
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913092289429504 |
|---|---|
| author | Wang, Dannong Chen, Jintai Lu, Yingzhou Shen, Minjie Chen, Lulu Liang, Zhiding Fu, Tianfan Liu, Xiao-Yang |
| author_facet | Wang, Dannong Chen, Jintai Lu, Yingzhou Shen, Minjie Chen, Lulu Liang, Zhiding Fu, Tianfan Liu, Xiao-Yang |
| contents | Synthesizable molecular design (also known as synthesizable molecular optimization) is a fundamental problem in drug discovery, and involves designing novel molecular structures to improve their properties according to drug-relevant oracle functions (i.e., objective) while ensuring synthetic feasibility. However, existing methods are mostly based on random search. To address this issue, in this paper, we introduce a novel approach using the reinforcement learning method with quantum-inspired simulated annealing policy neural network to navigate the vast discrete space of chemical structures intelligently. Specifically, we employ a deterministic REINFORCE algorithm using policy neural networks to output transitional probability to guide state transitions and local search using genetic algorithm to refine solutions to a local optimum within each iteration. Our methods are evaluated with the Practical Molecular Optimization (PMO) benchmark framework with a 10K query budget. We further showcase the competitive performance of our method by comparing it against the state-of-the-art genetic algorithms-based method. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_09183 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Quantum-inspired Reinforcement Learning for Synthesizable Drug Design Wang, Dannong Chen, Jintai Lu, Yingzhou Shen, Minjie Chen, Lulu Liang, Zhiding Fu, Tianfan Liu, Xiao-Yang Machine Learning Biomolecules Synthesizable molecular design (also known as synthesizable molecular optimization) is a fundamental problem in drug discovery, and involves designing novel molecular structures to improve their properties according to drug-relevant oracle functions (i.e., objective) while ensuring synthetic feasibility. However, existing methods are mostly based on random search. To address this issue, in this paper, we introduce a novel approach using the reinforcement learning method with quantum-inspired simulated annealing policy neural network to navigate the vast discrete space of chemical structures intelligently. Specifically, we employ a deterministic REINFORCE algorithm using policy neural networks to output transitional probability to guide state transitions and local search using genetic algorithm to refine solutions to a local optimum within each iteration. Our methods are evaluated with the Practical Molecular Optimization (PMO) benchmark framework with a 10K query budget. We further showcase the competitive performance of our method by comparing it against the state-of-the-art genetic algorithms-based method. |
| title | Quantum-inspired Reinforcement Learning for Synthesizable Drug Design |
| topic | Machine Learning Biomolecules |
| url | https://arxiv.org/abs/2409.09183 |