Dannong Wang, Jintai Chen, Zhiding Liang, Tianfan Fu, Xiao-Yang Liu
{"title":"用于可合成药物设计的量子启发强化学习","authors":"Dannong Wang, Jintai Chen, Zhiding Liang, Tianfan Fu, Xiao-Yang Liu","doi":"arxiv-2409.09183","DOIUrl":null,"url":null,"abstract":"Synthesizable molecular design (also known as synthesizable molecular\noptimization) is a fundamental problem in drug discovery, and involves\ndesigning novel molecular structures to improve their properties according to\ndrug-relevant oracle functions (i.e., objective) while ensuring synthetic\nfeasibility. However, existing methods are mostly based on random search. To\naddress this issue, in this paper, we introduce a novel approach using the\nreinforcement learning method with quantum-inspired simulated annealing policy\nneural network to navigate the vast discrete space of chemical structures\nintelligently. Specifically, we employ a deterministic REINFORCE algorithm\nusing policy neural networks to output transitional probability to guide state\ntransitions and local search using genetic algorithm to refine solutions to a\nlocal optimum within each iteration. Our methods are evaluated with the\nPractical Molecular Optimization (PMO) benchmark framework with a 10K query\nbudget. We further showcase the competitive performance of our method by\ncomparing it against the state-of-the-art genetic algorithms-based method.","PeriodicalId":501022,"journal":{"name":"arXiv - QuanBio - Biomolecules","volume":"20 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Quantum-inspired Reinforcement Learning for Synthesizable Drug Design\",\"authors\":\"Dannong Wang, Jintai Chen, Zhiding Liang, Tianfan Fu, Xiao-Yang Liu\",\"doi\":\"arxiv-2409.09183\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Synthesizable molecular design (also known as synthesizable molecular\\noptimization) is a fundamental problem in drug discovery, and involves\\ndesigning novel molecular structures to improve their properties according to\\ndrug-relevant oracle functions (i.e., objective) while ensuring synthetic\\nfeasibility. However, existing methods are mostly based on random search. To\\naddress this issue, in this paper, we introduce a novel approach using the\\nreinforcement learning method with quantum-inspired simulated annealing policy\\nneural network to navigate the vast discrete space of chemical structures\\nintelligently. Specifically, we employ a deterministic REINFORCE algorithm\\nusing policy neural networks to output transitional probability to guide state\\ntransitions and local search using genetic algorithm to refine solutions to a\\nlocal optimum within each iteration. Our methods are evaluated with the\\nPractical Molecular Optimization (PMO) benchmark framework with a 10K query\\nbudget. We further showcase the competitive performance of our method by\\ncomparing it against the state-of-the-art genetic algorithms-based method.\",\"PeriodicalId\":501022,\"journal\":{\"name\":\"arXiv - QuanBio - Biomolecules\",\"volume\":\"20 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-13\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - QuanBio - Biomolecules\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2409.09183\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - QuanBio - Biomolecules","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.09183","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Quantum-inspired Reinforcement Learning for Synthesizable Drug Design
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.