期刊
COMPUTERS IN BIOLOGY AND MEDICINE
卷 157, 期 -, 页码 -出版社
PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.compbiomed.2023.106721
关键词
Drug discovery; De novo drug design; Multi-objective optimisation; SELFIES; Reinforcement learning
We proposed a multi-objective molecular generation method with a novel parsing algorithm for molecular string representation and a modified reinforcement learning method for efficient training. Our model achieved success rates of 84% in GSK3b+JNK3 inhibitor generation and 99% in Bcl-2 family inhibitor generation tasks.
The discovery of drugs to selectively remove disease-related cells is challenging in computer-aided drug design. Many studies have proposed multi-objective molecular generation methods and demonstrated their superiority using the public benchmark dataset for kinase inhibitor generation tasks. However, the dataset does not contain many molecules that violate Lipinski's rule of five. Thus, it remains unclear whether existing methods are effective in generating molecules violating the rule, such as navitoclax. To address this, we analysed the limitations of existing methods and propose a multi-objective molecular generation method with a novel parsing algorithm for molecular string representation and a modified reinforcement learning method for the efficient training of multi-objective molecular optimisation. The proposed model had success rates of 84% in GSK3b+JNK3 inhibitor generation and 99% in Bcl-2 family inhibitor generation tasks.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据