Machine Learning-Assisted High-Throughput Virtual Screening for On-Demand Customization of Advanced Energetic Materials

作     者：Siwei Song Yi Wang Fang Chen Mi Yan Qinghua Zhang Siwei Song;Yi Wang;Fang Chen;Mi Yan;Qinghua Zhang

作者机构：Institute of Chemical MaterialsChina Academy of Engineering PhysicsMianyang 621900China 

出 版 物：《Engineering》 (工程（英文）)

年 卷 期：2022年第8卷第3期

页      面：99-109页

核心收录：

学科分类：12[管理学] 081702[工学-化学工艺] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 08[工学] 0817[工学-化学工程与技术] 081104[工学-模式识别与智能系统] 0703[理学-化学] 0835[工学-软件工程] 0811[工学-控制科学与工程] 0702[理学-物理学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：the Science Challenge Project(TZ2018004) the National Natural Science Foundation of China(21875228 and 21702195)for financial support 

主　　题：Energetic materials Machine learning High-throughput virtual screening Molecular properties Synthesis 

摘      要：Finding energetic materials with tailored properties is always a significant challenge due to low research efficiency in trial and ***,a methodology combining domain knowledge,a machine learning algorithm,and experiments is presented for accelerating the discovery of novel energetic materials.A high-throughput virtual screening(HTVS)system integrating on-demand molecular generation and machine learning models covering the prediction of molecular properties and crystal packing mode scoring is *** the proposed HTVS system,candidate molecules with promising properties and a desirable crystal packing mode are rapidly targeted from the generated molecular space containing 25112 ***,a study of the crystal structure and properties shows that the good comprehensive performances of the target molecule are in agreement with the predicted results,thus verifying the effectiveness of the proposed *** work demonstrates a new research paradigm for discovering novel energetic materials and can be extended to other organic materials without manifest obstacles.