An explainable molecular property prediction via multi-granularity
文献类型:期刊论文
作者 | Sun, Haichao1,2; Wang, Guoyin1,2; Liu, Qun1,2; Yang, Jie3; Zheng, Mingyue4 |
刊名 | INFORMATION SCIENCES |
出版日期 | 2023-09-01 |
卷号 | 642页码:17 |
ISSN号 | 0020-0255 |
关键词 | Multi-granularity Black-box Explainable model Molecular property prediction Quantitative characterization |
DOI | 10.1016/j.ins.2023.119094 |
通讯作者 | Wang, Guoyin(wanggy@cqupt.edu.cn) |
英文摘要 | Molecular property prediction is an important task in drug discovery, especially the charac-terization of relationships between molecular substructures and their property. It is usually implemented by deep learning methods. However, deep model is a black-box that would lead to the prediction process and results are unbelievable and unreliable. To address these issues, re-searchers have begun to work on investigating explainable or substitute models for deep model. In this paper, an explainable framework of molecular property prediction with their multi -granularity representation (MgR) is proposed to characterize the contribution of substructures to prediction, called MgRX for short ('X' comes from 'eXplainable'). Specifically, the MgRX is constructed to denote the substructures' contribution of different granularity, in which each sub-structure is progressively finer from top to bottom. The finest substructures' contribution to target is implemented by the deep learning model with SHAP. Besides, several experiments are executed to analyze the effectiveness of the multi-granularity framework to molecular property. Based on above discussions, we develop a basic framework of quantitative characterization on substruc-tures' contribution to property via multi-granularity. |
WOS关键词 | INTERPRETABILITY |
资助项目 | National Key Research and Development Program of China[2021YFF0704100] ; Na-tional Natural Science Foundation of China[61936001] ; Na-tional Natural Science Foundation of China[62221005] ; Na-tional Natural Science Foundation of China[62066049] ; Chongqing Natural Science Foundation[cstc2019jcyj-cxttX0002] ; Chongqing Natural Science Foundation[cstc2021ycjh-bgzxm0013] ; Chongqing Natural Science Foundation[cstc2020jcyj-msxmX0737] ; key cooperation project of Chongqing Municipal Education Commission[HZ2021008] ; Doctoral Innovation Talent Program of Chongqing University of Posts and Telecommunica-tions[BYJS201913] ; Doctoral Innovation Talent Program of Chongqing University of Posts and Telecommunica-tions[BYJS202108] ; Doctoral Innovation Talent Program of Chongqing University of Posts and Telecommunica-tions[BYJS201902] ; Science and Technology Research Program of Chongqing Education Commission of China[KJQN201900638] ; Chongqing Postgraduate Research Innovation Project[CYB20174] |
WOS研究方向 | Computer Science |
语种 | 英语 |
出版者 | ELSEVIER SCIENCE INC |
WOS记录号 | WOS:000999135900001 |
源URL | [http://119.78.100.183/handle/2S10ELR8/306674] |
专题 | 新药研究国家重点实验室 |
通讯作者 | Wang, Guoyin |
作者单位 | 1.Chongqing Univ Posts & Telecommun, Chongqing Key Lab Computat Intelligence, Chongqing 400065, Peoples R China 2.Chongqing Univ Posts & Telecommun, Key Lab Big Data Intelligent Comp, Chongqing 400065, Peoples R China 3.Zunyi Normal Univ, Sch Phys & Elect Sci, Zunyi 563002, Peoples R China 4.Chinese Acad Sci, Shanghai Inst Mat Med, Drug Discovery & Design Ctr, State Key Lab Drug Res, Shanghai 201203, Peoples R China |
推荐引用方式 GB/T 7714 | Sun, Haichao,Wang, Guoyin,Liu, Qun,et al. An explainable molecular property prediction via multi-granularity[J]. INFORMATION SCIENCES,2023,642:17. |
APA | Sun, Haichao,Wang, Guoyin,Liu, Qun,Yang, Jie,&Zheng, Mingyue.(2023).An explainable molecular property prediction via multi-granularity.INFORMATION SCIENCES,642,17. |
MLA | Sun, Haichao,et al."An explainable molecular property prediction via multi-granularity".INFORMATION SCIENCES 642(2023):17. |
入库方式: OAI收割
来源:上海药物研究所
浏览0
下载0
收藏0
其他版本
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。