中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 上海药物研究所
  3. 中国科学院上海药物研究所
  4. 新药研究国家重点实验室
A hybrid framework for improving uncertainty quantification in deep learning-based QSAR regression modeling

文献类型：期刊论文

作者Wang, Dingyan1,2,3; Yu, Jie2,3; Chen, Lifan2,3; Li, Xutong2,3; Jiang, Hualiang2,3; Chen, Kaixian2,3; Zheng, Mingyue2,3; Luo, Xiaomin1,2,3
刊名JOURNAL OF CHEMINFORMATICS
出版日期2021-09-20
卷号13期号:1页码:17
关键词Uncertainty quantification Quantitative structure-activity relationship Bayesian neural network Applicability domain Bayesian inference Error prediction Artificial intelligence
ISSN号1758-2946
DOI10.1186/s13321-021-00551-x
通讯作者Zheng, Mingyue(myzheng@simm.ac.cn) ; Luo, Xiaomin(xmluo@simm.ac.cn)
英文摘要Reliable uncertainty quantification for statistical models is crucial in various downstream applications, especially for drug design and discovery where mistakes may incur a large amount of cost. This topic has therefore absorbed much attention and a plethora of methods have been proposed over the past years. The approaches that have been reported so far can be mainly categorized into two classes: distance-based approaches and Bayesian approaches. Although these methods have been widely used in many scenarios and shown promising performance with their distinct superiorities, being overconfident on out-of-distribution examples still poses challenges for the deployment of these techniques in real-world applications. In this study we investigated a number of consensus strategies in order to combine both distance-based and Bayesian approaches together with post-hoc calibration for improved uncertainty quantification in QSAR (Quantitative Structure-Activity Relationship) regression modeling. We employed a set of criteria to quantitatively assess the ranking and calibration ability of these models. Experiments based on 24 bioactivity datasets were designed to make critical comparison between the model we proposed and other well-studied baseline models. Our findings indicate that the hybrid framework proposed by us can robustly enhance the model ability of ranking absolute errors. Together with post-hoc calibration on the validation set, we show that well-calibrated uncertainty quantification results can be obtained in domain shift settings. The complementarity between different methods is also conceptually analyzed.
WOS关键词APPLICABILITY DOMAIN ; MOLECULAR-PROPERTIES ; TRAINING SET ; PREDICTION ; SIMILARITY ; DISCOVERY
资助项目National Science & Technology Major Project Key New Drug Creation and Manufacturing Program of China[2018ZX09711002-001-003] ; National Natural Science Foundation of China[81773634] ; Shanghai Municipal Science and Technology Major Project ; Opening Funds of Shanghai Key Laboratory of Forensic Medicine (Academy of Forensic Science)[KF1907]
WOS研究方向Chemistry ; Computer Science
语种英语
WOS记录号WOS:000698428500002
出版者BMC
源URL[http://119.78.100.183/handle/2S10ELR8/297897]  
专题新药研究国家重点实验室
通讯作者Zheng, Mingyue; Luo, Xiaomin
作者单位1.Acad Forens Sci, Shanghai Key Lab Forens Med, Shanghai 200063, Peoples R China
2.Univ Chinese Acad Sci, 19A Yuquan Rd, Beijing 100049, Peoples R China
3.Chinese Acad Sci, Drug Discovery & Design Ctr, Shanghai Inst Mat Med, State Key Lab Drug Res, 555 Zuchongzhi Rd, Shanghai 201203, Peoples R China
推荐引用方式
GB/T 7714		 Wang, Dingyan,Yu, Jie,Chen, Lifan,et al. A hybrid framework for improving uncertainty quantification in deep learning-based QSAR regression modeling[J]. JOURNAL OF CHEMINFORMATICS,2021,13(1):17.
APA Wang, Dingyan.,Yu, Jie.,Chen, Lifan.,Li, Xutong.,Jiang, Hualiang.,...&Luo, Xiaomin.(2021).A hybrid framework for improving uncertainty quantification in deep learning-based QSAR regression modeling.JOURNAL OF CHEMINFORMATICS,13(1),17.
MLA Wang, Dingyan,et al."A hybrid framework for improving uncertainty quantification in deep learning-based QSAR regression modeling".JOURNAL OF CHEMINFORMATICS 13.1(2021):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。