Reducing overconfident errors in molecular property classification using Posterior Network
文献类型：期刊论文
| 作者 | Fan, Zhehuan1,2; Yu, Jie1,2; Zhang, Xiang3; Chen, Yijie3; Sun, Shihui3; Zhang, Yuanyuan1,2; Chen, Mingan1,4,5; Xiao, Fu3; Wu, Wenyong5; Li, Xutong1,2 |
| 刊名 | PATTERNS
 |
| 出版日期 | 2024-06-14 |
| 卷号 | 5期号:6页码:100991 |
| DOI | 10.1016/j.patter.2024.100991 |
| 文献子类 | Article |
| 英文摘要 | Deep -learning -based classification models are increasingly used for predicting molecular properties in drug development. However, traditional classification models using the Softmax function often give overconfident mispredictions for out -of -distribution samples, highlighting a critical lack of accurate uncertainty estimation. Such limitations can result in substantial costs and should be avoided during drug development. Inspired by advances in evidential deep learning and Posterior Network, we replaced the Softmax function with a normalizing flow to enhance the uncertainty estimation ability of the model in molecular property classification. The proposed strategy was evaluated across diverse scenarios, including simulated experiments based on a synthetic dataset, ADMET predictions, and ligand-based virtual screening. The results demonstrate that compared with the vanilla model, the proposed strategy effectively alleviates the problem of giving overconfident but incorrect predictions. Our findings support the promising application of evidential deep learning in drug development and offer a valuable framework for further research. |
| WOS关键词 | UNCERTAINTY QUANTIFICATION ; PREDICTION ; DISCOVERY ; ADMET |
| WOS研究方向 | Computer Science |
| 语种 | 英语 |
| WOS记录号 | WOS:001255906600001 |
| 出版者 | CELL PRESS |
| 源URL | [http://119.78.100.183/handle/2S10ELR8/317015]  |
| 专题 | 新药研究国家重点实验室 |
| 通讯作者 | Zheng, Mingyue; Luo, Xiaomin; Wang, Dingyan |
| 作者单位 | 1.Chinese Acad Sci, Shanghai Inst Mat Med, Drug Discovery & Design Ctr, State Key Lab Drug Res, 555 Zuchongzhi Rd, Shanghai 201203, Peoples R China 2.Univ Chinese Acad Sci, 19A Yuquan Rd, Beijing 100049, Peoples R China 3.Nanjing Univ Chinese Med, Sch Chinese Mat Med, Nanjing 210023, Peoples R China 4.Shanghai Tech Univ, Sch Phys Sci & Technol, Shanghai 201210, Peoples R China 5.Lingang Lab, Shanghai 200031, Peoples R China |
| 推荐引用方式 GB/T 7714 | Fan, Zhehuan,Yu, Jie,Zhang, Xiang,et al. Reducing overconfident errors in molecular property classification using Posterior Network[J]. PATTERNS,2024,5(6):100991. |
| APA | Fan, Zhehuan.,Yu, Jie.,Zhang, Xiang.,Chen, Yijie.,Sun, Shihui.,...&Wang, Dingyan.(2024).Reducing overconfident errors in molecular property classification using Posterior Network.PATTERNS,5(6),100991. |
| MLA | Fan, Zhehuan,et al."Reducing overconfident errors in molecular property classification using Posterior Network".PATTERNS 5.6(2024):100991. |
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。