Virtual data augmentation method for reaction prediction
文献类型:期刊论文
作者 | Wu, Xinyi3; Zhang, Yun3; Yu, Jiahui3; Zhang, Chengyun3; Qiao, Haoran1; Wu, Yejian3; Wang, Xinqiao3; Wu, Zhipeng3; Duan, Hongliang2,3 |
刊名 | SCIENTIFIC REPORTS
![]() |
出版日期 | 2022-10-12 |
卷号 | 12期号:1页码:11 |
ISSN号 | 2045-2322 |
DOI | 10.1038/s41598-022-21524-6 |
通讯作者 | Duan, Hongliang(hduan@zjut.edu.cn) |
英文摘要 | To improve the performance of data-driven reaction prediction models, we propose an intelligent strategy for predicting reaction products using available data and increasing the sample size using fake data augmentation. In this research, fake data sets were created and augmented with raw data for constructing virtual training models. Fake reaction datasets were created by replacing some functional groups, i.e., in the data analysis strategy, the fake data as compounds with modified functional groups to increase the amount of data for reaction prediction. This approach was tested on five different reactions, and the results show improvements over other relevant techniques with increased model predictivity. Furthermore, we evaluated this method in different models, confirming the generality of virtual data augmentation. In summary, virtual data augmentation can be used as an effective measure to solve the problem of insufficient data and significantly improve the performance of reaction prediction. |
WOS关键词 | DEEP ; TRANSFORMER ; OUTCOMES ; SMILES |
资助项目 | National Natural Science Foundation of China[81903438] ; Natural Science Foundation of Zhejiang Province[LD22H300004] |
WOS研究方向 | Science & Technology - Other Topics |
语种 | 英语 |
WOS记录号 | WOS:000867364300051 |
出版者 | NATURE PORTFOLIO |
源URL | [http://119.78.100.183/handle/2S10ELR8/303250] ![]() |
专题 | 新药研究国家重点实验室 |
通讯作者 | Duan, Hongliang |
作者单位 | 1.Shanghai Univ Elect Power, Coll Math & Phys, Shanghai 201203, Peoples R China 2.Chinese Acad Sci, Shanghai Inst Mat Med SIMM, State Key Lab Drug Res, Shanghai 201203, Peoples R China 3.Zhejiang Univ Technol, Coll Pharmaceut Sci, Artificial Intelligence Aided Drug Discovery Inst, Hangzhou 310014, Peoples R China |
推荐引用方式 GB/T 7714 | Wu, Xinyi,Zhang, Yun,Yu, Jiahui,et al. Virtual data augmentation method for reaction prediction[J]. SCIENTIFIC REPORTS,2022,12(1):11. |
APA | Wu, Xinyi.,Zhang, Yun.,Yu, Jiahui.,Zhang, Chengyun.,Qiao, Haoran.,...&Duan, Hongliang.(2022).Virtual data augmentation method for reaction prediction.SCIENTIFIC REPORTS,12(1),11. |
MLA | Wu, Xinyi,et al."Virtual data augmentation method for reaction prediction".SCIENTIFIC REPORTS 12.1(2022):11. |
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。