Predictive deep learning models for environmental properties: the direct calculation of octanol-water partition coefficients from molecular graphs | |
Wang, Zihao1; Su, Yang1; Shen, Weifeng1; Jin, Saimeng1; Clark, James H.2; Ren, Jingzheng3; Zhang, Xiangping4 | |
刊名 | GREEN CHEMISTRY |
2019-08-21 | |
卷号 | 21期号:16页码:4555-4565 |
ISSN号 | 1463-9262 |
DOI | 10.1039/c9gc01968e |
英文摘要 | As an essential environmental property, the octanol-water partition coefficient (K-OW) quantifies the lipophilicity of a compound and it could be further employed to predict toxicity. Thus, it is an indispensable factor that should be considered for screening and development of green solvents with respect to unconventional and novel compounds. Herein, a deep-learning-assisted predictive model has been developed to accurately and reliably calculate log K-OW values for organic compounds. An embedding algorithm was specifically established for generating signatures automatically for molecular structures to express structural information and connectivity. Afterwards, the Tree-structured long short-term memory (Tree-LSTM) network was used in conjunction with signature descriptors for automatic feature selection, and it was then coupled with the back-propagation neural network to develop a deep neural network (DNN), which is used for modeling quantity structure-property relationship (QSPR) to predict log K-OW. Compared with an authoritative estimation method, the proposed DNN-based QSPR model exhibited better predictive accuracy and greater discriminative power in terms of the structural isomers and stereoisomers. As such, the proposed deep learning approach can act as a promising and intelligent tool for developing environmental property prediction methods for guiding development or screening of green solvents. |
资助项目 | National Natural Science Foundation of China[21606026] ; National Natural Science Foundation of China[21878028] ; Fundamental Research Funds for the Central Universities[2019CDQYHG021] ; Fundamental Research Funds for the Central Universities[2019CDXYHG0013] ; Beijing Hundreds of Leading Talents Training Project of Science and Technology[Z171100001117154] |
WOS关键词 | PHYSICOCHEMICAL PROPERTIES ; EXTRACTIVE DISTILLATION ; IONIC LIQUIDS ; AQUEOUS SOLUBILITY ; GREEN CHEMISTRY ; QSAR MODELS ; PART 2. ; CHEMICALS ; DESIGN ; VALIDATION |
WOS研究方向 | Chemistry ; Science & Technology - Other Topics |
语种 | 英语 |
出版者 | ROYAL SOC CHEMISTRY |
WOS记录号 | WOS:000480643800028 |
资助机构 | National Natural Science Foundation of China ; Fundamental Research Funds for the Central Universities ; Beijing Hundreds of Leading Talents Training Project of Science and Technology |
内容类型 | 期刊论文 |
源URL | [http://ir.ipe.ac.cn/handle/122111/30536] |
专题 | 中国科学院过程工程研究所 |
通讯作者 | Shen, Weifeng; Jin, Saimeng |
作者单位 | 1.Chongqing Univ, Sch Chem & Chem Engn, Chongqing 400044, Peoples R China 2.Univ York, Green Chem Ctr Excellence, York YO105D, N Yorkshire, England 3.Hong Kong Polytech Univ, Dept Ind & Syst Engn, Hong Kong, Peoples R China 4.Chinese Acad Sci, Beijing Key Lab Ion Liquids Clean Proc, Inst Proc Engn, CAS Key Lab Green Proc & Engn, Beijing 100190, Peoples R China |
推荐引用方式 GB/T 7714 | Wang, Zihao,Su, Yang,Shen, Weifeng,et al. Predictive deep learning models for environmental properties: the direct calculation of octanol-water partition coefficients from molecular graphs[J]. GREEN CHEMISTRY,2019,21(16):4555-4565. |
APA | Wang, Zihao.,Su, Yang.,Shen, Weifeng.,Jin, Saimeng.,Clark, James H..,...&Zhang, Xiangping.(2019).Predictive deep learning models for environmental properties: the direct calculation of octanol-water partition coefficients from molecular graphs.GREEN CHEMISTRY,21(16),4555-4565. |
MLA | Wang, Zihao,et al."Predictive deep learning models for environmental properties: the direct calculation of octanol-water partition coefficients from molecular graphs".GREEN CHEMISTRY 21.16(2019):4555-4565. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
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。
修改评论