Multi-task machine learning models for simultaneous prediction of tissue-to-blood partition coefficients of chemicals in mammals
文献类型：期刊论文
| 作者 | Zhang, Shuying1; Luo, Xiaojun1 ; Mai, Bixian1
|
| 刊名 | ENVIRONMENTAL RESEARCH
 |
| 出版日期 | 2024-01-15 |
| 卷号 | 241页码:8 |
| 关键词 | Risk assessment Applicability domain Artificial neural network Tissue-to-blood partition coefficient Multi-task learning Random forest |
| ISSN号 | 0013-9351 |
| DOI | 10.1016/j.envres.2023.117603 |
| 英文摘要 | Tissue-to-blood partition coefficients (P-tb) are crucial for assessing the distribution of chemicals in organisms. Given the lack of experimental data and laborious nature of experimental methods, there is an urgent need to develop efficient predictive models. With the help of machine learning algorithms, i,e., random forest (RF), and artificial neural network (ANN), this study developed multi-task (MT) models that can simultaneously predict P-tb values for various mammalian tissues, including liver, muscle, brain, lung, and adipose. Single-task (ST) models using partial least squares regression, RF, and ANN algorithms for each endpoint were established for comparison. Overall, the performances of MT models were superior to those of ST models. The MT model using ANN algorithms showed the highest prediction accuracy with determination coefficients ranging from 0.704 to 0.886, root mean square errors between 0.223 and 0.410, and mean absolute errors ranging from 0.178 to 0.285 log units. Results showed that lipophilicity and polarizability of molecules significantly influence their partition behavior in organisms. Applicability domains (ADs) of the models were characterized by weighted molecular similarity density, and weighted inconsistency in molecular activities of structure-activity landscapes. When constrained by ADs, the models displayed enhanced predictive accuracy, making them valuable tools for the risk assessment and management of chemicals. |
| WOS研究方向 | Environmental Sciences & Ecology ; Public, Environmental & Occupational Health |
| 语种 | 英语 |
| WOS记录号 | WOS:001160804800001 |
| 源URL | [http://ir.gig.ac.cn/handle/344008/76294]  |
| 专题 | 有机地球化学国家重点实验室 |
| 通讯作者 | Luo, Xiaojun |
| 作者单位 | 1.Chinese Acad Sci, State Key Lab Organ Geochem, Guangzhou 510640, Peoples R China 2.Chinese Acad Sci, Guangzhou Inst Geochem, Guangdong Key Lab Environm Resources Utilizat & Pr, Guangzhou 510640, Peoples R China |
| 推荐引用方式 GB/T 7714 | Zhang, Shuying,Luo, Xiaojun,Mai, Bixian. Multi-task machine learning models for simultaneous prediction of tissue-to-blood partition coefficients of chemicals in mammals[J]. ENVIRONMENTAL RESEARCH,2024,241:8. |
| APA | Zhang, Shuying,Luo, Xiaojun,&Mai, Bixian.(2024).Multi-task machine learning models for simultaneous prediction of tissue-to-blood partition coefficients of chemicals in mammals.ENVIRONMENTAL RESEARCH,241,8. |
| MLA | Zhang, Shuying,et al."Multi-task machine learning models for simultaneous prediction of tissue-to-blood partition coefficients of chemicals in mammals".ENVIRONMENTAL RESEARCH 241(2024):8. |
入库方式： OAI收割
来源：广州地球化学研究所
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。