Prediction of soil adsorption coefficient based on deep recursive neural network
- Autores: Shi X.1, Tian S.1, Yu L.2, Li L.3, Gao S.1
-
Afiliações:
- School of Software
- Network Center
- College of Engineering, Xinjiang Medical University
- Edição: Volume 51, Nº 5 (2017)
- Páginas: 321-330
- Seção: Article
- URL: https://journals.rcsi.science/0146-4116/article/view/174935
- DOI: https://doi.org/10.3103/S0146411617050066
- ID: 174935
Citar
Resumo
It is expensive and time consuming to measure soil adsorption coefficient (logKoc) of compounds using traditional methods, and some existing models show lower accuracies. To solve these problems, a deep learning (DL) method based on undirected graph recursive neural network (UG-RNN) is proposed in this paper. Firstly, the structures of molecules are represented by directed acyclic graphs (DAG) using RNN model; after that when a number of such neural networks are bundled together, they form a multi-level and weight sharing deep neural network to extract the features of molecules; Third, logKoc values of compounds have been predicted using back-propagation neural network. The experimental results show that the UG-RNN model achieves a better prediction effect than some shallow models. After five-fold cross validation, the root mean square error (RMSE) value is 0.46, the average absolute error (AAE) value is 0.35, and the square correlation coefficient (R2) value is 0.86.
Sobre autores
Xinyu Shi
School of Software
Email: tianshengwei@163.com
República Popular da China, Urumqi, 830008
Shengwei Tian
School of Software
Autor responsável pela correspondência
Email: tianshengwei@163.com
República Popular da China, Urumqi, 830008
Long Yu
Network Center
Email: tianshengwei@163.com
República Popular da China, Urumqi, 830046
Li Li
College of Engineering, Xinjiang Medical University
Email: tianshengwei@163.com
República Popular da China, Urumqi, 830011
Shuangyin Gao
School of Software
Email: tianshengwei@163.com
República Popular da China, Urumqi, 830008