Premium
Prediction of Soil Adsorption Coefficient in Pesticides Using Physicochemical Properties and Molecular Descriptors by Machine Learning Models
Author(s) -
Kobayashi Yoshiyuki,
Uchida Takumi,
Yoshida Kenichi
Publication year - 2020
Publication title -
environmental toxicology and chemistry
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.1
H-Index - 171
eISSN - 1552-8618
pISSN - 0730-7268
DOI - 10.1002/etc.4724
Subject(s) - quantitative structure–activity relationship , molecular descriptor , support vector machine , pesticide , linear regression , decision tree , applicability domain , robustness (evolution) , biological system , adsorption , computer science , machine learning , data mining , chemistry , artificial intelligence , ecology , biochemistry , gene , biology , organic chemistry
The soil adsorption coefficient ( K OC ) plays an important role in environmental risk assessment of pesticide registration. Based on this risk assessment, applied and registered pesticides can be allowed in the European Union. Almost 1 yr is required to study and obtain the K OC value of a pesticide. Furthermore, acquiring the K OC requires a large cost. It is necessary to efficiently estimate the K OC value in the early stages of pesticide development. In the present study, the experimental values of physicochemical properties and molecular descriptors of chemical structures were collected to develop a quantitative structure–property relationship (QSPR) model, and the prediction performance of the model was evaluated. More specifically, we compared the accuracies of models based on a gradient boosting decision tree, multiple linear regression, and support vector machine. The experimental results suggest that it is possible to develop a QSPR model with high accuracy using both the molecular descriptors calculated from the structural formula and experimental values of physicochemical properties from open literature and databases. Comparing to the previously established models, we achieved high prediction accuracy, fitness, and robustness by only using freeware. Therefore, our developed QSPR models can be useful preliminary risk assessment in the early developmental stages of pesticides. Environ Toxicol Chem 2020;39:1451–1459. © 2020 SETAC