Machine learning-based prediction of toxicity of organic compounds towards fathead minnow.

ABSTRACT: Predicting the acute toxicity of a large dataset of diverse chemicals against fathead minnows (Pimephales promelas) is challenging. In this paper, 963 organic compounds with acute toxicity towards fathead minnows were split into a training set (482 compounds) and a test set (481 compounds) with an approximate ratio of 1 : 1. Only six molecular descriptors were used to establish the quantitative structure-activity/toxicity relationship (QSAR/QSTR) model for 96 hour pLC₅₀ through a support vector machine (SVM) along with genetic algorithm. The optimal SVM model (R ² = 0.756) was verified using both internal (leave-one-out cross-validation) and external validations. The validation results (q _int ² = 0.699 and q

SUBMITTER: Chen X 

PROVIDER: S-EPMC9056962 | biostudies-literature | 2020 Sep

REPOSITORIES: biostudies-literature