当前位置: X-MOL 学术Toxicol. Res. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
In silico prediction of pesticide aquatic toxicity with chemical category approaches
Toxicology Research ( IF 2.2 ) Pub Date : 2017-07-31 00:00:00 , DOI: 10.1039/c7tx00144d
Fuxing Li 1, 2, 3, 4, 5 , Defang Fan 1, 2, 3, 4, 5 , Hao Wang 1, 2, 3, 4, 5 , Hongbin Yang 1, 2, 3, 4, 5 , Weihua Li 1, 2, 3, 4, 5 , Yun Tang 1, 2, 3, 4, 5 , Guixia Liu 1, 2, 3, 4, 5
Affiliation  

Aquatic toxicity is an important issue in pesticide development. In this study, using nine molecular fingerprints to describe pesticides, binary and ternary classification models were constructed to predict aquatic toxicity of pesticides via six machine learning methods, namely Naïve Bayes (NB), Artificial Neural Network (ANN), k-Nearest Neighbor (kNN), Classification Tree (CT), Random Forest (RF) and Support Vector Machine (SVM). For the binary models, local models were obtained with 829 pesticides on rainbow trout (RT) and 151 pesticides on lepomis (LP), and global models were constructed on the basis of 1258 diverse pesticides on RT, LP and 278 other fish species. After analyzing the local binary models, we found that the fish species caused influence in terms of accuracy. Considering the data size and the predictive range, the 1258 pesticides were also used to build global ternary models. The best local binary models were Maccs_ANN for RT and Maccs_SVM for LP, which exhibited accuracies of 0.90 and 0.90, respectively. For global binary models, the best one was Graph_SVM with an accuracy of 0.89. Accuracy of the best global ternary model Graph_SVM was 0.81, which was a little lower than that of the best global binary model. In addition, several substructural alerts were identified, including nitrobenzene, chloroalkene and nitrile, which could significantly correlate with pesticides aquatic toxicity. This study provides a useful tool for an early evaluation of pesticides aquatic toxicity in environmental risk assessment.

中文翻译:

使用化学类别方法对农药水生毒性进行计算机模拟预测

水生毒性是农药开发中的重要问题。在这项研究中,使用九种分子指纹描述农药,构建了二元和三元分类模型,以通过六种机器学习方法预测农药的水生毒性,这六种机器学习方法分别是朴素贝叶斯(NB),人工神经网络(ANN),k最近邻( kNN),分类树(CT),随机森林(RF)和支持向量机(SVM)。对于二元模型,获得了本地模型,其中使用了虹鳟鱼(RT)上的829种农药和对油菜(LP)上的151种农药,并基于RT,LP和278种其他鱼类上的1258种不同农药建立了全局模型。通过分析本地二元模型,我们发现鱼类物种在准确性方面产生了影响。考虑到数据大小和预测范围,还使用了1258种农药来建立全局三元模型。最好的本地二进制模型是RT的Maccs_ANN和LP的Maccs_SVM,它们的精确度分别为0.90和0.90。对于全局二进制模型,最好的模型是Graph_SVM,精度为0.89。最佳全局三元模型Graph_SVM的精度为0.81,比最佳全局二元模型的精度低一点。此外,还确定了一些亚结构警报,包括硝基苯,氯代烯烃和腈,这些警报可能与农药的水生毒性显着相关。该研究为环境风险评估中农药水生毒性的早期评估提供了有用的工具。其准确度分别为0.90和0.90。对于全局二进制模型,最好的模型是Graph_SVM,精度为0.89。最佳全局三元模型Graph_SVM的精度为0.81,比最佳全局二元模型的精度低一点。此外,还确定了一些亚结构警报,包括硝基苯,氯代烯烃和腈,这些警报可能与农药的水生毒性显着相关。该研究为环境风险评估中农药水生毒性的早期评估提供了有用的工具。其准确度分别为0.90和0.90。对于全局二进制模型,最好的模型是Graph_SVM,精度为0.89。最佳全局三元模型Graph_SVM的精度为0.81,比最佳全局二元模型的精度低一点。此外,还确定了一些亚结构警报,包括硝基苯,氯代烯烃和腈,这些警报可能与农药的水生毒性显着相关。该研究为环境风险评估中农药水生毒性的早期评估提供了有用的工具。确定了几种亚结构警报,包括硝基苯,氯代烯烃和腈,它们可能与农药的水生毒性显着相关。该研究为环境风险评估中农药水生毒性的早期评估提供了有用的工具。确定了几种亚结构警报,包括硝基苯,氯代烯烃和腈,它们可能与农药的水生毒性显着相关。该研究为环境风险评估中农药水生毒性的早期评估提供了有用的工具。
更新日期:2017-08-03
down
wechat
bug