In silico prediction of pesticide aquatic toxicity with chemical category approaches

Abstract

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 six machine learning methods: 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 and LP and 278 on other fish species. After analyzing the local binary models, we found that fish species caused influence in terms of accuracy. Considering the data size and 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 model 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 pesticide aquatic toxicity. This study provides a useful tool for an early evaluation of pesticide aquatic toxicity in environmental risk assessment.

Predicting Chemical Hazard across Taxa through Machine Learning

“…The best performances are obtained by the RF, followed by the DF-RASAR and other models that obtained performances that were not too far. This similarity between different models was already found previously [11,13], and the superiority of RFs had already been pointed out [13]. Even though the DF-RASAR obtains good performances, they do not seem to outperform other traditional machine learning models.…”

“…Estimates of y2 from the whole dataset x = ( x ch , xtax, xex), using the distances defined in Eq. (11). We only list the models that rely on the definition of the distance [Eqs.…”

“…Acute toxicity predictions have also been the focus of few applications of ML in ecotoxicology, though a critical lack of literature on machine learning in this area has been denounced [10]. Li et al aimed to predict toxicity categories for acute toxicity to fish of pesticides by making use of nine chemical descriptors [11]. Their dataset was rather small (∼ 1000 entries), and dominated by two species, rainbow trout (RT) and bluegill sunfish (BS).…”

Subtilisin an Eminent Microbial Product as a Potential Skin Care Regulator of Melanogenesis –A Paradigm Synchronized With in Vitro / in Silico Approach

“…Where the resulted peptides were found to be non-toxic and there were mutations found on the sequences. It showed good scores that ranged from -0.37 to -1.38 which is consistent with global binary models (Li et al,2017). The molecular weights were was within 500KD which is an ideal mass for a drug.…”

In Silico Prediction of Chemical Toxicity for Drug Design Using Machine Learning Methods and Structural Alerts

“…Our group previously collected LC 50 data of three fish species from ECOTOX database and built several local and global models (Sun et al, 2015 ). Recently, we reported a model focusing on the aquatic toxicity of pesticides and found that the molecule fingerprints performed different between local and global models (Li et al, 2017 ). For the avian species, several in silico models were developed including classification (Zhang et al, 2015 ) and regression (Mazzatorta et al, 2006 ; Toropov and Benfenati, 2006 ).…”