Dataset Information

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 via 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.

SUBMITTER: Li F

PROVIDER: S-EPMC6062408 | biostudies-literature | 2017 Nov

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

<i>In silico</i> prediction of pesticide aquatic toxicity with chemical category approaches.

Li Fuxing F Fan Defang D Wang Hao H Yang Hongbin H Li Weihua W Tang Yun Y Liu Guixia G

Toxicology research 20170731 6

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 <i>via</i> 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 pestic ...[more]

PMID: 30090546

Similar Datasets

Project description:BackgroundNanomaterials in plant protection promise many benefits over conventional pesticide products. Nano-enabled pesticides may alter the functionality or risk profile of active ingredients. Cationic nanochitin whiskers (NC) possess strong biological activity against wheat aphids. However, toxicity and synergistic effects of NC with chemical pesticides against pest insects has not been systemically reported. This study investigated the insecticidal enhancement by NC with Omethoate (40% EC), Imidacloprid (10% WP), and Acetamiprid (40% WG) for pest control using wheat aphid as piercing-sucking mouthparts insect. Fluorescein isothiocyanate labelled NC was used to monitor the uptake and transportation pathway of NC inside the target insects. Toxicity of NC was tested with Sprague-Dawley (SD) rat. Our findings provide a theoretical basis for future application of NC in plant protection against pest insects.ResultsNCs synthesized by acidic hydrolysis were rod-like nanoparticles in a range of 50-150 nm in length and 30-50 nm in width, which examined by electron microscopy and dynamic light scattering methods. The charge density and zeta potential were about 63 mmol/kg and + 36.4 mV, respectively. By absorption and/or contact action of 30-50 mg/L of NC suspension, the corrected mortality of wheat aphids reached up to 80% or above after 12 h treatment, NC could be distributed through digestive system and relocated from mouth to other tissues inside the insect body. When associated with dilutions of conventional pesticides, the corrected mortality were significantly increased up to 95% or above. The dosage of the chemical pesticide and nanochitin in the mixtures (1:1 by volume) were all reduced to half. The acute oral toxicity Lethal Dose 50% (LD50) to SD rat is greater than 5000 mg/kg BW (body weight) in male and female, acute dermal toxicity LD50 is greater than 2000 mg/kg BW of NC.ConclusionsNC has a strong promotive effect on insecticidal effectiveness of chemical insecticides. It was easily absorbed by plant, transported and distributed from mouth to other tissues of the insects while sucking plant fluid. Low acute oral and dermal toxicity to SD rat indicated that it is safe to apply in agriculture and food industry. NCs has a great potential for water-based nanopesticide formulation to reduce chemical pesticide use for future agro-environmental sustainability.

Dataset Information

In silico prediction of pesticide aquatic toxicity with chemical category approaches.

Publications

<i>In silico</i> prediction of pesticide aquatic toxicity with chemical category approaches.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets