BeeToxAI: an artificial intelligence-based web app to assess acute toxicity of chemicals to honey bees
Nenhuma Miniatura disponível
Data
2021
Título da Revista
ISSN da Revista
Título de Volume
Editor
Resumo
An innovative artificial intelligence-based web app (BeeToxAI) for assessing the acute toxicity of chemicals to
Apis mellifera. Initially, we developed and externally validated QSAR models for classification (external set accu racy ∼91%) through the combination of Random Forest and molecular fingerprints to predict the potential for
chemicals to cause acute contact toxicity and acute oral toxicity to honey bees. Then, we developed and exter nally validated regression QSAR models (𝑅2 = 0.75) using Feedforward Neural Networks (FNNs). Afterward, the
best models were implemented in the publicly available BeeToxAI web app (http://beetoxai.labmol.com.br/).
The outputs of BeeToxAI are: toxicity predictions with estimated confidence, applicability domain estimation,
and color-coded maps of relative structure fragment contributions to toxicity. As an additional assessment of
BeeToxAI performance, we collected an external set of pesticides with known bee toxicity that were not included
in our modeling dataset. BeeToxAI classification models were able to predict four out of five pesticides correctly.
The acute contact toxicity model correctly predicted all of the eight pesticides. Here we demonstrate that Bee ToxAI can be used as a rapid new approach methodology for predicting acute toxicity of chemicals in honey
bees.
Descrição
Palavras-chave
Apis mellifera, Artificial intelligence, Pollinators, Ecotoxicology, Machine learning, Predictive modeling
Citação
MOREIRA-FILHO, José T. et al. BeeToxAI: an artificial intelligence-based web app to assess acute toxicity of chemicals to honey bees. Artificial Intelligence in the Life Sciences, v. 1, e100013, 2021. DOI: 10.1016/j.ailsci.2021.100013. Disponível em: https://www.sciencedirect.com/science/article/pii/S2667318521000131. Acesso em: 6 set. 2024.