A. Furuhama

TL;DR: The descriptors that predicted acute toxicities to fish and algae were daphnia toxicity, molecular weight (an indicator of molecular size and uptake) and selected indicator variables that discriminated between the absence or presence of various substructures.

TL;DR: The KATE system has the potential to enable chemicals to be categorised as potential hazards and external validation indicates that a group of chemicals with an in-domain of KATE C-judgements exhibits a lower root mean square error (RMSE).

TL;DR: This study verifies the utility of similarity-based machine learning methods in predicting the acute aquatic toxicity of diverse organic chemicals on Daphnia magna and Oryzias latipes and highlights the importance of lipophilicity, electrophilic reactivity, molecular polarizability, and size in determining acute toxicity.

TL;DR: This study investigated the applicability of log D-based criteria to the eco-toxicity of other kinds of chemicals, including aliphatic compounds, and selected more than 100 chemicals whose acute fish toxicities or algal growth inhibition toxicities were almost equal to their acute daphnid toxicities.

TL;DR: A comparative analysis of the performance of the two modeling schemes indicates that the local models, trained on homogeneous data sets, are less error prone, and therefore superior to the global model, whereas the global models showed worse performance metrics compared to the local ones, thereby significantly increasing their usefulness in practical applications for regulatory purposes.