In-silico model to predict springtail toxicity
2021
Istituto di Ricerche Farmacologiche Mario Negri IRCCS, Milan, Italy
Soil pollution is a critical environmental challenge. In this study, two quantitative structure activity relationship (QSAR) models for the prediction of reproductive toxicity induced by organic compounds in the springtail Folsomia candida were developed.
Therefore, 28 days No Observed Effect Concentration (NOEC) data were used that were collected from publicly available databases. A dataset with 54 compounds including plant protection products, industrial chemicals, household and cosmetic ingredients, drugs, and other substances was assembled. 80% of the data was used to train the models, while 20% were used to validate them. The models were developed using partial least squares regression (PLS) and the Monte Carlo technique with open-source tools.
Both QSAR models gave good predictive performance and could serve for the ecological risk assessment of chemicals for terrestrial organisms.
QSAR models for soil ecotoxicity: Development and validation of models to predict reproductive toxicity of organic chemicals in the collembola Folsomia candida
Diego Baderna
Added on: 02-29-2024
[1] https://www.sciencedirect.com/science/article/pii/S0304389421022044?via%3Dihub
