First report on a classification-based QSAR model for chemical toxicity to earthworm

• Published in: Journal of hazardous materials Vol. 386; p. 121660
• Main Authors: Roy, Joyita, Kumar Ojha, Probir, Carnesecchi, Edoardo, Lombardo, Anna, Roy, Kunal, Benfenati, Emilio
• Format: Journal Article
• Language: English
• Published: Netherlands Elsevier B.V 15.03.2020
• Subjects: Animals; Classification; Earthworm; LDA; Models, Biological; Oligochaeta - drug effects; Pesticides - toxicity; QSAR; Quantitative Structure-Activity Relationship; Reproducibility of Results; toxicity; Earthworm; toxicity; LDA; QSAR; Classification
• ISSN: 0304-3894; 1873-3336
• DOI: 10.1016/j.jhazmat.2019.121660

[Display omitted] •We developed a classification-based QSAR model using earthworm toxicity data (LC50).•Only 2D descriptors were used for the model development.•All models have been validated using stringent internal and external validation parameters.•This is the first report of classification-based model development for earthworm toxicity.•The model explores the chemical features responsible for and mechanism of toxicity As the use of the pesticides has increased extensively in the farming fields to have a better agricultural production, the negative impacts of such use have also increased exponentially. Hence, the toxic effects of pesticides along with the targeted organisms affect the non-targeted terrestrial organisms such as earthworm. Therefore, in the present work, we have developed a classification-based quantitative structure-activity relationship (QSAR) model using linear discriminant analysis (LDA) to capture the specific information of pesticides / diverse chemicals in order to determine the structural information responsible for toxicity manifestation towards the non-targeted organism, i.e., earthworm (Eisenia foetida). After variable selection, the model was developed using 2D descriptors only and was subjected to rigorous statistical validation. The best discriminant model obtained with 8 descriptors showed appreciable Wilks’ λ value of 0.490, F (Fischer’s statistics) value of 14.03, χ2 value of 79.098, canonical regression coefficient (R) value of 0.714 and ρ value of 14.63. The sensitivity, specificity, accuracy, precision and F-measure values of the training set are 90.00, 80.52, 83.76, 70.59 and 79.12 respectively whereas for the test set, these are 58.82, 79.31, 71.74, 62.50 and 60.61 respectively. The insights obtained from the LDA model suggested that lipophilicity, electronrichness, and lower degree of branching of the organic compounds are responsible for earthworm toxicity through various mechanisms. On the other hand, polar and bulky diverse chemicals do not have such toxic effects on earthworm. Hence, this model can be an effective tool to tailor molecular structures of the existing pesticides to develop novel compounds or pesticides which would be less toxic to the non-targeted organisms, specifically earthworm.