Machine Learning Applied to Aquatic Toxicity and Chemical Reactions of Xenobiotic Compounds
TL;DR
In this work, machine learning and chemoinformatics tools were used in conjunction with the RDKit library to study OH radical chemical reactions in an aquatic environment, and the quantitative structure-activity relationship (QSAR) was used as the basis for a toxicity prediction model.
Abstract
Environmental toxicity, especially in aquatic ecosystems, is an extremely relevant topic in the current global scenario due to the increased contamination caused by human activities and industrial processes. Chemical substances, such as pesticides, industrial waste, cosmetics, and microplastics, are frequently released into water bodies, endangering aquatic biodiversity and human health. These pollutants can cause cumulative and synergistic effects, amplifying the reach and severity of the environmental impact. In this work, machine learning and chemoinformatics tools were used in conjunction with the RDKit library to study OH radical chemical reactions in an aquatic environment. Bond change type plots were generated for 17 chemical reactions, testing approximately 1500 xenobiotic reagents, identifying the main changes between products and reagents. The quantitative structure-activity relationship (QSAR) was used as the basis for a toxicity prediction model, using ExtraTreeRegressor, for (lethal dose 50% (LD50)) values obtained from the US EPA Ecotox database. An R2 score of 0.6134 for the validation set was obtained. The three most important QSAR descriptors was identified in this prediction model using variable selection tools from the Scikit-learn library.