Artificial Intelligence-Based Toxicity Prediction of Environmental Chemicals: Future Directions for Chemical Management Applications

Abstract

Recently, research on the development of artificial intelligence (AI)-based computational toxicology models that predict toxicity without the use of animal testing has emerged because of the rapid development of computer technology. Various computational toxicology techniques that predict toxicity based on the structure of chemical substances are gaining attention, including the quantitative structure–activity relationship. To understand the recent development of these models, we analyzed the databases, molecular descriptors, fingerprints, and algorithms considered in recent studies. Based on a selection of 96 papers published since 2014, we found that AI models have been developed to predict approximately 30 different toxicity end points using more than 20 toxicity databases. For model development, molecular access system and extended-connectivity fingerprints are the most commonly used molecular descriptors. The most used algorithm among the machine learning techniques is the random forest, while the most used algorithm among the deep learning techniques is a deep neural network. The use of AI technology in the development of toxicity prediction models is a new concept that will aid in achieving a scientific accord and meet regulatory applications. The comprehensive overview provided in this study will provide a useful guide for the further development and application of toxicity prediction models.

TOXRIC: a comprehensive database of toxicological data and benchmarks

“…The endpoint datasets can be used as label data for ML models, while the feature datasets can be used as input. Four typical ML algorithms widely used for toxicity prediction are evaluated ( 48 ), including eXtreme Gradient Boosting (XGB) ( 49 ), Random Forest (RF) ( 50 ), Support Vector Machine (SVM) ( 51 ) and Deep Neural Network (DNN) ( 10 ). XGB and RF are two advanced ensemble learning algorithms, which are representative of sequential ensemble and parallel ensemble, respectively.…”

“…( 71 ), Jeong et al. ( 48 ), Vo et al. ( 72 ) and the resources provided by American Society of Cellular and Computational Toxicology ( https://www.ascctox.org/resources ).…”

Toward Property-Based Regulation

“…QSARs may therefore be helpful tools in the prediction of certain physicochemical properties, but their lack of transparency when predicting complex chemical behaviors may hamper efforts by chemical designers to make safer chemicals. Artificial intelligence-based predictions similarly often suffer from a lack of mechanistic interpretability . Just as the PER provides a clear path to commercialization for polymers meeting its specifications, property-based regulation would allow chemists to make safer chemicals with greater confidence that they can be expeditiously brought to market.…”

“…Artificial intelligence-based predictions similarly often suffer from a lack of mechanistic interpretability. 111 Just as the PER provides a clear path to commercialization for polymers meeting its specifications, property-based regulation would allow chemists to make safer chemicals with greater confidence that they can be expeditiously brought to market. This regulatory approach minimizes the likelihood of late-stage failures while at the same time encouraging the development of safer chemistries a priori.…”

Transformers enable accurate prediction of acute and chronic chemical toxicity in aquatic organisms

“…Due to the narrow applicability domains, multiple QSAR models are often required to make predictions for more than one single chemical class. Alternatively, machine learning techniques have been suggested as an approach to integrate large volumes of heterogeneous data into a single, more general, model (Jeong and Choi, 2022). For example, deep learning has been used to predict various biological activities, such as toxicity, based on chemical structures (Ciallella et al, 2021;Goh et al, 2017;LeCun et al, 2015;Mayr et al, 2016).…”