FRAM seminar series: How well can we predict chemical toxicity using AI based models? (25 feb, 2026) скачать в хорошем качестве

FRAM seminar series: How well can we predict chemical toxicity using AI based models? (25 feb, 2026)

The total number of chemicals on the world market continues to increase, and traditionally, risk assessments of these chemicals have been made with data from exposed model organisms. This approach is both time consuming and costly, and computational models are increasingly used to fill data gaps, with recent advances in AI expanding what these models can do. But how good are these models, and can we trust their predictions? This seminar provides insight into how well the established QSAR models perform in predicting toxicity, and presents a new transformer-based AI model used to predict chemical toxicity across a broad range of chemicals and species. "TRIDENT-2: Predicting chemical toxicity across eukaryota" Chemical pollution is a major driver of biodiversity loss at a planetary scale and contributes substantially to the declining ecological status of ecosystems worldwide. Chemical risk assessments currently rely on animal exposure data from a limited number of model organisms to define environmentally safe boundaries, but generating such data is resource-intensive and time-consuming. Computational methods offer fast and cost-efficient alternatives; however, their limited accuracy, narrow applicability domains, and continued focus on a small set of model organisms make them ill-suited for addressing existing data gaps across both chemicals and species. Here, we present TRIDENT-2, a transformer-based model trained on over 550,000 exposure experiments, for predicting chemical toxicity towards 6674 eukaryotic species for a broad range of chemicals. "Prediction biases in Quantitative Structure-Activity Relationship (QSAR) models" The total number of chemicals on the world market continues to increase, and empirical toxicity testing is struggling to keep up. In silico tools, such as ecotoxicological quantitative structure-activity relationship (QSAR) models, are being used to fill data gaps when performing risk assessment, but to what extent can we trust these predictions? Three freely available ecotoxicity QSAR platforms (ECOSAR, Vega and T.E.S.T.) have been tested against empirical data from the United States Environmental Protection Agency (USEPA) ECOTOX database, to determine model predictivity for both acute and chronic toxicity. Predictivity for each platform was assessed with coverage (percent successful predictions across the list of chemicals), median absolute error and large deviations (percent predictions deviating from empirical data by more than a factor 10). Additionally, CLP-classification thresholds were used to examine predictivity for regulatory toxicity ranges, to find out if models are more or less accurate for different classes. Results indicate some differences in platform predictivity among the tested endpoints, and, more importantly, a problematic trend when stratifying with CLP-classes – toxicity of the most toxic compounds is underestimated. The presenters are: Styrbjörn Käll, PhDc, Chalmers. "TRIDENT-2: Predicting chemical toxicity across eukaryota" Patrik Svedberg, PhDc, University of Gothenburg. "Prediction biases in Quantitative Structure-Activity Relationship (QSAR) models"