Species sensitivity distribution modeling for ecotoxicity prediction of industrial chemicals

Environmental contaminants (ECs) exert species-specific impacts modulated by biological traits and exposure parameters, such as concentration and duration. Traditional empirical methods struggle to address the vast combinatorial space of chemical-species interactions, necessitating robust computational frameworks. Species Sensitivity Distribution (SSD) models address this gap by statistically aggregating toxicity data to quantify the distribution of species sensitivities, enabling estimation of hazardous concentrations (e.g., HC-5, the concentration affecting 5% of species) for ecological risk assessment. In this study, we developed global and class-specific SSD models using a curated dataset of 3250 toxicity entries from the U.S. EPA ECOTOX database, spanning 14 taxonomic groups across four trophic levels, producers (e.g., algae), primary consumers (e.g., insects), secondary consumers (e.g., amphibians), and decomposers (e.g., fungi). By integrating acute (EC₅₀/LC₅₀) and chronic (NOEC/LOEC) endpoints, the models predict pHC-5 values for untested chemicals and identify toxicity-driving substructures through interpretable feature selection. Specialized SSDs were tailored for high-priority chemical classes, including personal care products (PCPs) and agrochemicals, addressing regulatory needs for targeted risk mitigation. This work advances ecological risk assessment by reducing reliance on animal testing and aligning with new approach methodologies (NAMs). The models provide a scalable framework to prioritize chemicals, support data-poor assessments, and inform evidence-based regulation. All datasets, model architectures, and interactive tools are publicly accessible via the OpenTox SSDM platform (https://my-opentox-ssdm.onrender.com/#/), fostering transparency and collaboration in environmental toxicology. The models were further applied to ∼8449 industrial chemicals from the US EPA CDR database, leading to the prioritization of 188 high-toxicity compounds for regulatory attention.