A curated and enriched dataset for PFAS acute oral toxicity in rats. The dataset was compiled from two previous studies by Chen et al. (2024) (https://doi.org/10.1016/j.jhazmat.2024.136071) and da Silva and de Melo (2024) (https://doi.org/10.1080/1062936X.2024.2417250). The curated oral toxicity dataset comprises 307 PFAS molecules and 777 molecular descriptors extracted from their 2D structure using the EnalosMold2 KNIME node. Useful metadata include CAS Numbers, SMILES representations, IUPAC names, MW values etc. Modelling subset information is additionally provided to support model reproducibility and transparency. Compounds are classified as “High” or “Low” toxicity based on their LD50 (mg/kg) values and the toxicity category thresholds proposed by US EPA.

Dataset DOI: https://doi.org/10.5281/zenodo.17864120

Synthesizing Knowledge, Curating Insights: