A curated and enriched dataset focused on the skin sensitization potential of small organic molecules. The data were sourced from the Interagency Coordinating Committee on the Validation of Alternative Methods (ICCVAM) and the Registration, Evaluation, Authorization and Restriction of Chemicals (REACH) study results databases, and were curated as part of the study by Borba et al. (https://ehp.niehs.nih.gov/doi/10.1289/EHP9341). The final dataset comprises 1,000 unique compounds, classified as skin sensitizers (label 1) and non-sensitizers (label 0). Data are enriched with 1098 Mordred descriptors, as well as MACCS and Morgan fingerprints derived from their 2D molecular structures. Information on the compounds CAS, CID, InChIKey etc. are also included whenever possible, retrieved from the PubChem database.

Synthesizing Knowledge, Curating Insights: