This study evaluated practical approaches for applying symbolic regression (SR) in toxicology and used these approaches to identify chemical and transcriptomic drivers of wildfire smoke lung injury. SR performance was benchmarked against two machine learning algorithms (random forest and XGBoost). This dataset is associated with the following publication: Chappel, J., Y.H. Kim, I. Gilmour, E. Baker, i. Jaspers, T. Weigand, and J. Rager. Interpretable Machine Learning to Understand Wildfire Toxicity: Bridging Chemicals, Omics, and Toxicological Outcomes via Symbolic Regression with Novel Feature Scoring. CHEMICAL RESEARCH IN TOXICOLOGY. American Chemical Society, Washington, DC, USA, 39(4): 530–543, (2026).