Interpretable Machine Learning to Understand Wildfire Toxicity: Bridging Chemicals, Omics, and Toxicological Outcomes via Symbolic Regression with Novel Feature Scoring
) showing the strongest association. Overall, this study demonstrates SR and associated DECS as practical, interpretable tools for modeling environmental mixtures, such as wildfire smoke, and their toxicological effects.
Authors
- M. Ian Gilmour (ORCID: https://orcid.org/0000-0002-3070-6704)
- T. M. Weigand (ORCID: https://orcid.org/0000-0003-4880-3331)
- Ilona Jaspers (ORCID: https://orcid.org/0000-0001-8728-0305)
- Julia E. Rager (ORCID: https://orcid.org/0000-0002-2882-5042)
- Jessie R. Chappel (ORCID: https://orcid.org/0009-0005-1492-118X)
- Yong Ho Kim (ORCID: https://orcid.org/0000-0001-7527-0134)
- Erin S. Baker
Institutions
- University of North Carolina at Chapel Hill (US)
- Center for Environmental Health (US)
- Impact Assessment (US)
- Czech Academy of Sciences, Institute of Microbiology (CZ)
- Public Health Solutions (US)
Publication Details
- Journal
- Chemical Research in Toxicology
- Published
- 2026-04-03
- DOI
- https://doi.org/10.1021/acs.chemrestox.5c00440
- Primary Topic
- Fire effects on ecosystems
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- U.S. Environmental Protection Agency
- National Institutes of Health
- Gillings School of Public Health
- National Institute of General Medical Sciences