Technology Profile

Model graphic

The two-stage machine learning model will be used to expand the coverage of organic chemicals that can be evaluated for their human health risks. (Image adapted from Kvasnicka et al., 2024)

Researchers at the Texas A&M University (TAMU) Superfund Research Program (SRP) Center created a new method to predict chemical points of departure (PODs), the lowest dose of a chemical that triggers a biological response. A two-stage machine learning-based approach first identifies the structural, physical, chemical, and toxicological properties of a chemical using information from a variety of databases. The second stage uses those properties and data on health effects to predict the chemical’s biological activity.

The TAMU SRP Center studies how chemical mixtures from hazardous waste sites and disaster-related contamination events affect human health. The team is creating tools for first responders, impacted communities, and government agencies to characterize and mitigate the effects of disaster-related chemical mixtures on human health.

TechnologyThe TAMU SRP Center developed a machine learning model that predicts the biological activity of chemicals based on their physical and chemical properties. Researchers tested their model on over 34,000 chemicals and found that it accurately predicted PODs for chemicals that had them already available. The model also identified PODs for chemicals that previously lacked them. The results identified several thousand chemicals of moderate concern and several hundred of high concern for health effects.
InnovationA primary strength of the framework is in its two-stage model used to identify the chemical’s characteristics and predict the biological activity. This information allows regulatory agencies and university researchers to prioritize their chemical assessments. The model can be limited by its first stage, if a chemical does not have known characteristic data.
Contaminant and MediaAll contaminants that lack in vivo toxicity data or do not have a comprehensive human health assessment by regulatory or authoritative assessment agencies.
Technology Readiness LevelTRL 8 – Actual system completed and “flight qualified” through test and demonstration.
Principal InvestigatorIvan Rusyn
InstitutionTexas A&M University
Grant NumberP42ES027704
Back
to Top