Artificial intelligence is rapidly improving scientists’ ability to detect chemicals in the environment and the human body. The New Perspective article argues that the next major step is not simply to identify more chemicals, but to determine which exposures are most likely to disrupt biological systems and contribute to disease.
Published in Artificial intelligence and environmentarticle describes the transition to functional chemistry exposomics, a new approach that combines high-resolution mass spectrometry, artificial intelligence, toxicology databases, and biological response data.
Exposomics examines the total range of environmental exposures experienced throughout a person’s life. Modern analytical instruments can detect thousands of chemical signals in blood, urine, tissue, and environmental samples. However, many of the detected compounds remain unidentified, and the biological significance of others is poorly understood.
“The future of exposomics is not only to discover what chemicals exist, but also to predict what those chemicals do in biological systems,” said corresponding author Hemi Luan from Guangdong University of Technology. “AI can help researchers focus limited experimental resources on the exposures most relevant to human health.”
The authors propose transforming AI from a chemical “discovery engine” to a functional prediction engine. Such systems have the potential to integrate chemical structures, toxicity predictions, molecular interactions, and changes in genes, proteins, and metabolites. Each chemical can then obtain a biological activity risk score, allowing researchers to prioritize candidates for clinical testing and health risk assessment.
The framework also incorporates machine learning approaches for causal inference, which may help distinguish meaningful exposure effects from simple statistical correlations.
Significant challenges remain, including limited high-quality training data, chemical mixtures, unknown confounders, and the need for transparent and interpretable models. Experimental validation using cells, organoids, or animal models also remains essential.
The authors conclude that by working closely with chemists, toxicologists, epidemiologists, bioinformaticians, and computer scientists, exposomics can be transformed from a chemical inventory to a predictive and preventive tool for public health action.
sauce:
Shenyang Agricultural University
Reference magazines:
Luan H; Advancing AI/ML-driven chemical exposomics to identify biologically relevant environmental exposures. AI approx. 2026, DOI: 10.66178/aie-0026-0008. https://www.the-newpress.com/aie/article/doi/10.66178/aie-0026-0008
