Academic Journal
Adverse outcome pathway-informed machine learning for predicting vascular toxicity of emerging organic pollutants.
| Τίτλος: | Adverse outcome pathway-informed machine learning for predicting vascular toxicity of emerging organic pollutants. |
|---|---|
| Συγγραφείς: | Siewetcheu Toukak A; School of Environmental Science and Engineering, Tianjin Key Lab of Biomass/Wastes Utilization, Tianjin University, Tianjin 300350, China. liningec@tju.edu.cn., Gao W; School of Environmental Science and Engineering, Tianjin Key Lab of Biomass/Wastes Utilization, Tianjin University, Tianjin 300350, China. liningec@tju.edu.cn., Wan S; School of Environmental Science and Engineering, Tianjin Key Lab of Biomass/Wastes Utilization, Tianjin University, Tianjin 300350, China. liningec@tju.edu.cn., Li N; School of Environmental Science and Engineering, Tianjin Key Lab of Biomass/Wastes Utilization, Tianjin University, Tianjin 300350, China. liningec@tju.edu.cn., Chen G; School of Environmental Science and Engineering, Tianjin Key Lab of Biomass/Wastes Utilization, Tianjin University, Tianjin 300350, China. liningec@tju.edu.cn.; School of Mechanical Engineering, Tianjin University of Commerce, Tianjin 300134, China.; School of Ecology and Environment, Xizang University, Lhasa 850000, China. |
| Πηγή: | Environmental science. Processes & impacts [Environ Sci Process Impacts] 2026 May 01; Vol. 28 (4), pp. 1064-1080. Date of Electronic Publication: 2026 May 01. |
| Τύπος έκδοσης: | Journal Article |
| Γλώσσα: | English |
| Στοιχεία περιοδικού: | Publisher: Royal Society of Chemistry Country of Publication: England NLM ID: 101601576 Publication Model: Electronic Cited Medium: Internet ISSN: 2050-7895 (Electronic) Linking ISSN: 20507887 NLM ISO Abbreviation: Environ Sci Process Impacts Subsets: MEDLINE |
| Imprint Name(s): | Original Publication: Cambridge : Royal Society of Chemistry |
| Ιατρικοί όροι (MeSH): | Water Pollutants, Chemical*/toxicity , Organic Chemicals*/toxicity , Cardiovascular System*/drug effects , Multilayer Perceptrons* , Deep Learning*, Environmental Monitoring/methods ; Humans ; Animals ; Adverse Outcome Pathways |
| Περίληψη: | Emerging organic pollutants (EOPs) are increasingly detected in wastewater and pose potential vascular toxicity risks that remain inadequately assessed in current regulatory frameworks. This study developed an adverse outcome pathway (AOP)-informed machine learning approach to evaluate vascular toxicity for 312 EOPs. By integrating ToxCast high-throughput bioassay data with Morgan fingerprints, we trained fourteen multilayer perceptron (MLP) models targeting key events in AOP 509, including Nrf2 inhibition, oxidative stress, mitochondrial dysfunction, apoptosis, endothelial impairment, and angiogenesis disruption. Our optimized models achieved high predictive accuracy (70-95%), enabling activity classification for both tested and untested chemicals. The predicted activation profiles prioritized chemicals such as ketoconazole, sertraline, and miconazole, with literature evidence supporting their vascular toxicity potential. This AOP-guided modelling framework demonstrates how integrating mechanistic pathways with machine learning can inform chemical risk assessment and prioritization, supporting hazard evaluation and environmental decision-making for pollutants with limited toxicological data. |
| Substance Nomenclature: | 0 (Water Pollutants, Chemical) 0 (Organic Chemicals) |
| Entry Date(s): | Date Created: 20260306 Date Completed: 20260505 Latest Revision: 20260505 |
| Update Code: | 20260506 |
| DOI: | 10.1039/d5em00562k |
| PMID: | 41789594 |
| Βάση Δεδομένων: | MEDLINE |
| ISSN: | 2050-7895 |
|---|---|
| DOI: | 10.1039/d5em00562k |