Molecular Representation and Closed-Loop Validation for Toxicity Assessment of Organic Compounds in Ambient Air PM2.5

Clinical Snapshot

Key Findings

• P Value: Not reported in abstract

• Effect Size: AUC >0.8 for stacking ensemble model

• Primary Outcome: Machine learning model performance for predicting organic compound cytotoxicity in PM2.5

• Nnt Or Sensitivity: 51 of 387 compounds confirmed toxic from Hong Kong PM2.5 samples (13.2% confirmation rate)

• Confidence Interval: Not specified in abstract

Clinical Application

Computationally feasible for routine air quality assessment and regulatory toxicity screening Highly relevant for Australian environmental health agencies and air quality monitoring, particularly in major cities. Could inform TGA chemical assessment processes and support development of PM2.5 exposure guidelines aligned with NHMRC recommendations Populations exposed to ambient air pollution, particularly in urban environments with high PM2.5 concentrations

Abstract

Although the health impacts of fine particulate matter (PM2.5) are primarily attributed to its chemically diverse composition rather than to mass concentration, assessing the toxicity of PM2.5 constituent compounds remains highly challenging due to chemical complexity and limited experimental scalability. This study introduces an interpretable machine learning (ML) framework using a curated A549 cytotoxicity data set (19,841 compounds) that integrates customized Molecular Access System (MACCS) fingerprints, six base models, and a stacking ensemble meta-model, all optimized with a biobjective strategy to assess the toxicity of organic compounds in PM2.5. The stacking ensemble model demonstrated satisfactory performance (test AUC > 0.8), exhibiting good generalization, adaptability, and robustness. Nontargeted analysis generated and experimentally validated a prediction set from the Hong Kong PM2.5 samples (51 of 387 compounds confirmed from 13 classes), demonstrating broad applicability on an independent Nanjing PM2.5 set (572 compounds). Key substructures driving toxicity, identified through a SHapley Additive exPlanations (SHAP) analysis and cell experimental validation, revealed that PM2.5 compounds with aromatic rings and nitrogen-based functional groups (e.g., aromatic α,β-unsaturated ketones, aromatic amines, aromatic nitro compounds, and tertiary amines) likely contribute to high toxicity. The derived "structure-toxicity" rules narrow the search space from thousands of compounds to those containing critical substructures, enabling efficient prioritization of toxic components and providing a foundation for improving model specificity and predictive accuracy in future studies.

References

1. 1.Lu, Y., Wu, Y., & Li, X. (2026). Molecular representation and closed-loop validation for toxicity assessment of organic compounds in ambient air PM2.5. Environmental Science & Technology. https://doi.org/10.1021/acs.est.5c17667