We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
A Machine-Learning-Driven Pathophysiology-Based New Approach Method for the Dose-Dependent Assessment of Hazardous Chemical Mixtures and Experimental Validations
Summary
Researchers developed a machine learning method combined with biological pathway analysis to predict the toxic effects of chemical mixtures, including PFAS (forever chemicals), at different doses. The approach was validated with lab experiments and accurately identified how chemical mixtures cause harm at the cellular level. While focused on PFAS rather than microplastics, this tool is relevant because microplastics often carry chemical mixtures, and better methods to assess combined toxicity are needed to understand real-world health risks.
Environmental chemicals, such as PFAS, exist as mixtures and are frequently encountered at varying concentrations, which can lead to serious health effects, such as cancer. Therefore, understanding the dose-dependent toxicity of chemical mixtures is essential for health risk assessment. However, comprehensive methods to assess toxicity and identify the mechanisms of these harmful mixtures are currently absent. In this study, the dose-dependent toxicity assessments of chemical mixtures are performed in three methodologically distinct phases. In the first phase, we evaluated our machine-learning method (AI-HNN) and pathophysiology method (CPTM) for predicting toxicity. In the second phase, we integrated AI-HNN and CPTM to establish a comprehensive new approach method (NAM) framework called AI-CPTM that is targeted at refining prediction accuracy and providing a comprehensive understanding of toxicity mechanisms. The third phase involved experimental validations of the AI-CPTM predictions. Initially, we developed binary, multiclass classification, and regression models to predict binary, categorical toxicity, and toxic potencies using nearly a thousand experimental mixtures. This empirical dataset was expanded with assumption-based virtual mixtures, compensating for the lack of experimental data and broadening the scope of the dataset. For comparison, we also developed machine-learning models based on RF, Bagging, AdaBoost, SVR, GB, KR, DT, KN, and Consensus methods. The AI-HNN achieved overall accuracies of over 80%, with the AUC exceeding 90%. In the final phase, we demonstrated the superior performance and predictive capability of AI-CPTM, including for PFAS mixtures and their interaction effects, through rigorous literature and statistical validations, along with experimental dose-response zebrafish-embryo toxicity assays. Overall, the AI-CPTM approach significantly improves upon the limitations of standalone AI models, showing extensive enhancements in identifying toxic chemicals and mixtures and their mechanisms. This study is the first to develop a hybrid NAM that integrates AI with a pathophysiology method to comprehensively predict chemical-mixture toxicity, carcinogenicity, and mechanisms.
Sign in to start a discussion.
More Papers Like This
Metabolomics‑driven, data‑augmented machine learning for predicting toxicity of microplastic mixtures
Scientists developed a computer model that can predict how harmful mixtures of microplastics (tiny plastic particles) might be to our cells without testing each combination individually. The model works by analyzing how these plastic particles change the way cells produce energy, which helps explain why microplastics can be toxic. This breakthrough could help researchers quickly assess health risks from the complex mix of microplastics we're exposed to in real life through food, water, and air.
Machine learning-driven QSAR models for predicting the mixture toxicity of nanoparticles
Researchers used machine learning to predict how toxic different mixtures of metal nanoparticles are to bacteria. Their models outperformed traditional methods at predicting combined toxicity effects. While focused on engineered nanoparticles rather than microplastics, the computational approach could be adapted to predict health risks from the complex mixtures of nano-sized pollutants people encounter.
Microplastics and PFAS as ubiquitous pollutants affect potencies of highly toxic chemicals in mixtures
Researchers investigated how ubiquitous pollutants like PFAS and microplastics affect the toxicity of other highly toxic chemicals when present together in mixtures. They found that even at non-toxic concentrations, PFAS and microplastics could alter the potency of co-occurring toxic compounds. The study highlights the importance of considering pollutant interactions in complex environmental mixtures rather than assessing chemicals in isolation.
The emerging threat of hybrid microplastics: Impacts on per(poly)fluoroalkyl substance bioaccumulation and phytotoxicity in floating macrophytes
This study examined how mixtures of different microplastic types interact with PFAS (forever chemicals) and found that more diverse microplastic mixtures increased the absorption and toxicity of PFAS in aquatic plants. The complexity of real-world microplastic pollution, where multiple plastic types coexist, appears to make forever chemical contamination worse. This finding is important because most lab studies test single plastic types, potentially underestimating the actual environmental risk.
Unraveling the complexities of microplastics and PFAS synergy to foster sustainable environmental remediation and ecosystem protection: A critical review with novel insights
This review examines how microplastics and PFAS (sometimes called 'forever chemicals') interact in the environment, since both often come from the same everyday products. The authors found that microplastics can carry PFAS on their surface, and when organisms are exposed to both together, the combined toxic effects including oxidative stress and reproductive harm can be worse than either pollutant alone.