We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
Predicting the toxicity of microplastic particles through machine learning models
Summary
Researchers developed machine learning models to predict microplastic particle toxicity from physical and chemical descriptors, addressing the classification challenge posed by the enormous diversity of particle types that cannot be characterized using conventional chemical hazard methods. The models provided accurate toxicity predictions across diverse microplastic types, offering a practical screening tool for the field.
Unlike chemicals, which can be identified based on their well-defined molecular structure and stable properties (e.g. CAS numbers, SMILES), micro- and nanoplastic particles (MNP) lack such straightforward classification. Each MNP has its own combination of traits, including characteristics such as polymer composition, particle dimensions (length and width), and shape, as well as physicochemical properties like surface charge, surface chemistry, and plastic-associated chemicals. Furthermore, these traits may change over time, particularly due to degradation processes when MNPs are exposed to natural environments. To achieve reliable hazard and risk assessments for MNPs, it is thus necessary to predict the toxicity of MNPs with trait combinations that have not been tested directly in the lab. Similar to Quantitative Structure-Activity Relationship (QSAR) models that link molecular structures of chemicals to toxic outcomes, models are needed to link MNPs traits to their toxicities. The recently compiled Toxicity of Microplastics Explorer (ToMEx) 2.0 database consisting of 13,412 data points from 290 published studies of MNP effects on aquatic species offers a unique opportunity to approach this task. Using ToMEx 2.0 data, we trained machine learning models on tasks to predict the toxicity (presence/absence of effects, effect direction, effective concentrations) of untested MNP. We compare the predictive performance of two machine learning algorithms (boosted regression trees and deep neural networks) and use methods of explainable AI (average marginal effects) to gain insights into the relationships between toxic outcomes and MNP traits, experimental parameters, and species traits. We also compared whether the predictions change when filtering the dataset according to study quality based on assigned quality scores. Finally, we discuss how such models can be used to predict the toxicity of environmentally relevant mixtures of MNPs and how they contribute to the development of less toxic and more environmentally friendly plastic materials in the future. Also see: https://micro2024.sciencesconf.org/559370/document
Sign in to start a discussion.
More Papers Like This
Predicting the toxicity of microplastic particles through machine learning models
Researchers applied machine learning models to predict the toxicity of microplastic particles from their physical and chemical properties, addressing the challenge that microplastics lack the standardized identifiers used for chemical hazard classification. The models successfully predicted toxicity outcomes from particle descriptors, offering a framework for hazard screening of the diverse and complex microplastic contaminant class.
Potential threat of microplastics to humans: toxicity prediction modeling by small data analysis
Researchers developed a toxicity prediction model for microplastics using small data analysis techniques, enabling the anticipation of varying toxic effects depending on microplastic types and compositions found in nature.
Machine learning-driven QSAR models for predicting the cytotoxicity of five common microplastics
Researchers used machine learning to predict the toxicity of five common microplastic types on human lung cells, finding that particle size, plastic type, and exposure concentration were the most important factors determining harm. This computational approach could help assess the health risks of different microplastics more efficiently than traditional lab testing alone.
Machine-Learning-Accelerated Prediction of Water Quality Criteria for Microplastics
Researchers developed a machine learning framework to predict microplastic toxicity in aquatic organisms and derive water quality criteria for five common polymer types. The random forest model outperformed other algorithms, with particle size, density, and aquatic species group accounting for 72% of prediction variability. The study found that polystyrene and PET exhibited the greatest toxicity, and that microplastics were generally more toxic in freshwater than saltwater environments.
[Overview of the Application of Machine Learning for Identification and Environmental Risk Assessment of Microplastics].
This review examines the application of machine learning (ML) methods for identifying microplastics and assessing their environmental risks, covering techniques for improving the accuracy and reliability of microplastic detection across different environmental media. Researchers highlight how ML can systematically analyse pollution characteristics and support ecological risk evaluation of microplastic contamination.