We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
Machine-Learning-Based Prediction of Plant Cuticle–Air Partition Coefficients for Organic Pollutants: Revealing Mechanisms from a Molecular Structure Perspective
Summary
Researchers developed machine-learning models using multiple linear regression, multi-layer perceptron, k-nearest neighbors, and gradient-boosting decision tree algorithms to predict plant cuticle-air partition coefficients for organic pollutants from molecular structure descriptors. They found that gradient-boosting models provided the best predictive accuracy, revealing key molecular structural features governing pollutant partitioning between plant surfaces and air.
Accurately predicting plant cuticle-air partition coefficients (Kca) is essential for assessing the ecological risk of organic pollutants and elucidating their partitioning mechanisms. The current work collected 255 measured Kca values from 25 plant species and 106 compounds (dataset (I)) and averaged them to establish a dataset (dataset (II)) containing Kca values for 106 compounds. Machine-learning algorithms (multiple linear regression (MLR), multi-layer perceptron (MLP), k-nearest neighbors (KNN), and gradient-boosting decision tree (GBDT)) were applied to develop eight QSPR models for predicting Kca. The results showed that the developed models had a high goodness of fit, as well as good robustness and predictive performance. The GBDT-2 model (Radj2 = 0.925, QLOO2 = 0.756, QBOOT2 = 0.864, Rext2 = 0.837, Qext2 = 0.811, and CCC = 0.891) is recommended as the best model for predicting Kca due to its superior performance. Moreover, interpreting the GBDT-1 and GBDT-2 models based on the Shapley additive explanations (SHAP) method elucidated how molecular properties, such as molecular size, polarizability, and molecular complexity, affected the capacity of plant cuticles to adsorb organic pollutants in the air. The satisfactory performance of the developed models suggests that they have the potential for extensive applications in guiding the environmental fate of organic pollutants and promoting the progress of eco-friendly and sustainable chemical engineering.
Sign in to start a discussion.
More Papers Like This
Predicting aqueous sorption of organic pollutants on microplastics with machine learning
Researchers developed machine learning models to predict how organic pollutants bind to microplastics in water, using data from 475 published experiments. The models outperformed traditional approaches by accounting for properties of both the microplastics and the pollutants simultaneously. The study provides a more universal tool for understanding how microplastics can transport and concentrate harmful chemicals in freshwater systems.
Versatile in silico modelling of microplastics adsorption capacity in aqueous environment based on molecular descriptor and machine learning
Researchers developed machine learning models using molecular descriptors to predict the adsorption capacity of microplastics for organic pollutants in aqueous environments, achieving high accuracy across multiple polymer types and enabling faster environmental risk assessment.
Prediction of the joint toxicity of microplastics and organic pollutants on algae based on machine learning
Researchers used machine learning models to predict the combined toxicity of microplastics and organic pollutants on algae, achieving high accuracy with gradient-boosted decision tree models. They found that microplastic concentration, particle size, and the hydrophobicity of organic pollutants were the most important factors influencing toxic effects. The study provides a computational framework that could help assess environmental risks from microplastic-pollutant mixtures more efficiently than traditional laboratory testing.
In Silico Models for Predicting Adsorption of Organic Pollutants on Atmospheric Nanoplastics by Combining Grand Canonical Monte Carlo/Density Functional Theory and Quantitative Structure Activity Relationship Approach
This computational study used molecular simulations and machine learning to build predictive models for how 48 different organic pollutants — including flame retardants — adsorb onto 12 types of atmospheric nanoplastics. The resulting models revealed that van der Waals and electrostatic forces dominate these interactions, and a single multi-dimensional model can rapidly screen thousands of pollutant-nanoplastic combinations at once. Accurate adsorption predictions are crucial for assessing how nanoplastics carry toxic chemicals through the atmosphere and into ecosystems or human lungs.
Rapidly Predicting Aqueous Adsorption Constants of Organic Pollutants onto Polyethylene Microplastics by Combining Molecular Dynamics Simulations and Machine Learning
Researchers developed a computational method combining molecular simulations with machine learning to rapidly predict how organic pollutants adsorb onto polyethylene microplastics in water. The approach accurately predicted adsorption behavior across different conditions including particle size, water salinity, and pH without requiring time-consuming laboratory experiments. The tool could help environmental scientists more quickly assess how microplastics interact with and transport chemical contaminants in aquatic environments.