Exploring the response of bacterial community functions to microplastic features in lake ecosystems through interpretable machine learning.

Microplastics (MPs) are ubiquitous and have various characteristics. However, their impacts on bacterial community functions in lakes remain elusive. In this study, we identified 33 different MPs features including their abundance, shape, color, size, and polymer type, from Taihu Lake, China. These features were used to construct 48 machine learning models, utilizing four types of machine learning regression algorithms, to investigate how different MP features influence human health, carbon/nitrogen cycling, and energy source-related functions of bacterial communities. The XGBoost models provided the best performance with an average R2 of 0.85 in explaining the abundance of functions. Yellow-, fragment-, and polyethylene terephthalate (PET) MPs were the most important features by Shapley values. Yellow- and PET-MPs mainly had primarily negative impacts on human pathogens pneumonia and chemoheterotrophy, respectively. Fragment-MPs had a primarily positive impact, which shifted from positive to negative at a proportion of 0.5 for methanol oxidation. Moreover, MPs may affect community structure by filtering for functional traits. These findings are important for understanding the effects of MP pollution on bacterial community function and its role in the global carbon and nitrogen cycling and human health and help us to determine the potential impacts of MP pollution on ecosystems.