Predicting microbial community compositions in wastewater treatment plants using artificial neural networks

Background Activated sludge (AS) of wastewater treatment plants (WWTPs) is one of the world’s largest artificial microbial ecosystems and the microbial community of the AS system is closely related to WWTPs' performance. However, how to predict its community structure is still unclear. Results Here, we used artificial neural networks (ANN) to predict the microbial compositions of AS systems collected from WWTPs located worldwide. The predictive accuracy R 2 1:1 of the Shannon–Wiener index reached 60.42%, and the average R 2 1:1 of amplicon sequence variants (ASVs) appearing in at least 10% of samples and core taxa were 35.09% and 42.99%, respectively. We also found that the predictability of ASVs was significantly positively correlated with their relative abundance and occurrence frequency, but significantly negatively correlated with potential migration rate. The typical functional groups such as nitrifiers, denitrifiers, polyphosphate-accumulating organisms (PAOs), glycogen-accumulating organisms (GAOs), and filamentous organisms in AS systems could also be well recovered using ANN models, with R 2 1:1 ranging from 32.62% to 56.81%. Furthermore, we found that whether industry wastewater source contained in inflow (IndConInf) had good predictive abilities, although its correlation with ASVs in the Mantel test analysis was weak, which suggested important factors that cannot be identified using traditional methods may be highlighted by the ANN model. Conclusions We demonstrated that the microbial compositions and major functional groups of AS systems are predictable using our approach, and IndConInf has a significant impact on the prediction. Our results provide a better understanding of the factors affecting AS communities through the prediction of the microbial community of AS systems, which could lead to insights for improved operating parameters and control of community structure. 2jzZ-nU4sRefzvXQz6KqH6 Video Abstract