Machine learning aided analyses of thousands of draft genomes reveal plant- and environment-specific features of activated sludge process

Abstract

25Microorganisms in activated sludge (AS) play key roles in the wastewater treatment 26 process. However, the ecological behavior of microorganisms in AS and their 27 differences with microorganisms in other environments have mainly been studied using 2816S rRNA gene that may not truly represent their in-situ functions. Here, we present 29 2045 bacterial and archaeal metagenome-assembled genomes (MAGs) recovered from 301.35 Tb of metagenomic sequencing data generated from 114 AS samples of 23 full-31 scale wastewater treatment plants (WWTPs). The average completeness and 32 contamination of the MAGs are 82.0% and 2.0%, respectively. We find that the AS 33MAGs have obviously plant-specific features and few proteins are shared by different 34WWTPs, especially for WWTPs located in geographically distant areas. Despite the 35 differences, specific functional traits (e.g. functions related to aerobic metabolism, 36 nutrient sensing/acquisition, biofilm formation, etc.) of AS MAGs could be identified 37 by a machine learning approach, and based on these traits, AS MAGs could be 38 differentiated from MAGs of other environments with an accuracy of 96.6%. Our work 39 provides valuable genome resources for future investigation of the AS microbiome and 40 also introduces a novel approach to understand the microbial ecology in different 41 ecosystems. 42 43