Machine Learning-Guided Synthetic Microbial Communities Enable Functional and Sustainable Degradation of Persistent Environmental Pollutants

Abstract Persistent environmental pollutants demand the use of diverse microbial metabolic capabilities for effective degradation. While naturally occurring consortia or single strains often fall short in efficiency, synthetic microbial communities (SynComs) hold greater promise for enhanced degradation. To address this challenge, we developed GENIA (Genomically and Environmentally Networked Intelligent Assemblies), a genome-informed and machine learning–guided framework for the rational design of SynComs capable of multi-pollutant degradation under simulated environmental conditions. Using a microfluidic high-throughput cultivation platform, 2,155 bacterial strains were isolated from xenobiotic-enriched environments and screened for pollutant-specific growth. Whole-genome sequencing and functional annotation of 45 prioritized strains revealed metabolic traits associated with the potential degradation of challenging persistent environmental pollutants as proof of concept, i.e., lignin oxidation, atrazine dechlorination, and PFAS defluorination. These genomic profiles were encoded into spline-based graph representations and integrated within the GENIA pipeline, which combines graph neural networks, pathway complementarity modeling, and functional redundancy minimization to predict optimal community assemblies. The resulting nine-member community—comprising Pantoea dispersa , Atlantibacter hermannii , Pseudomonas fulva , Paenibacillus polymyxa , Bacillus cabrialesii , Micrococcus luteus , Bacillus pseudomycoides , Bacillus licheniformis , and Pseudomonas pergaminensis —was predicted to exhibit broad catabolic capacity and minimal intra-community competition. Kinetic experiments in minimal medium demonstrated simultaneous multi-pollutant degradation: lignin (91.6% removal by day 5), atrazine (91.4% removal by day 3), and PFOS (93.1% removal within seven days), representing a 2-4-fold improvement over existing approaches. GENIA establishes a scalable and generalizable framework that integrates systems-level genomics, phenotypic screening, and predictive modeling to engineer ecologically coherent microbial consortia with application to complex environmental bioremediation. Graphical Abstract