EPSCoR Research Fellows: NSF: Genome-Resolved and AI-Informed Modeling of Soil Microbiome Functions Across Regional Agroecosystem Gradients

This Research Infrastructure Improvement (RII) EPSCoR Research Fellows project provides a fellowship to [an Assistant Professor and training for a postdoctoral researcher at North Dakota State University. This work is conducted in collaboration with collaborators at the Georgia Institute of Technology. Through the fellowship, the PI will investigate how the functional properties of soil microbiomes regulate agricultural productivity and resilience across environmental gradients. The project will use genome-resolved metagenomics, community-scale metabolic modeling, and artificial intelligence to identify microbial functions that cannot be detected using traditional approaches based only on microbial identity. By uncovering hidden functional diversity and developing predictive relationships between microbiome function and agroecosystem performance, this work will improve understanding of how soil microbiomes contribute to sustainable agriculture. The fellowship will also strengthen research capacity within an EPSCoR jurisdiction, expand collaborations between North Dakota State University and the Georgia Institute of Technology, and provide advanced training in computational microbiome science and data science. This project will develop genome-resolved and AI-informed approaches to predict soil microbiome functions across regional agroecosystem gradients. The central hypothesis is that incorporating genome-resolved microbial traits, including previously undescribed lineages, into artificial intelligence frameworks will improve prediction of agroecosystem functions and resilience compared with taxonomy-based approaches. The project will reconstruct microbial genomes from regional agricultural soils, derive community-weighted microbial traits including genome size and metabolic potential, and integrate these data with community-scale metabolic modeling, machine learning, deep learning, and environmental variables to identify key drivers of crop yield and resilience to environmental stressors. The fellowship will provide advanced training for the PI and a postdoctoral researcher in genome-resolved metagenomics, metabolic modeling, and AI-informed analyses. The project will further strengthen interdisciplinary collaborations, expand research capacity within an EPSCoR jurisdiction, develop data-driven teaching modules and predictive modeling exercises, and provide workshops in microbiome data analysis for undergraduate and graduate students. This project is supported by the EPSCoR Research Infrastructure Improvement Program: EPSCoR Research Fellows (ERF). The ERF program supports early- and mid-career investigators in eligible jurisdictions to develop collaborations at the nation’s private, government, or academic research institutions. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.