Model-to-crop conserved NUE Regulons enhance machine learning predictions of nitrogen use efficiency

Authors: HUANG, JI - New York University; CHENG, CHAI-YI - National Taiwan University; Brooks, Matthew; JEFFERS, TIM - New York University; DONER, NATHAN - New York University; SHIH, HUNG-JUI - New York University; FRANGOS, SAMANTHA - New York University; KATARI, MANPREET SINGH - New York University; CORUZZI, GLORIA - New York University

Submitted to: The Plant Cell
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 4/7/2025
Publication Date: 5/14/2025
Citation: Huang, J., Cheng, C., Brooks, M.D., Jeffers, T.L., Doner, N., Shih, H.S., Frangos, S., Katari, M., Coruzzi, G.M. 2025. Model-to-crop conserved NUE Regulons enhance machine learning predictions of nitrogen use efficiency. The Plant Cell. https://doi.org/10.1093/plcell/koaf093.
DOI: https://doi.org/10.1093/plcell/koaf093

Interpretive Summary: The amount of applied nitrogen that is recovered during crop harvest is estimated to be less than 55% Therefore, improving nitrogen use efficiency maize could dramatically reduce fertilizer costs and the negative impact of agriculture on the environment. To accomplish this it is important to understand the gene in maize that sense and trigger responses to nitrogen nutrition. This study uses a network biology approach that combines time-series gene expression analysis and the transfer of knowledge from model organisms to crop species. The resulting gene regulatory network was validated using a plant cell-based assay. This study has revealed new transcription factors important to nitrogen use traits in the field, including a new role for the KNOTTED1, a well-known transcription factor involved in plant development.

Technical Abstract: In this data-rich era, the promise of systems biology is to learn gene regulatory networks controlling key agricultural traits. However, validating these networks in crops remains challenging. By integrating network inference and machine learning, we functionally validated network regulons predicting nitrogen use efficiency (NUE) in Arabidopsis and maize. Our time-course nitrogen response transcriptome analysis uncovered a conserved N-response cascade between maize and Arabidopsis. Using Dynamic Factor Graph, we inferred N-regulated gene regulatory networks (N-GRNs) in maize and validated TF-target interactions for 23 maize TFs with the TARGET, a cell-based TF-perturbation assay. We pruned the N-GRNs by Precision-Recall analysis. Combining these data, we uncovered a previously unknown role for KNOTTED1 in the dynamic N-signaling network. We learned gene-to-NUE trait models across 16 maize varieties using XGBoost trained on N-response genes conserved model-to-crop. Integrating NUE importance scores within our GRN, we ranked maize TFs by their NUENet scores. In a model-to-crop approach, we validated orthologous N-regulated TF-targets for the top-ranked maize NUENet TFs (MYB34/R4''24 targets) and the orthologous Arabidopsis TF (AtDIV1''23 targets) using the cell-based TARGET assay. The genes in this orthologous model-to-crop NUENet regulons were superior at predicting NUE traits in XGBoost models learned in both maize and Arabidopsis. Thus, our model-to-crop approach combining GRNs, machine learning, and orthologous network modules offers a strategic framework for crop trait improvement.