Predictive prioritization of genes significantly associated with biotic and abiotic stresses in maize using machine learning algorithms

Authors: PRADHAN, ANJAN KUMAR - LSU Agcenter; GANDHAM, PRASAD - LSU Agcenter; Rajasekaran, Kanniah; BAISAKH, NIRANJAN - LSU Agcenter

Submitted to: Frontiers in Plant Science
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 5/26/2025
Publication Date: N/A
Citation: N/A

Interpretive Summary: Both biotic and environmental stresses cause loss of productivity of maize worldwide. Identifying genes associated with stress resistance responses in maize is paramount. A meta- analysis of 39,756 genes that respond differently to stress conditions in maize followed by seven machine learning based prediction methods identified top-most significant genes for different types of stress. Some of these genes were identified to specifically respond to biotic stress including mycotoxin producing fungi - Aspergillus flavus and Fusarium verticillioides. Most of these top-most predicted genes were involved in hormone signaling pathways in the plant. The top-ranked genes in maize need further research to ascertain their roles in multiple stress response and further utilization in developing stress-resistant maize varieties. Genes identified in this study can serve as primary targets for editing and other biotechnological manipulations.

Technical Abstract: Both Biotic and abiotic stresses pose serious threats to the growth and productivity of crop plants including maize worldwide. Identifying genes and associated networks underlying stress resistance responses in maize is paramount. A meta-transcriptome approach was undertaken with 39,756 genes differentially expressed in response to biotic and abiotic stresses in maize. Gene expression values were interrogated for prioritization through seven machine learning (ML) models, such as support vector machine (SVM), partial least square discriminant analysis (PLSDA), k-nearest neighbor (KNN), gradient boost machine (GBM), random forest (RF), naïve bayes (NB), and decision tree (DT) to identify top genes in maize. Improved performances of the algorithms via feature selection from the raw gene features identified 235 unique genes as top candidate genes across all models for all stresses. Three genes such as Zm00001eb176680, Zm00001eb176940, and Zm00001eb179190 expressed as bZIP transcription factor 68, glycine-rich cell wall structural protein 2, and aldehyde dehydrogenase 11 (ALDH11), respectively were commonly predicted as top-most candidates between abiotic stress and combined stresses and were identified from a weighted gene co-expression network as the hub genes in the brown module. However, only one gene Zm00001eb038720 encoding RNA-binding protein AU-1/Ribonuclease E/G, predicted by the PLSDA algorithm, was found commonly expressed under both biotic and abiotic stress. Gene ontology and biological pathway analysis suggested genes involved in hormone signaling and nucleotide binding were significantly differentially regulated under stress conditions. These genes also had an abundance of antioxidant responsive elements and abscisic acid responsive elements in their promoter region, further establishing their role in stress response mechanisms. The top-ranked genes predicted to play key candidates in the multiple stress resistance in maize need to be functional validated to ascertain their roles and further utilization in developing stress-resistant maize varieties.