Location: Sunflower and Plant Biology Research
Project Number: 3060-21220-033-018-S
Project Type: Non-Assistance Cooperative Agreement
Start Date: Jan 15, 2022
End Date: Mar 31, 2024
To develop and use machine learning algorithms to identify gene expression patterns associated with competition, and identify gene networks by which corn perceives and alters its expression when presented with inter -or intra-species competition, and develop testable hypotheses for altering perception of competition to reduce corn yield losses.
The accumulated RNAseq data from corn growing with or without weeds under varying conditions will be analyzed using machine learning algorithms needed to identify temporally regulated clusters of genes that are responsive to our cover-crop (winter canola), weed (red root pigweed), or high-density planting (corn with corn) interference. These clusters will then be further analyzed using pattern discerning artificial intelligence technologies to identify likely regulatory genes controlling the later changes in gene expression. Such regulatory genes will be targeted for future research and manipulation. Additionally, the function of genes in the observed clusters will be analyzed to determine the specific physiological and developmental processes impacted by weed presence or high-density planting conditions using gene set and subnetwork enrichment analysis.