Machine Learning-Guided Transcription Factor Discovery for Increased Seed Lipid Content in Arabidopsis

Researchers at Purdue developed a method to increase seed lipid content through controlled over-expression of transcriptional regulators of Arabidopsis thaliana. Using machine-learning, this technology can target an organ and pinpoint key transcription factors and associated biological processes. Using this technology as a framework to better understand the seed lipid biosynthesis pathway, Purdue researchers identified both known transcriptional factor regulators of seed lipid content and predicted unknown ones. This technology helps researchers to better understand the role transcriptional factor regulators play in the expression of genes.

Technology Validation: Organ-specific datasets were created for the leaf, root, shoot, flower, seed, seedling, silique, and stem of model plant Arabidopsis thaliana, and then validated against known transcription factors regulators in the seed lipid biosynthesis pathway.

Advantages:

-Optimize transcriptional hypotheses test

-Improve understanding of gene regulatory networks

Applications:

-Increased seed lipid content

-Discovery of new transcription factors

TRL: 4

Intellectual Property:

Keywords: seed lipid biosynthesis,transcription factor discovery,lipid-rich seeds,Arabidopsis model system,organ-specific gene regulation,machine learning in plant biology,seed oil enhancement,plant metabolic engineering,AI-driven trait prediction,high oil yield crops,transcriptional network modeling,precision trait development