Genome-wide, Organ-delimited gene regulatory networks (OD-GRN) provide high accuracy in candidate Transcription Factor (TF) selection across diverse processes

<p>Organ-specific gene expression datasets that include hundreds to thousands of experiments allow reconstruction of organ-level gene regulatory networks. However, creating such datasets is greatly hampered by the requirements of extensive and tedious manual curation. Here we trained a supervised classification model that can accurately classify the organ-of-origin for a plant transcriptome. This K-Nearest Neighbor-based multiclass classifier was used to create organ-specific gene expression datasets for the leaf, root, shoot, flower and seed in <em>Arabidopsis thaliana</em>. A gene regulatory network (GRN) inference approach was then used to determine: <em>i.</em> influential transcription factors (TFs) in each organ and, <em>ii.</em> the most influential TFs for specific biological processes in that organ. These genome-wide, organ-delimited GRNs (OD-GRNs), recalled many known regulators of organ development and processes operating in those organs. Importantly, many previously unknown TF regulators were uncovered as potential regulators of these processes. As a proof-of-concept, we focused on experimentally validating the predicted TF regulators of lipid biosynthesis in seeds, with relevance to food and biofuel production. Of the top twenty candidate TFs, eight are known regulators of seed oil content, including WRI1, LEC1, and FUS3. Importantly, we validated five previously unknown TFs MybS2, TGA4, SPL12, AGL18 and DiV2 as regulators of seed lipid biosynthesis. We elucidated the molecular mechanism of MyB2 and show that it induces PAP family genes and lipid synthesis genes to enhance seed lipid content. This general approach has the potential to be extended to any species with sufficiently large gene expression datasets to discover novel regulators of any trait-of-interest. </p>

<p>A web tool for querying and visualizing the OD-GRNs is available here: https://www.purdue.edu/hla/sites/varalalab/od-grns/ . The underlying gene expression datasets shared here can be used to create custom subsets, or as input for alternate GRN inference or other ML applications. </p>