Transcription factors are proteins that bind to DNA sequences to help or hinder transcription and thus determine the rate at which RNA and protein is produced. RNA and protein are often used to regulate each other, which can result in chain reactions within a system and ultimately affect the expression of a large collection of genes, or gene modules. To better see the connections between gene modules, networks can be created. Presently, due to the computational intensity of creating transcription factor regulatory networks, many networks are created using small sets of genes taken out of a specified genome. These smaller networks are then pieced together to form a larger network. However, this method leaves out sections of the network and is not always accurate. In my project, gene expression data from different labs and experiments, found in the TAIR Arabidopsis databank, were used to create a more comprehensive network. GPU acceleration is used to address the problem of computational intensity and allows for me to use a large set of genes within the genome to create one large network. This method gives us a more complete and accurate network where we can find linkages between different genes and map out regulatory pathways that will help us better understand how cellular and organism function is regulated and controlled. It will also give insight into how a stimuli affecting one gene can affect the whole system or regulatory pathway.