SimpleChrome: Encoding of Combinatorial Effects for Predicting Gene Expression

With the breakthrough of recent state-of-the-art sequencing technology, genomics data sets have become ubiquitous. The emergence of large-scale data sets provides great opportunities for better understanding of genomics and one fundamental task is to understand gene regulation. Although each cell in the human body contains the same set of DNA information, gene expression controls the functions of these cells. There are two important factors that control the expression level of each gene: (1) Gene regulation such as histone modification can directly regulate gene expression. (2) Neighbor genes that are functional related or interact to each other can effect the gene expression level. Previous efforts tried to address the former using Attention-based model. To address the second problem, it requires incorporation of all potential related gene information into the model. Though modern machine learning and deep learning models were able to capture signals when applied to moderately sized data, they struggled to recover the underlying signals of the data due to the data's higher dimensionality. To remedy this issue, we present SimpleChrome, a deep learning model that learns the latent histone modification representations of genes. The features learned from the model allow us to better understand the combinatorial effects of cross-gene interactions and direct gene regulation on the target gene expression. The results of this paper show outstanding improvements on the predictive capabilities of downstream models and greatly relaxes the need for a large data set to learn a robust, generalized neural network. These results have immediate downstream effects in epigenomics research and drug development.