Deep learning decodes the principles of differential gene expression

Identifying the molecular mechanisms that control differential gene expression (DE) is a major goal of basic and disease biology. Here, we develop a systems biology model to predict DE and mine the biological basis of the factors that influence predicted gene expression to understand how it may be generated. This model, called DEcode, utilizes deep learning to predict DE based on genome-wide binding sites on RNAs and promoters. Ranking predictive factors from DEcode indicates that clinically relevant expression changes between thousands of individuals can be predicted mainly through the joint action of post-transcriptional RNA-binding factors. We also show the broad potential applications of DEcode to generate biological insights, by predicting DE between tissues, differential transcript usage, and drivers of ageing throughout the human lifespan, of gene co-expression relationships on a genome-wide scale, and of frequently differentially expressed genes across diverse conditions. DEcode is freely available to researchers to identify influential molecular mechanisms for any human expression data. A goal of biology is to identify the molecular mechanisms that control differential gene expression. Tasaki et al. have developed a framework that integrates genomic data into a deep learning model of transcriptome regulations to predict multiple transcriptional effects in tissue- and person-specific transcriptomes.