A multi-modal neural network for learning cis and trans regulation of stress response in yeast

Deciphering gene regulatory networks is a central problem in computational biology. Here, we explore the use of multi-modal neural networks to learn predictive models of gene expression that include cis and trans regulatory components. We learn models of stress response in the budding yeast Saccharomyces cerevisiae. Our models achieve high performance and substantially outperform other state-of-the-art methods such as boosting algorithms that use pre-defined cis-regulatory features. Our model learns several cis and trans regulators including well-known master stress response regulators. We use our models to perform in-silico TF knock-out experiments and demonstrate that in-silico predictions of target gene changes correlate with the results of the corresponding TF knockout microarray experiment.