Studying cellular signal transduction systems with deep hierarchical models
Abstract: Cellular signal transduction systems are organized as hierarchical network. When stimulated by environment changes, cellular signals are transmitted through signaling cascades in which signals are compositionally encoded. For example, the signal of an activated growth factor receptor, EGFR, is then compositional encoded by RAS, PI3K, AKT, and then by STAT3 and cJUN etc. Often, the effect of perturbation of cellular signaling system can be read out as changed gene expression. In this presentation, I will discuss the computational problem of modeling the signal transduction inside cells, based on the gene expression data collected under different perturbations of cellular signal system. I will discuss our experience in using probabilistic graphical models to represent the hierarchical organization of cellular signaling system and to capture its information.