Visualized Stochastic Modeling of Galactose Regulatory Feedback Loops with Deep Learning Models

Feedback loops, which can produce significant phenotypic heterogeneity by links the output of a circuit back to its input. Although deterministic models have been used for studying the existence of bistability properties under various system conditions, these models cannot realize cell-to-cell fluctuations in genetic switching. However, stochastic model is a much better way to studying the impact of both external or intrinsic noise in bistable systems, which is harder for deterministic modeling in the situation of lacking detailed knowledge of biochemical reactions, kinetic rates, and molecular numbers. In this work, we build a stochastic system based on the yeast galactose regulatory network, and talk about the ways to determine the percentages of switching in the system with noise. The deep learning is integrated to reduce the complexity of the model.