Optimizing sequential gene expression modulation for cellular reprogramming - Coupled Boolean modeling and Reinforcement Learning based method

Abstract

Regenerative medicine entails regenerating damaged cells and tissues from healthy cells through the process of cellular reprogramming. The most common method to achieve reprogramming of cells of one type to another is by modulating the activity of specific genes. However, identifying the most suitable genes for reprogramming is a challenge due to their large number in humans and their complex interactions. This study describes a computational method to predict sequential gene expression modulation for reprogramming a starting cell type to a target cell type. The proposed method integrates: (1) a Boolean model of the concerned gene regulatory network (GRN); and (2) a reinforcement learning (RL) based model for optimization. The Boolean model is used to capture the dynamic behavior of the GRN and to understand how the gene expression modulation alters its behavior. RL model is used to optimize sequential decision-making of predicting the suitable sequence of gene expression modulation. Coupling of the Boolean model and RL plays a crucial role in the proposed computational method. Boolean model captures the GRN dynamics, and thereby, constrains the combinatorially large state space. The RL model operates in this constrained state space and uses the Boolean model to evaluate the effect of modulations on GRN dynamics to predict the sequence of suitable gene expression modulations. Applicability of the proposed method is demonstrated using a toy network of 4 genes, and a biological network of heart development representing the dynamics of 15 genes.