Deep Reinforcement Learning for Stabilization of Large-scale Probabilistic Boolean Networks
This addresses the challenge of directing biological networks to desired states for targeted therapeutics, but it is incremental as it applies an existing deep RL approach to a specific domain problem.
The paper tackled the problem of controlling large-scale Probabilistic Boolean Networks (PBNs) for applications like cancer therapy by developing a model-free deep reinforcement learning method that avoids using probability transition matrices, and demonstrated successful stabilization on networks with up to 200 nodes, such as a metastatic melanoma PBN.
The ability to direct a Probabilistic Boolean Network (PBN) to a desired state is important to applications such as targeted therapeutics in cancer biology. Reinforcement Learning (RL) has been proposed as a framework that solves a discrete-time optimal control problem cast as a Markov Decision Process. We focus on an integrative framework powered by a model-free deep RL method that can address different flavours of the control problem (e.g., with or without control inputs; attractor state or a subset of the state space as the target domain). The method is agnostic to the distribution of probabilities for the next state, hence it does not use the probability transition matrix. The time complexity is linear on the time steps, or interactions between the agent (deep RL) and the environment (PBN), during training. Indeed, we explore the scalability of the deep RL approach to (set) stabilization of large-scale PBNs and demonstrate successful control on large networks, including a metastatic melanoma PBN with 200 nodes.