Approximation of Intractable Likelihood Functions in Systems Biology via Normalizing Flows

TL;DR

This paper introduces a novel method using normalizing flows to approximate intractable likelihood functions in systems biology, enabling more efficient inference and model selection.

Contribution

It presents a new framework applying normalizing flows to approximate complex likelihoods in systems biology, facilitating simulation-based inference and model comparison.

Findings

Effective approximation of likelihood functions in real-world systems biology problems

Enhanced inference and model selection capabilities using normalizing flows

Practical guidance for implementing the proposed method

Abstract

Systems biology relies on mathematical models that often involve complex and intractable likelihood functions, posing challenges for efficient inference and model selection. Generative models, such as normalizing flows, have shown remarkable ability in approximating complex distributions in various domains. However, their application in systems biology for approximating intractable likelihood functions remains unexplored. Here, we elucidate a framework for leveraging normalizing flows to approximate complex likelihood functions inherent to systems biology models. By using normalizing flows in the Simulation-based inference setting, we demonstrate a method that not only approximates a likelihood function but also allows for model inference in the model selection setting. We showcase the effectiveness of this approach on real-world systems biology problems, providing practical guidance for implementation and highlighting its advantages over traditional computational methods.