Comparing AI versus Optimization Workflows for Simulation-Based Inference of Spatial-Stochastic Systems

Abstract

Listen

Translate article

Abstract Model parameter inference is a universal problem across science. This challenge is particularly pronounced in developmental biology, where faithful mechanistic descriptions require spatial-stochastic models with numerous parameters, yet quantitative empirical data often lack sufficient granularity due to experimental limitations. Parameterizing such complex models therefore necessitates methods that elaborate on classical Bayesian inference by incorporating notions of optimality and goal-orientation through low-dimensional objective functions that quantitatively encapsulate target system behavior. In this study, we contrast two such inference workflows and apply them to biophysically inspired spatial-stochastic models. Technically, both workflows employ simulation-based inference (SBI) methods: the first leverages a modern deep-learning technique known as sequential neural posterior estimation (SNPE), while the second relies on a classical optimization technique called simulated annealing (SA). We evaluate these workflows by inferring the parameters of two complementary models for the inner cell mass (ICM) lineage differentiation in the blastocyst-stage mouse embryo. This developmental biology system serves as a paradigmatic example of a highly robust and reproducible cell-fate proportioning process that self-organizes under strongly stochastic conditions, such as intrinsic biochemical noise and cell-cell signaling delays. Our results reveal that while both methods provide consistent model parameter estimates, the modern SBI workflow yields significantly richer inferred distributions at an equivalent computational cost. We identify the computational scenarios that favor the modern SBI method over its classical counterpart, and propose a plausible strategy to exploit the complementary strengths of both workflows for enhanced parameter space exploration.