A Symbolic and Statistical Learning Framework to Discover Bioprocessing Regulatory Mechanism: Cell Culture Example

TL;DR

This paper presents a novel symbolic-statistical framework for identifying key regulatory mechanisms in bioprocessing, improving model accuracy and robustness despite limited data, with applications demonstrated in cell culture systems.

Contribution

It introduces a Bayesian learning framework combining symbolic and statistical methods to discover regulatory mechanisms and quantify uncertainty in bioprocess models.

Findings

Enhanced sample efficiency over existing Bayesian methods

Successful recovery of missing regulatory mechanisms

Improved model fidelity with limited data

Abstract

Bioprocess mechanistic modeling is essential for advancing intelligent digital twin representation of biomanufacturing, yet challenges persist due to complex intracellular regulation, stochastic system behavior, and limited experimental data. This paper introduces a symbolic and statistical learning framework to identify key regulatory mechanisms and quantify model uncertainty. Bioprocess dynamics is formulated with stochastic differential equations characterizing intrinsic process variability, with a predefined set of candidate regulatory mechanisms constructed from biological knowledge. A Bayesian learning approach is developed, which is based on a joint learning of kinetic parameters and regulatory structure through a formulation of the mixture model. To enhance computational efficiency, a Metropolis-adjusted Langevin algorithm with adjoint sensitivity analysis is developed for posterior exploration. Compared to state-of-the-art Bayesian inference approaches, the proposed framework achieves improved sample efficiency and robust model selection. An empirical study demonstrates its ability to recover missing regulatory mechanisms and improve model fidelity under data-limited conditions.