Sequential Design of Genetic Circuits Under Uncertainty With Reinforcement Learning

2026-05-07

AI Summary

This work addresses the dual challenges of intrinsic stochasticity in molecular reactions and variability across experimental conditions in biological system design. The authors propose a sequential optimization framework that integrates simulators based on differential equations or Markov jump processes with policy-based reinforcement learning to adaptively refine experimental designs using real-time observations, without requiring explicit parameter inference. By incorporating a pre-trained amortized policy, the method circumvents the computationally expensive inference and optimization steps typical of conventional Bayesian sequential design, enabling immediate adaptation to unknown experimental contexts. Experiments on heterologous gene expression and repressilator circuit models demonstrate that the approach efficiently handles molecular noise and inter-laboratory variability, substantially improving experimental efficiency and robustness.

Abstract

The design of biological systems is hindered by uncertainty arising from both intrinsic stochasticity of biomolecular reactions and variability across laboratory or experimental conditions. In this work, we present a sequential framework to optimize genetic circuits under both forms of uncertainty. By employing simulator models based on differential equations or Markov jump processes alongside a reinforcement learning (RL) policy-based approach, our method suggests experiments that adapt to unknown laboratory conditions while accounting for inherent stochasticity. While previous Bayesian methods address uncertainty through iterative experiment-inference-optimization cycles, they typically require computationally expensive inference and optimization steps after each experimental round, leading to delays. To overcome this bottleneck, we propose an amortized approach trained up-front across a distribution of possible uncertain parameters. This strategy sidesteps the need for explicit parameter inference during the design cycle, enabling immediate, observation-based adaptation. We demonstrate our framework on models for heterologous gene expression and a repressilator circuit, showing that it efficiently handles both molecular noise and cross-laboratory variability.

Problem

• genetic circuits
• uncertainty
• stochasticity
• experimental variability
• sequential design

Innovation

• reinforcement learning
• genetic circuits
• uncertainty quantification
• amortized inference
• sequential experimental design