Sequential Design of Genetic Circuits Under Uncertainty With Reinforcement Learning
For synthetic biologists designing genetic circuits, this work offers a more efficient sequential design method that handles multiple uncertainty sources without costly inference steps.
This work presents a reinforcement learning-based framework for sequential design of genetic circuits under both intrinsic stochasticity and cross-laboratory variability, achieving efficient adaptation without explicit parameter inference. The method outperforms previous Bayesian approaches by amortizing training upfront, as demonstrated on heterologous gene expression and repressilator circuit models.
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.