External control of a genetic toggle switch via Reinforcement Learning
This work addresses the challenge of practical control in synthetic biology, though it appears incremental as it builds on existing methods with a new application.
The researchers tackled the problem of stabilizing a synthetic genetic toggle switch using an external control approach, and they achieved viability in in-silico experiments by adopting a sim-to-real paradigm to overcome data efficiency issues.
We investigate the problem of using a learning-based strategy to stabilize a synthetic toggle switch via an external control approach. To overcome the data efficiency problem that would render the algorithm unfeasible for practical use in synthetic biology, we adopt a sim-to-real paradigm where the policy is learnt via training on a simplified model of the toggle switch and it is then subsequently exploited to control a more realistic model of the switch parameterized from in-vivo experiments. Our in-silico experiments confirm the viability of the approach suggesting its potential use for in-vivo control implementations.