Closing the Loop: Establishing an autonomous test-learn cycle to optimize induction of bacterial systems using a robotic platform

Jan Benedict Spannenkrebs ¹ Aron Eiermann ² Thomas Zoll ³ Silke Hackenschmidt ³ Johannes Kabisch ^1*

• ¹ Norwegian University of Science and Technology, Trondheim, Norway
• ² Proteineer GmbH, Dietzenbach, Germany
• ³ Darmstadt University of Technology, Darmstadt, Hesse, Germany

One goal of synthetic biology is to provide well-characterised biological parts that behave predictably in genetic assemblies. To achieve this, each part must be characterised in a time-resolved manner under relevant conditions. Robotic platforms can be used to automate this task and provide sufficiently large and reproducible data sets including provenance. Although robotics can significantly speed up the data collection process, the collation and analysis of the resulting data, needed to reprogram and refine workflows for future iterations, is often a manual process. As a result, even in times of rapidly advancing artificial intelligence, the common design-build-test-learn (DBTL) cycle is still not circular without human intervention. To move towards fully automated DBTL cycles, we developed a software framework to enable a robotic platform to autonomously adjust test parameters. This interdisciplinary work between computer science and biology thus transforms a static robotic platform into a dynamic one. The software framework includes software components such as an importer that retrieves measurement data from the platform's devices and writes it to a database. This is followed by an optimizer that selects the next measurement points based on a balance between exploration and exploitation. The platform is shown to be able to automatically and autonomously optimize the inducer concentration for a B. subtilis system and the combination of inducer and feed release for a E. coli system. As a target product the readily measurable green fluorescent reporter protein (GFP) is produced over multiple, consecutive iterations of testing. An evaluation of chosen (learning) algorithms for single and dual factor optimization was performed. In this article, we share the lessons learned from the development, implementation and execution of this automated design-build-test-learn cycles on a robotic platform.