Iterative design of a NAND hybrid riboswitch by deep batch Bayesian optimization.

The design of large genetic circuits requires genetic regulatory devices capable of performing complex logic operations that place no excessive metabolic burden on the host cell. Hybrid riboswitches, synthetically enhanced compact RNA elements (<100 nucleotides) that form a tertiary structure with the ability to specifically bind two different target molecules, can be used to design genetic regulators that emulate Boolean logic. When inserted into the 5' UTR of a messenger RNA, these devices can regulate translation initiation upon specific binding of one or both ligands without the need for additional auxiliary factors. The goal of this study is to design hybrid riboswitches that emulate Boolean NAND logic in yeast. We propose a novel machine learning-based design framework combining high-throughput in vivo screening and deep Bayesian optimization. Through an initial screening, we discovered a hybrid riboswitch with NAND behavior. Using batch Bayesian optimization with an ensemble neural network as surrogate, we improved the NAND functionality of our hybrid riboswitch with respect to a performance score, thereby achieving near-digital NAND behavior. With its focus on model-based and score-driven design, our proposed method can complement experiment-driven approaches by allowing fine grained adaptation of functionality, including constructs sensitive to single nucleotide changes.