Abstract

Cell-free gene expression (CFE) systems enable transcription and translation using crude cellular extracts, offering a versatile platform for synthetic biology by eliminating the need to maintain living cells. This allows direct manipulation of molecular components and the focused synthesis of specific products. However, the optimization of CFE systems is constrained by cumbersome composition, high costs, and limited yields due to numerous additional components required to maintain biocatalytic efficiency. While optimizing such complicated systems is daunting for existing high-throughput screening means, we introduce DropAI, a droplet-based, AI-driven screening strategy designed to optimize CFE systems with high throughput and economic efficiency. DropAI employs microfluidics to generate picoliter reactors and utilizes a fluorescent color-based coding-decoding system to address and screen a vast array of additive combinations. The in-droplet screening is complemented by in silico optimization, where experimental results train a machine-learning model to estimate the contribution of the components and predict high-yield combinations, which are then validated in vitro. Applying DropAI to an Escherichia coli-based CFE system, we simplified a set of 12 additives to only 3 essential components. Through further optimization, we achieved a 2.1-fold cost reduction and a 1.9-fold increase in yield for the expression of superfolder green fluorescent protein (sfGFP). This optimized formulation was further validated across 12 different proteins. Notably, the established E. coli model is successfully adapted to a Bacillus subtilis-based system through transfer learning, leading to doubled yield through prediction. DropAI thus offers a generalizable and scalable method for optimizing CFE systems, enhancing their potential for biochemical engineering and biomanufacturing applications.