Department of Biochemistry & Synthetic Metabolism, Max Planck Institute for Terrestrial Microbiology, Marburg, Germany.
DataChef, Amsterdam, The Netherlands.
Nat Commun. 2022 Jul 5;13(1):3876. doi: 10.1038/s41467-022-31245-z.
Optimization of biological networks is often limited by wet lab labor and cost, and the lack of convenient computational tools. Here, we describe METIS, a versatile active machine learning workflow with a simple online interface for the data-driven optimization of biological targets with minimal experiments. We demonstrate our workflow for various applications, including cell-free transcription and translation, genetic circuits, and a 27-variable synthetic CO-fixation cycle (CETCH cycle), improving these systems between one and two orders of magnitude. For the CETCH cycle, we explore 10 conditions with only 1,000 experiments to yield the most efficient CO-fixation cascade described to date. Beyond optimization, our workflow also quantifies the relative importance of individual factors to the performance of a system identifying unknown interactions and bottlenecks. Overall, our workflow opens the way for convenient optimization and prototyping of genetic and metabolic networks with customizable adjustments according to user experience, experimental setup, and laboratory facilities.
生物网络的优化通常受到湿实验室工作和成本的限制，并且缺乏方便的计算工具。在这里，我们描述了 METIS，这是一种通用的主动机器学习工作流程，具有简单的在线界面，可通过最少的实验对生物靶标进行数据驱动的优化。我们展示了我们的工作流程在各种应用中的应用，包括无细胞转录和翻译、遗传电路以及 27 个变量的合成 CO 固定循环 (CETCH 循环)，将这些系统提高了一到两个数量级。对于 CETCH 循环，我们仅使用 1000 次实验探索了 10 种条件，从而产生了迄今为止描述的最有效的 CO 固定级联。除了优化之外，我们的工作流程还量化了单个因素对系统性能的相对重要性，从而确定了未知的相互作用和瓶颈。总的来说，我们的工作流程为根据用户经验、实验设置和实验室设施进行遗传和代谢网络的方便优化和原型设计开辟了道路。
