Journal Article

A versatile active learning workflow for optimization of genetic and metabolic networks

Faure, Léon, Cortina, Niña, Socorro, LOEWE Center for Synthetic Microbiology (SYNMIKRO) ; Philipps Universität Marburg = Philipps University of Marburg, Yazdizadeh Kharrazi, Ali, Pandi, Amir, DataChef, Bobkova, Elizaveta, Foroughijabbari, Yeganeh, Erb, Tobias, J, Paczia, Nicole, Nattermann, Maren, Scholz, Scott, A, MICrobiologie de l'ALImentation au Service de la Santé (MICALIS) ; AgroParisTech-Université Paris-Saclay-Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement (INRAE), Adam, David, Diehl, Christoph, Max Planck Institute for Terrestrial Microbiology ; Max-Planck-Gesellschaft, Faulon, Jean-Loup, Chapin, Nils, Moritz, Charles

2022

Overview

Abstract 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 2 -fixation cycle (CETCH cycle), improving these systems between one and two orders of magnitude. For the CETCH cycle, we explore 10 25 conditions with only 1,000 experiments to yield the most efficient CO 2 -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.

• Publisher: Nature Publishing Group,CCSD,Nature Publishing Group UK,Nature Portfolio
• Subject: 49 / 631/114/2390 / 631/553/2691 / 631/553/552 / 631/61/318 / Carbon dioxide / Carbon dioxide fixation / Computer applications / Fixation / Humanities and Social Sciences / Labor / Learning algorithms / Life Sciences / Machine learning / Metabolic networks / Metabolism / Microbiology and Parasitology / multidisciplinary / Networks / Optimization / Prototyping / Science / Science (multidisciplinary) / Software / Standardization / User experience / User interfaces / Workflow
• ISBN: 0008219012000