One of the most important challenges in bioengineering is effectively using -omics data to guide metabolic engineering towards higher production levels. Here, we present the Automated Recommendation Tool (
ART), a tool that leverages machine learning and probabilistic modeling techniques to guide synthetic biology in a systematic fashion, without the need for a full mechanistic understanding of the biological system. ART provides a set of recommendations for the next engineering cycle, alongside probabilistic predictions of their outcomes. It can be used as a python library or through a web-based graphical
frontend that does not require coding expertise.
