How to use Machine Learning in Metabolic Engineering

In the journal Metabolic Engineering, the vital subject of how to incorporate machine learning was addressed by a group of rock-star researchers from Lawrence Berkeley National Laboratory, JBEI, Agile BioFoundry, the Basque Center for Applied Mathematics, PNNL, ABPDU, Ginkgo Bioworks and the University of California at Davis.

As the research team noted, “Machine learning provides researchers a unique opportunity to make metabolic engineering more predictable. In this review, we offer an introduction to this discipline in terms that are relatable to metabolic engineers, as well as providing in-depth illustrative examples leveraging omics data and improving production. We also include practical advice for the practitioner in terms of data management, algorithm libraries, computational resources, and important non-technical issues. A variety of applications ranging from pathway construction and optimization, to genetic editing optimization, cell factory testing, and production scale-up are discussed. Moreover, the promising relationship between machine learning and mechanistic models is thoroughly reviewed. Finally, the future perspectives and most promising directions for this combination of disciplines are examined.”

The wrote up includes perhaps the most accessible summary of Machine learning in terms that are relatable to metabolic engineers and practical advice for the practitioner in terms of data management, algorithm libraries, and computational resources, yet seen.