Combining mechanistic and machine learning models for predictive engineering and optimization of tryptophan metabolism
Journal article, 2020

Through advanced mechanistic modeling and the generation of large high-quality datasets, machine learning is becoming an integral part of understanding and engineering living systems. Here we show that mechanistic and machine learning models can be combined to enable accurate genotype-to-phenotype predictions. We use a genome-scale model to pinpoint engineering targets, efficient library construction of metabolic pathway designs, and high-throughput biosensor-enabled screening for training diverse machine learning algorithms. From a single data-generation cycle, this enables successful forward engineering of complex aromatic amino acid metabolism in yeast, with the best machine learning-guided design recommendations improving tryptophan titer and productivity by up to 74 and 43%, respectively, compared to the best designs used for algorithm training. Thus, this study highlights the power of combining mechanistic and machine learning models to effectively direct metabolic engineering efforts.

Author

J. Zhang

Technical University of Denmark (DTU)

Søren D. Petersen

Technical University of Denmark (DTU)

Tijana Radivojevic

DOE Agile BioFoundry

Lawrence Berkeley National Laboratory

Joint BioEnergy Institute, California

Andrés Ramirez

TeselaGen SpA

Andrés Pérez-Manríquez

TeselaGen SpA

Eduardo Abeliuk

TeselaGen Biotechnology, Inc.

Benjamín José Sánchez

Technical University of Denmark (DTU)

Zak Costello

DOE Agile BioFoundry

Joint BioEnergy Institute, California

Lawrence Berkeley National Laboratory

Yu Chen

Chalmers, Biology and Biological Engineering, Systems and Synthetic Biology

Michael J. Fero

TeselaGen Biotechnology, Inc.

Hector Garcia Martin

Joint BioEnergy Institute, California

DOE Agile BioFoundry

Lawrence Berkeley National Laboratory

Basque Center for Applied Mathematics (BCAM)

Jens B Nielsen

BioInnovation Institute

Chalmers, Biology and Biological Engineering, Systems and Synthetic Biology

Technical University of Denmark (DTU)

J.D. Keasling

Technical University of Denmark (DTU)

Shenzhen Institutes of Advanced Technologies

University of California

Joint BioEnergy Institute, California

Lawrence Berkeley National Laboratory

M. K. Jensen

Technical University of Denmark (DTU)

Nature Communications

2041-1723 (ISSN)

Vol. 11 1 4880

Predictive and Accelerated Metabolic Engineering Network (PAcMEN)

European Commission (EC), 2016-09-01 -- 2020-08-30.

Subject Categories

Language Technology (Computational Linguistics)

Bioinformatics (Computational Biology)

Computer Science

DOI

10.1038/s41467-020-17910-1

More information

Latest update

10/22/2020