Machine Learning Predicts the Yeast Metabolome from the Quantitative Proteome of Kinase Knockouts
Journal article, 2018

A challenge in solving the genotype-to-phenotype relationship is to predict a cell's metabolome, believed to correlate poorly with gene expression. Using comparative quantitative proteomics, we found that differential protein expression in 97 Saccharomyces cerevisiae kinase deletion strains is non-redundant and dominated by abundance changes in metabolic enzymes. Associating differential enzyme expression landscapes to corresponding metabolomes using network models provided reasoning for poor proteome-metabolome correlations; differential protein expression redistributes flux control between many enzymes acting in concert, a mechanism not captured by one-to-one correlation statistics. Mapping these regulatory patterns using machine learning enabled the prediction of metabolite concentrations, as well as identification of candidate genes important for the regulation of metabolism. Overall, our study reveals that a large part of metabolism regulation is explained through coordinated enzyme expression changes. Our quantitative data indicate that this mechanism explains more than half of metabolism regulation and underlies the interdependency between enzyme levels and metabolism, which renders the metabolome a predictable phenotype. Predicting metabolomes from gene expression data is a key challenge in understanding the genotype-phenotype relationship. Studying the enzyme expression proteome in kinase knockouts, we reveal the importance of a so far overlooked metabolism-regulatory mechanism. Enzyme expression changes are impacting on metabolite levels through many changes acting in concert. We show that one can map regulatory enzyme expression patterns using machine learning and use them to predict the metabolome of kinase-deficient cells on the basis of their enzyme expression proteome. Our study quantifies the role of enzyme abundance in the regulation of metabolism and by doing so reveals the potential of machine learning in gaining understanding about complex metabolism regulation.

hierarchical regulation

high-throughput proteomics

metabolic control analysis


enzyme abundance

machine learning

genotype-phenotype problem



Aleksej Zelezniak

The Francis Crick Institute

University of Cambridge

Royal Institute of Technology (KTH)

Chalmers, Biology and Biological Engineering, Systems and Synthetic Biology

Jakob Vowinckel

Biognosys AG

University of Cambridge

Floriana Capuano

University of Cambridge

Christoph B. Messner

The Francis Crick Institute

Vadim Demichev

The Francis Crick Institute

University of Cambridge

Nicole Polowsky

University of Cambridge

Michael Mülleder

University of Cambridge

The Francis Crick Institute

Stephan Kamrad

University College London (UCL)

The Francis Crick Institute

Bernd Klaus

European Molecular Biology Laboratory

M. A. Keller

Medical University of Innsbruck

University of Cambridge

M. Ralser

Charité University Medicine Berlin

The Francis Crick Institute

University of Cambridge

Cell Systems

2405-4712 (eISSN)

Vol. 7 3 269-283

Subject Categories

Medical Biotechnology (with a focus on Cell Biology (including Stem Cell Biology), Molecular Biology, Microbiology, Biochemistry or Biopharmacy)

Bioinformatics and Systems Biology






More information

Latest update