# Accurate prediction of flux distributions compatible with metabolite concentration effects in genome-scale metabolic networks

## TL;DR

KineFlux is a new method that uses machine learning and proteomic data to predict intracellular fluxes in genome-scale metabolic networks without needing detailed metabolite concentration data.

## Contribution

KineFlux introduces a hybrid machine learning and enzyme-constrained model approach for predicting flux distributions using only proteomic data.

## Key findings

- KineFlux accurately predicts steady-state flux distributions in Escherichia coli and Saccharomyces cerevisiae using proteomic data.
- The machine learning models in KineFlux are transferrable across independent E. coli datasets with minimal loss of accuracy.
- The method enables genome-scale flux prediction compatible with metabolite concentration effects without requiring enzyme kinetics.

## Abstract

Intracellular fluxes shape all cellular functions, and understanding how they are shaped by the joint effects of enzyme abundances and metabolite concentrations in vivo currently requires gathering matched quantitative proteomic and metabolomic data sets from resource-intensive experiments. Here, we present KineFlux, a hybrid approach that combines machine learning with enzyme-constrained metabolic models to accurately predict steady-state flux distributions using only quantitative proteomic data. KineFlux builds machine learning models for metabolite concentration effects on reaction fluxes, obtained by using fluxomics and proteomics data from a training set of experiments. Using fluxomic and proteomic data sets of Escherichia coli and Saccharomyces cerevisiae, we show that the steady-state flux distributions predicted by KineFlux are in line with fluxes estimated by classical approaches. We also demonstrate that the machine learning models embedded in KineFlux are transferrable at marginal loss of accuracy using independent testing data from E. coli. Therefore, KineFlux expands the usability of enzyme-constrained models towards accurate prediction of genome-scale flux distributions compatible with metabolite concentration effects without knowledge of enzyme kinetics.

Although intracellular fluxes shape the physiology of every organism, we still lack approaches for their accurate, high-throughput estimation. Here we show that a hybrid approach, that combines machine learning with enzyme-constrained metabolic models, can effectively address this challenge and allow accurate prediction of intracellular fluxes at a genome scale across diverse experimental scenarios with usage of proteomics data alone. The hybrid approach relies on deriving metabolite concentration effects from a training set of fluxomic and proteomic data, and uses machine learning models to predict these effects in a transferrable and interpretable fashion. The hybrid approach expands the applicability of enzyme-constrained metabolic models that are becoming available across diverse species.