Flux Transformer learns intracellular metabolic fluxes from isotope labeling and measured reaction rates

Cells convert incoming nutrients into energy and biomass via metabolic fluxes. Quantifying these fluxes involves feeding cells isotope-labeled nutrients, quantifying metabolite labeling patterns, and inverting the labeling data to retrieve the underlying flux distribution. Traditional metabolic flux analysis (MFA) is both computationally expensive and frequently requires manual refinement of the cost function to obtain plausible results. For this reason, MFA has remained inaccessible to non-experts. Here we present Flux Transformer, an AI model that uses reaction-specific attention to integrate isotope-labeling data with available reaction-rate measurements, reconstructing mass-balanced steady-state fluxes. The model is trained on simulated data with added noise and identifies the underlying fluxes from these data more effectively than traditional MFA. Provided experimental data from wild-type and mutant bacteria, yeast, plants, and mammalian T cells, it efficiently and accurately recovers expert-curated MFA fluxes. By making flux analysis accessible, Flux Transformer is poised to accelerate metabolic research and engineering.

Authors

Institutions

Publication Details

Journal
bioRxiv (Cold Spring Harbor Laboratory)
Published
2026-11-18
DOI
https://doi.org/10.64898/2026.11.16.767180
Primary Topic
Microbial Metabolic Engineering and Bioproduction
Type
preprint

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

Flux Transformer learns intracellular metabolic fluxes from isotope labeling and measured reaction rates

Daniel Weilandt, Md Toki Tahmid, Joshua D. Rabinowitz, Rachid Ounit et al.
bioRxiv (Cold Spring Harbor Laboratory)
Microbial Metabolic Engineering and Bioproduction
preprint

Flux Transformer learns intracellular metabolic fluxes from isotope labeling and measured reaction rates

Daniel Weilandt, Md Toki Tahmid, Joshua D. Rabinowitz, Rachid Ounit, Jörg Schwender, Mona Singh
preprint en

Abstract

Cells convert incoming nutrients into energy and biomass via metabolic fluxes. Quantifying these fluxes involves feeding cells isotope-labeled nutrients, quantifying metabolite labeling patterns, and inverting the labeling data to retrieve the underlying flux distribution. Traditional metabolic flux analysis (MFA) is both computationally expensive and frequently requires manual refinement of the cost function to obtain plausible results. For this reason, MFA has remained inaccessible to non-experts. Here we present Flux Transformer, an AI model that uses reaction-specific attention to integrate isotope-labeling data with available reaction-rate measurements, reconstructing mass-balanced steady-state fluxes. The model is trained on simulated data with added noise and identifies the underlying fluxes from these data more effectively than traditional MFA. Provided experimental data from wild-type and mutant bacteria, yeast, plants, and mammalian T cells, it efficiently and accurately recovers expert-curated MFA fluxes. By making flux analysis accessible, Flux Transformer is poised to accelerate metabolic research and engineering.

bioRxiv (Cold Spring Harbor Laboratory)
Brookhaven National Laboratory (US), Princeton University (US)
U.S. Department of Energy, University of Pennsylvania, Rutgers Cancer Institute of New Jersey, Ludwig Institute for Cancer Research, National Institutes of Health, Office of Science, National Institute of General Medical Sciences, Biological and Environmental Research
Microbial Metabolic Engineering and Bioproduction
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon