Determination of Metabolic Fluxes by Deep Learning of Isotope Labeling Patterns.

Autor:	Law RC; Department of Chemical and Biomolecular Engineering, University of California, Los Angeles, Los Angeles, CA 90095., O'Keeffe S; Department of Chemical and Biomolecular Engineering, University of California, Los Angeles, Los Angeles, CA 90095., Nurwono G; Department of Chemistry and Biochemistry, University of California, Los Angeles, Los Angeles, CA 90095., Ki R; Department of Statistics and Data Science, University of California, Los Angeles, Los Angeles, CA 90095., Lakhani A; Department of Chemical and Biomolecular Engineering, University of California, Los Angeles, Los Angeles, CA 90095., Lai PK; Department of Chemical Engineering and Materials Science, Stevens Institute of Technology, Hoboken, NJ 07030., Park JO; Department of Chemical and Biomolecular Engineering, University of California, Los Angeles, Los Angeles, CA 90095.; California NanoSystems Institute and Jonsson Comprehensive Cancer Center at UCLA, Los Angeles, CA 90095.
Jazyk:	angličtina
Zdroj:	BioRxiv : the preprint server for biology [bioRxiv] 2023 Nov 08. Date of Electronic Publication: 2023 Nov 08.
DOI:	10.1101/2023.11.06.565907
Abstrakt:	Fluxomics offers a direct readout of metabolic state but relies on indirect measurement. Stable isotope tracers imprint flux-dependent isotope labeling patterns on metabolites we measure; however, the relationship between labeling patterns and fluxes remains elusive. Here we innovate a two-stage machine learning framework termed ML-Flux that streamlines metabolic flux quantitation from isotope tracing. We train machine learning models by simulating atom transitions across five universal metabolic models starting from 26 13 C-glucose, 2 H-glucose, and 13 C-glutamine tracers within feasible flux space. ML-Flux employs deep-learning-based imputation to take variable measurements of labeling patterns as input and successive neural networks to convert the ensuing comprehensive labeling information into metabolic fluxes. Using ML-Flux with multi-isotope tracing, we obtain fluxes through central carbon metabolism that are comparable to those from a least-squares method but orders-of-magnitude faster. ML-Flux is deployed as a webtool to expand the accessibility of metabolic flux quantitation and afford actionable information on metabolism. Competing Interests: Competing Interests The authors declare no competing financial or non-financial interests.
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu