Dataset Information

Machine learning of cellular metabolic rewiring.

ABSTRACT: Metabolic rewiring allows cells to adapt their metabolism in response to evolving environmental conditions. Traditional metabolomics techniques, whether targeted or untargeted, often struggle to interpret these adaptive shifts. Here, we introduce MetaboLiteLearner, a machine learning framework that harnesses the detailed fragmentation patterns from electron ionization (EI) collected in scan mode during gas chromatography/mass spectrometry (GC/MS) to predict abundance changes in metabolically adapted cells. When tested on breast cancer cells with different preferences to metastasize to specific organs, MetaboLiteLearner predicted the impact of metabolic rewiring on metabolites withheld from the training dataset using only the EI spectra, without metabolite identification or pre-existing knowledge of metabolic networks. The model learned captures shared and unique metabolomic shifts between brain- and lung-homing metastatic lineages, suggesting potential organ-tailored cellular adaptations. Integrating machine learning and metabolomics paves the way for new insights into complex cellular adaptations.

SUBMITTER: Xavier JB

PROVIDER: S-EPMC10462012 | biostudies-literature | 2023 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Machine learning of cellular metabolic rewiring.

Xavier Joao B JB

bioRxiv : the preprint server for biology 20231010

Metabolic rewiring allows cells to adapt their metabolism in response to evolving environmental conditions. Traditional metabolomics techniques, whether targeted or untargeted, often struggle to interpret these adaptive shifts. Here, we introduce <i>MetaboLiteLearner</i>, a machine learning framework that harnesses the detailed fragmentation patterns from electron ionization (EI) collected in scan mode during gas chromatography/mass spectrometry (GC/MS) to predict abundance changes in metabolica ...[more]

PMID: 37645838

Similar Datasets

Project description:Xylose, the major component of lignocellulosic biomass, cannot be naturally or efficiently utilized by most microorganisms. Xylose (co)utilization is considered a cornerstone of efficient lignocellulose-based biomanufacturing. We evolved a rapidly xylose-utilizing strain, Cev2-18-5, which showed the highest reported specific growth rate (0.357 h-1) on xylose among plasmid-free Corynebacterium glutamicum strains. A genetically clear chassis strain, CGS15, was correspondingly reconstructed with an efficient glucose-xylose coutilization performance based on comparative genomic analysis and mutation reconstruction. With the introduction of a succinate-producing plasmid, the resulting strain, CGS15-SA1, can efficiently produce 97.1 g/L of succinate with an average productivity of 8.09 g/L/h by simultaneously utilizing glucose and xylose from corn stalk hydrolysate. We further revealed a novel xylose regulatory mechanism mediated by the endogenous transcription factor IpsA with global regulatory effects on C. glutamicum. A synergistic effect on carbon metabolism and energy supply, motivated by three genomic mutations (Psod(C131T)-xylAB, Ptuf(Δ21)-araE, and ipsAC331T), was found to endow C. glutamicum with the efficient xylose utilization and rapid growth phenotype. Overall, this work not only provides promising C. glutamicum chassis strains for a lignocellulosic biorefinery but also enriches the understanding of the xylose regulatory mechanism. IMPORTANCE A novel xylose regulatory mechanism mediated by the transcription factor IpsA was revealed. A synergistic effect on carbon metabolism and energy supply was found to endow C. glutamicum with the efficient xylose utilization and rapid growth phenotype. The new xylose regulatory mechanism enriches the understanding of nonnatural substrate metabolism and encourages exploration new engineering targets for rapid xylose utilization. This work also provides a paradigm to understand and engineer the metabolism of nonnatural renewable substrates for sustainable biomanufacturing.

Dataset Information

Machine learning of cellular metabolic rewiring.

Publications

Machine learning of cellular metabolic rewiring.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets