Digital twins for in vivo metabolic flux estimations in patients with brain cancer
Cet article présente le développement de deux algorithmes d'apprentissage automatique, l'un intégrant des principes de simulations stoechiométriques et isotopiques à l'aide de réseaux neuronaux convolutifs pour estimer les flux métaboliques globaux dans les échantillons tissulaires de patients atteints d'un cancer du cerveau, l'autre combinant des données de séquençage de l'ARN à l'échelle cellulaire et des données de traçage isotopique au carbone 13C pour quantifier les flux métaboliques au niveau des cellules cérébrales cancéreuses
Recent advancements in metabolic flux estimations in vivo are limited to preclinical models, primarily due to challenges in tissue sampling, tumor microenvironment (TME) heterogeneity, and non-steady-state conditions. To address these limitations and enable flux estimation in human patients, we developed two machine learning-based frameworks. First, the digital twin framework (DTF) integrates first-principles stoichiometric and isotopic simulations with convolutional neural networks to estimate fluxes in patient bulk samples. Second, the single-cell metabolic flux analysis (13C-scMFA) framework combines patient single-cell RNA sequencing (scRNA-seq) data with 13C-isotope tracing, allowing single-cell-level flux quantification. These studies allow quantification of metabolic activity in neoplastic glioma cells, revealing frequently elevated purine synthesis and serine uptake, compared with non-malignant cells. Our models also identify metabolic heterogeneity among patients and mice with brain cancer, in turn predicting treatment responses to metabolic inhibitors. Our frameworks advance in vivo metabolic flux analysis, may lead to novel metabolic therapies, and identify biomarkers for metabolism-directed therapies in patients.
Cell Metabolism , article en libre accès, 2026