Extracting interpretable single-cell metabolic states with graph-guided representation learning
- 1University of California, Berkeley
Abstract
Metabolism shapes cellular function and state, yet measuring single-cell metabolic states at scale remains a challenge. We present Metabolic Representation Net (MeRN), a graph-guided variational autoencoder that leverages prior metabolic knowledge as a topology graph to learn latent representations of metabolic state and reaction activity from single-cell transcriptomes. MeRN's scalable estimation of reaction activity enables the definition of data-driven pathways (DDPs): context-specific metabolic modules supported by transcriptomic evidence and agnostic of standard pathway definitions. Using DDPs, we introduce the weakest link analysis to identify metabolic network rewiring. MeRN recovers metabolic zonation in the mouse intestine, links a folate deficiency-induced break in de novo purine synthesis to embryonic neural tube defects, shows cytokines with similar non-metabolic effects can elicit divergent T cell metabolism, and identifies metabolic drivers of T cell exhaustion and therapy response in human cancers. Our results establish MeRN as a unified method for metabolic analysis of single-cell transcriptomes.
Related
- Single-channel EEG sleep stage classification using synchrosqueezed transform and sequential representation learning
- CellMSA: Context Modeling for Single-Cell Representation Learning
- scRep: A Latent-Space Self-Distilled Foundation Model for Single-Cell Representation Learning
- Minkowski Tensors as a Lightweight and Interpretable Representation for Three-Dimensional Morphology
- CellART: a unified framework for extracting single-cell information from high-resolution spatial transcriptomics
BibTeX
@misc{lewinsohn2026extracting,
title = {{Extracting interpretable single-cell metabolic states with graph-guided representation learning}},
author = {D. P. Lewinsohn and N. Dias and A. Chau and Y. Koike and Z. D. Smith and N. M. Ioannidis and A. Wagner},
howpublished = {bioRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.17.751504},
url = {https://www.biorxiv.org/content/10.64898/2026.09.17.751504v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - Extracting interpretable single-cell metabolic states with graph-guided representation learning
AU - D. P. Lewinsohn
AU - N. Dias
AU - A. Chau
AU - Y. Koike
AU - Z. D. Smith
AU - N. M. Ioannidis
AU - A. Wagner
PY - 2026
DA - 2026/09/17
PB - bioRxiv
DO - 10.64898/2026.09.17.751504
UR - https://www.biorxiv.org/content/10.64898/2026.09.17.751504v1
AB - Metabolism shapes cellular function and state, yet measuring single-cell metabolic states at scale remains a challenge. We present Metabolic Representation Net (MeRN), a graph-guided variational autoencoder that leverages prior metabolic knowledge as a topology graph to learn latent representations of metabolic state and reaction activity from single-cell transcriptomes. MeRN's scalable estimation of reaction activity enables the definition of data-driven pathways (DDPs): context-specific metabolic modules supported by transcriptomic evidence and agnostic of standard pathway definitions. Using DDPs, we introduce the weakest link analysis to identify metabolic network rewiring. MeRN recovers metabolic zonation in the mouse intestine, links a folate deficiency-induced break in de novo purine synthesis to embryonic neural tube defects, shows cytokines with similar non-metabolic effects can elicit divergent T cell metabolism, and identifies metabolic drivers of T cell exhaustion and therapy response in human cancers. Our results establish MeRN as a unified method for metabolic analysis of single-cell transcriptomes.
ER -