Biology subjects

Lewinsohn, D. P.

Publications and source records attributed to Lewinsohn, D. P..

3 recordsLinked to original sources

bioRxiv2026

Extracting interpretable single-cell metabolic states with graph-guided representation learning

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.

bioinformatics↗

bioRxiv2026

Folate deficiency disrupts key metabolic transitions within the developing neural ectoderm

Despite long-standing epidemiological associations, the mechanism linking folate availability to gestational neural tube defects remains unclear, partly because measuring and interpreting metabolic activity in dynamic biological systems remains challenging. Here, we apply a deep-learning-based graph-guided variational autoencoder (MeRN; Metabolic Representation Network) to infer single-cell metabolic activity and states from scRNA-seq data of mouse embryogenesis. By analyzing folate-deficient embryogenesis from E7.0 to E9.0, we identify a transient state within the nascent neural lineage that is acutely sensitive to folate availability, leading to an interconnected disruption between key bioenergetic pathways and de novo purine biosynthesis. Moreover, metabolically induced growth defects lead to permanent morphological disruptions along the dorsal-ventral axis, which we confirm by generating whole-embryo fate maps using a prime-editing-based lineage recorder (PEtracer). Collectively, our results establish a highly scalable framework for interpreting dynamic changes in embryonic metabolism and elucidating the mechanistic bases underlying environmentally linked congenital disorders.

genomics↗

bioRxiv2022

Consensus Label Propagation with Graph Convolutional Networks for Single-Cell RNA Sequencing Cell Type Annotation

MotivationSingle-cell RNA sequencing (scRNA-seq) data, annotated by cell type, is useful in a variety of downstream biological applications, such as profiling gene expression at the single-cell level. However, manually assigning these annotations with known marker genes is both time-consuming and subjective. ResultsWe present a Graph Convolutional Network (GCN) based approach to automate the annotation process. Our process builds upon existing labeling approaches, using state-of-the-art tools to find cells with highly confident label assignments through consensus and spreading these confident labels with a semi-supervised GCN. Using simulated data and two scRNA-seq data sets from different tissues, we show that our method improves accuracy over a simple consensus algorithm and the average of the underlying tools. We also compare our method to a non-parametric neighbor majority approach, showing comparable results. We then demonstrate that our GCN method allows for feature interpretation, identifying important genes for cell type classification. We present our completed pipeline, written in PyTorch, as an end-to-end tool for automating and interpreting the classification of scRNA-seq data. AvailabilityOur code for conducting the experiments in this paper and using our model is available at https://github.com/lewinsohndp/scSHARP Contactd_lewinsohn@coloradocollege.edu Supplementary informationSupplementary data are available at Journal Name online.

bioinformatics↗