skip to main content


Title: A graph neural network model to estimate cell-wise metabolic flux using single-cell RNA-seq data
The metabolic heterogeneity and metabolic interplay between cells are known as significant contributors to disease treatment resistance. However, with the lack of a mature high-throughput single-cell metabolomics technology, we are yet to establish systematic understanding of the intra-tissue metabolic heterogeneity and cooperative mechanisms. To mitigate this knowledge gap, we developed a novel computational method, namely, single-cell flux estimation analysis (scFEA), to infer the cell-wise fluxome from single-cell RNA-sequencing (scRNA-seq) data. scFEA is empowered by a systematically reconstructed human metabolic map as a factor graph, a novel probabilistic model to leverage the flux balance constraints on scRNA-seq data, and a novel graph neural network–based optimization solver. The intricate information cascade from transcriptome to metabolome was captured using multilayer neural networks to capitulate the nonlinear dependency between enzymatic gene expressions and reaction rates. We experimentally validated scFEA by generating an scRNA-seq data set with matched metabolomics data on cells of perturbed oxygen and genetic conditions. Application of scFEA on this data set showed the consistency between predicted flux and the observed variation of metabolite abundance in the matched metabolomics data. We also applied scFEA on five publicly available scRNA-seq and spatial transcriptomics data sets and identified context- and cell group–specific metabolic variations. The cell-wise fluxome predicted by scFEA empowers a series of downstream analyses including identification of metabolic modules or cell groups that share common metabolic variations, sensitivity evaluation of enzymes with regards to their impact on the whole metabolic flux, and inference of cell–tissue and cell–cell metabolic communications.  more » « less
Award ID(s):
2047631 1850360
NSF-PAR ID:
10320020
Author(s) / Creator(s):
; ; ; ; ; ; ; ; ; ; ; ;
Date Published:
Journal Name:
Genome Research
Volume:
31
Issue:
10
ISSN:
1088-9051
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. Abstract

    In recent years, the explosive growth of spatial technologies has enabled the characterization of spatial heterogeneity of tissue architectures. Compared to traditional sequencing, spatial transcriptomics reserves the spatial information of each captured location and provides novel insights into diverse spatially related biological contexts. Even though two spatial transcriptomics databases exist, they provide limited analytical information. Information such as spatial heterogeneity of genes and cells, cell-cell communication activities in space, and the cell type compositions in the microenvironment are critical clues to unveil the mechanism of tumorigenesis and embryo differentiation. Therefore, we constructed a new spatial transcriptomics database, named SPASCER (https://ccsm.uth.edu/SPASCER), designed to help understand the heterogeneity of tissue organizations, region-specific microenvironment, and intercellular interactions across tissue architectures at multiple levels. SPASCER contains datasets from 43 studies, including 1082 sub-datasets from 16 organ types across four species. scRNA-seq was integrated to deconvolve/map spatial transcriptomics, and processed with spatial cell-cell interaction, gene pattern and pathway enrichment analysis. Cell–cell interactions and gene regulation network of scRNA-seq from matched spatial transcriptomics were performed as well. The application of SPASCER will provide new insights into tissue architecture and a solid foundation for the mechanistic understanding of many biological processes in healthy and diseased tissues.

     
    more » « less
  2. Abstract

    To understand phenotypic variations and key factors which affect disease susceptibility of complex traits, it is important to decipher cell‐type tissue compositions. To study cellular compositions of bulk tissue samples, one can evaluate cellular abundances and cell‐type‐specific gene expression patterns from the tissue transcriptome profiles. We develop both fixed and mixed models to reconstruct cellular expression fractions for bulk‐profiled samples by using reference single‐cell (sc) RNA‐sequencing (RNA‐seq) reference data. In benchmark evaluations of estimating cellular expression fractions, the mixed‐effect models provide similar results as an elegant machine learning algorithm named cell‐type identification by estimating relative subsets of RNA transcripts (CIBERSORTx), which is a well‐known and reliable procedure to reconstruct cell‐type abundances and cell‐type‐specific gene expression profiles. In real data analysis, the mixed‐effect models outperform or perform similarly as CIBERSORTx. The mixed models perform better than the fixed models in both benchmark evaluations and data analysis. In simulation studies, we show that if the heterogeneity exists in scRNA‐seq data, it is better to use mixed models with heterogeneous mean and variance–covariance. As a byproduct, the mixed models provide fractions of covariance between subject‐specific gene expression and cell types to measure their correlations. The proposed mixed models provide a complementary tool to dissect bulk tissues using scRNA‐seq data.

     
    more » « less
  3. Mathelier, Anthony (Ed.)
    Abstract Motivation Recent breakthroughs of single-cell RNA sequencing (scRNA-seq) technologies offer an exciting opportunity to identify heterogeneous cell types in complex tissues. However, the unavoidable biological noise and technical artifacts in scRNA-seq data as well as the high dimensionality of expression vectors make the problem highly challenging. Consequently, although numerous tools have been developed, their accuracy remains to be improved. Results Here, we introduce a novel clustering algorithm and tool RCSL (Rank Constrained Similarity Learning) to accurately identify various cell types using scRNA-seq data from a complex tissue. RCSL considers both local similarity and global similarity among the cells to discern the subtle differences among cells of the same type as well as larger differences among cells of different types. RCSL uses Spearman’s rank correlations of a cell’s expression vector with those of other cells to measure its global similarity, and adaptively learns neighbor representation of a cell as its local similarity. The overall similarity of a cell to other cells is a linear combination of its global similarity and local similarity. RCSL automatically estimates the number of cell types defined in the similarity matrix, and identifies them by constructing a block-diagonal matrix, such that its distance to the similarity matrix is minimized. Each block-diagonal submatrix is a cell cluster/type, corresponding to a connected component in the cognate similarity graph. When tested on 16 benchmark scRNA-seq datasets in which the cell types are well-annotated, RCSL substantially outperformed six state-of-the-art methods in accuracy and robustness as measured by three metrics. Availability and implementation The RCSL algorithm is implemented in R and can be freely downloaded at https://cran.r-project.org/web/packages/RCSL/index.html. Supplementary information Supplementary data are available at Bioinformatics online. 
    more » « less
  4. Acinar to ductal metaplasia (ADM) occurs in the pancreas in response to tissue injury and is a potential precursor for adenocarcinoma. The goal of these studies was to define the populations arising from genetically wild type ADM, the associated transcriptionalchanges, and to identify markersof disease progression. Acinar cells were lineage-traced with enhanced yellow fluorescent protein (EYFP)to follow their fate upon injury. Transcripts of over 13,000 EYFP+ cells were determined using single-cellRNA sequencing (scRNA-seq). Single-celltrajectories were generated. Data were compared to gastric metaplasia and human pancreatitis. Results were confirmed by immunostaining and electron microscopy. Surgical specimens of chronic pancreatitis from 15 patients were evaluatedby immunostaining. scRNA-seq of ADM revealed emergence of a mucin/ductal population (Muc6+, Tff2+) resembling gastric pyloric, gland-base cells. Lineage trajectories suggest that this pyloric metaplasia is an intermediate cell identity between acinar cells and the generation of metaplastic tuft and enteroendocrine cells (EECs). 3-D electron microscopy demonstrates that all identified lineages populate ADM lesions. EECs exhibit substantial heterogeneity, including emergence of enterochromaffin (5-HT+) and delta (SST+) cells. Human pancreatitis shows a similar pyloric metaplasia phenotype anda conserved transcriptional program. Under conditions of chronic injury, acinar cells undergo pyloric metaplasia to mucinous progenitor-like populations, some of which can then seed disparate tuft cell and EEC lineages. EEC subtypes are diverse with the potential to direct disease progression. This program is conserved in human pancreatitis, providing insightinto early events in pancreasdiseases. 
    more » « less
  5. null (Ed.)
    Single cell RNA-sequencing (scRNA-seq) technology enables comprehensive transcriptomic profiling of thousands of cells with distinct phenotypic and physiological states in a complex tissue. Substantial efforts have been made to characterize single cells of distinct identities from scRNA-seq data, including various cell clustering techniques. While existing approaches can handle single cells in terms of different cell (sub)types at a high resolution, identification of the functional variability within the same cell type remains unsolved. In addition, there is a lack of robust method to handle the inter-subject variation that often brings severe confounding effects for the functional clustering of single cells. In this study, we developed a novel data denoising and cell clustering approach, namely CIBS, to provide biologically explainable functional classification for scRNA-seq data. CIBS is based on a systems biology model of transcriptional regulation that assumes a multi-modality distribution of the cells’ activation status, and it utilizes a Boolean matrix factorization approach on the discretized expression status to robustly derive functional modules. CIBS is empowered by a novel fast Boolean Matrix Factorization method, namely PFAST, to increase the computational feasibility on large scale scRNA-seq data. Application of CIBS on two scRNA-seq datasets collected from cancer tumor micro-environment successfully identified subgroups of cancer cells with distinct expression patterns of epithelial-mesenchymal transition and extracellular matrix marker genes, which was not revealed by the existing cell clustering analysis tools. The identified cell groups were significantly associated with the clinically confirmed lymph-node invasion and metastasis events across different patients. Index Terms—Cell clustering analysis, Data denoising, Boolean matrix factorization, Cancer microenvirionment, Metastasis. 
    more » « less