scholarly journals DSTG: Deconvoluting Spatial Transcriptomics Data through Graph-based Artificial Intelligence

2020 ◽  
Author(s):  
Jing Su ◽  
Qianqian Song
Keyword(s):  
Spatial Data ◽  
Spatial Information ◽  
Cell Types ◽  
Cellular Heterogeneity ◽  
Superior Performance ◽  
Gene Expressions ◽  
Mouse Cortex ◽  
Hippocampus Slice ◽  
Transcriptomics Data ◽  
High Level

AbstractRecent development of spatial transcriptomics (ST) is capable of associating spatial information at different spots in the tissue section with RNA abundance of cells within each spot, which is particularly important to understand tissue cytoarchitectures and functions. However, for such ST data, since a spot is usually larger than an individual cell, gene expressions measured at each spot are from a mixture of cells with heterogenous cell types. Therefore, ST data at each spot needs to be disentangled so as to reveal the cell compositions at that spatial spot. In this study, we propose a novel method, named DSTG, to accurately deconvolute the observed gene expressions at each spot and recover its cell constitutions, thus achieve high-level segmentation and reveal spatial architecture of cellular heterogeneity within tissues. DSTG not only demonstrates superior performance on synthetic spatial data generated from different protocols, but also effectively identifies spatial compositions of cells in mouse cortex layer, hippocampus slice, and pancreatic tumor tissues. In conclusion, DSTG accurately uncovers the cell states and subpopulations based on spatial localization.

scholarly journals GCNG: Graph convolutional networks for inferring cell-cell interactions

2019 ◽  
Author(s):  
Ye Yuan ◽  
Ziv Bar-Joseph
Keyword(s):  
Spatial Data ◽  
Spatial Information ◽  
Cell Types ◽  
Expression Vectors ◽  
Gene Interactions ◽  
Cellular Interactions ◽  
Expression Data ◽  
Neural Network Approach ◽  
Convolutional Networks ◽  
Transcriptomics Data

AbstractSeveral methods have been developed for inferring gene-gene interactions from expression data. To date, these methods mainly focused on intra-cellular interactions. The availability of high throughput spatial expression data opens the door to methods that can infer such interactions both within and between cells. However, the spatial data also raises several new challenges. These include issues related to the sparse, noisy expression vectors for each cell, the fact that several different cell types are often profiled, the definition of a neighborhood of cell and the relatively small number of extracellular interactions. To enable the identification of gene interactions between cells we extended a Graph Convolutional Neural network approach for Genes (GCNG). We encode the spatial information as a graph and use the network to combine it with the expression data using supervised training. Testing GCNG on spatial transcriptomics data we show that it improves upon prior methods suggested for this task and can propose novel pairs of extracellular interacting genes. Finally, we show that the output of GCNG can also be used for down-stream analysis including functional assignment.Supporting website with software and data: https://github.com/xiaoyeye/GCNG.

scholarly journals Dissecting Cellular Heterogeneity Based on Network Denoising of scRNA-seq Using Local Scaling Self-Diffusion

2022 ◽  
Vol 12 ◽  
Author(s):  
Xin Duan ◽  
Wei Wang ◽  
Minghui Tang ◽  
Feng Gao ◽  
Xudong Lin
Keyword(s):  
Metric Learning ◽  
Cell Types ◽  
Primary Objective ◽  
The Self ◽  
Cellular Heterogeneity ◽  
Clustering Methods ◽  
Local Scaling ◽  
Self Diffusion ◽  
Cell Clustering ◽  
High Level

Identifying the phenotypes and interactions of various cells is the primary objective in cellular heterogeneity dissection. A key step of this methodology is to perform unsupervised clustering, which, however, often suffers challenges of the high level of noise, as well as redundant information. To overcome the limitations, we proposed self-diffusion on local scaling affinity (LSSD) to enhance cell similarities’ metric learning for dissecting cellular heterogeneity. Local scaling infers the self-tuning of cell-to-cell distances that are used to construct cell affinity. Our approach implements the self-diffusion process by propagating the affinity matrices to further improve the cell similarities for the downstream clustering analysis. To demonstrate the effectiveness and usefulness, we applied LSSD on two simulated and four real scRNA-seq datasets. Comparing with other single-cell clustering methods, our approach demonstrates much better clustering performance, and cell types identified on colorectal tumors reveal strongly biological interpretability.

scholarly journals Mapping multicellular programs from single-cell profiles

2020 ◽  
Author(s):  
Livnat Jerby-Arnon ◽  
Aviv Regev
Keyword(s):  
Single Cell ◽  
Spatial Data ◽  
Spatial Information ◽  
Single Cells ◽  
Cell Types ◽  
Risk Genes ◽  
Health And Disease ◽  
Different Cell Types ◽  
Cellular Components ◽  
Acting In Concert

ABSTRACTTissue homeostasis relies on orchestrated multicellular circuits, where interactions between different cell types dynamically balance tissue function. While single-cell genomics identifies tissues’ cellular components, deciphering their coordinated action remains a major challenge. Here, we tackle this problem through a new framework of multicellular programs: combinations of distinct cellular programs in different cell types that are coordinated together in the tissue, thus forming a higher order functional unit at the tissue, rather than only cell, level. We develop the open-access DIALOGUE algorithm to systematically uncover such multi-cellular programs not only from spatial data, but even from tissue dissociated and profiled as single cells, e.g., by single-cell RNA-Seq. Tested on spatial transcriptomes from the mouse hypothalamus, DIALOGUE recovered spatial information, predicted the properties of a cell’s environment only based on its transcriptome, and identified multicellular programs that mark animal behavior. Applied to brain samples and colon biopsies profiled by scRNA-Seq, DIALOGUE identified multicellular configurations that mark Alzheimer’s disease and ulcerative colitis (UC), including a program spanning five cell types that is predictive of response to anti-TNF therapy in UC patients and enriched for UC risk genes from GWAS, each acting in different cell types, but all cells acting in concert. Taken together, our study provides a novel conceptual and methodological framework to unravel multicellular regulation in health and disease.

CCST: Cell clustering for spatial transcriptomics data with graph neural network

2021 ◽  
Author(s):  
Jiachen Li ◽  
Siheng Chen ◽  
Xiaoyong Pan ◽  
Ye Yuan ◽  
Hong-bin Shen
Keyword(s):  
Neural Network ◽  
Gene Expression ◽  
Spatial Information ◽  
Cultured Cells ◽  
Cell Types ◽  
Convolutional Network ◽  
Cell Clustering ◽  
Essential Question ◽  
Transcriptomics Data

Abstract Spatial transcriptomics data can provide high-throughput gene expression profiling and spatial structure of tissues simultaneously. An essential question of its initial analysis is cell clustering. However, most existing studies rely on only gene expression information and cannot utilize spatial information efficiently. Taking advantages of two recent technical development, spatial transcriptomics and graph neural network, we thus introduce CCST, Cell Clustering for Spatial Transcriptomics data with graph neural network, an unsupervised cell clustering method based on graph convolutional network to improve ab initio cell clustering and discovering of novel sub cell types based on curated cell category annotation. CCST is a general framework for dealing with various kinds of spatially resolved transcriptomics. With application to five in vitro and in vivo spatial datasets, we show that CCST outperforms other spatial cluster approaches on spatial transcriptomics datasets, and can clearly identify all four cell cycle phases from MERFISH data of cultured cells, and find novel functional sub cell types with different micro-environments from seqFISH+ data of brain, which are all validated experimentally, inspiring novel biological hypotheses about the underlying interactions among cell state, cell type and micro-environment.

scholarly journals Integrating Pathway Knowledge with Deep Neural Networks to Reduce the Dimensionality in Single-Cell RNA-Seq Data

2021 ◽  
Author(s):  
Pelin Gundogdu ◽  
Carlos Loucera ◽  
Inmaculada Alamo-Alvarez ◽  
Joaquin Dopazo ◽  
Isabel Nepomuceno
Keyword(s):  
Neural Networks ◽  
Single Cell ◽  
Deep Neural Networks ◽  
Cell Types ◽  
Cellular Heterogeneity ◽  
Biological Information ◽  
Superior Performance ◽  
Biological Knowledge ◽  
Additional Advantage ◽  
Functional Relationships

Abstract BackgroundSingle-cell RNA sequencing (scRNA-seq) data provides valuable insights into cellular heterogeneity which is significantly improving the current knowledge on biology and human disease. One of the main applications of scRNA-seq data analysis is the identification of new cell types and cell states. Deep neural networks (DNNs) are among the best methods to address this problem. However, this performance comes with the trade-off for a lack of interpretability in the results. In this work we propose an intelligible pathway-driven neural network to correctly solve cell-type related problems at single-cell resolution while providing a biologically meaningful representation of the data.ResultsIn this study, we explored the deep neural networks constrained by several types of prior biological information, e.g. signaling pathway information, as a way to reduce the dimensionality of the scRNA-seq data. We have tested the proposed biologically-based architectures on thousands of cells of human and mouse origin across a collection of public datasets in order to check the performance of the model. Specifically, we tested the architecture across different validation scenarios that try to mimic how unknown cell types are clustered by the DNN and how it correctly annotates cell types by querying a database in a retrieval problem. Moreover, our approach demonstrated to be comparable to other less interpretable DNN approaches constrained by using protein-protein interactions gene regulation data. Finally, we show how the latent structure learned by the network could be used to visualize and to interpret the composition of human single cell datasets.ConclusionsHere we demonstrate how the integration of pathways, which convey fundamental information on functional relationships between genes, with DNNs, that provide an excellent classification framework, results in an excellent alternative to learn a biologically meaningful representation of scRNA-seq data. In addition, the introduction of prior biological knowledge in the DNN reduces the size of the network architecture. Comparative results demonstrate a superior performance of this approach with respect to other similar approaches. As an additional advantage, the use of pathways within the DNN structure enables easy interpretability of the results by connecting features to cell functionalities by means of the pathway nodes, as demonstrated with an example with human melanoma tumor cells.

scholarly journals Integrating pathway knowledge with deep neural networks to reduce the dimensionality in single-cell RNA-seq data

2022 ◽  
Vol 15 (1) ◽  
Author(s):  
Pelin Gundogdu ◽  
Carlos Loucera ◽  
Inmaculada Alamo-Alvarez ◽  
Joaquin Dopazo ◽  
Isabel Nepomuceno
Keyword(s):  
Neural Networks ◽  
Single Cell ◽  
Deep Neural Networks ◽  
Cell Types ◽  
Cellular Heterogeneity ◽  
Biological Information ◽  
Superior Performance ◽  
Biological Knowledge ◽  
Additional Advantage ◽  
Functional Relationships

Abstract Background Single-cell RNA sequencing (scRNA-seq) data provide valuable insights into cellular heterogeneity which is significantly improving the current knowledge on biology and human disease. One of the main applications of scRNA-seq data analysis is the identification of new cell types and cell states. Deep neural networks (DNNs) are among the best methods to address this problem. However, this performance comes with the trade-off for a lack of interpretability in the results. In this work we propose an intelligible pathway-driven neural network to correctly solve cell-type related problems at single-cell resolution while providing a biologically meaningful representation of the data. Results In this study, we explored the deep neural networks constrained by several types of prior biological information, e.g. signaling pathway information, as a way to reduce the dimensionality of the scRNA-seq data. We have tested the proposed biologically-based architectures on thousands of cells of human and mouse origin across a collection of public datasets in order to check the performance of the model. Specifically, we tested the architecture across different validation scenarios that try to mimic how unknown cell types are clustered by the DNN and how it correctly annotates cell types by querying a database in a retrieval problem. Moreover, our approach demonstrated to be comparable to other less interpretable DNN approaches constrained by using protein-protein interactions gene regulation data. Finally, we show how the latent structure learned by the network could be used to visualize and to interpret the composition of human single cell datasets. Conclusions Here we demonstrate how the integration of pathways, which convey fundamental information on functional relationships between genes, with DNNs, that provide an excellent classification framework, results in an excellent alternative to learn a biologically meaningful representation of scRNA-seq data. In addition, the introduction of prior biological knowledge in the DNN reduces the size of the network architecture. Comparative results demonstrate a superior performance of this approach with respect to other similar approaches. As an additional advantage, the use of pathways within the DNN structure enables easy interpretability of the results by connecting features to cell functionalities by means of the pathway nodes, as demonstrated with an example with human melanoma tumor cells.

Extending UML for Space- and Time-Dependent Applications

2002 ◽  
pp. 342-366 ◽  
Author(s):  
Rosanne Price ◽  
Nectaria Tryfona ◽  
Christian S. Jensen
Keyword(s):  
Spatial Data ◽  
Spatial Information ◽  
Continuous Process ◽  
Spatiotemporal Data ◽  
Temporal Dimension ◽  
Spatial Information Systems ◽  
Time Period ◽  
High Level ◽  
Changes Over Time ◽  
Measurement Location

In recent years, the need for a temporal dimension in traditional spatial information systems and for high-level models useful for the conceptual design of the resulting spatiotemporal systems has become clear. Although having in common a need to manage spatial data and their changes over time, various spatiotemporal applications may manage different types of spatiotemporal data and may be based on very different models of space, time, and change. For example, the term spatiotemporal data is used to refer both to temporal changes in spatial extents, such as redrawing the boundaries of a voting precinct or land deed, and to changes in the value of thematic (i.e., alphanumeric) data across time or space, such as variation in soil acidity measurements depending on the measurement location and date. A spatiotemporal application may be concerned with either or both types of data. This, in turn, is likely to influence the underlying model of space employed, e.g., the two types of spatiotemporal data generally correspond to an object- versus a field-based spatial model. For either type of spatiotemporal data, change may occur in discrete steps, e.g., changes in land deed boundaries, or in a continuous process, e.g., changes in the position of a moving object such as a car. Another type of spatiotemporal data is composite data whose components vary depending on time or location. An example is the minimum combination of equipment and wards required in a certain category of hospital (e.g., general, maternity, psychiatric), where the relevant regulations determining the applicable base standards vary by locality and time period.

scholarly journals A multiresolution framework to characterize single-cell state landscapes

2020 ◽  
Vol 11 (1) ◽  
Author(s):  
Shahin Mohammadi ◽  
Jose Davila-Velderrain ◽  
Manolis Kellis
Keyword(s):  
Single Cell ◽  
Single Cell Analysis ◽  
Real Data ◽  
Cell Types ◽  
Cellular Heterogeneity ◽  
Superior Performance ◽  
Data Sets ◽  
Structural Representation ◽  
Archetypal Analysis ◽  
Cell State

Abstract Dissecting the cellular heterogeneity embedded in single-cell transcriptomic data is challenging. Although many methods and approaches exist, identifying cell states and their underlying topology is still a major challenge. Here, we introduce the concept of multiresolution cell-state decomposition as a practical approach to simultaneously capture both fine- and coarse-grain patterns of variability. We implement this concept in ACTIONet, a comprehensive framework that combines archetypal analysis and manifold learning to provide a ready-to-use analytical approach for multiresolution single-cell state characterization. ACTIONet provides a robust, reproducible, and highly interpretable single-cell analysis platform that couples dominant pattern discovery with a corresponding structural representation of the cell state landscape. Using multiple synthetic and real data sets, we demonstrate ACTIONet’s superior performance relative to existing alternatives. We use ACTIONet to integrate and annotate cells across three human cortex data sets. Through integrative comparative analysis, we define a consensus vocabulary and a consistent set of gene signatures discriminating against the transcriptomic cell types and subtypes of the human prefrontal cortex.

scholarly journals SpatialDWLS: accurate deconvolution of spatial transcriptomic data

2021 ◽  
Author(s):  
Rui Dong ◽  
Guo-Cheng Yuan
Keyword(s):  
Spatial Information ◽  
Cell Types ◽  
Computational Method ◽  
The Other ◽  
Cellular Heterogeneity ◽  
Biological Information ◽  
Cell Type ◽  
Transcriptomic Data ◽  
Cell Type Composition ◽  
Type Composition

AbstractRecent development of spatial transcriptomic technologies has made it possible to systematically characterize cellular heterogeneity while preserving spatial information, which greatly enables the investigation of structural organization of a tissue and its impact on modulating cellular behavior. On the other hand, the technology often does not have sufficient resolution to distinguish neighboring cells which may belong to different cell types, therefore it is difficult to identify cell-type distribution directly from the data. To overcome this challenge, we have developed a computational method, called spatialDWLS, to quantitatively estimate the cell-type composition at each spatial location. We benchmarked the performance of spatialDWLS by comparing with a number of existing deconvolution methods using both real and simulated datasets, and we found that spatialDWLS outperformed the other methods in terms of accuracy and speed. By applying spatialDWLS to analyze a human developmental heart dataset, we observed striking spatial-temporal changes of cell-type composition which becomes increasing spatially coherent during development. As such, spatialDWLS provides a valuable computational tool for faithfully extracting biological information from spatial transcriptomic data.

scholarly journals SpatialDWLS: accurate deconvolution of spatial transcriptomic data

2021 ◽  
Vol 22 (1) ◽  
Author(s):  
Rui Dong ◽  
Guo-Cheng Yuan
Keyword(s):  
Spatial Information ◽  
Spatial Location ◽  
Cell Types ◽  
The Other ◽  
Cellular Heterogeneity ◽  
Cell Type ◽  
Neighboring Cell ◽  
Transcriptomic Data ◽  
Cell Type Composition ◽  
Type Composition

AbstractRecent development of spatial transcriptomic technologies has made it possible to characterize cellular heterogeneity with spatial information. However, the technology often does not have sufficient resolution to distinguish neighboring cell types. Here, we present spatialDWLS, to quantitatively estimate the cell-type composition at each spatial location. We benchmark the performance of spatialDWLS by comparing it with a number of existing deconvolution methods and find that spatialDWLS outperforms the other methods in terms of accuracy and speed. By applying spatialDWLS to a human developmental heart dataset, we observe striking spatial temporal changes of cell-type composition during development.

Sign in / Sign up

Export Citation Format

Share Document