Inferring biologically relevant molecular tissue substructures by agglomerative clustering of digitized spatial transcriptomes with multilayer

Moehlin, Julien; Mollet, Bastien; Colombo, Bruno Maria; Mendoza-Parra, Marco Antonio

doi:10.1016/j.cels.2021.04.008

Cited by 27 publications

(21 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…stLearn utilizes morphological information to perform spatial smoothing before clustering 20 . MULTILAYER uses graph partitioning to segment tissue domains 21 . MERINGUE performs graph-based clustering using a weighted graph that combines spatial and transcriptional similarity 22 .…”

mentioning

confidence: 99%

Identifying multicellular spatiotemporal organization of cells with SpaceFlow

et al. 2022

View full text Add to dashboard Cite

One major challenge in analyzing spatial transcriptomic datasets is to simultaneously incorporate the cell transcriptome similarity and their spatial locations. Here, we introduce SpaceFlow, which generates spatially-consistent low-dimensional embeddings by incorporating both expression similarity and spatial information using spatially regularized deep graph networks. Based on the embedding, we introduce a pseudo-Spatiotemporal Map that integrates the pseudotime concept with spatial locations of the cells to unravel spatiotemporal patterns of cells. By comparing with multiple existing methods on several spatial transcriptomic datasets at both spot and single-cell resolutions, SpaceFlow is shown to produce a robust domain segmentation and identify biologically meaningful spatiotemporal patterns. Applications of SpaceFlow reveal evolving lineage in heart developmental data and tumor-immune interactions in human breast cancer data. Our study provides a flexible deep learning framework to incorporate spatiotemporal information in analyzing spatial transcriptomic data.

show abstract

mentioning

confidence: 99%

Identifying multicellular spatiotemporal organization of cells with SpaceFlow

et al. 2022

View full text Add to dashboard Cite

show abstract

“…6,42 In spatial transcriptomics, pixel-level features have been used to perform cell annotation and infer tissue substructures. [43][44][45][46] These methods demonstrate the utility of pixel-level analysis. Here, we buildupon this previous work by providing a comprehensive evaluation of the pre-processing steps and parameter choices that optimize clustering performance, show use cases across imaging platforms and biological questions, and present a user-friendly pipeline for running this method.…”

Section: Discussionmentioning

confidence: 86%

Robust phenotyping of highly multiplexed tissue imaging data using pixel-level clustering

Liu

Greenwald

Kong

et al. 2022

Preprint

View full text Add to dashboard Cite

While technologies for multiplexed imaging have provided an unprecedented understanding of tissue composition in health and disease, interpreting this data remains a significant computational challenge. To understand the spatial organization of tissue and how it relates to disease processes, imaging studies typically focus on cell-level phenotypes. However, images can capture biologically important objects that are outside of cells, such as the extracellular matrix. Here, we developed a pipeline, Pixie, that achieves robust and quantitative annotation of pixel-level features using unsupervised clustering and show its application across a variety of biological contexts and multiplexed imaging platforms. Furthermore, current cell phenotyping strategies that rely on unsupervised clustering can be labor intensive and require large amounts of manual adjustments. We demonstrate how pixel clusters that lie within cells can be used to improve cell annotations and decrease the amount of manual fine-tuning needed. We comprehensively evaluate pre-processing steps and parameter choices to optimize clustering performance and quantify the reproducibility of our method. Importantly, Pixie is open source and easily customizable through a user-friendly interface.

show abstract

“…Detailly, after obtaining the results of deconvolution, a series of downstream data analyses can be performed to detect biologically relevant features, including spatially variable genes, spatial gene patterns, and spatial regions. Many tools are developed by implementing different strategies to process these tasks, such as MULTILAYER [49] , Trendsceek [50] , SpatialDE [51] , SPARK [52] , SOMDE [53] , and Giotto [54] . Among them, MULTILAYER is able to infer biologically relevant features by utilizing contiguous spots as a readout of gene co-expression patterns within the analyzed tissue, thereby making better use of the spatial information.…”

Section: Discussionmentioning

confidence: 99%