Statistical and machine learning methods for spatially resolved transcriptomics with histology

Hu, Jian; Schroeder, Amelia; Coleman, Kyle; Chen, Chixiang; Auerbach, Benjamin D.; Li, Mingyao

doi:10.1016/j.csbj.2021.06.052

Cited by 66 publications

(61 citation statements)

References 93 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One common analysis task is to identify genes that vary in expression across a tissue, defined as ‘spatially variable genes’ by [12] (SVGs). These SVGs can then be further investigated individually as potential markers of biological processes, or used as the input for downstream analyses such as spatially-aware unsupervised clustering [8, 13, 14] or registering the spatial locations of single-cell RNA sequencing (scRNA-seq) data [11, 15, 16].…”

Section: Introductionmentioning

confidence: 99%

nnSVG for the scalable identification of spatially variable genes using nearest-neighbor Gaussian processes

Weber

Saha

Datta

et al. 2022

Preprint

View full text Add to dashboard Cite

Feature selection to identify spatially variable genes is a key step during analyses of spatially-resolved transcriptomics data. Here, we propose nnSVG, a scalable approach to identify spatially variable genes based on nearest-neighbor Gaussian processes. Our method (i) identifies genes that vary in expression continuously across the entire tissue or within a priori defined spatial domains, (ii) uses gene-specific estimates of length scale parameters within the Gaussian process models, and (iii) scales linearly with the number of spatial locations. We demonstrate the performance of our method using experimental data from several technological platforms and simulations. A software implementation is available at https://bioconductor.org/packages/nnSVG.

show abstract

Section: Introductionmentioning

confidence: 99%

nnSVG for the scalable identification of spatially variable genes using nearest-neighbor Gaussian processes

Weber

Saha

Datta

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…ProxiMeta [76] can devolve plasmid genomes and generate high-quality bins without relying on prior information. bin3C [77] has an effective pipeline for contact map generation, bias removal and interaction strength normalization, and it uses the Louvain algorithm [78] for scaffold community detection. HiCBin [79] uses HiCzin [80] to normalize the interaction map and applies the Leiden community detection algorithm to group scaffolds.…”

Section: Tools For Upstream Analyses To Construct Magsmentioning

confidence: 99%

A review of computational tools for generating metagenome-assembled genomes from metagenomic sequencing data

Yang

Chowdhury

Zhang

et al. 2021

Computational and Structural Biotechnology Journal

133

View full text Add to dashboard Cite

show abstract

“…CCI has been investigated using both scRNAseq and RNAseq, wherein most approaches test for enrichment in ligand-receptor profiles in the expression data 199–201 . However, ST data can offer a more comprehensive view of CCI, since the distance traveled by ligand signal is crucial in determining the type of cell–cell signaling 182 . Given the importance of CCI and the advantages that ST data provides, several computational approaches for inferring cellular interactions using ST data have been developed, such as SpaOTsc 78 , Giotto 81 , MISTy 80 .…”

Section: Deep Learning Models For Spatially-resolved Transcriptomics ...mentioning

confidence: 99%

“…Spatial Transcriptomics , Visium, DBiT-seq 180 , Nanostring GeoMx 181 and SlideSeq) do not have a single-cell resolution. The number of cells captured in each spot still varies based on the tissues (about 1-10 182 ) and the technology used. On the other hand, we can not assume that all cells within a spot are the same, due to the heterogeneity of the cells.…”

Section: Deep Learning Models For Spatially-resolved Transcriptomics ...mentioning

confidence: 99%

Deep Learning in Spatial Transcriptomics: Learning From the Next Next-Generation Sequencing

Heydari

Sindi

2022

Preprint

View full text Add to dashboard Cite

Spatial transcriptomics (ST) technologies are rapidly becoming the extension of single-cell RNA sequencing (scRNAseq), holding the potential of profiling gene expression at a single-cell resolution while maintaining cellular compositions within a tissue. Having both expression profiles and tissue organization enables researchers to better understand cellular interactions and heterogeneity, providing insight into complex biological processes that would not be possible with traditional sequencing technologies. The data generated by ST technologies are inherently noisy, high-dimensional, sparse, and multi-modal (including histological images, count matrices, etc.), thus requiring specialized computational tools for accurate and robust analysis. However, many ST studies currently utilize traditional scRNAseq tools, which are inadequate for analyzing complex ST datasets. On the other hand, many of the existing ST-specific methods are built upon traditional statistical or machine learning frameworks, which have shown to be sub-optimal in many applications due to the scale, multi-modality, and limitations of spatially-resolved data (such as spatial resolution, sensitivity and gene coverage). Given these intricacies, researchers have developed deep learning (DL)-based models to alleviate ST-specific challenges. These methods include new state-of-the-art models in alignment, spatial reconstruction, and spatial clustering among others. However, deep-learning models for ST analysis are nascent and remain largely underexplored. In this review, we provide an overview of existing state-of-the-art tools for analyzing spatially-resolved transcriptomics, while delving deeper into the DL-based approaches. We discuss the new frontiers and the open questions in this field and highlight the domains in which we anticipate transformational DL applications.

show abstract

Statistical and machine learning methods for spatially resolved transcriptomics with histology

Abstract: Graphical abstract

Cited by 66 publications

References 93 publications

nnSVG for the scalable identification of spatially variable genes using nearest-neighbor Gaussian processes

nnSVG for the scalable identification of spatially variable genes using nearest-neighbor Gaussian processes

A review of computational tools for generating metagenome-assembled genomes from metagenomic sequencing data

Deep Learning in Spatial Transcriptomics: Learning From the Next Next-Generation Sequencing

Contact Info

Product

Resources

About