DSTG: deconvoluting spatial transcriptomics data through graph-based artificial intelligence

Song, Qisheng; Su, Jing

doi:10.1093/bib/bbaa414

Cited by 144 publications

(121 citation statements)

References 54 publications

Supporting

Mentioning

102

Contrasting

Order By: Relevance

“…To overcome this, several computational methods have been developed to deconvolve the cell mixture of the spatial spot. 13,14,15,16,17,18,19,20 Recently, improvements in mRNA capture methods have led to smaller subcellular capture areas that are ~1-10μm in diameter. These high-resolution spatial transcriptomics methods can obtain spatially resolved transcriptomes with increased spatial fidelity, without compromising the number of genes captured.…”

Section: Introductionmentioning

confidence: 99%

Unsupervised Spatially Embedded Deep Representation of Spatial Transcriptomics

Chong

et al. 2021

Preprint

108

View full text Add to dashboard Cite

Spatial transcriptomics enable us to dissect tissue heterogeneity and map out inter-cellular communications. Optimal integration of transcriptomics data and associated spatial information is essential towards fully exploiting the data. We present SEDR, an unsupervised spatially embedded deep representation of both transcript and spatial information. The SEDR pipeline uses a deep autoencoder to construct a low-dimensional latent representation of gene expression, which is then simultaneously embedded with the corresponding spatial information through a variational graph autoencoder. We applied SEDR on human dorsolateral prefrontal cortex data and achieved better clustering accuracy, and correctly retraced the prenatal cortex development order with trajectory analysis. We also found the SEDR representation to be eminently suited for batch integration. Applying SEDR to human breast cancer data, we discerned heterogeneous sub-regions within a visually homogenous tumor region, identifying a tumor core with pro-inflammatory microenvironment and an outer ring region enriched with tumor associated macrophages which drives an immune suppressive microenvironment.

show abstract

Section: Introductionmentioning

confidence: 99%

Unsupervised Spatially Embedded Deep Representation of Spatial Transcriptomics

Chong

et al. 2021

Preprint

108

View full text Add to dashboard Cite

show abstract

“…Single-cell omics technologies have allowed biologists to gain insights into the individual cellular components of complex biological ecosystems [44][45][46] . Given the explosive growth in singlecell data, there is a critical need to leverage the existing, wellcharacterized datasets as references to ensure reliable and consistent annotations of data.…”

Section: Discussionmentioning

confidence: 99%

scGCN is a graph convolutional networks algorithm for knowledge transfer in single cell omics

Song

Zhang

2021

Nat Commun

Self Cite

View full text Add to dashboard Cite

Single-cell omics is the fastest-growing type of genomics data in the literature and public genomics repositories. Leveraging the growing repository of labeled datasets and transferring labels from existing datasets to newly generated datasets will empower the exploration of single-cell omics data. However, the current label transfer methods have limited performance, largely due to the intrinsic heterogeneity among cell populations and extrinsic differences between datasets. Here, we present a robust graph artificial intelligence model, single-cell Graph Convolutional Network (scGCN), to achieve effective knowledge transfer across disparate datasets. Through benchmarking with other label transfer methods on a total of 30 single cell omics datasets, scGCN consistently demonstrates superior accuracy on leveraging cells from different tissues, platforms, and species, as well as cells profiled at different molecular layers. scGCN is implemented as an integrated workflow as a python software, which is available at https://github.com/QSong-github/scGCN.

show abstract

“…where the expression of neighboring (neighborhood ) cells/ROIs, , are used to predict the current ROI's expression 17,18 : " = <∑ B B B∈M ?.…”

Section: Mets No Metsmentioning

confidence: 99%

Mixed Effects Machine Learning Models for Colon Cancer Metastasis Prediction using Spatially Localized Immuno-Oncology Markers

Levy

Bobak

Nasir-Moin

et al. 2021

Preprint

View full text Add to dashboard Cite

Spatially resolved characterization of the transcriptome and proteome promises to provide further clarity on cancer pathogenesis and etiology, which may inform future clinical practice through classifier development for clinical outcomes. However, batch effects may potentially obscure the ability of machine learning methods to derive complex associations within spatial omics data. Profiling thirty-five stage three colon cancer patients using the GeoMX Digital Spatial Profiler, we found that mixed-effects machine learning (MEML) methods may provide utility for overcoming significant batch effects to communicate key and complex disease associations from spatial information. These results point to further exploration and application of MEML methods within the algorithm development life cycle for clinical deployment.

show abstract

DSTG: deconvoluting spatial transcriptomics data through graph-based artificial intelligence

Cited by 144 publications

References 54 publications

Unsupervised Spatially Embedded Deep Representation of Spatial Transcriptomics

Unsupervised Spatially Embedded Deep Representation of Spatial Transcriptomics

scGCN is a graph convolutional networks algorithm for knowledge transfer in single cell omics

Mixed Effects Machine Learning Models for Colon Cancer Metastasis Prediction using Spatially Localized Immuno-Oncology Markers

Contact Info

Product

Resources

About