Spall: accurate and robust unveiling cellular landscapes from spatially resolved transcriptomics data using a decomposition network

Abstract Recent developments in spatially resolved transcriptomics (SRT) enable the characterization of spatial structures for different tissues. Many decomposition methods have been proposed to depict the cellular distribution within tissues. However, existing computational methods struggle to bala...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhongning Jiang, Wei Huang, Raymond H. W. Lam, Wei Zhang
Format: Article
Language:English
Published: BMC 2024-12-01
Series:BMC Bioinformatics
Subjects:
Online Access:https://doi.org/10.1186/s12859-024-06003-1
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846112130427781120
author Zhongning Jiang
Wei Huang
Raymond H. W. Lam
Wei Zhang
author_facet Zhongning Jiang
Wei Huang
Raymond H. W. Lam
Wei Zhang
author_sort Zhongning Jiang
collection DOAJ
description Abstract Recent developments in spatially resolved transcriptomics (SRT) enable the characterization of spatial structures for different tissues. Many decomposition methods have been proposed to depict the cellular distribution within tissues. However, existing computational methods struggle to balance spatial continuity in cell distribution with the preservation of cell-specific characteristics. To address this, we propose Spall, a novel decomposition network that integrates scRNA-seq data with SRT data to accurately infer cell type proportions. Spall introduced the GATv2 module, featuring a flexible dynamic attention mechanism to capture relationships between spots. This improves the identification of cellular distribution patterns in spatial analysis. Additionally, Spall incorporates skip connections to address the loss of cell-specific information, thereby enhancing the prediction capability for rare cell types. Experimental results show that Spall outperforms the state-of-the-art methods in reconstructing cell distribution patterns on multiple datasets. Notably, Spall reveals tumor heterogeneity in human pancreatic ductal adenocarcinoma samples and delineates complex tissue structures, such as the laminar organization of the mouse cerebral cortex and the mouse cerebellum. These findings highlight the ability of Spall to provide reliable low-dimensional embeddings for downstream analyses, offering new opportunities for deciphering tissue structures.
format Article
id doaj-art-9894c841b2b847d0bb4b3244e7b4576f
institution Kabale University
issn 1471-2105
language English
publishDate 2024-12-01
publisher BMC
record_format Article
series BMC Bioinformatics
spelling doaj-art-9894c841b2b847d0bb4b3244e7b4576f2024-12-22T12:51:14ZengBMCBMC Bioinformatics1471-21052024-12-0125111910.1186/s12859-024-06003-1Spall: accurate and robust unveiling cellular landscapes from spatially resolved transcriptomics data using a decomposition networkZhongning Jiang0Wei Huang1Raymond H. W. Lam2Wei Zhang3Department of Biomedical Engineering, City University of Hong KongDepartment of Biomedical Engineering, City University of Hong KongDepartment of Biomedical Engineering, City University of Hong KongCenter of Intelligent Medicine, School of Control Science and Engineering, Shandong UniversityAbstract Recent developments in spatially resolved transcriptomics (SRT) enable the characterization of spatial structures for different tissues. Many decomposition methods have been proposed to depict the cellular distribution within tissues. However, existing computational methods struggle to balance spatial continuity in cell distribution with the preservation of cell-specific characteristics. To address this, we propose Spall, a novel decomposition network that integrates scRNA-seq data with SRT data to accurately infer cell type proportions. Spall introduced the GATv2 module, featuring a flexible dynamic attention mechanism to capture relationships between spots. This improves the identification of cellular distribution patterns in spatial analysis. Additionally, Spall incorporates skip connections to address the loss of cell-specific information, thereby enhancing the prediction capability for rare cell types. Experimental results show that Spall outperforms the state-of-the-art methods in reconstructing cell distribution patterns on multiple datasets. Notably, Spall reveals tumor heterogeneity in human pancreatic ductal adenocarcinoma samples and delineates complex tissue structures, such as the laminar organization of the mouse cerebral cortex and the mouse cerebellum. These findings highlight the ability of Spall to provide reliable low-dimensional embeddings for downstream analyses, offering new opportunities for deciphering tissue structures.https://doi.org/10.1186/s12859-024-06003-1Spatially resolved transcriptomicsDecompositionCell type proportionTissue structureGraph neural network
spellingShingle Zhongning Jiang
Wei Huang
Raymond H. W. Lam
Wei Zhang
Spall: accurate and robust unveiling cellular landscapes from spatially resolved transcriptomics data using a decomposition network
BMC Bioinformatics
Spatially resolved transcriptomics
Decomposition
Cell type proportion
Tissue structure
Graph neural network
title Spall: accurate and robust unveiling cellular landscapes from spatially resolved transcriptomics data using a decomposition network
title_full Spall: accurate and robust unveiling cellular landscapes from spatially resolved transcriptomics data using a decomposition network
title_fullStr Spall: accurate and robust unveiling cellular landscapes from spatially resolved transcriptomics data using a decomposition network
title_full_unstemmed Spall: accurate and robust unveiling cellular landscapes from spatially resolved transcriptomics data using a decomposition network
title_short Spall: accurate and robust unveiling cellular landscapes from spatially resolved transcriptomics data using a decomposition network
title_sort spall accurate and robust unveiling cellular landscapes from spatially resolved transcriptomics data using a decomposition network
topic Spatially resolved transcriptomics
Decomposition
Cell type proportion
Tissue structure
Graph neural network
url https://doi.org/10.1186/s12859-024-06003-1
work_keys_str_mv AT zhongningjiang spallaccurateandrobustunveilingcellularlandscapesfromspatiallyresolvedtranscriptomicsdatausingadecompositionnetwork
AT weihuang spallaccurateandrobustunveilingcellularlandscapesfromspatiallyresolvedtranscriptomicsdatausingadecompositionnetwork
AT raymondhwlam spallaccurateandrobustunveilingcellularlandscapesfromspatiallyresolvedtranscriptomicsdatausingadecompositionnetwork
AT weizhang spallaccurateandrobustunveilingcellularlandscapesfromspatiallyresolvedtranscriptomicsdatausingadecompositionnetwork