Skip to content
DraconiticResearch
Search Sources API
201,683 studies31 sourcesUpdated 20 min ago
Peer-reviewedCC BYBriefings in bioinformatics

WDGTA: a wavelet-denoised graph attention framework for spatial transcriptomics deconvolution.

  • Hao Zhu1
  • Chenggong Ma1
  • Zhenchun Ran1
  • Xumeng Liu1
  • Haobo Tang1
  • Tongquan Wu2
  • Xinglong Wu1
  • Yicheng Xie3,4
4 affiliations
  1. 1School of Computer Science and Engineering, Hubei Key Laboratory of Intelligent Robot, Wuhan Institute of Technology, No. 206 Guanggu 1st Road, East Lake High-Tech Development Zone, Wuhan, Hubei 430205, China.
  2. 2School of Mechanical Engineering, Hefei University of Technology, No. 193 Tunxi Road, Baohe District, Hefei, Anhui 230009, China.
  3. 3Department of Pulmonology and Genetics and Metabolism, Children's Hospital, Zhejiang University School of Medicine, National Clinical Research Center for Children's and Adolescents' Health and Diseases, No. 3333 Binsheng Road, Binjiang District, Hangzhou, Zhejiang 310052, China.
  4. 4Zhejiang Key Laboratory of Neonatal Diseases, No. 3333 Binsheng Road, Binjiang District, Hangzhou, Zhejiang 310052, China.
Read full textPDFDOICite

Abstract

Spatial transcriptomics (ST) facilitates the spatial resolution of gene expression profiling; however, many widely used spot-based sequencing platforms capture transcripts from multiple neighboring cells at each location, producing mixed profiles that require accurate cell-type deconvolution. The wavelet-denoised graph attention framework for spatial transcriptomics deconvolution (WDGTA), a graph attention-based framework for ST cell-type deconvolution, was developed and validated on five datasets from two species and four organs. Through the integration of real with pseudo-ST spots, WDGTA introduces a wavelet-based multiscale denoising and reconstruction module, constructs a weighted topological graph using random projection forests, and applies multi-head graph attention to infer cell-type proportions in spatial spots. WDGTA achieved optimal performance in comparison with seven established deconvolution methods. Ablation and discrete wavelet transform (DWT)-specific analyses confirmed the contributions of wavelet denoising, weighted graph construction, and semi-supervised learning. Furthermore, DWT performance remained stable after feature-order perturbation. In mouse brain, cerebellum and ultraviolet radiation (UVR) skin data, WDGTA recovered biologically consistent spatial cell-type patterns and demonstrated robust cross-platform applicability and improved resolution of low-abundance melanocyte signals. Furthermore, it accurately captured melanocyte-associated spatial changes under conditions of UVR exposure and drug intervention. WDGTA provides a unified framework for ST deconvolution across the evaluated tissue contexts. In UVR-exposed skin, it resolved localized melanocyte-associated patterns that were concordant with marker-gene evidence and detected changes associated with UVR exposure and drug treatment. These findings support its use for characterizing spatial cell-type organization and low-abundance cell populations in heterogeneous tissues.

Related

  1. spOT-NMF: gene expression deconvolution via optimal transport with proximity-aware niche mapping for spatial transcriptomics
    Aly O Abdelkareem, Gurveer S Gill, Varsha Thoppey Manoharan +2
    Briefings in BioinformaticsPeer-reviewedCC BY-NC 4.0Full text1 citedMolecular biology & gene regulationPMC
  2. Systematic evaluation of robustness of deconvolution methods for spatial transcriptomics data in case of cell type mismatch.
    Utkarsh M Mahamune, Aldo Jongejan, Antoine H C van Kampen +2
    Briefings in bioinformaticsPeer-reviewedCC BYFull textMolecular biology & gene regulationEurope PMCPMC
  3. Enhancing cell type deconvolution in spatial transcriptomics through incorporating multiple reference panels
    Peiyao Zhao, Justin A Colacino, Ying Ma +1
    PLOS GeneticsPeer-reviewedCC BYFull textMolecular biology & gene regulationBioinformatics & computational biologyPLOSEurope PMCEurope PMCPMC
  4. Chroma-Agent-Alpha: An Open-Source Framework for Automated Chromatography Preprocessing, GNN-Based Peak Deconvolution, and FAIR Data Lineage
    Devendra Kataria
    ChemRxivPreprintCC BYFull textMolecular biology & gene regulationChemRxiv
  5. AreTomoLive: automated reconstruction of comprehensively corrected and denoised cryo-electron tomograms in real time and at high throughput
    Ariana Peck, Yue Eric Yu, Mohammadreza Paraan +16
    Nature MethodsPeer-reviewedCC BYFull text31 citedStructural biologyOpenAlex

Cite

BibTeXRIS
BibTeX
@article{zhu2026wdgta,
  title = {{WDGTA: a wavelet-denoised graph attention framework for spatial transcriptomics deconvolution.}},
  author = {Hao Zhu and Chenggong Ma and Zhenchun Ran and Xumeng Liu and Haobo Tang and Tongquan Wu and Xinglong Wu and Yicheng Xie},
  journal = {Briefings in bioinformatics},
  year = {2026},
  month = sep,
  doi = {10.1093/bib/bbag584},
  url = {https://europepmc.org/article/MED/42896093},
  note = {CC BY},
}
RIS
TY  - JOUR
TI  - WDGTA: a wavelet-denoised graph attention framework for spatial transcriptomics deconvolution.
AU  - Hao Zhu
AU  - Chenggong Ma
AU  - Zhenchun Ran
AU  - Xumeng Liu
AU  - Haobo Tang
AU  - Tongquan Wu
AU  - Xinglong Wu
AU  - Yicheng Xie
PY  - 2026
DA  - 2026/09/01
JO  - Briefings in bioinformatics
DO  - 10.1093/bib/bbag584
UR  - https://europepmc.org/article/MED/42896093
AB  - Spatial transcriptomics (ST) facilitates the spatial resolution of gene expression profiling; however, many widely used spot-based sequencing platforms capture transcripts from multiple neighboring cells at each location, producing mixed profiles that require accurate cell-type deconvolution. The wavelet-denoised graph attention framework for spatial transcriptomics deconvolution (WDGTA), a graph attention-based framework for ST cell-type deconvolution, was developed and validated on five datasets from two species and four organs. Through the integration of real with pseudo-ST spots, WDGTA introduces a wavelet-based multiscale denoising and reconstruction module, constructs a weighted topological graph using random projection forests, and applies multi-head graph attention to infer cell-type proportions in spatial spots. WDGTA achieved optimal performance in comparison with seven established deconvolution methods. Ablation and discrete wavelet transform (DWT)-specific analyses confirmed the contributions of wavelet denoising, weighted graph construction, and semi-supervised learning. Furthermore, DWT performance remained stable after feature-order perturbation. In mouse brain, cerebellum and ultraviolet radiation (UVR) skin data, WDGTA recovered biologically consistent spatial cell-type patterns and demonstrated robust cross-platform applicability and improved resolution of low-abundance melanocyte signals. Furthermore, it accurately captured melanocyte-associated spatial changes under conditions of UVR exposure and drug intervention. WDGTA provides a unified framework for ST deconvolution across the evaluated tissue contexts. In UVR-exposed skin, it resolved localized melanocyte-associated patterns that were concordant with marker-gene evidence and detected changes associated with UVR exposure and drug treatment. These findings support its use for characterizing spatial cell-type organization and low-abundance cell populations in heterogeneous tissues.
SN  - 1467-5463
SN  - 1477-4054
ER  -