Spatial transcriptomics methods model tissue context, co-expression and protein levels

Published papers

• Microenvironment-aware transcriptome reconstruction in spatial transcriptomics.

  Nature communications2026-09-03Shi-Tong Yang et al.

  Emerge, a microenvironment-aware framework that combines cell identity with local tissue context to reconstruct transcriptome-scale expression from targeted…

• Decoding cell-cell communication in spatial transcriptomics: mechanistic insights, modeling constraints, and analytical caveats.

  Briefings in bioinformatics2026-09-01Yuesong Wu et al.

  Reviews spatial-aware cell-cell communication inference methods, including optimal transport and deep learning, plus permutation biases.

• DPAS-Graph: adaptive spatial-feature relation learning for spatial RNA-to-protein prediction and virtual protein profiling.

  Briefings in bioinformatics2026-09-01Mingyuan Xu et al.

  DPAS-Graph adaptively learns spatial-proximity and transcriptomic-similarity relations to predict protein abundance from spatial RNA data, benchmarked…

• Single-cell-level perturbation-induced and condition-related signal estimation with batch effect removal using NDreamer.

  Briefings in bioinformatics2026-09-01Xiao Xiao et al.

  NDreamer uses neural discrete representation learning with matching and mutual-information loss to remove batch effects and estimate perturbation or condition…

• SpaHDSRL: hierarchical dual-graph self-supervised representation learning for integrating spatially resolved multi-omics data.

  Briefings in bioinformatics2026-09-01Xiang Li et al.

  SpaHDSRL: a hierarchical dual-graph self-supervised method integrating spatial multi-omics data, improving spatial domain identification over existing methods.

• spMosaic: multi-sample integration for scalable spatial domain discovery based on spatial transcriptomics.

  Briefings in bioinformatics2026-09-01Shiwei Fu et al.

  spMosaic is a scalable framework for multi-sample spatial domain discovery using spatial smoothing and a batch-aware dual-encoder autoencoder, benchmarked…

• ST-ConMa: a multimodal foundation framework for spatial transcriptomics via image-gene contrastive and matching learning.

  Briefings in bioinformatics2026-09-01Taelim Yeom et al.

  ST-ConMa is a multimodal foundation model pretrained on spot-level tissue images and gene expression via contrastive and matching learning, with…

• Topology-guided dual-masked contrastive learning for weakly supervised cell-type annotation in single-cell multi-omics.

  Briefings in bioinformatics2026-09-01Yi Zhang et al.

  DMCL, a topology-guided dual-masked contrastive learning framework, uses KNN graphs, graph autoencoders and attention fusion for weakly supervised cell-type…

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

  Briefings in bioinformatics2026-09-01Hao Zhu et al.

  WDGTA is a wavelet-denoised graph attention method for cell-type deconvolution of spot-based spatial transcriptomics, validated on five datasets and…

• DiST: disentangling structure via self-supervised tensors for heterophilous spatial transcriptomics.

  Briefings in bioinformatics2026-09-01Yaozhang Liu et al.

  DiST, a self-supervised tensor learning framework with ego-network tensors and low-rank plus sparse decomposition, improves spatial domain identification in…

Preprints

• Subcellularly Resolved Single-Cell Embedding Learning with Transcriptomic data, Protein Structure and Localization Information

  arXiv2026-09-02Zhen Zhou et al.

  Proposes a multimodal cross-attention framework producing subcellularly resolved single-cell embeddings by integrating RNA expression, protein sequence, and…

• SCG: Spatially Co-Expressed Gene Identification through Spatially Varying Networks

  bioRxiv2026-09-05Buker, I. E. et al.

  Introduces spatial covariance regression (SCR), a scalable Bayesian factor-model framework for spatially resolved gene co-expression networks and…

Related topics

• Spatial Context Expression Attribution
• Cross Modal Spatial Omics Inference
• Multimodal Biological Representation Learning

Topic history