Experiments

Searchable full-text extractions: founding hypothesis, core claims, experimental setups, key results and statistics — pulled out of each paper as structure. Search a cell line, an assay or an entity (e.g. HUH7) and find every paper that worked with it. This corpus stands on its own: most entries carry no reproduction assessment (yet).

• DANST enables cell-type deconvolution in spatial transcriptomics using deep domain adversarial neural networks.

  PMID 41663685 · PMC12996496 · Communications biology · 2026 · 7 claims · 6 setups

  Full-text index only

  DANST, a deconvolution framework using deep domain adversarial neural networks, achieves superior cell-type deconvolution accuracy compared with existing methods on human and mouse benchmark datasets

  heart cortex visual brain spatial cell-type

• SA2E: spatial-aware auto-encoder for cell type deconvolution of spatial transcriptomics data.

  PMID 41863296 · PMC13070677 · Bioinformatics (Oxford, England) · 2026 · 8 claims · 5 setups

  Full-text index only

  SA2E is a spatial-aware auto-encoder framework for cell-type deconvolution that does not require predefined cell-type biomarkers

  olfactory legacy breast brain simulated real scrna-seq

• DiSCO: deconvoluting spatial transcriptomics via combinatorial optimization with a foundational diffusion model.

  PMID 42101928 · PMC13155122 · Briefings in bioinformatics · 2026 · 7 claims · 2 setups

  Full-text index only

  Deconvolution of spatial transcriptomics data can be formulated as a combinatorial optimization (CO) problem of assigning single cells to spatial spots so that aggregated single-cell profiles best approximate observed spot expression

  sccube-simulated real simulation-based spatial

• SpaJoint: a transfer learning method for spatial transcriptomics deconvolution.

  PMID 41955028 · PMC13069903 · Briefings in bioinformatics · 2026 · 8 claims · 1 setups

  Full-text index only

  SpaJoint is a transfer-learning-based deconvolution method that integrates scRNA-seq and ST gene expression while accounting for spatial correlation across spots.

  simulated spatial

• scComm: a contrastive learning framework for deciphering cell-cell communications at single-cell resolution.

  PMID 41877186 · PMC13134144 · Genome biology · 2026 · 8 claims · 7 setups

  Full-text index only

  scComm infers cell-cell communications at single-cell resolution using a data-adaptive L-R weighting module and supervised contrastive learning (SupCon loss) to distinguish significant CCC events from background noise

  simulated spatial liver single-cell simulated spatial scrna-seq

• Benchmarking tools for deciphering cellular crosstalk in spatially-resolved transcriptomics.

  PMID 41952215 · PMC13174004 · Genome biology · 2026 · 8 claims · 5 setups

  Full-text index only

  No prior systematic, quantitative benchmark exists for CCI inference methods specifically developed for spatial transcriptomics across multiple platforms

  synthetic real simulated simulation spot-purity real-data

• HRCHY-CytoCommunity identifies hierarchical tissue organization in cell-type spatial maps.

  PMID 41764165 · PMC13065825 · Nature communications · 2026 · 8 claims · 5 setups

  Full-text index only

  HRCHY-CytoCommunity is an end-to-end graph neural network framework that jointly identifies multi-level (coarse tissue compartment and fine cellular neighborhood) tissue structures from cell-type spatial maps using differentiable graph pooling, adaptive edge pruning, and consistency/balance regularization.

  healthy colorectal simulated breast codex visium merfish

• Cell neighborhood topology directs rare cell population identification.

  PMID 41912521 · PMC13199379 · Nature communications · 2026 · 8 claims · 8 setups

  Full-text index only

  RareQ is a framework that quantifies neighborhood connectivity (Q), a cell-specific measure of kNN-graph cliquishness, to detect rare cell populations from single-cell and spatial omics data

  downsampled pbmc brain simulated scrna-seq cite-seq single-cell

• SMART: spatial multi-omic aggregation using graph neural networks and metric learning.

  PMID 41896208 · PMC13031631 · Nature communications · 2026 · 8 claims · 5 setups

  Full-text index only

  SMART accurately identifies spatial regions of anatomical structures and is compatible with spatial datasets of any type and number of omics layers

  simulated lymph brain spleen simulated spatial multi-section

• A spatially coordinated keratinocyte-fibroblast circuit recruits MMP9(+) myeloid cells to drive type I interferon-driven inflammation in photosensitive autoimmunity.

  PMID 42032302 · PMC13226071 · Nature immunology · 2026 · 8 claims · 8 setups

  Full-text index only

  MMP9+CD14+ myeloid cells are critical mediators of photosensitivity, expanding in lesional skin, producing IFNβ, and colocalizing with cytotoxic CD4+ T cells at the dermal-epidermal junction

  skin blister punch donor scrna-seq 250-plex seqfish

• A differential single-cell transcriptome atlas of left-sided and right-sided colorectal cancer.

  PMID 41844817 · PMC13111741 · Discover oncology · 2026 · 8 claims · 8 setups

  Full-text index only

  MTRNR2L8 is markedly upregulated in RCRC tumor cells and is associated with poorer patient survival

  crc epithelial rcrc tcga-read scrna-seq copy gene