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

• 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

• PreTSA: computationally efficient modeling of temporal and spatial gene expression patterns.

  PMID 41673899 · PMC12998178 · Genome biology · 2026 · 7 claims · 8 setups

  Full-text index only

  PreTSA dramatically reduces computational time and memory versus GAM (Monocle, TSCAN) and PseudotimeDE for identifying temporally variable genes (TVGs) while producing highly similar results

  simulated null pbmc pancreas pseudotime tvg false-positive