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).

• Geometry-aware graph attention networks to explain single-cell chromatin states and gene expression with SEAGALL.

  PMID 42026624 · PMC13238118 · Genome biology · 2026 · 8 claims · 6 setups

  Full-text index only

  SEAGALL combines a geometry-regularised autoencoder (GRAE) to embed cells and build a cell-cell graph with a graph attention network (GAT) classifier and GNNExplainer-based XAI to identify features driving cell type/phenotype.

  count same scchip-seq ten count latent classification

• Topography-aware optimal transport for alignment of spatial omics data.

  PMID 41916307 · PMC13107060 · Cell reports methods · 2026 · 7 claims · 4 setups

  Full-text index only

  TOAST extends the classical FGW objective by adding a spatial coherence term and a neighborhood consistency term to model local spatial organization and molecular heterogeneity.

  simulated dorsolateral simulated multislice ablation

• A tumor-intrinsic WNT-inhibitory NOTUM program drives immune resistance in microsatellite stable colorectal cancer.

  PMID 42097145 · PMC13198260 · Cell reports. Medicine · 2026 · 8 claims · 7 setups

  Full-text index only

  A distinct NOTUM/NKD1/APCDD1-high, WNT-inhibitory cancer cell population (WICC) emerges predominantly in advanced-stage MSS CRC

  crc patient-derived ibd mmr-proficient single-cell cell-cycle patient-level

• Lineage commitment of dermal fibroblast progenitors is controlled by Kdm6b-mediated chromatin demethylation.

  PMID 37602956 · PMC10548174 · The EMBO journal · 2023 · 6 claims · 5 setups

  Has reproduction · 91

  E14.5 DFPs have a repressed transcriptional profile marked by high H3K27me3 and inaccessible chromatin at lineage-specific genes

  skin dermal single-cell chamber chip-seq

• A unified framework for correcting batch effects and integrating multi-omics data.

  PMID 41786846 · PMC13079841 · Scientific reports · 2026 · 7 claims · 6 setups

  Full-text index only

  MoDAmix, a four-stage domain adaptation framework (pre-training, single-omics adversarial adaptation, multi-omics adversarial alignment, semi-supervised class alignment), unifies batch correction across multiple omics layers.

  brain aml same single-cell bulk k-means

• Transcriptomic data meta-analysis reveals common and injury model specific gene expression changes in the regenerating zebrafish heart.

  PMID 37012284 · PMC10070245 · Scientific reports · 2023 · 7 claims · 8 setups

  Has reproduction · 90

  Batch correction using sequencing platform as the correcting variable (via Combat-Seq) removes technical variability so that samples cluster by injury condition rather than dataset origin.

  zebrafish orthologs ortholog core bulk overrepresentation network

• EpiXFormer: a cross-attention neural network for predicting cell type-specific transcription factor binding sites.

  PMID 41527854 · PMC12796812 · Briefings in bioinformatics · 2026 · 8 claims · 8 setups

  Full-text index only

  EpiXFormer achieves high accuracy (mean AUROC ~0.99) predicting binding sites of both TFs and non-sequence-specific DBPs across 199 DBP-cell type pairs

  dbps tfs common ctcf deep comparative feature-ablation

• S3RL: Enhancing Spatial Single-Cell Transcriptomics With Separable Representation Learning.

  PMID 41556263 · PMC13042551 · Advanced science (Weinheim, Baden-Wurttemberg, Germany) · 2026 · 8 claims · 8 setups

  Full-text index only

  S3RL is a separable representation learning framework that denoises sparse spatial transcriptomic data and enhances biologically relevant signals by integrating gene expression, spatial coordinates, and histological image features.

  dorsolateral dlpfc nanostring spatial cell-type multi-platform

• CeLLTra: aligning cell names with gene expression via a pathway-informed transformer.

  PMID 41652996 · PMC12881829 · Bioinformatics (Oxford, England) · 2026 · 8 claims · 4 setups

  Full-text index only

  Grouping genes into pathway-defined gene sets as Transformer input tokens (instead of using individual genes or discretized bins) mitigates the long-sequence problem and improves representation learning of scRNA-Seq gene expression profiles.

  tabula tumor-infiltrating scrna-seq

• Hi-Compass: a depth-aware deep learning framework for predicting cell-type-specific 3D genome organization from single-cell to spatial resolution.

  PMID 41980945 · PMC13250166 · Nature communications · 2026 · 8 claims · 8 setups

  Full-text index only

  Hi-Compass predicts cell-type-specific Hi-C contact maps using only ATAC-seq as cell-type-specific input, plus DNA sequence and a generalized CTCF binding profile

  gm12878 curated bulk training hi-c ctcf matched

• MIMIC: a flexible pipeline to register and summarize IMC-MSI experiments.

  PMID 41917425 · PMC13201759 · Communications biology · 2026 · 7 claims · 6 setups

  Full-text index only

  MIMIC is a reproducible, semi-automated workflow that co-registers and jointly analyzes MALDI-MSI and IMC data using a chain of before/after microscopy images.

  liver regions artificial maldi-msi imaging multi-step

• scXDR: drug response prediction across single-cell datasets via heterogeneous network transfer learning.

  PMID 41507436 · PMC12859067 · Communications biology · 2026 · 7 claims · 7 setups

  Full-text index only

  scXDR outperforms seven methods that transfer drug response information from bulk RNA-seq to single-cell data, across all four evaluated scenarios

  single-cell scrna-seq scxdr gse117872 heterogeneous benchmarking type

• Evaluating the Utilities of Foundation Models in Single-Cell Data Analysis.

  PMID 41869863 · PMC13170260 · Advanced science (Weinheim, Baden-Wurttemberg, Germany) · 2026 · 8 claims · 8 setups

  Full-text index only

  Among ten/eleven evaluated single-cell FMs, scGPT, Geneformer, and CellFM are the top models considering both performance and user accessibility

  scrna-seq unpaired single-cell scgpt batch multi-omic cell-type

• ICE: robust detection of cellular senescence from weak single-cell signatures using imputation-based marker refinement.

  PMID 41668152 · PMC12990438 · Genome biology · 2026 · 8 claims · 7 setups

  Full-text index only

  Senescence-associated marker genes show weak, non-specific expression across human tissues and cell types compared to canonical tissue/cell-type markers

  tissues pancreas pancreatic brain bulk scrna-seq train

• Prior-guided factorization for reliable imputation of scRNA-seq data.

  PMID 41860953 · PMC13004523 · PLoS computational biology · 2026 · 8 claims · 8 setups

  Full-text index only

  scZN models scRNA-seq counts as a mixture of a two-state (Gamma-Poisson/negative binomial) transcriptional bursting process and dropout, formalized via a zero-inflated negative binomial (ZINB) and solved as constrained nonnegative matrix factorization into a cell-to-cell-type assignment matrix and a cell-type expression matrix

  ercc real randomly brain scrna-seq cell-cycle k-nn

• A novel deep learning-driven framework for improving lncRNA comprehensive annotation with LncADeep 2.0.

  PMID 41923359 · PMC13090826 · Bioinformatics (Oxford, England) · 2026 · 8 claims · 8 setups

  Full-text index only

  LncADeep 2.0 outperforms LncADeep and other existing tools for lncRNA identification on both GENCODE annotated transcripts and independent RNA-seq data

  lncrna hypertrophic gencode lncrna-protein-mirna mlp-based independent ablation

• 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

• Tachykinin signaling defines distinct populations of glia in the enteric nervous system.

  PMID 41512855 · PMC12832054 · Neuron · 2026 · 8 claims · 8 setups

  Full-text index only

  Mucosal and muscularis glia are transcriptionally distinct populations, with mucosal glia resembling microglia and muscularis glia resembling satellite glia/astrocytes

  ileum gfp+ intestinal intestine bulk scrna-seq bayesprism