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).

• Lorentz-regularized interpretable VAE for multi-scale single-cell transcriptomic and epigenomic embeddings.

  PMID 41555918 · PMC12812404 · Frontiers in genetics · 2025 · 7 claims · 5 setups

  Full-text index only

  LiVAE, a dual-pathway VAE with Lorentzian geometric regularization between a primary Euclidean pathway and an information-bottleneck pathway, balances local fidelity with global topology coherence in single-cell embeddings

  single-cell same dapp1 benchmarking umap component-wise

• CellPredX, a computational framework for cross-data type, cross-sample, and cross-protocol cell type annotation through domain adaptation and deep metric learning.

  PMID 41481570 · PMC12758788 · PLoS computational biology · 2026 · 8 claims · 7 setups

  Full-text index only

  CellPredX is a unified semi-supervised framework integrating domain adaptation and deep metric learning to align heterogeneous embeddings for cross-modality cell type annotation.

  pbmc fetal pancreas gse149683 matched unmatched cross-protocol

• 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

• 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

• CellFishing.jl: an ultrafast and scalable cell search method for single-cell RNA sequencing.

  PMID 30744683 · PMC6371477 · Genome biology · 2019 · 8 claims · 5 setups

  Has reproduction · 97

  CellFishing.jl achieves accuracy comparable to state-of-the-art software (scmap-cell) but is markedly faster

  scrna-seq shekhar2016 svd lsh hamming

• Cis-regulatory evolution shapes facial diversity in birds and mammals.

  PMID 42090501 · PMC13148318 · Science advances · 2026 · 8 claims · 6 setups

  Full-text index only

  Mesenchymal populations show markedly greater transcriptomic/regulatory divergence between mouse and chicken than ectodermal populations, pointing to a central role of mesenchyme in shaping facial morphology

  embryo chicken embryos single-cell situ cross-species

• Single-cell omics data-driven decoding of tumor clonal evolution through reinforcement learning.

  PMID 41998716 · PMC13224513 · Genome medicine · 2026 · 8 claims · 3 setups

  Full-text index only

  scRevol is an RL-based model that infers tumor clonal evolution from scRNA-seq-derived CNV profiles via a label assignment learning strategy.

  simulated lineage ovarian scrna-seq-derived

• scDEBGCL: a deep embedding approach based on bipartite graph contrastive learning for single-cell RNA-seq data.

  PMID 41981652 · PMC13188691 · BMC biology · 2026 · 7 claims · 3 setups

  Full-text index only

  scDEBGCL is a deep embedding method for scRNA-seq data based on bipartite graph contrastive learning, integrating contrastive learning, graph reconstruction, and ZINB-based data reconstruction losses.

  nine yan dpt scrna-seq trajectory

• scGACL: a generative adversarial network with multi-scale contrastive learning for accurate single-cell RNA sequencing imputation.

  PMID 41632596 · PMC12866930 · Briefings in bioinformatics · 2026 · 8 claims · 6 setups

  Full-text index only

  scGACL, a GAN integrated with multi-scale contrastive learning, is proposed to overcome the over-smoothing problem in scRNA-seq imputation

  simulated real-world scrna-seq scrna-seq clustering gene

• scDecorr: feature decorrelation based representation learning enables self-supervised alignment of multiple single-cell experiments.

  PMID 42056283 · PMC13128840 · Scientific reports · 2026 · 7 claims · 1 setups

  Full-text index only

  scDecorr learns robust cell representations of unlabelled single-cell experiments in a negative-sample-free self-supervised fashion using feature decorrelation

  datasets scrna-seq

• PanglaoDB: a web server for exploration of mouse and human single-cell RNA sequencing data.

  PMID 30951143 · PMC6450036 · Database : the journal of biological databases and curation · 2019 · 7 claims · 7 setups

  Has reproduction · 80

  PanglaoDB is a web server providing pre-processed and pre-computed analyses of published mouse and human scRNA-seq experiments through a user-friendly interface.

  randomly single-cell single scrna-seq cell-type orthogonal

• Bulk and single-cell characterisation of the immune heterogeneity of atherosclerosis identifies novel targets for immunotherapy.

  PMID 36855107 · PMC9974063 · BMC biology · 2023 · 8 claims · 8 setups

  Has reproduction · 70

  Integration of scRNA-seq datasets from human atherosclerosis samples identifies 28 distinct immune cell subpopulations with heterogeneity in tissue preference, genetics, function, immune dynamics, transcriptional regulators, metabolism, and cell communication.

  immune atherosclerotic cd4+ cd8+ scrna-seq gsea pseudotime

• Cell-type annotation with accurate unseen cell-type identification using multiple references.

  PMID 37379341 · PMC10335708 · PLoS computational biology · 2023 · 8 claims · 4 setups

  Has reproduction · 68

  mtANN integrates multiple reference datasets and eight gene selection methods via ensemble learning (multiple deep classification models + majority voting) to improve cell-type annotation accuracy

  pbmc pancreas covid-19 scrna-seq

• CanCellCap: robust cancer cell capture across tissue types on single-cell RNA-seq data by multi-domain learning.

  PMID 40739511 · PMC12312500 · BMC biology · 2025 · 8 claims · 7 setups

  Has reproduction · 42

  CanCellCap identifies cancer cells in scRNA-seq data across 13 tissue types, 23 cancer types, and 7 sequencing platforms with 0.977 average accuracy

  cancer testing sequencing unseen scrna-seq spatial

• Deep-Learning Tool ScVital Enables Species-Agnostic Integration of Cancer Cell States.

  PMID 41223329 · PMC13053053 · Cancer research · 2026 · 7 claims · 7 setups

  Full-text index only

  scVital is a variational autoencoder with an adversarially trained discriminator that embeds scRNA-seq data from different species into a species-agnostic latent space to overcome batch effect.

  pbmc normal pancreatic lung scrna-seq

• An integrated single-cell lung cancer atlas reveals distinct fibroblast phenotypes between adenocarcinoma and squamous cell carcinomas.

  PMID 41577803 · PMC12920623 · NPJ precision oncology · 2026 · 8 claims · 8 setups

  Full-text index only

  Inflammatory CAFs (iCAFs) predominate in LUAD, whereas myofibroblastic CAFs (mCAFs) predominate in LUSC

  nsclc epithelial macrophage caf scrna-seq copy gene-set

• Aurkb deficiency disrupts microglial development, homeostasis and hinders remyelination following cuprizone-induced demyelination.

  PMID 41704758 · PMC12907124 · iScience · 2026 · 8 claims · 8 setups

  Full-text index only

  Aurkb is upregulated in a subset of fetal/neonatal microglia and in microglia following CPZ-induced demyelination and in MS patient microglia

  microglia brain neonatal corpus scrna-seq western immunofluorescence

• 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

• scDenorm: a denormalization tool for integrating single-cell transcriptomics data.

  PMID 41915012 · PMC13142155 · GigaScience · 2026 · 8 claims · 7 setups

  Full-text index only

  Inconsistent delta-method normalization across datasets introduces biases (e.g., B-cell separation) that persist even after integration with Harmony, scanorama, or BBKNN.

  10x brain ucsc datasets scrna-seq integration snrna-seq

• Benchmarking RNA velocity methods across 17 independent studies.

  PMID 41916302 · PMC13106975 · Cell reports methods · 2026 · 8 claims · 6 setups

  Full-text index only

  No single RNA velocity method exhibited superior performance across all accuracy, stability, and usability assessments

  scrna-seq same representative dyngen-simulated velocity cross-method downsampling