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).

• FLASH-MM: fast and scalable single-cell differential expression analysis using linear mixed-effects models.

  PMID 41644528 · PMC12982622 · Nature communications · 2026 · 8 claims · 6 setups

  Full-text index only

  FLASH-MM produces LMM parameter estimates identical to lmer (lme4) up to the sixth decimal place while being 50- to 140-fold faster as sample size increases from 20,000 to 120,000 cells

  simulated same healthy female-biased simulated comparative single-cell

• Deep single-cell decoding of human pancreatic islets reveals T2D β-cell gene expression defects.

  PMID 41986506 · PMC13226668 · The EMBO journal · 2026 · 8 claims · 6 setups

  Full-text index only

  Single-cell transcriptome profiling of 245,878 islet cells from 48 donors (ND/PD/T2D) identifies 14 distinct, robust islet cell types detected in every donor

  pancreatic aggregated endoc-βh3 subset droplet-based pseudobulk unsupervised

• Cross-ancestry genome-wide association studies of liver function biomarkers uncover pleiotropic variants, systemic disease links and therapeutic targets.

  PMID 41689074 · PMC13005531 · Genome medicine · 2026 · 8 claims · 8 setups

  Full-text index only

  5,507 lead signals (P<5x10^-9) were identified for seven LFQBs across ancestries, including 210 novel loci

  hope biobank combined cross-ancestry gwas cross-ancestry functional-informed

• l-2-Hydroxyglutarate impairs neuronal differentiation through epigenetic activation of MYC expression.

  PMID 41842973 · PMC13132370 · The Journal of clinical investigation · 2026 · 8 claims · 8 setups

  Full-text index only

  L2HGDH deficiency causes L-2HG (not D-2HG) accumulation in patient plasma, fibroblasts, iPSCs, and NPCs

  plasma patient-derived unedited day-14 metabolomics crispr proliferation

• Cell type-specific eQTL analysis of COVID-19 based on single-cell transcriptomic data.

  PMID 41064594 · PMC12501775 · NAR genomics and bioinformatics · 2025 · 8 claims · 8 setups

  Has reproduction · 51

  Single-cell eQTL analysis across eight immune cell types identified 2593 genes whose expression is significantly associated with common genetic polymorphisms, with most genes showing cell type-specific effects

  pbmcs eight pbmc monocytes scrna-seq genetic cis-eqtl

• Partial domain adaptation enables cross domain cell type annotation between scRNA-seq and snRNA-seq.

  PMID 42090457 · PMC13170964 · PLoS computational biology · 2026 · 7 claims · 5 setups

  Full-text index only

  ScNucAdapt is a partial domain adaptation framework that enables cross-domain cell type annotation between paired or unpaired scRNA-seq and snRNA-seq datasets.

  bladder kidney cortex frozen scrna-seq snrna-seq

• 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

• 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

• 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

• 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

• Cell-type- and chromosome-specific chromatin landscapes and DNA replication programs of Drosophila testis tumor stem cell-like cells.

  PMID 41371963 · PMC12758400 · Genome research · 2026 · 8 claims · 6 setups

  Full-text index only

  GSC-like and CySC-like cells isolated from upd tumor testes are transcriptionally comparable to wild-type GSC/early-spermatogonia and CySC clusters, respectively

  upd gsc-like wild-type scrna-seq differential gene

• Cell type-specific network analysis in Diversity Outbred mice identifies genes potentially responsible for human bone mineral density GWAS associations.

  PMID 41811178 · PMC12978698 · eLife · 2026 · 8 claims · 8 setups

  Full-text index only

  Cell type-specific Bayesian and co-expression networks generated from BMSC-OB scRNA-seq data in Diversity Outbred mice can prioritize and contextualize genes underlying human BMD GWAS associations

  bmsc-ob genes mesenchymal gtex scrna-seq cellect iterativewgcna

• VIST: variational inference for single cell time series.

  PMID 41535949 · PMC12892444 · Genome biology · 2026 · 8 claims · 6 setups

  Full-text index only

  VIST is a VAE-based method that decomposes single-cell gene expression into time-dependent and time-independent latent components

  toy drosophila aorta lung synthetic time-course latent

• scSurv: a deep generative model for single-cell survival analysis.

  PMID 41429574 · PMC12797213 · Bioinformatics (Oxford, England) · 2026 · 8 claims · 6 setups

  Full-text index only

  scSurv combines a Cox proportional hazards model with a deep generative model (VAE) of single-cell transcriptomes to estimate individual cellular contributions to clinical outcomes

  simulated tcga melanoma renal scrna-seq bulk single-cell

• Hierarchical cell-type identifier accurately distinguishes immune-cell subtypes enabling precise profiling of tissue microenvironment with single-cell RNA-sequencing.

  PMID 36681937 · PMC10025442 · Briefings in bioinformatics · 2023 · 8 claims · 8 setups

  Has reproduction · 94

  HiCAT is a hierarchical, marker-based cell-type identifier that uses gene set analysis (GSA) scoring with markers structured in a three-level taxonomy tree (major-type, minor-type, subset)

  pbmc cord melanoma lung scrna-seq computational

• Mouse-Geneformer: A deep learning model for mouse single-cell transcriptome and its cross-species utility.

  PMID 40106407 · PMC11964219 · PLoS genetics · 2025 · 7 claims · 6 setups

  Has reproduction · 95

  Mouse-Geneformer, a Transformer Encoder model pre-trained via masked-token self-supervised learning on mouse-Genecorpus-20M, was successfully constructed following the original human Geneformer architecture.

  healthy scrna-seq disease scrna-seq type perturbation

• PAH-former: Transfer learning for efficient discovery of pulmonary arterial hypertension-associated genes.

  PMID 41790620 · PMC12965534 · PloS one · 2026 · 7 claims · 7 setups

  Full-text index only

  PAH-former, a Geneformer model fine-tuned on public PAH scRNA-seq data, can perform in silico perturbation to identify and rank candidate PAH disease-associated genes

  pah scrna-seq pah-former candidate scrna-seq transfer perturbation

• 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

• A unique malignant cell type per patient tumor encoded in each cancer cell transcriptome.

  PMID 41884004 · PMC13010111 · iScience · 2026 · 8 claims · 8 setups

  Full-text index only

  Malignant cells cluster predominantly by tumor of origin, while non-malignant cells from the same tumors cluster by cell type independent of patient

  malignant non-malignant ovarian normal scrna-seq alternative paired

• Deconvolving cell-type-specific gene expression profiles from bulk RNA-seq samples.

  PMID 41886524 · PMC13038110 · PLoS computational biology · 2026 · 8 claims · 6 setups

  Full-text index only

  BLUE, a U-Net-based deep learning model with dual branches (U-Net for GEPs, MLP for proportions), accurately predicts cell-type proportions and cell-type-specific gene expression profiles from bulk RNA-seq.

  pbmc pancreatic aml scrna-seq-derived real scrna-seq