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).
-
Full-text index only
scArchon: a scalable benchmarking framework for assessing single-cell perturbation models.
PMID 42121287 · PMC13162514 · Genome biology · 2026 · 8 claims · 8 setups
scArchon is a reproducible, modular, Snakemake-based benchmarking platform that evaluates perturbation response prediction tools in a standardized, containerized, extensible manner.
-
Full-text index only
Dictionary of human intestinal organoid responses to secreted niche factors at single cell resolution.
PMID 41513700 · PMC12891662 · Nature communications · 2026 · 8 claims · 8 setups
Cytomix (TNFɑ+IFNɣ+IL1β) treatment of human colon organoids best recapitulates molecular features of human IBD compared to DSS or irradiation injury models.
-
Has reproduction · 62
scATD: a high-throughput and interpretable framework for single-cell cancer drug resistance prediction and biomarker identification.
PMID 40501071 · PMC12159290 · Briefings in bioinformatics · 2025 · 8 claims · 6 setups
scATD enables high-throughput single-cell drug sensitivity prediction for new patients without model parameter retraining via bidirectional Bi-AdaIN style transfer
-
Has reproduction · 56
Analysis of subcellular transcriptomes by RNA proximity labeling with Halo-seq.
PMID 34875090 · PMC8887463 · Nucleic acids research · 2022 · 6 claims · 8 setups
Halo-seq pairs a light-activatable Halo-DBF ligand with Click chemistry to label and purify spatially defined RNA populations in living cells with high spatial specificity (~100 nm radius)
-
Full-text index only
MultiPert: An adversarial alignment and dual attention framework for single-cell multi-omics perturbation prediction.
PMID 41811907 · PMC12998955 · PLoS computational biology · 2026 · 8 claims · 7 setups
MultiPert reliably predicts both perturbed gene expression and protein abundance profiles from single-cell multi-omics data
-
Has reproduction · 50
An atlas of the human liver diurnal transcriptome and its perturbation by hepatitis C virus infection.
PMID 39209804 · PMC11362569 · Nature communications · 2024 · 7 claims · 7 setups
Human hepatocytes engrafted in liver chimeric mice display a large rhythmic transcriptome of ~1700 protein-coding orthologous genes, including transcription factors, chromatin modifiers, and metabolic enzymes.
-
Full-text index only
PAH-former: Transfer learning for efficient discovery of pulmonary arterial hypertension-associated genes.
PMID 41790620 · PMC12965534 · PloS one · 2026 · 7 claims · 7 setups
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
-
Full-text index only
A ligand-centered framework for γδ T cell activation in colorectal cancer revealed by single-cell and transformer-based perturbation.
PMID 41607803 · PMC12835328 · Frontiers in immunology · 2025 · 8 claims · 8 setups
CRC-infiltrating γδ T cells show varied activation levels, with the TRM-like population being the major tumor-infiltrating subtype and exhibiting the lowest effector and exhaustion signature scores.
-
Full-text index only
scLong: a billion-parameter foundation model for capturing long-range gene context in single-cell transcriptomics.
PMID 41639087 · PMC12982784 · Nature communications · 2026 · 7 claims · 4 setups
scLong performs self-attention across all ~27,874 human genes, including lowly expressed ones, to capture long-range gene dependencies missed by models restricted to highly expressed gene subsets
-
Has reproduction · 68
Systematic identification of ACE2 expression modulators reveals cardiomyopathy as a risk factor for mortality in COVID-19 patients.
PMID 35012625 · PMC8743438 · Genome biology · 2022 · 8 claims · 9 setups
GENEVA (Gene Expression Variance Analysis) is a semi-automated framework that mines large-scale public RNA-seq datasets to identify conditions associated with a gene's expression variance
-
Has reproduction · 88
AuPairWise: A Method to Estimate RNA-Seq Replicability through Co-expression.
PMID 27082953 · PMC4833304 · PLoS computational biology · 2016 · 7 claims · 6 setups
Sample-sample correlation of transcript abundances is a misleading measure of replicability for assessing differential expression, because it is dominated by gene-specific dynamic ranges rather than condition-dependent variation.
-
Has reproduction · 95
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
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.
-
Full-text index only
Embeddings from language models are good learners for single-cell data analysis.
PMID 41726097 · PMC12921509 · Patterns (New York, N.Y.) · 2026 · 8 claims · 8 setups
scELMo combines LLM-derived embeddings of gene and cell metadata with raw single-cell expression data via matrix operations to generate cell embeddings without pretraining a new model
-
Has reproduction · 82
Temporal control of progenitor competence shapes maturation in GABAergic neuron development in mice.
PMID 40629142 · PMC12321585 · Nature neuroscience · 2025 · 8 claims · 8 setups
Ganglionic eminence (ventral) progenitors maintain stable differentiation competence throughout neurogenesis, generating a consistent set of postmitotic precursor states at all stages, unlike dorsal cortical progenitors whose differentiation competence changes gradually.
-
Full-text index only
Multiomics and deep learning dissect regulatory syntax in human development.
PMID 41951735 · PMC13216069 · Nature · 2026 · 8 claims · 8 setups
The Human Development Multiomic Atlas (HDMA) is a single-cell atlas of chromatin accessibility and gene expression from 817,740 fetal cells across 12 organs, spanning 203 cell types
-
Full-text index only
CellPolaris: Transfer Learning for Gene Regulatory Network Construction to Guide Cell State Transitions.
PMID 41498638 · PMC12948241 · Advanced science (Weinheim, Baden-Wurttemberg, Germany) · 2026 · 8 claims · 8 setups
CellPolaris is a unified computational framework performing TF-centered GRN construction, master TF identification, and TF perturbation simulation
-
Full-text index only
Predicting the effect of CRISPR-Cas9-based epigenome editing.
PMID 41524535 · PMC12795505 · eLife · 2026 · 8 claims · 6 setups
Machine learning (CNN and ridge regression) models trained on histone PTM ChIP-seq and RNA-seq data from 13 ENCODE cell types accurately predict endogenous gene expression, with transcriptome-wide correlations of ~0.70-0.79 for most cell types
-
Full-text index only
BMP and NODAL paracrine signalling regulate the totipotent-like cell state in embryonic stem cells.
PMID 41660012 · PMC12876259 · Frontiers in cell and developmental biology · 2025 · 7 claims · 8 setups
BMP and NODAL (TGF-β) paracrine signalling are key routes of intercellular communication that respectively enhance or diminish the totipotent-like cell (TLC) state in mouse ESCs
-
Full-text index only
Modeling nascent transcription from chromatin landscape and structure with CLASTER.
PMID 41691282 · PMC13011747 · Genome biology · 2026 · 7 claims · 8 setups
CLASTER, a deep neural network combining chromatin landscape tracks and 3D contact maps, accurately predicts kilobasepair-resolution nascent RNA (EU-seq) profiles in a DNA-sequence-agnostic manner
-
Full-text index only
Scalable cell-specific coexpression networks for granular regulatory pattern discovery with NeighbourNet.
PMID 41786602 · PMC13138013 · Genome research · 2026 · 7 claims · 5 setups
NNet uses PCA embedding followed by local KNN regression in PC space to construct cell-specific coexpression networks (CSNs), improving computational efficiency and estimate stability versus pairwise approaches.