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

• Genome-wide kinetic properties of transcriptional bursting in mouse embryonic stem cells.

  PMID 32596448 · PMC7299619 · Science advances · 2020 · 8 claims · 8 setups

  Has reproduction · 57

  Transcriptional bursting kinetics is regulated by a combination of promoter- and gene body-binding proteins, including the polycomb repressive complex 2 (PRC2) and transcription elongation factors

  cast knock-in mesc mescs single-cell single-molecule flow

• HIF3A-mediated aberrant activation of TXNIP promotes Alzheimer's disease progression.

  PMID 41807716 · PMC13096512 · Scientific reports · 2026 · 8 claims · 8 setups

  Full-text index only

  OS activity is significantly elevated in AD and shows pronounced heterogeneity across brain cell types

  entorhinal brain middle c57bl scrna-seq bulk animal

• Early feature extraction drives model performance in high-resolution chromatin accessibility prediction.

  PMID 41526189 · PMC12951969 · Genome research · 2026 · 8 claims · 6 setups

  Full-text index only

  Early feature extraction (via ConvNeXt V2 blocks), rather than downstream architecture type, is the primary determinant of prediction accuracy in high-resolution chromatin accessibility prediction.

  lines cancer sets gm12878 atac-seq peak input-shift

• Human-scATAC-Corpus: a comprehensive database of scATAC-seq data.

  PMID 41296545 · PMC12807747 · Nucleic acids research · 2026 · 8 claims · 6 setups

  Full-text index only

  Human-scATAC-Corpus is a comprehensive database of human scATAC-seq data comprising 5,407,621 cells from 35 datasets across 37 tissues or cell lines

  tissues scatac-seq five subset scatac-seq genome unified

• Benchmarking component choices for unpaired single cell RNA and epigenomic integration.

  PMID 41987329 · PMC13192178 · Genome biology · 2026 · 7 claims · 8 setups

  Full-text index only

  Gene activity scores (GAS) show limited correlation with actual gene expression but effectively preserve cellular neighborhood structure and support clustering.

  e18 pbmc brain kidney scrna-seq share-seq gas

• Visualizing stability: a sensitivity analysis framework for t-SNE embeddings.

  PMID 41552665 · PMC12808344 · Frontiers in bioinformatics · 2025 · 8 claims · 5 setups

  Full-text index only

  The Implicit Function Theorem, combined with automatic differentiation, can be used to efficiently compute the complete sensitivity Jacobian of a converged t-SNE embedding with respect to the input data, avoiding differentiation through the full iterative optimizer.

  bulk proteomics single-cell biological t-sne gaussian

• Adaptive learning embedding features to improve the predictive performance of SARS-CoV-2 phosphorylation sites.

  PMID 37847658 · PMC10628388 · Bioinformatics (Oxford, England) · 2023 · 8 claims · 6 setups

  Has reproduction · 67

  PSPred-ALE outperforms state-of-the-art SARS-CoV-2 phosphorylation site predictors (e.g. DeepIPs) and handcrafted feature-based methods in benchmarking comparisons

  a549 sequence same bulk pathway gene

• Leveraging the germ layer development patterns to predict prognosis and identify MEST as a novel therapeutic target in glioma.

  PMID 41501725 · PMC12870398 · Cancer cell international · 2026 · 7 claims · 8 setups

  Full-text index only

  MEST is a key oncogenic GLD-related gene and a novel therapeutic target in glioma, identified via a machine learning feature selection framework

  bulk single-cell tcga glioma gsva aucell machine

• KRT15 identified by scRNA-Seq and machine learning as stemness regulator and prognostic biomarker in ESCC.

  PMID 41907411 · PMC13018899 · iScience · 2026 · 8 claims · 8 setups

  Full-text index only

  A malignant epithelial subpopulation (Cluster 0) with the highest CytoTRACE stemness potential and highest EMT activity exists in ESCC scRNA-seq data

  escc degs eca109 kyse180 scrna-seq machine immunohistochemistry

• TDAGENE: Inference of Gene Regulatory Network Based on Topological Data Analysis and Graph Attention Network for Single-Cell RNA Sequencing Data.

  PMID 42093817 · PMC13139726 · Computational and structural biotechnology journal · 2026 · 7 claims · 5 setups

  Full-text index only

  TDAGENE combines TDA features with a multilayer GAT via gate-controlled fusion to improve GRN inference accuracy

  scrna-seq gene string chip-seq grn persistent prior

• A workflow reproducibility scale for automatic validation of biological interpretation results.

  PMID 37150537 · PMC10164546 · GigaScience · 2022 · 8 claims · 4 setups

  Has reproduction · 100

  Comparing output files by checksum alone is insufficient to verify reproducibility, since checksums can differ even when the underlying biological interpretation is unchanged

  nf-core sam vcf workflow checksum biological workflow

• Predicting enhancers in mammalian genomes using supervised hidden Markov models.

  PMID 30917778 · PMC6437899 · BMC bioinformatics · 2019 · 8 claims · 8 setups

  Has reproduction · 70

  eHMM predicts enhancers with high precision and recall comparable to state-of-the-art methods and consistently outperforms them in accuracy and resolution

  esc atac-seq chip-seq cage

• Developing prognostic gene panel of survival time in lung adenocarcinoma patients using machine learning.

  PMID 35117753 · PMC8799101 · Translational cancer research · 2020 · 8 claims · 5 setups

  Has reproduction · 32

  Naïve Bayes using a 22-gene panel is the best-performing and most stable machine learning model for predicting LUAD survival time (>3 vs <3 years)

  tcga geo rna-seq methylation sequencing

• TSniffer: unbiased de novo identification of RNA editing sites and quantification of editing activity in RNA-seq data.

  PMID 41549280 · PMC12838065 · Genome biology · 2026 · 8 claims · 6 setups

  Full-text index only

  TSniffer is a novel tool that uses a rolling window Fisher's exact test approach to identify RNA editing sites (TsRegions) de novo in RNA-seq data without relying on editing databases or two-sample differential comparison.

  type hela mm10 brain rna-seq genomic database

• Multi-omics feature engineering driven by biomedical foundation models improves drug response prediction for inflammatory bowel disease patients.

  PMID 41844950 · PMC13129071 · Scientific reports · 2026 · 8 claims · 7 setups

  Full-text index only

  FM (MAMMAL)-derived drug-target binding affinity (BA) inference can be used to rank/select biologically relevant protein targets and their associated genes/SNPs for a drug of interest without knowledge of protein structure or active sites

  reference top surgical snp-mutated inference gene genomic

• GDSim: accurate simulation for single-cell transcriptomes based on the guided diffusion model.

  PMID 41978379 · PMC13076945 · Briefings in bioinformatics · 2026 · 8 claims · 4 setups

  Full-text index only

  GDSim, a label-guided diffusion-based deep generative network, can simulate scRNA-seq data that closely reflects the true distribution of original data

  real simulated annotated scrna-seq subtype differential

• WASP: a versatile, web-accessible single cell RNA-Seq processing platform.

  PMID 33736596 · PMC7977290 · BMC genomics · 2021 · 7 claims · 7 setups

  Has reproduction · 59

  WASP is a software platform for processing Drop-Seq-based scRNA-seq data generated with ddSEQ or 10x protocols, combining a Snakemake pre-processing pipeline with an R Shiny post-processing application.

  specified generic scrna-seq read reference

• Score Matching for Differential Abundance Testing of Compositional High-Throughput Sequencing Data.

  PMID 41944570 · PMC13055433 · Statistics in medicine · 2026 · 8 claims · 3 setups

  Full-text index only

  cosmoDA extends the a-b power interaction model by adding a linear covariate effect on the location vector, enabling differential abundance testing on compositional data with feature interactions.

  simulated cell-type microbial simulated single-cell 16s

• Dynamic Gene Attention Focus (DyGAF): Enhancing Biomarker Identification Through Dual-Model Attention Networks.

  PMID 40160891 · PMC11951896 · Bioinformatics and biology insights · 2025 · 6 claims · 5 setups

  Has reproduction · 44

  DyGAF, a dual-model attention neural network (independent Model A + dependent Model B), identifies and ranks genes by significance for COVID-19 biomarker discovery more effectively than differential expression analysis (DEA) and random forest (RF) feature selection

  nasopharyngeal same dygaf-ranked bulk differential random