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).
-
Has reproduction · 44
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
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
-
Full-text index only
Transcriptome-based high-frequency recurrence index predicts frequent recurrence in non-muscle-invasive bladder cancer after Bacillus Calmette-Guérin therapy.
PMID 41749284 · PMC13040970 · BMC medicine · 2026 · 8 claims · 7 setups
A 75-gene HfRI signature predicts high-frequency recurrence (≥2 recurrences) in NMIBC patients
-
Full-text index only
Predicting FOX gene candidates for oxic nitrogen fixation using multi-omic machine learning and comparative bioinformatics.
PMID 41764348 · PMC13056922 · Scientific reports · 2026 · 8 claims · 6 setups
Random Forest, XGBoost, and logistic regression classifiers can meaningfully differentiate literature-validated FOX genes from conserved non-essential genes, with Random Forest achieving the best ROC-AUC (~0.80)
-
Full-text index only
Cataloging coding sequence variations in human genome databases.
PMID 18974781 · PMC2570488 · PloS one · 2008 · 8 claims · 7 setups
A significant proportion of CVs overlap between HGMD and dbSNP (4.36% of HGMD CVs registered in dbSNP; 8.11% of dbSNP CVs registered in HGMD), warranting caution when interpreting phenotypic relevance of concurrent CVs.
-
Full-text index only
The circadian isoform landscape of mouse livers.
PMID 41987907 · PMC13076092 · NAR genomics and bioinformatics · 2026 · 5 claims · 6 setups
R2C2 long-read nanopore sequencing generates highly accurate, full-length cDNA reads suitable for quantitative detection of circadian oscillations
-
Full-text index only
Decoding unchanged transcriptome of Alzheimer's disease reveals an NCAM1 mRNA switch as a potential biomarker.
PMID 42006342 · PMC13090632 · iScience · 2026 · 8 claims · 7 setups
Most genes are gene-level non-differentially expressed (nDEGs) in AD but nDEGs are strongly associated with neuronal function pathways
-
Has reproduction · 62
Metatranscriptomics of the human oral microbiome during health and disease.
PMID 24692635 · PMC3977359 · mBio · 2014 · 8 claims · 8 setups
Disease-associated periodontal communities display conserved community-level metabolic gene expression profiles between patients, whereas the metabolic gene expression of individual species is highly variable between patients.
-
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
-
Full-text index only
Annotation-free prediction of immunotherapy response in melanoma using single-cell transcriptomic data.
PMID 41758825 · PMC12948085 · PloS one · 2026 · 8 claims · 6 setups
AI-based predictive models built on unannotated scRNA-seq data (cell-by-gene expression matrices) can classify melanoma patients as ICI responders vs. non-responders
-
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
BaGPipe: an automated, reproducible, and flexible pipeline for bacterial genome-wide association studies.
PMID 41896736 · PMC13147680 · BMC microbiology · 2026 · 7 claims · 8 setups
BaGPipe is an automated, reproducible Nextflow pipeline that integrates pre-processing, Pyseer-based association analysis, and downstream visualisation into a unified bacterial GWAS workflow
-
Full-text index only
Distinct molecular and tumor microenvironment characteristics of mucinous adenocarcinoma in colorectal cancer.
PMID 42100746 · PMC13145884 · iScience · 2026 · 8 claims · 8 setups
MAC is associated with significantly worse overall survival than CAC, but only within the MSS subtype
-
Full-text index only
Parameter-efficient fine-tuning enables scalable transfer of regulatory sequence models to novel contexts.
PMID 41618434 · PMC12930932 · Genome biology · 2026 · 8 claims · 7 setups
PEFT enables accurate transfer of Borzoi to new datasets while significantly reducing GPU memory and runtime compared to joint training or full fine-tuning
-
Full-text index only
Functional germline variants together with somatic mutations alter the integrity of cancer hallmark regulatory networks.
PMID 42057121 · PMC13151107 · Genome medicine · 2026 · 8 claims · 6 setups
Combined germline and somatic alterations disturb cancer hallmark pathway integrity in individual-specific ways, potentially explaining unique clinical behavior of each cancer.