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).

• 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

  Full-text index only

  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)

  anabaena diazotrophic gene-level trained bulk quantitative transcription-start-site-derived

• Scalable Prediction of Acute Myeloid Leukemia Using High-Dimensional Machine Learning and Blood Transcriptomics.

  PMID 31918046 · PMC6992905 · iScience · 2020 · 8 claims · 8 setups

  Has reproduction · 96

  Assembled the largest reference blood gene expression profiling (GEP) dataset for AML to date: 12,029 samples from 105 studies across three platforms.

  peripheral datasets hg-u133 disjoint bulk machine deep

• Pathway signatures derived from on-treatment tumor specimens predict response to anti-PD1 blockade in metastatic melanoma.

  PMID 34654806 · PMC8519947 · Nature communications · 2021 · 6 claims · 8 setups

  Has reproduction · 100

  A pathway-based super signature from on-treatment samples (PASS-ON) predicts anti-PD1 response with high accuracy (validation AUC 0.85-0.89, combined AUC 0.88) and outperforms existing signatures across all four datasets.

  metastatic pathway bulk gene elastic-net

• Identification and characterization of tryptophan metabolism-related genes in carotid artery plaques.

  PMID 41628167 · PMC12863520 · PloS one · 2026 · 8 claims · 6 setups

  Full-text index only

  446 differentially expressed genes (DEGs) were identified between carotid plaque and normal tissue, enriched in immune and tryptophan-related pathways

  carotid degs six bulk kegg logistic

• Context-specific regulatory genetic variation in MTOR dampens neutrophil-T cell crosstalk in pneumonia-associated sepsis.

  PMID 41741465 · PMC13057173 · Nature communications · 2026 · 8 claims · 7 setups

  Full-text index only

  The MTOR eQTL variant rs4845987 has context-specific, opposite effects on MTOR expression: decreasing it in activated T cells and increasing it in neutrophils.

  blood bulk eqtl sepsis bulk cell-type colocalisation

• Classification of ALS molecular subtypes: a literature review on machine learning applications and their clinical value.

  PMID 41731547 · PMC13037183 · BMC medicine · 2026 · 8 claims · 5 setups

  Full-text index only

  Unsupervised ML analysis of ALS transcriptomes consistently identifies molecular subtypes reflecting distinct biological processes, primarily oxidative stress (ALS-Ox) and glial activation/neuroinflammation (ALS-Glia), found in every study reviewed.

  post-mortem peripheral bulk rna-seq blood

• 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

• Distinct radial glia subtypes regulate midbrain dopaminergic neuron development.

  PMID 41699318 · PMC13061605 · Nature neuroscience · 2026 · 8 claims · 8 setups

  Full-text index only

  Rgl1 is the progenitor of the mesDA neuronal lineage

  embryonic developing wa09 bulk scrna-seq ligand-receptor

• Integrating single-cell and bulk transcriptomes identifies B cell features associated with neoadjuvant chemoradiotherapy sensitivity in rectal cancer.

  PMID 41484196 · PMC12800305 · Scientific reports · 2026 · 8 claims · 8 setups

  Full-text index only

  A B cell subpopulation co-expressing HLA-DRB5, HLA-DQA2, HLA-DQB1, CD74, and ACTG1 is significantly associated with favorable nCRT response in rectal cancer

  larc scrna-seq scissor+ single-cell bulk pseudotime

• Smoking promotes colorectal cancer via the CKAP2L/AREG axis.

  PMID 41823522 · PMC13038336 · International journal of oncology · 2026 · 8 claims · 8 setups

  Full-text index only

  Smoking is positively associated with CRC risk, confirmed by both cross-sectional (NHANES) and Mendelian randomization analyses

  participants european crc hct116 cross-sectional two-sample single-cell

• PDLIM2 repression: a common mechanism in viral lung infection.

  PMID 41904702 · PMC13168810 · ImmunoHorizons · 2026 · 8 claims · 7 setups

  Full-text index only

  PDLIM2 expression is repressed in blood leukocytes, BAL cells, and lung tissue of patients infected with influenza or SARS-CoV-2 compared to uninfected controls

  peripheral blood bal influenza gene bulk single-cell

• CX-5461 and doxorubicin activate a shared DNA damage-associated transcriptional response in human cardiomyocytes.

  PMID 41543508 · PMC12958809 · G3 (Bethesda, Md.) · 2026 · 6 claims · 7 setups

  Full-text index only

  CX induces cell death in iPSC-derived cardiomyocytes at micromolar concentrations

  ipsc-derived undifferentiated colorectal viability γ-h2ax bulk

• RaMBat: Accurate identification of medulloblastoma subtypes from diverse data sources with severe batch effects.

  PMID 41571436 · PMC13060657 · Molecular oncology · 2026 · 7 claims · 5 setups

  Full-text index only

  RaMBat achieves a median accuracy of 99% across 13 independent benchmark datasets, significantly outperforming state-of-the-art MB subtyping methods and conventional ML classifiers

  medulloblastoma gse85217 ger microarray bulk intrasample

• Annotation-free prediction of immunotherapy response in melanoma using single-cell transcriptomic data.

  PMID 41758825 · PMC12948085 · PloS one · 2026 · 8 claims · 6 setups

  Full-text index only

  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

  cd45+ scrna-seq independent scrna-seq single-gene-level pathway-level

• Graph Random Forest: A Graph Embedded Algorithm for Identifying Highly Connected Important Features.

  PMID 37509188 · PMC10377046 · Biomolecules · 2023 · 8 claims · 6 setups

  Has reproduction · 89

  GRF identifies effective features that form highly connected sub-graphs on the underlying biological network

  synthetic tcga embryonic simulation sub-graph reproducibility

• Integrative transcriptomic and machine learning framework reveals candidate genes and potential mechanisms of aflatoxin B1 exposure in breast cancer.

  PMID 41688730 · PMC12982753 · Scientific reports · 2026 · 7 claims · 8 setups

  Has reproduction · 83

  170 unique human AFB1 targets were identified by merging ChEMBL, SwissTargetPrediction, and PharmMapper predictions

  afb1 breast training candidate computational bulk weighted

• Single-cell transcriptomics identifies regulatory T cell heterogeneity in gestational diabetes mellitus.

  PMID 41933176 · PMC13223204 · Communications medicine · 2026 · 8 claims · 8 setups

  Full-text index only

  Treg cluster proportions do not significantly differ between GDM and healthy control patients

  sorted pbmcs treg gdm-patient single-cell mass gene