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).

• Macrophages on the run: Exercise balances macrophage polarization for improved health.

  PMID 39476967 · PMC11585839 · Molecular metabolism · 2024 · 8 claims · 7 setups

  Has reproduction · 81

  Immediate/acute exercise triggers an M1 (pro-inflammatory) macrophage polarization surge.

  gene affymetrix pooled muscle meta-analysis stepminer gene

• scMILD: Single-cell multiple instance learning for sample classification and associated subpopulation discovery.

  PMID 41907409 · PMC13019583 · iScience · 2026 · 8 claims · 8 setups

  Full-text index only

  scMILD identifies condition-associated cells using only sample-level labels via a dual-branch MIL architecture with a shared encoder

  simulated lupus covid-19 ulcerative simulated mixture scrna-seq

• AI-guided multi-omics analysis identifies NPC1-modulated susceptibility to SARS-CoV-2 infection under PM(2.5) exposure.

  PMID 41912520 · PMC13194984 · Nature communications · 2026 · 8 claims · 6 setups

  Full-text index only

  A fine-tuned Geneformer (single-cell transcriptomics transformer) model classifies PM2.5 exposure status and generalizes better than BERT models trained from scratch, especially with limited data.

  lung fine-tuned biobank single-cell bulk gene

• Constructing support vector machine ensembles for cancer classification based on proteomic profiling.

  PMID 16689692 · PMC5173238 · Genomics, proteomics & bioinformatics · 2005 · 7 claims · 4 setups

  Full-text index only

  CSVME, built by selecting a subset of base SVMs via SVM-RFE ranking and fusing them with a trained upper-layer SVM, achieves better classification performance than an ensemble of all base SVMs.

  serum computational seldi-tof svm-rfe-based 10-fold

• Statistical learning of peptide retention behavior in chromatographic separations: a new kernel-based approach for computational proteomics.

  PMID 18053132 · PMC2254445 · BMC bioinformatics · 2007 · 6 claims · 5 setups

  Full-text index only

  The paired oligo-border kernel (POBK) combined with SVMs predicts peptide adsorption/elution in SAX-SPE and retention time in IP-RP-HPLC more accurately than existing methods.

  peptides peptide sax-spe ip-rp-hplc cross-run

• Prediction of myeloid malignant cells in Fanconi anemia using machine learning.

  PMID 41557613 · PMC12818649 · PloS one · 2026 · 6 claims · 7 setups

  Full-text index only

  A DNN classifier trained on AML scRNA-seq data accurately predicts AML-like transcriptional profiles at single-cell resolution

  bone predicted-aml healthy scrna-seq reference-based stemnet

• CLAMP: predicting specific protein-mediated chromatin loops in diverse species with a chromatin accessibility language model.

  PMID 41555433 · PMC12903630 · Genome biology · 2026 · 8 claims · 8 setups

  Full-text index only

  CLAMP, a chromatin-accessibility language model, predicts protein-mediated chromatin loops across 10 species, 18 proteins, and 24 cell types with superior performance versus existing methods.

  species gm12878 types chromatin cross-protein cross-cell-type

• An OMICs-based meta-analysis to support infection state stratification.

  PMID 33560295 · PMC8388022 · Bioinformatics (Oxford, England) · 2021 · 7 claims · 6 setups

  Has reproduction · 44

  Multi-class Random Forest models built from meta-analyzed blood gene expression data can predict infection state (bacterial/viral/none) with high accuracy, correctly classifying 93% of bacterial and 89% of viral samples in the best model.

  blood merged affymetrix-trained microarray random gene

• Machine and Deep Learning Reveal Sequence Determinants Encoding Bivalent Histone Modifications.

  PMID 41946881 · PMC13057473 · Communications biology · 2026 · 8 claims · 7 setups

  Full-text index only

  Bivalent domains have higher GC content and stronger evolutionary conservation than monovalent regions

  embryonic mesc random bivalent chip-seq rna-seq k-mer-based

• A generic reference defined by consensus peaks for single-cell ATAC-seq data analysis.

  PMID 41663439 · PMC12996591 · Nature communications · 2026 · 7 claims · 7 setups

  Full-text index only

  Aggregating peaks from 624 high-quality bulk ATAC-seq datasets defines ~1.4 million observed consensus peaks (cPeaks) covering ~30% of the genome.

  bulk scatac-seq cnn gm12878 bulk scatac-seq deep

• 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

• Application of alternative de novo motif recognition models for analysis of structural heterogeneity of transcription factor binding sites: a case study of FOXA2 binding sites.

  PMID 34547062 · PMC8408018 · Vavilovskii zhurnal genetiki i selektsii · 2021 · 8 claims · 4 setups

  Has reproduction · 62

  MultiDeNA pipeline combines PWM, diPWM, BaMM and InMoDe models to train, evaluate, threshold, and classify ChIP-seq peaks for TFBS structural heterogeneity

  foxa2 genomic frequency chip-seq novo threshold