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).

• 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

• 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

  Twenty-two genes lie at the intersection of AFB1-predicted targets and breast cancer-associated co-expression modules/DEGs

  afb1 breast training candidate computational bulk weighted

• 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 · 6 claims · 7 setups

  Has reproduction · 62

  Combining four de novo models (PWM, diPWM, BaMM, InMoDe) significantly increases the fraction of recognized peaks versus PWM alone (by 26.3%).

  hg38 foxa2 pwm whole-genome chip-seq pwm dipwm

• SpaGene: A Deep Adversarial Framework for Spatial Gene Imputation.

  PMID 42146899 · PMC13176606 · Computational and structural biotechnology journal · 2026 · 8 claims · 6 setups

  Has reproduction · 74

  SpaGene improves average PCC and SSIM and reduces RMSE compared to 6 baseline methods (SpaGE, gimVI, Tangram, VISTA, spRefine, stDiff) across 8 diverse ST-SC dataset pairs under gene-holdout evaluation.

  pairs nanostring st-sc osmfish_zeisel st-sc 5-fold spatially

• Wiggle-predicting functionally flexible regions from primary sequence.

  PMID 16839194 · PMC1500818 · PLoS computational biology · 2006 · 7 claims · 6 setups

  Full-text index only

  A GNM-derived, correlation-weighted 'FF score' can objectively define functionally flexible regions (FFRs) that match experimentally confirmed flexible/functional regions (hinges, recognition loops, catalytic loops).

  hiv bovine calmodulin nonredundant gaussian gnm support

• Computational disease gene identification: a concert of methods prioritizes type 2 diabetes and obesity candidate genes.

  PMID 16757574 · PMC1475747 · Nucleic acids research · 2006 · 6 claims · 8 setups

  Full-text index only

  Applying seven independent computational disease-gene prioritization methods in concert to 9556 positional candidate genes identifies a prioritized set of likely T2D and obesity candidate genes

  pubmed genes same randomly geneseeker evoc disease

• Systematic benchmarking of tools for CpG methylation detection from nanopore sequencing.

  PMID 34103501 · PMC8187371 · Nature communications · 2021 · 7 claims · 4 setups

  Has reproduction · 99

  Nanopore methylation detection tools exhibit a tradeoff between false positives and false negatives and high dispersion relative to expected per-site methylation frequencies.

  coli lymphoblastoid na12878 mixture nanopore cas9-targeted whole-genome

• Machine-learning approaches for classifying haplogroup from Y chromosome STR data.

  PMID 18551166 · PMC2396484 · PLoS computational biology · 2008 · 8 claims · 5 setups

  Full-text index only

  Y-STR allelic variability is partitioned more by differences among haplogroups than by differences among populations, suggesting Y-STRs carry haplogroup information

  globally same computational publicly y-str snp supervised

• Cancer-specific high-throughput annotation of somatic mutations: computational prediction of driver missense mutations.

  PMID 19654296 · PMC2763410 · Cancer research · 2009 · 7 claims · 7 setups

  Full-text index only

  CHASM, a Random Forest-based computational method, was developed to identify and prioritize missense mutations likely to be functional drivers of tumor cell proliferation.

  missense same synthetic tp53 random support principal

• Integration of Transcriptomics With Interpretable Artificial Intelligence for Identifying Molecular Signatures of Physiological Stress in Sleep Deprivation.

  PMID 42216239 · PMC13240488 · Journal of cellular and molecular medicine · 2026 · 8 claims · 8 setups

  Has reproduction · 49

  S100A3 is a robust candidate biomarker showing consistent discriminatory performance across the acute sleep deprivation training cohort, an independent sleep deprivation cohort, and a chronic insomnia cohort.

  peripheral blood normal integrated bulk interpretable immune

• Genome-wide prediction of DNase I hypersensitivity using gene expression.

  PMID 29051481 · PMC5715040 · Nature communications · 2017 · 6 claims · 3 setups

  Has reproduction · 79

  Gene expression substantially predicts genome-wide DNase I hypersensitivity (DH), demonstrating transcriptome-based prediction as a feasible approach for regulome mapping

  distinct encode dnase-seq exon computational

• SNiPer: improved SNP genotype calling for Affymetrix 10K GeneChip microarray data.

  PMID 16262895 · PMC1280925 · BMC genomics · 2005 · 8 claims · 5 setups

  Full-text index only

  Poorly performing SNPs (NoCall rate ≥25%) fail primarily due to inadequate training/localization of the MPAM statistical model call zone, not detection filter failure

  genomic genotype genotyped chromosomal snp clustering mendelian

• Logical Analysis of Data (LAD) model for the early diagnosis of acute ischemic stroke.

  PMID 18616825 · PMC2492849 · BMC medical informatics and decision making · 2008 · 7 claims · 5 setups

  Full-text index only

  An LAD classification model built from a support-set of 3 peptide peaks can distinguish stroke patients from controls with 75% accuracy on an independent validation set

  plasma discretized seldi-tof serum logical

• Topologically inferring pathway activity toward precise cancer classification via integrating genomic and metabolomic data: prostate cancer as a case.

  PMID 26286638 · PMC4541321 · Scientific reports · 2015 · 6 claims · 4 setups

  Has reproduction · 76

  DRW-GM integrates gene expression and metabolomic profiles via directed random walk on a global gene–metabolite pathway graph to weight genes by topological importance and infer reproducible pathway activities

  prostate global gene metabolomic computational

• Detection of venous thromboembolism by proteomic serum biomarkers.

  PMID 17579716 · PMC1891085 · PloS one · 2007 · 5 claims · 8 setups

  Full-text index only

  A neural network-based classifier built from direct MALDI-TOF MS serum protein expression profiles can diagnose VTE with sensitivity/specificity that exceeds D-dimer assays

  serum anova-selected citrated depleted direct artificial d-dimer

• 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

• Identification of deleterious non-synonymous single nucleotide polymorphisms using sequence-derived information.

  PMID 18588693 · PMC2446391 · BMC bioinformatics · 2008 · 8 claims · 5 setups

  Full-text index only

  A decision tree built on 10 selected sequence-derived features classifies SAPs as Disease or Polymorphism with 82.6% accuracy and 0.607 MCC in cross-validation.

  sap sequence-derived humvar same decision independent greedy

• Optimized mixed Markov models for motif identification.

  PMID 16749929 · PMC1534070 · BMC bioinformatics · 2006 · 8 claims · 4 setups

  Full-text index only

  OMiMa can incorporate more than NNSplice's pairwise dependencies

  simulated regulatory splice biological motif pairwise

• Combining evidence of preferential gene-tissue relationships from multiple sources.

  PMID 23950964 · PMC3741196 · PloS one · 2013 · 8 claims · 8 setups

  Has reproduction · 53

  A high-level integration approach combining three methods across four human microarray datasets, merged by consensus voting and a rule-based inner/total score, predicts preferentially expressed genes while reducing method- and study-specific bias.

  normal four microarray genes microarray computational bayes

• A temporal classifier predicts histopathology state and parses acute-chronic phasing in inflammatory bowel disease patients.

  PMID 36694043 · PMC9873918 · Communications biology · 2023 · 8 claims · 7 setups

  Has reproduction · 83

  The DSS phenotype-by-time interaction defines parsimonious temporal (dynamic) expression and splicing signatures of acute and chronic colitis distinct from time-specific differential expression.

  intestine colon dss distal bulk phenotypic h&e