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).

• Application of Machine Learning in Predicting Hepatic Metastasis or Primary Site in Gastroenteropancreatic Neuroendocrine Tumors.

  PMID 37887568 · PMC10605255 · Current oncology (Toronto, Ont.) · 2023 · 8 claims · 7 setups

  Has reproduction · 59

  Multi-gene random forest models classify primary tumor vs. liver metastasis samples with 100% accuracy in training/test cohorts and >90% accuracy in an independent validation cohort

  pancreatic rna-seq liver tumor bulk machine multi-label

• MiPred: classification of real and pseudo microRNA precursors using random forest prediction model with combined features.

  PMID 17553836 · PMC1933124 · Nucleic acids research · 2007 · 8 claims · 8 setups

  Full-text index only

  A hybrid feature combining local contiguous triplet structure-sequence composition, MFE of the secondary structure, and P-value of a randomization test improves classification of real vs pseudo pre-miRNAs

  real combined pre-mirna training random independent repeated

• Speeding disease gene discovery by sequence based candidate prioritization.

  PMID 15766383 · PMC1274252 · BMC bioinformatics · 2005 · 7 claims · 8 setups

  Full-text index only

  Disease genes (OMIM) differ significantly from non-disease genes in sequence-based features including gene/cDNA/protein size, exon number, homolog conservation, secretion signal, 3' UTR length, CpG islands, and distance to nearest gene.

  ensembl training same hgmd comparative machine tenfold

• 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

• Hierarchical classification-based pan-cancer methylation analysis to classify primary cancer.

  PMID 38066424 · PMC10709847 · BMC bioinformatics · 2023 · 8 claims · 5 setups

  Has reproduction · 83

  CHCT, a hierarchical classification tool, splits classification of 30 cancer types into ten smaller subproblems using a two-tier architecture to classify primary cancer by methylation profile

  cancer clinical training independent methylation upgma random

• Predicting the phenotypic effects of non-synonymous single nucleotide polymorphisms based on support vector machines.

  PMID 18005451 · PMC2216041 · BMC bioinformatics · 2007 · 8 claims · 5 setups

  Full-text index only

  Parepro, an SVM-based method integrating three attribute sets (RD, MI, IE) derived from evolutionary and residue-property information, predicts whether an nsSNP is deleterious or neutral.

  sequences target svm benchmark homology

• 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

• Molecular Classification Models for Triple Negative Breast Cancer Subtype Using Machine Learning.

  PMID 34575658 · PMC8472680 · Journal of personalized medicine · 2021 · 6 claims · 4 setups

  Has reproduction · 86

  A training gene set of 719 unique upregulated DEGs (subtype-specific) can be used to build ML models that classify TNBC into BLIA, BLIS, MES, and LAR subtypes.

  known tnbc unique unknown gene machine term

• Classification of real and pseudo microRNA precursors using local structure-sequence features and support vector machine.

  PMID 16381612 · PMC1360673 · BMC bioinformatics · 2005 · 7 claims · 7 setups

  Full-text index only

  A 32-dimensional triplet structure-sequence feature vector combined with SVM (triplet-SVM) can distinguish real human pre-miRNAs from pseudo pre-miRNA hairpins with ~90% accuracy.

  pre-mirnas test conserved-hairpin cross-species secondary svm cross-species

• Metagenomic analysis of human diarrhea: viral detection and discovery.

  PMID 18398449 · PMC2290972 · PLoS pathogens · 2008 · 8 claims · 7 setups

  Full-text index only

  Micro-mass sequencing (minimal stool input, minimal purification, ~384 reads/sample) can detect known enteric viruses in diarrhea specimens

  stool divergent extract preparations sequence-independent maximum enzyme

• CLEAN: CLustering Enrichment ANalysis.

  PMID 19640299 · PMC2734555 · BMC bioinformatics · 2009 · 8 claims · 4 setups

  Full-text index only

  The gene-specific CLEAN score improves reproducibility of cluster analysis conclusions across independent datasets compared to the traditional cluster-wide score (cwCLEAN).

  four breast combined hierarchical cluster csimm-based

• An SVM-based system for predicting protein subnuclear localizations.

  PMID 16336650 · PMC1325059 · BMC bioinformatics · 2005 · 7 claims · 3 setups

  Full-text index only

  New kernels defined on k-peptide vectors mapped by BLOSUM62-based high-scored pair matrices (D1, D2, D3) improve SVM discrimination of protein subnuclear localization compared to conventional k-peptide encodings.

  single-localization multi-localization same svm sequence

• 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

• Swarm intelligence based wavelet coefficient feature selection for mass spectral classification: an application to proteomics data.

  PMID 19733729 · PMC2748225 · Analytica chimica acta · 2009 · 8 claims · 4 setups

  Full-text index only

  ACA-based wavelet coefficient feature selection can achieve up to 100% classification accuracy on training, validating, and independent testing sets using only 5 selected features.

  blood baseline-corrected 953-dimensional training seldi-tof wavelet ant

• SNAP: predict effect of non-synonymous polymorphisms on function.

  PMID 17526529 · PMC1920242 · Nucleic acids research · 2007 · 7 claims · 8 setups

  Full-text index only

  SNAP, a neural network-based method using sequence-derived information, predicts whether a non-synonymous SNP is neutral or non-neutral for protein function

  combined escherichia bacteriophage hiv-1 neural benchmark comparative

• Prediction of Antimicrobial Resistance in Gram-Negative Bacteria From Whole-Genome Sequencing Data.

  PMID 32528441 · PMC7262952 · Frontiers in microbiology · 2020 · 8 claims · 4 setups

  Has reproduction · 100

  WGS data enables prediction of antimicrobial resistance in Gram-negative bacteria using machine learning

  baumannii gram-negative in-house cchmc whole-genome xgboost antimicrobial

• Interaction preferences across protein-protein interfaces of obligatory and non-obligatory components are different.

  PMID 16105176 · PMC1201154 · BMC structural biology · 2005 · 8 claims · 5 setups

  Full-text index only

  Interaction patterns across obligatory and non-obligatory interfaces are different, with obligatory contacts predominantly non-polar

  pdb obligatory same psi-blast solvent residue

• Utah's Family High Risk Program: bridging the gap between genomics and public health.

  PMID 15888235 · PMC1327718 · Preventing chronic disease · 2005 · 8 claims · 6 setups

  Full-text index only

  Collection of family history through the Family High Risk Program (FHRP) is a cost-effective method for identifying and intervening with high-risk populations for chronic disease

  high high-risk fhrp health family-based satisfaction

• Bayesian prediction of microbial oxygen requirement.

  PMID 26913185 · PMC4743139 · F1000Research · 2013 · 7 claims · 8 setups

  Has reproduction · 76

  A naive Bayesian classifier based on presence/absence of class-associated Pfam-A domains can distinguish three oxygen requirement classes (aerobe, anaerobe, facultative anaerobe) from genome sequence, unlike prior studies that only made pairwise distinctions.

  bacterial selected predicted pfam-a genome gene domain

• Up regulation in gene expression of chromatin remodelling factors in cervical intraepithelial neoplasia.

  PMID 18248679 · PMC2277413 · BMC genomics · 2008 · 8 claims · 4 setups

  Full-text index only

  Chromatin remodelling-associated genes SMARCC1, NCOR1, MRFAP1 and MORF4L2 are upregulated during progression of cervical intraepithelial neoplasia

  cervical independent computational long real-time gene