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 the pathogenicity of missense variants using features derived from AlphaFold2.

  PMID 37084271 · PMC10203375 · Bioinformatics (Oxford, England) · 2023 · 6 claims · 8 setups

  Has reproduction · 85

  AlphaFold2-derived structural features (solvent accessibility, amino acid network features, physicochemical environment, pLDDT) can be used to train a random forest classifier (AlphScore) that distinguishes proxy-benign from proxy-pathogenic missense variants.

  gnomad alphafold2-predicted alphscore proteins machine secondary physicochemical

• Interaction profile-based protein classification of death domain.

  PMID 15189571 · PMC459208 · BMC bioinformatics · 2004 · 7 claims · 6 setups

  Full-text index only

  An SVM-based classifier using Residue Pair Interaction Profiles (RPIPs) can classify death domain superfamily members into subfamilies with 89% average cross-validation accuracy

  homology-modeled death homology putative rigid-body homology model

• Functional coverage of the human genome by existing structures, structural genomics targets, and homology models.

  PMID 16118666 · PMC1188274 · PLoS computational biology · 2005 · 8 claims · 5 setups

  Full-text index only

  Existing PDB structures provide single-domain coverage for 37% of functional classes in the human genome and complete (whole-protein) structure coverage for 25%.

  genome functional registered omim comparative kendall's homology

• Searching for interpretable rules for disease mutations: a simulated annealing bump hunting strategy.

  PMID 16984653 · PMC1618409 · BMC bioinformatics · 2006 · 8 claims · 6 setups

  Full-text index only

  The proposed feature set outperforms existing published feature sets for predicting effects of amino acid substitutions

  coli bacteriophage lac proteins svm simulated pearson

• Vertebrate gene finding from multiple-species alignments using a two-level strategy.

  PMID 16925840 · PMC1810555 · Genome biology · 2006 · 8 claims · 5 setups

  Full-text index only

  DOGFISH cleanly separates a multi-species alignment classifier (RVM cascade) from an HMM-based structure predictor, avoiding tight coupling of alignment complexity with HMM formalism

  genomic encode entire chromosome multi-species hmm-based classifier

• Applications for protein sequence-function evolution data: mRNA/protein expression analysis and coding SNP scoring tools.

  PMID 16912992 · PMC1538848 · Nucleic acids research · 2006 · 7 claims · 8 setups

  Full-text index only

  PANTHER HMMs built from family/subfamily multiple sequence alignments can classify novel protein sequences into functional groups based on statistically significant HMM match scores

  input gene genome-wide genes sequence gene numerical

• Prediction of catalytic residues using Support Vector Machine with selected protein sequence and structural properties.

  PMID 16790052 · PMC1534064 · BMC bioinformatics · 2006 · 8 claims · 7 setups

  Full-text index only

  The Sequential Minimal Optimization (SMO) SVM algorithm was the best-performing classifier among 26 WEKA classifiers for predicting catalytic residues

  benchmarking same pirsf pdb supervised wrapper sequence

• Predicting deleterious nsSNPs: an analysis of sequence and structural attributes.

  PMID 16630345 · PMC1489951 · BMC bioinformatics · 2006 · 8 claims · 7 setups

  Full-text index only

  Sequence conservation (PSIC score difference) at the nsSNP position is the single most useful attribute for predicting deleterious vs neutral status.

  swissprot nssnp-containing nssnps machine single-attribute sequence

• Accurate splice site prediction using support vector machines.

  PMID 18269701 · PMC2230508 · BMC bioinformatics · 2007 · 8 claims · 5 setups

  Full-text index only

  Weighted degree (WD) kernel SVMs outperform Markov Chains, GeneSplicer and SpliceMachine for genome-wide splice site recognition

  nn269 dgsplicer caenorhabditis arabidopsis svm genome-wide

• Optimality driven nearest centroid classification from genomic data.

  PMID 17912341 · PMC1991588 · PloS one · 2007 · 7 claims · 5 setups

  Full-text index only

  A theoretical result determines the subset of features of a given size that minimizes the misclassification rate for a nearest-centroid (LDA) classifier, based on equation (4).

  artificial simulated previously-published simulated simulation clinical

• The DAVID Gene Functional Classification Tool: a novel biological module-centric algorithm to functionally analyze large gene lists.

  PMID 17784955 · PMC2375021 · Genome biology · 2007 · 8 claims · 6 setups

  Full-text index only

  Gene-gene functional similarity can be measured using kappa statistics applied to a binary gene-annotation-term matrix built from 14 annotation categories.

  genome protein-protein genes artificial kappa clustering gene

• Uncovering information on expression of natural antisense transcripts in Affymetrix MOE430 datasets.

  PMID 17598913 · PMC1929078 · BMC genomics · 2007 · 8 claims · 4 setups

  Full-text index only

  Standard Affymetrix expression GeneChips (MOE430, HG-U133) contain probe sets that detect natural antisense transcripts (NATs)

  moe430 pooled organs probe strand-specific microarray

• CanPredict: a computational tool for predicting cancer-associated missense mutations.

  PMID 17537827 · PMC1933186 · Nucleic acids research · 2007 · 8 claims · 7 setups

  Full-text index only

  CanPredict is a web application providing public access to a random forest classifier that combines SIFT, LogR.E-value, and GOSS scores to predict whether a missense mutation is cancer-associated

  missense observed sjoblom refseq cross-validation recurrence comparative

• 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

• Peptide bioinformatics: peptide classification using peptide machines.

  PMID 19065810 · PMC7122642 · Methods in molecular biology (Clifton, N.J.) · 2008 · 8 claims · 4 setups

  Full-text index only

  The bio-basis function, which converts peptides into numerical vectors using nongapped pairwise homology alignment scores against indicator peptides, can statistically quantify peptide similarity for classification.

  illustrative query generic synthetic bio-basis orthogonal hyperplane

• A general definition and nomenclature for alternative splicing events.

  PMID 18688268 · PMC2467475 · PLoS computational biology · 2008 · 6 claims · 4 setups

  Full-text index only

  Existing AS nomenclatures (Malko et al.'s 5-letter strings, Nagasaki et al.'s bit matrices, and the ASD/ATD/AEdb system) are redundant, ambiguous, or incapable of representing complex or large splicing variations.

  refseq reference metazoan example computational comparative

• 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

• Improving melanoma classification by integrating genetic and morphologic features.

  PMID 18532874 · PMC2408611 · PLoS medicine · 2008 · 7 claims · 5 setups

  Full-text index only

  BRAF-mutant melanomas show distinct morphological features (upward migration and nesting of intraepidermal melanocytes, epidermal thickening, sharper lateral demarcation, larger/rounder/more pigmented tumor cells) compared to non-mutant melanomas

  archival same subset patients histopathological mutation quantitative

• Needles in the haystack: identifying individuals present in pooled genomic data.

  PMID 19798441 · PMC2747273 · PLoS genetics · 2009 · 8 claims · 7 setups

  Full-text index only

  The distribution of T for null samples (individuals not in F or G) deviates strongly from the assumed standard normal, in both location and width.

  cgems hapmap genetic-distance within-population snp-count

• 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