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).

• Enhanced Generalizability of RNA Secondary Structure Prediction via Convolutional Block Attention Network and Ensemble Learning.

  PMID 40871599 · PMC12388828 · Molecules (Basel, Switzerland) · 2025 · 8 claims · 8 setups

  Has reproduction · 87

  TrioFold integrates base-pairing clues from thermodynamic- and DL-based methods via ensemble learning and a convolutional block attention mechanism to enhance RSS prediction generalizability.

  testseta bprna-new ts-inter individual jaccard pca ensemble

• VIRGO: computational prediction of gene functions.

  PMID 16845022 · PMC1538839 · Nucleic acids research · 2006 · 8 claims · 6 setups

  Full-text index only

  VIRGO constructs a functional linkage network (FLN) from gene expression and molecular interaction data, labels genes with GO annotations, and propagates these labels to predict functions of unlabelled genes

  cerevisiae sapiens leave-one-out gene protein-protein

• Species-specific protein sequence and fold optimizations.

  PMID 12487631 · PMC139977 · BMC bioinformatics · 2002 · 7 claims · 7 setups

  Full-text index only

  Environmental niche is a significant factor explaining variability in amino acid composition across 100 complete genomes

  predicted mean over orf principal hierarchical domain-based

• Protein structure quality assessment based on the distance profiles of consecutive backbone Cα atoms.

  PMID 24555103 · PMC3892923 · F1000Research · 2013 · 8 claims · 8 setups

  Has reproduction · 71

  The distance between consecutive backbone Cα atoms in high-quality structures is normally distributed with mean 3.8 Å and standard deviation 0.04 Å, justifying a reference state in which all consecutive Cα atoms are 3.8 Å apart.

  top100h decoys i-tasser non-homologous statistical rdcc comparative

• Does distance matter? Variations in alternative 3' splicing regulation.

  PMID 17704130 · PMC2018619 · Nucleic acids research · 2007 · 8 claims · 7 setups

  Full-text index only

  Alternative 3' splice sites can be distinguished from constitutive splice sites by a combination of sequence/conservation properties that vary depending on the distance between the splice sites.

  intronic human-mouse same comparative polypyrimidine branch

• A computational screen for type I polyketide synthases in metagenomics shotgun data.

  PMID 18953415 · PMC2568958 · PloS one · 2008 · 8 claims · 6 setups

  Full-text index only

  Combining HMM domain searches with maximum-likelihood phylogenetic trees can discriminate true PKS I sequences from evolutionarily related but functionally different enzymes (e.g., FAS I) in metagenomic data.

  predicted hmm-identified reference hmm hmm maximum-likelihood robinson-foulds

• Prodepth: predict residue depth by support vector regression approach from protein sequences only.

  PMID 19759917 · PMC2742725 · PloS one · 2009 · 8 claims · 8 setups

  Full-text index only

  Residue depth can be reliably predicted solely from protein primary sequence using support vector regression on sequence-derived features.

  structure sequences sequence residue dssp psi-blast

• Prediction of candidate primary immunodeficiency disease genes using a support vector machine learning approach.

  PMID 19801557 · PMC2780952 · DNA research : an international journal for rapid publication of reports on genes and genomes · 2009 · 6 claims · 3 setups

  Full-text index only

  An SVM trained on 69 binary features of known PID genes can accurately classify PID vs non-PID genes and predict novel candidate PID genes

  genome training svm support leave-one-out sensitivity

• A map of human protein interactions derived from co-expression of human mRNAs and their orthologs.

  PMID 18414481 · PMC2387231 · Molecular systems biology · 2008 · 8 claims · 6 setups

  Full-text index only

  Comparing human mRNA co-expression with co-expression of orthologous gene pairs in five other organisms identifies proteins that physically associate

  genes hela proteins worm co-expression quantitative functional

• Correlating novel variable and conserved motifs in the Hemagglutinin protein with significant biological functions.

  PMID 18681973 · PMC2553082 · Virology journal · 2008 · 8 claims · 6 setups

  Full-text index only

  14 MEME blocks were identified in the HA protein of H3N2 strains (1968-1999), with blocks 1, 2, 3, and 7 correlating with several biological functions

  h3n2 meme sequence entropy

• Machine learning and free energy clustering reveal PAH protein binding linked to AD risk.

  PMID 41953002 · PMC13053772 · iScience · 2026 · 7 claims · 8 setups

  Has reproduction · 78

  An integrated framework of bioinformatics, machine learning, and ΔG clustering can prioritize PAHs for AD-associated neurotoxicity.

  proteins microarray ad-associated pahs target differential wgcna

• Whole genome association mapping by incompatibilities and local perfect phylogenies.

  PMID 17042942 · PMC1624851 · BMC bioinformatics · 2006 · 8 claims · 8 setups

  Full-text index only

  Blossoc scores the perfect phylogenetic tree spanning the largest compatible region around each marker as a decision tree for case/control status to detect association

  coalescent-simulated artificial empirical same perfect-phylogeny hapminer haplotype

• Web-based resources for comparative genomics.

  PMID 16197736 · PMC3525128 · Human genomics · 2005 · 8 claims · 8 setups

  Full-text index only

  Comparative genomics is an indispensable tool for identifying functional genome elements and exploring evolutionary genome dynamics

  yeast chimpanzee mammalian protein-coding comparative genome maximum-likelihood

• Assessment tool based on fatty acid metabolic signatures for predicting the prognosis and treatment response in bladder cancer.

  PMID 38076064 · PMC10703629 · Heliyon · 2023 · 8 claims · 8 setups

  Has reproduction · 71

  Consensus clustering of prognosis-related fatty acid metabolism genes (FAMGs) identifies three molecular subtypes of BLCA (FAMC1, FAMC2, FAMC3) with distinct prognoses and tumor microenvironments

  tcga-blca famc1-3 differentially gse32894 bulk consensus gene

• Reconstructing the genomic architecture of mammalian ancestors using multispecies comparative maps.

  PMID 15601531 · PMC3525001 · Human genomics · 2003 · 8 claims · 4 setups

  Full-text index only

  The MGR algorithm applied to human, mouse, cat and cattle comparative maps can impute an ancestral mammalian genome composed of conserved segments.

  cat mammalian genome grimm-synteny comparative

• Automatic annotation of eukaryotic genes, pseudogenes and promoters.

  PMID 16925832 · PMC1810547 · Genome biology · 2006 · 8 claims · 6 setups

  Full-text index only

  Fgenesh++ gene prediction pipeline identifies 91% of coding nucleotides with 90% specificity

  encode regions genes chromosome computational pseudogene promoter

• Comparative metagenomics revealed commonly enriched gene sets in human gut microbiomes.

  PMID 17916580 · PMC2533590 · DNA research : an international journal for rapid publication of reports on genes and genomes · 2007 · 7 claims · 7 setups

  Full-text index only

  Adult and weaned-children gut microbiota show high functional (gene-content) uniformity despite taxonomic differences, while unweaned infant microbiota show high inter-individual variation in both taxonomic and gene composition.

  fecal assembled predicted gut whole-genome gene reciprocal

• In silico whole-genome screening for cancer-related single-nucleotide polymorphisms located in human mRNA untranslated regions.

  PMID 17201911 · PMC1774567 · BMC genomics · 2007 · 8 claims · 5 setups

  Full-text index only

  A computational EST-based pipeline can identify UTR-SNPs that are statistically over-represented in cancerous versus normal tissue libraries

  est acute 100-nt whole-genome est-based pcr-based secondary

• SysZNF: the C2H2 zinc finger gene database.

  PMID 18974185 · PMC2686507 · Nucleic acids research · 2009 · 7 claims · 6 setups

  Full-text index only

  SysZNF is a database that systematically catalogs C2H2-ZNF genes in human and mouse with physical location, gene models, expression probes, protein domains, homologs, and literature links

  user-defined hmm domain all-to-all

• OptiType: precision HLA typing from next-generation sequencing data.

  PMID 25143287 · PMC4441069 · Bioinformatics (Oxford, England) · 2014 · 8 claims · 8 setups

  Has reproduction · 95

  OptiType, an ILP-based HLA genotyping algorithm, produces accurate four-digit HLA-I predictions from NGS data not enriched for the HLA cluster.

  colorectal lymphoblastic hapmap genomes rna-seq low-coverage exome