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).

• PolySearch: a web-based text mining system for extracting relationships between human diseases, genes, mutations, drugs and metabolites.

  PMID 18487273 · PMC2447794 · Nucleic acids research · 2008 · 8 claims · 7 setups

  Full-text index only

  PolySearch supports more than 50 different classes of queries against nearly a dozen types of text, abstract, or bioinformatic databases

  manually biomedical text feature real-life

• Mapping proteins to disease terminologies: from UniProt to MeSH.

  PMID 18460185 · PMC2367626 · BMC bioinformatics · 2008 · 8 claims · 7 setups

  Full-text index only

  Developed a three-step procedure (disease name extraction, exact matching, partial/similarity-based matching) to map UniProtKB/Swiss-Prot disease names to MeSH terms

  randomly swiss-prot uniprotkb mesh manual exact partial

• Feature selection and nearest centroid classification for protein mass spectrometry.

  PMID 15788095 · PMC1274262 · BMC bioinformatics · 2005 · 8 claims · 5 setups

  Full-text index only

  Sequential forward selection and a novel boosted feature selection algorithm produce the most consistent classification results across all five cancer data sets tested

  serum seldi-tof