Skip to main content

Table 1 Members of the UAG represent a diverse sample of end users with multiple text mining needs

From: BioCreative III interactive task: an overview

Domains represented by UAG members and Chair*

Model Organism Databases

dictyBase, MGI, TAIR, Gramene, Wormbase

Protein Sequence Databases

UniProtKB

Protein-Protein Interaction Databases

BioGrid, MINT

Ontologies

Gene Ontology, Protein Ontology, Plant Ontology, Microbial Phenotype Ontology

Pharmaceutical Companies

Dupont, Merck KGaA, Pfizer

Examples of text mining needs among UAG members

â–¡ gene normalization

â–¡ mapping to ontologies (e.g., GO, PO, PRO) either for annotation or semantic integration

â–¡ entity normalization and relevance scoring to help automate relationship extraction and data integration of text mined facts with external and internal sources

Identification of articles:

â–¡ related to a specific topic (PPI, biomarkers)

â–¡ reporting experimental information for gene/proteins in a given organism

â–¡ with experimental characterization of gene/protein with associated reporting of organism and gene normalization when available

â–¡ new articles not yet in the database

  1. *Note that some members represent more than one resource