Figure 1.

Extraction and grounding framework. Full-text documents (1) are run through a GATE pipeline with gazetteers derived from Swiss-Prot (2) and created with MutationFinder (3). Mutations and proteins are grounded (4). Protein properties are extracted with use of MuNPEx and custom JAPE rules (5) and grounded to the Gene Ontology when applicable. The impact extractor (6) makes use of the previous annotations to establish relations between mutants and impacts on protein properties. The output consists of annotated text (8).

Laurila et al. BMC Genomics 2010 11(Suppl 4):S24   doi:10.1186/1471-2164-11-S4-S24