Figure 1.

IAA statistics for ChEBI and GO BP/MF, and GO CC markup. Plot of IAA versus number of training sessions/meetings (approximately weekly) for annotation of the corpus with the ChEBI ontology, GO BP & MF, and CC. IAA has been calculated as F-score, which is the harmonic mean of precision and recall.

Bada et al. BMC Bioinformatics 2012 13:161   doi:10.1186/1471-2105-13-161
Download authors' original image