Table 2.

Performance for gene mention normalization for mouse, yeast, and fruit fly datasets

Short description of the submitted run	Precision	Recall	F measure (%)	True positives (n)	False positives (n)	False negatives (n)
Mouse, training set	86.6	69.2	77.0	322	50	143
Yeast, training set	89.0	84.0	86.4	219	27	42
Fly, training set	87.9	55.6	68.1	124	17	99
Mouse, test set	91.6	72.6	81.0	355	36	149
Yeast, test set	94.9	84.8	89.6	520	28	93
Fly, test set	82.1	69.5	75.3	298	65	131

Current performance of the gene mention normalization component on the BioCreative I gene normalization sets. Each run includes an extended gene name lexicon (based on BioCreative I data and with additional synonyms from EntrezGene), all false positive filters, and the disambiguation.