Table 4.
Training performance values obtained by the validation of naïve Bayes and BERT classifiers trained with the FlyBase, ZFIN and MGI data sets
Naïve Bayes (10-fold cv) | BERT (train/test split 80:20) | |||||
---|---|---|---|---|---|---|
DB name | FlyBase | ZFIN | MGI | FlyBase | ZFIN | MGI |
Precision | 0.97 | 0.97 | 0.98 | 0.98 | 0.97 | 0.94 |
Recall | 0.82 | 0.75 | 0.85 | 0.97 | 0.94 | 0.98 |
F-measure | 0.89 | 0.84 | 0.91 | 0.97 | 0.95 | 0.96 |