Table 4.
Performance of different multilabel classifiers with features derived from gene ontology and pathway information via a natural language processing approach.
| Scheme (base classifier) | Exact match | Accuracy | Hamming loss | Integrated score |
|---|---|---|---|---|
| RAKEL (RF) | 0.761 | 0.762 | 0.083 | 0.5324 |
| RAKEL (SVM-polynomial kernel) | 0.808 | 0.810 | 0.067 | 0.6106 |
| RAKEL (SVM-RBF kernel) | 0.808 | 0.810 | 0.068 | 0.6099 |
| BR (RF) | 0.584 | 0.584 | 0.087 | 0.3113 |
| BR (SVM-polynomial kernel) | 0.717 | 0.738 | 0.068 | 0.4931 |
| BR (SVM-RBF kernel) | 0.747 | 0.755 | 0.063 | 0.5284 |