Classifier | ReliefF | SVM | Wrapper | All pathways | Random |
---|
J48 | 0.50 | 0.00 | 0.00 | 0.00 | 0.01 |
 | (0.68) | (0.68) | (0.36) | (0.25) | (0.29) |
IB1 | 0.75 | 0.75 | 0.74 | 0.50 | 0.08 |
 | (0.75) | (0.50) | (0.75) | (0.18) | (0.28) |
Naïve Bayes | 0.65 | 0.50 | 0.72 | 0.50 | 0.05 |
 | (0.61) | (0.75) | (0.75) | (0.45) | (0.29) |
SMO | 0.00 | 0.75 | 0.00 | 0.25 | 0.00 |
 | (0.75) | (0.68) | (0.36) | (0.50) | (0.11) |
- The 266 (15 oral cavity) genomes of the complete data set were classified into genomes related and not related to periodontal disease using only ten (eight in the case of wrapper) most relevant pathways derived by the three attribute selection methods. We applied four different classifiers (J48, IB1, naïve Bayes, and SMO) with tenfold cross-validation. In addition, the genomes were classified based on all pathways (290) in the pathway profile as well as on ten randomly chosen pathways. To estimate the quality of classification, we calculated the product of classification selectivity and sensitivity, which is shown in this table. In the case of randomly chosen pathways, the value was derived by averaging the classification quality of 25 sets of 10 randomly chosen pathways. The data in parentheses are for the dataset containing the 15 oral cavity genomes.