Table 4 Accuracy percentiles and characteristics of models from 50 cross-validation samples of DS2, 700 <m/z < 12000
From: Performance of a genetic algorithm for mass spectrometry proteomics
Algorithm | Test Set Accuracy 25th, 75th | Median # Clusters | Median # Markers | Proportion of Perfect Chromosomes |
|---|---|---|---|---|
GA(p1 = 0, p2 = 0) | .70, .80 | 91.5 | 17 | 1.0 |
GA(0, .001) | .63, .75 | 100 | 11 | 1.0 |
GA(0, .002) | .61, .74 | 100 | 10 | 1.0 |
GA(.002, 0) | .89, .93 | 22.5 | 19.5 | .86 |
GA(.002, .001) | .88, .93 | 22 | 14.5 | .90 |
GA(.002, .002) | .87, .91 | 22 | 8 | .86 |
GA(.005, 0) | .88, .93 | 7 | 19 | .20 |
GA(.005, .001) | .88, .93 | 7 | 11 | .20 |
GA(.005, .002) | .87, .93 | 7 | 6 | .16 |
GA(.008, 0) | .86, .91 | 5 | 18 | .02 |
GA(.008, .001) | .86, .91 | 5 | 10 | .04 |
GA(.008, .002) | .86, .91 | 5 | 4 | .02 |
Best GA | .88, .93 | 7 | 12 | .24 |
Boosting | .92, .95 | NA | NA | NA |
PAM | .83, .86 | NA | NA | NA |