Random_Intensity_300_2a: 300 Cases, 300 Controls, 300 Peaks
Brian T. Luke (lukeb@ncifcrf.gov)Return to Description of Tables
BMDK Analysis
31 peaks selected as putative biomarkers by the 10 methods within BMDK
| Peak | catboot | student | dtgini | dtinfg | nnfeat | chisq | kruswal | kolsmir | extreme | yip |
| 7 | 5 | |||||||||
| 9 | 3 | |||||||||
| 25 | 4 | 4 | 5 | 4 | ||||||
| 28 | 5 | |||||||||
| 50 | 5 | |||||||||
| 57 | 5 | |||||||||
| 79 | 4 | |||||||||
| 82 | 5 | |||||||||
| 97 | 3 | 3 | 2 | 5 | ||||||
| 105 | 4 | |||||||||
| 111 | 4 | |||||||||
| 120 | 5 | |||||||||
| 148 | 5 | |||||||||
| 156 | 5 | |||||||||
| 172 | 1 | 1 | 1 | 1 | 1 | 1 | ||||
| 178 | 2 | 3 | 2 | |||||||
| 187 | 1 | |||||||||
| 188 | 5 | |||||||||
| 192 | 1 | 5 | 2 | 2 | 5 | 1 | 3 | 5 | ||
| 197 | 3 | 5 | 1 | |||||||
| 222 | 3 | |||||||||
| 226 | 4 | 4 | ||||||||
| 227 | 4 | |||||||||
| 228 | 3 | 2 | 3 | |||||||
| 235 | 2 | 2 | ||||||||
| 255 | 3 | |||||||||
| 257 | 1 | |||||||||
| 261 | 4 | 5 | ||||||||
| 264 | 3 | |||||||||
| 281 | 2 | |||||||||
| 286 | 5 |
Peaks used in each of the best distance-dependent 6-nearest neighbor classifiers
| Peak | 1-ad | 2-ad | 3-ad | 1-rd | 2-rd | 3-rd | 2-cr | 3-cr | 2-sd | 3-sd |
| 7 | ||||||||||
| 9 | ||||||||||
| 25 | X | X | ||||||||
| 28 | ||||||||||
| 50 | X | |||||||||
| 57 | ||||||||||
| 79 | ||||||||||
| 82 | ||||||||||
| 97 | X | X | X | X | X | |||||
| 105 | X | X | ||||||||
| 111 | X | |||||||||
| 120 | ||||||||||
| 148 | ||||||||||
| 156 | ||||||||||
| 172 | ||||||||||
| 178 | X | |||||||||
| 187 | ||||||||||
| 188 | ||||||||||
| 192 | ||||||||||
| 197 | ||||||||||
| 222 | ||||||||||
| 226 | X | |||||||||
| 227 | X | |||||||||
| 228 | X | |||||||||
| 235 | ||||||||||
| 255 | ||||||||||
| 257 | X | X | ||||||||
| 261 | ||||||||||
| 264 | ||||||||||
| 281 | X | X | X | X | X | |||||
| 286 |
Sensitivity, specificity, %undetermined, and quality (sensitivity + specificity - %undetermined) for each of the best distance-dependent 6-nearest neighbor classifiers using any of the 31 putative biomarkers.
| Metric | 1-ad | 2-ad | 3-ad | 1-rd | 2-rd | 3-rd | 2-cr | 3-cr | 2-sd | 3-sd |
| Sens | 54.0 | 63.2 | 65.6 | 54.2 | 64.9 | 58.5 | 61.5 | 61.6 | 61.4 | 60.5 |
| Spec | 56.7 | 58.2 | 56.9 | 57.4 | 53.8 | 61.9 | 58.9 | 59.5 | 57.9 | 60.3 |
| %Undet | 0.0 | 0.3 | 0.3 | 0.8 | 7.2 | 20.7 | 0.3 | 11.3 | 0.5 | 11.2 |
| Quality | 110.7 | 121.1 | 122.1 | 110.8 | 111.5 | 99.8 | 120.1 | 109.7 | 118.8 | 109.7 |
Sensitivity, specificity, %undetermined, and quality (sensitivity + specificity - %undetermined) for each of the best distance-dependent 6-nearest neighbor classifiers using any of the 31 putative biomarkers with the caveat that %Undetermined cannot exceed 5.0%.
| Metric | 1-ad | 2-ad | 3-ad | 1-rd | 2-rd | 3-rd | 2-cr | 3-cr | 2-sd | 3-sd |
| Sens | 54.0 | 63.2 | 65.6 | 54.2 | 56.4 | None | 61.5 | None | 61.4 | None |
| Spec | 56.7 | 58.2 | 56.9 | 57.4 | 53.4 | None | 58.9 | None | 57.9 | None |
| %Undet | 0.0 | 0.3 | 0.3 | 0.8 | 5.0 | None | 0.3 | None | 0.5 | None |
| Quality | 110.7 | 121.1 | 122.1 | 110.8 | 104.8 | None | 120.1 | None | 118.8 | None |
Fingerprint Analysis
Sensitivity, specificity and quality (sensitivity + specificity) for the best and 200th best decision tree constructed from any of the 300 peak intensities.Ê The evolutionary programming search used a population size of 400 and ran for 800 generations.Ê A decision node became a terminal node when it contained 1% (3 samples) or 4% (12 samples) of a given State.
| Metric | 1% | 1% | 4% | 4% | ||||
| 1st | 200th | 1st | 200th | 1st | 200th | 1st | 200th | |
| Sensitivity | 67.0 | 67.7 | 67.7 | 66.3 | 72.7 | 71.3 | 76.3 | 70.7 |
| Specificity | 70.0 | 68.3 | 68.7 | 69.0 | 64.3 | 64.3 | 61.3 | 65.7 |
| Quality | 137.0 | 136.0 | 136.3 | 135.0 | 137.0 | 135.7 | 137.7 | 136.3 |
Sensitivity, specificity and quality (sensitivity + specificity) for the best and 200th best medoid classifier algorithm in each of the two runs using 5-, 6-, and 7-peak intensities from the set of 300.Ê The evolutionary programming search used a population size of 1000 and ran for 2000 generations with the requirement that there are at most 200 Case-cells and 200 Control-cells.
| Metric | 5-Features | 5-Features | 6-Features | 6-Features | 7-Features | 7-Features | ||||||
| 1st | 200th | 1st | 200th | 1st | 200th | 1st | 200th | 1st | 200th | 1st | 200th | |
| Sens | 100.0 | 100.0 | 69.3 | 63.3 | 100.0 | 100.0 | 79.0 | 72.7 | 100.0 | 100.0 | 80.3 | 75.7 |
| Spec | 69.7 | 63.3 | 100.0 | 100.0 | 75.3 | 71.3 | 100.0 | 100.0 | 78.7 | 74.0 | 100.0 | 100.0 |
| Quality | 169.7 | 163.3 | 169.3 | 163.3 | 175.3 | 171.3 | 179.0 | 172.7 | 178.7 | 174.0 | 180.3 | 175.7 |
(Last updated 4/21/07)
