Random_Intensity_30_3a: 30 Cases, 30 Controls, 300 Peaks

Brian T. Luke (lukeb@ncifcrf.gov)
Return to Description of Tables
PDF Version

BMDK Analysis

22 peaks selected as putative biomarkers by the 10 methods within BMDK

13           1   3    
26 5 3     2   1     3
51 3         5        
72   4         5     4
113 1 1 1 3 1 3 3 1   1
118           5        
125                 4  
136             4      
147     3 1   4     1  
168     4 2   2     2  
184         4          
208         3     3    
213   2         2   4 2
217     5         2    
227 2             3    
256                 4  
266   5   5           5
269         5          
271 4                  
272     2 4       3    
277                 3  
284                 4  

Peaks used in each of the best distance-dependent 6-nearest neighbor classifiers

13     X       X   X  
26                    
51                    
72                    
113   X                
118                    
125                    
136     X     X   X   X
147         X          
168     X       X   X  
184           X   X   X
208                    
213           X   X   X
217                    
227                    
256 X     X X          
266   X                
269                    
271                    
272                    
277                    
284                    

Sensitivity, specificity, %undetermined, and quality (sensitivity + specificity - %undetermined) for each of the best distance-dependent 6-nearest neighbor classifiers using any of the 22 putative biomarkers.

76.7 74.1 80.8 76.7 65.4 77.3 80.8 90.0 76.9 90.0
72.4 77.8 77.8 69.0 86.4 90.9 76.9 82.1 77.8 85.2
1.7 10.0 11.7 1.7 20.0 26.7 13.3 20.0 11.7 21.7
147.4 141.9 146.9 144.0 131.7 141.5 144.4 152.1 143.0 153.5

Sensitivity, specificity, %undetermined, and quality (sensitivity + specificity - %undetermined) for each of the best distance-dependent 6-nearest neighbor classifiers using any of the 22 putative biomarkers with the caveat that %undetermined cannot exceed 5.0%.

76.7 69.0 71.4 76.7 None None 72.4 None 72.4 None
72.4 70.0 79.3 69.0 None None 64.3 None 64.3 None
1.7 1.7 5.0 1.7 None None 5.0 None 5.0 None
147.4 137.3 145.7 144.0 None None 131.7 None 131.7 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.  The evolutionary programming search used a population size of 200 and ran for 400 generations.  A decision node became a terminal node when it contained 1% (no samples) or 4% (1 sample) of a given State.

Metric 1 1 4 4
1st 200th 1st 200th 1st 200th 1st 200th
Sensitivity 96.7 96.7 93.3 90.0 96.7 93.3 100.0 100.0
Specificity 93.3 93.3 100.0 100.0 100.0 100.0 96.7 93.3
Quality190.0 190.0 193.3 190.0 196.7 193.3 196.7 193.3

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.  The evolutionary programming search used a population size of 400 and ran for 800 generations with the requirement that there are at most 20 Case-cells and 20 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 100.0 100.0 100.0 93.3 100.0 100.0 100.0 100.0 100.0 100.0 100.0 96.7
Spec 100.0 90.0 100.0 100.0 100.0 96.7 100.0 100.0 100.0 100.0 100.0 100.0
Quality 200.0 190.0 200.0 193.3 200.0 196.7 200.0 200.0 200.0 200.0 200.0 196.7

(Last updated 4/21/07)