This is a summary of a set of 1 experiments using a LONI pipeline workflow file that performs 3000 independent jobs, each one with the CBDA-SL and the knockoff filter feature mining strategies. Each experiments has a total of 9000 jobs and is uniquely identified by 6 input arguments: # of jobs [M], % of missing values [misValperc], min [Kcol_min] and max [Kcol_max] % for FSR-Feature Sampling Range, min [Nrow_min] and max [Nrow_max] % for SSR-Subject Sampling Range.
This document has the final results, by experiment. See https://drive.google.com/file/d/0B5sz_T_1CNJQWmlsRTZEcjBEOEk/view?ths=true for some general documentation of the CBDA-SL project and github https://github.com/SOCR/CBDA for some of the code.
Features selected by both the knockoff filter and the CBDA-SL algorithms are shown as spikes in the histograms shown below. I list the top features selected, set to 15 here.
## [1] EXPERIMENT 1
## M misValperc Kcol_min Kcol_max Nrow_min Nrow_max
## 9000 0 5 15 60 80
## [1] 90 900
## [1] 1 100 200 300 400 500 600 700 800 900
## [1] 300 1501
## [1] "TABLE with CBDA-SL & KNOCKOFF FILTER RESULTS"
## CBDA Frequency Density Knockoff Density
## 800 22 0.4843681 800 21.219598
## 700 18 0.3963012 900 12.442721
## 353 14 0.3082343 400 12.266479
## 200 13 0.2862175 1 6.520973
## 44 12 0.2642008 840 5.992245
## 249 12 0.2642008 8 3.489602
## 472 12 0.2642008 808 3.172365
## 877 12 0.2642008 200 2.361650
## 6 11 0.2421841 471 1.797674
## 96 11 0.2421841 34 1.691928
## 129 11 0.2421841 700 1.480437
## 321 11 0.2421841 415 1.374692
## 415 11 0.2421841 737 1.339443
## 500 11 0.2421841 100 1.268946
## 741 11 0.2421841 317 1.092704
## [1] "Nonzero Features"
## [1] 1 100 200 300 400 500 600 700 800 900
## [1] "Top Features Selected across multiple experiments,shared between CBDA-SL and Knockoff filter"
## [1] 800 700 353 200 44 249 472 877 6 96 129 321 415 500 741 900 400
## [18] 1 840 8 808 471 34 737 100 317
The features listed above are then used to run a final analysis applying both the CBDA-SL and the knockoff filter. The ONLY features used for analysis are the ones listed above. A final summary of the accuracy of the overall procedure is determined by using the CDBA-SL object on the subset of subjects held off for prediction. The predictions are then used to generate the confusion matrix. We basically combine the CBDA-SL & Knockoff Filter algorithms to first select the top features during the first round. Then, the second stage uses the top features to run a final predictive modeling step that can ultimately be tested for accuracy, sensitivity,…..