Ensemble Methods with Voting Protocols Exhibit Superior Performance for Predicting Cancer Clinical Endpoints and Providing More Complete Coverage of Disease-Related Genes
Table 3
Voting results of BRCA.
Platforms
Class
Vote from all methods
Vote after filtering
MCC avg
MCC max
BRCA-mRNA
bayes
0.7620
0.7620
0.5327
0.7766
functions
0.7252
0.7766
0.3696
0.7938
lazy
0.7620
0.7423
0.6797
0.7793
meta
0.7274
0.7274
0.7295
0.8085
misc
0.5821
0.6466
0.5449
0.7869
rules
0.7274
0.7274
0.5069
0.7967
trees
0.7274
0.7274
0.7207
0.8085
overall
0.7274
0.7274
0.5985
0.8085
BRCA-miRNA
bayes
0.7237
0.6895
0.3544
0.7067
functions
0.6733
0.6908
0.1080
0.7566
lazy
0.6214
0.6214
0.5067
0.6736
meta
0.6278
0.6278
0.6142
0.7269
misc
0.3203
0.5773
0.2816
0.6383
rules
0.5990
0.6278
0.3933
0.7234
trees
0.6427
0.6602
0.6066
0.7566
overall
0.6405
0.6908
0.4427
0.7566
BRCA-mRNA and BRCA-miRNA
bayes
0.7423
0.7252
0.4436
0.7766
functions
0.6555
0.7915
0.2388
0.7938
lazy
0.7595
0.7595
0.5932
0.7793
meta
0.7595
0.7595
0.6719
0.8085
misc
0.5624
0.6756
0.4133
0.7869
rules
0.7080
0.7746
0.4501
0.7967
trees
0.7595
0.7595
0.6636
0.8085
overall
0.7407
0.7746
0.5206
0.8085
All of the measurements in the tables are MCCs, and the vote after filtering is the MCC based on the eliminated methods. The “avg” is the average of the MCCs.
