Knowledge transfer via classification rules using functional mapping for integrative modeling of gene expression data

Table 9 Comparison of classification performance of all non-transfer rule learning classifiers on post meta-analysis datasets. Using the AW [34] meta-analysis method only biomarkers with statistically significant effect size within a particular disease type are used for a class prediction task (see Additional File 6 for further details)

Dataset	SVM	LDA	RF	C4.5	NB	PLR	RL
Emblom	1.00	1.00	1.00	0.99	0.99	0.99	0.96
Freije	0.77	0.74	0.74	0.71	0.72	0.79	0.73
Gravendeel	0.50	0.73	0.73	0.59	0.69	0.67	0.49
KangA	0.82	0.72	0.72	0.86	0.93	0.96	0.86
KangB	0.94	0.89	0.89	0.85	0.94	0.93	0.83
Konishi	0.88	0.58	0.58	0.77	0.88	0.87	0.80
Lapointe	0.95	0.92	0.92	0.91	0.95	0.95	0.91
Larsson	0.33	0.33	0.33	0.67	0.42	0.67	0.75
Nanni	0.56	0.68	0.68	0.55	0.72	0.66	0.75
Pardo	0.88	0.88	0.88	0.78	0.83	0.88	0.80
Paugh	0.57	0.45	0.45	0.65	0.51	0.66	0.52
Petalidis	0.86	0.66	0.66	0.75	0.82	0.79	0.84
Phillips	0.75	0.83	0.83	0.68	0.80	0.81	0.64
Singh	0.92	0.86	0.86	0.84	0.87	0.90	0.92
Sun	0.73	0.66	0.66	0.66	0.73	0.73	0.69
Varambally	0.75	0.92	0.92	0.79	0.92	1.00	0.83
Wallace	0.81	0.82	0.82	0.77	0.76	0.81	0.70
Welsh	0.98	0.80	0.80	0.85	0.98	0.91	0.92
Yamanaka	0.63	0.42	0.42	0.79	0.71	0.70	0.61
Yang	0.74	0.51	0.51	0.90	0.71	0.80	0.94
Yu	0.91	0.92	0.92	0.87	0.92	0.95	0.90
AVG AUC	0.78	0.73	0.73	0.77	0.80	0.83	0.78
AVG SEM	0.06	0.07	0.07	0.07	0.06	0.06	0.07

ISSN: 1471-2105