Preprocessing differential methylation hybridization microarray data

Table 3 Breast cancer AUC measurement table

(1): p < 0.05		none	sub	edwards	normexp	normexp50
	none	0.779	0.782	0.781	0.841	0.842
	LOESS	0.852	0.842	0.841	0.868	0.861
	composite	0.864	0.849	0.849	0.868	0.872
	control	0.896	0.854	0.859	0.869	0.875
(2): p < 0.04		none	sub	edwards	normexp	normexp50
	none	0.773	0.775	0.774	0.848	0.830
	LOESS	0.846	0.855	0.855	0.851	0.854
	composite	0.856	0.844	0.846	0.867	0.882
	control	0.896	0.849	0.854	0.866	0.883
(3): p < 0.03		none	sub	edwards	normexp	normexp50
	none	0.763	0.771	0.771	0.815	0.830
	LOESS	0.851	0.836	0.836	0.841	0.835
	composite	0.862	0.852	0.850	0.860	0.884
	control	0.877	0.861	0.868	0.869	0.879
(4): p < 0.02		none	sub	edwards	normexp	normexp50
	none	0.738	0.751	0.751	0.818	0.826
	LOESS	0.826	0.823	0.816	0.818	0.832
	composite	0.866	0.837	0.834	0.854	0.873
	control	0.866	0.853	0.854	0.864	0.871
(5): p < 0.01		none	sub	edwards	normexp	normexp50
	none	0.736	0.730	0.730	0.810	0.796
	LOESS	0.844	0.820	0.817	0.814	0.837
	composite	0.868	0.851	0.852	0.826	0.857
	control	0.871	0.87 1	0.872	0.861	0.863

Each row is for one p-value cutoff point. Within each row, the first column contains a p-value cutoff point; the second column contains a sub-table of 20 numbers corresponding to the AUC measurement results of 20 preprocessing methods. The underlined bold numbers are the top 3 largest numbers in each sub-table of the second column.

ISSN: 1756-0381