Table 4

Optimal subsets of AAPPs and number of selected features identified by EpicCapo+REF using 14 HLA-A allele datasets
Allele AUC of EpicCapo+REF IDs of AAPP used # of features selected
A *01:01 0.980 1,11,14,20,24,26,28,33 72
A *02:01 0.958 9,11,14,24,26,28,31 62
A *02:02 0.913 14,28 18
A *02:03 0.925 3,9,11,14,19,24,25,26,28,29,31,33 104
A *02:06 0.926 1,3,9,11,13,14,18,19,21,22,24,25,26,27,28,31,34,38,39 141
A *03:01 0.946 11,14,20,24,26,28,33 58
A *11:01 0.956 11,14,26,28 35
A *24:02 0.877 5,6,14,24,28,31 31
A *26:01 0.960 14,28 18
A *29:02 0.955 5,8,9,20,33 23
A *31:01 0.940 11,14,20,26,28,33 46
A *33:01 0.940 14,28 17
A *68:01 0.904 11,14,20,26,28,33 40
A *68:02 0.913 1,9,11,14,20,22,24,26,28,33,39 79
Average 0.935

Saethang et al.

Saethang et al. BMC Bioinformatics 2012 13:313   doi:10.1186/1471-2105-13-313

Open Data