Disease candidate gene identification and prioritization using protein interaction networks

BMC Bioinformatics

Table 1 AUC values from each cross validation run.

Test Type	Test ID	AUC	Test ID	AUC	Test ID	AUC	Test ID	AUC	Test ID	AUC
k1	1	0.66	2	0.66	3	0.87	4	0.66	5	0.66
k2	6	0.78	7	0.78	8	0.78	9	0.78	10	0.78
k4	11	0.8	12	0.8	13	0.8	14	0.8	15	0.8
k6	16	0.8	17	0.8	18	0.8	19	0.8	20	0.8
h3	21	0.8	22	0.8	23	0.8	24	0.8	25	0.8
h5	26	0.8	27	0.8	28	0.8	29	0.8	30	0.8
p01	36	0.73	37	0.73	38	0.73	39	0.73	40	0.73
p05	31	0.78	32	0.78	33	0.78	34	0.78	35	0.78
p1	41	0.79	42	0.79	43	0.79	44	0.79	45	0.79
p3	46	0.8	47	0.8	48	0.8	49	0.8	50	0.8
p5	51	0.8	52	0.8	53	0.8	54	0.8	55	0.8
p7	56	0.8	57	0.8	58	0.8	59	0.8	60	0.8
p9	61	0.79	62	0.8	63	0.79	64	0.8	65	0.8

Column "Test Type" indicates the method and parameter settings of the test. p01 through p9 stand for PageRank with Priors with back probability 0.01 to 0.9, respectively; k1, k2, k4 and k6 represent K-Step Markov with K = 1, 2, 4 and 6, accordingly; h3 and h5 are HITS with Priors with back probability 0.3 and 0.5, respectively. There were 13 test conditions, each repeated 5 times.

ISSN: 1471-2105