Impact of missing data imputation methods on gene expression clustering and classification

BMC Bioinformatics

Table 2 Statistics after non-supervised filtering

	No. genes (filtering + imputation)					No. MV (filtering + imputation)
Datasets	BPCA	KNN	LSS	Mean	Median	BPCA	KNN	LLS	Mean	Median
alizadeh-2000-v1	960	945	962	932	932	1.96	1.91	1.97	1.83	1.83
alizadeh-2000-v2	1075	1050	1081	1030	1030	2.71	2.63	2.72	2.59	2.59
alizadeh-2000-v3	1075	1050	1081	1030	1030	2.71	2.63	2.72	2.59	2.59
bredel-2005	3819	3833	3825	3850	3852	0.81	0.82	0.81	0.84	0.84
chen-2002	2240	2246	2238	2329	2340	2.25	2.24	2.23	2.31	2.32
garber-2001	2563	2540	2578	2584	2603	1.94	1.92	1.95	1.95	1.95
lapointe-2004-v1	4161	4159	4170	4196	4292	1.94	1.92	1.95	1.95	1.95
lapointe-2004-v2	3846	3811	3833	3838	3930	2.50	2.50	2.50	2.53	2.58
liang-2005	2531	2528	2529	2519	2521	2.32	2.29	2.31	2.33	2.37
risinger-2003	942	2074	2078	2073	2073	0.84	0.83	0.84	0.81	0.81
tomlins-2006	2027	2020	2039	2018	2018	2.41	2.40	2.43	2.40	2.40
tomlins-2006-v2	2118	2118	2124	2103	2103	2.37	2.34	2.37	2.34	2.34
Mean	2294	945	2378	2375	2018	2.06	2.04	2.07	2.04	2.05

ISSN: 1471-2105