Automatic learning of pre-miRNAs from different species

BMC Bioinformatics

Table 4 Centers of accuracy clusters obtained from classification models induced with examples from different species, per combination of feature set and learning algorithm. Range = Maximum - minimum

Feature set	Algorithm	c ₁	c ₂	c ₃	c ₄	c ₅	c ₆	Range
FS1	SVM	95	88	78	-	-	-	21
FS2		96	92	87	80	-	-	20
FS3		95	90	85	-	-	-	15
FS4		92	86	81	77	-	-	22
FS5		94	90	86	80	-	-	20
FS6		93	88	83	-	-	-	17
FS7		95	88	-	-	-	-	16
SELECT		96	92	86	80	-	-	20
FS1	RF	97	92	87	82	72	-	30
FS2		97	93	89	83	-	-	20
FS3		95	88	84	-	-	-	18
FS4		91	87	84	79	-	-	18
FS5		92	85	77	-	-	-	19
FS6		95	88	-	-	-	-	16
FS7		96	89	-	-	-	-	14
SELECT	J48	96	92	86	78	-	-	21
FS1		98	91	85	75	67	57	41
FS2		96	90	84	77	-	-	24
FS3		97	92	87	81	-	-	21
FS4		84	79	75	69	-	-	21
FS5		83	78	75	71	-	-	17
FS6		97	93	89	83	78	72	27
FS7		96	91	87	81	-	-	21
SELECT		97	92	86	80	74	-	26

ISSN: 1471-2105