Application of amino acid occurrence for discriminating different folding types of globular proteins

BMC Bioinformatics

Table 2 Performances of fold recognition. Leave-one-out cross validation performances [%] in each fold. wo: without re-weighting, w: with re-weighting

					Sensitivity		Precision		F1
ID	Fold	Fold Description	Number	Ratio	wo	w	wo	w	wo	w
		all-α
1	a.3	Cytochrome C	25	2	24	48	50	27	32	35
2	a.4	DNA/RNA binding 3-helical bundle	103	6	73	49	43	51	54	50
3	a.24	Four helical up and down bundle	26	2	23	38	35	20	28	26
4	a.39	EF hand-like fold	25	2	40	44	45	26	43	33
5	a.60	SAMdomain-like	26	2	8	27	29	12	12	16
6	a.118	α-α superhelix	47	3	47	45	50	50	48	47
		all-β
7	b.1	Immunoglobulin-like β-sandwich	173	11	76	38	41	69	54	49
8	b.2	Common fold of diphtheria toxin/transcription factors/cytochrome f	28	2	4	29	11	21	5	24
9	b.6	Cupredoxin-like	30	2	27	37	42	22	33	27
10	b.18	Galactose-binding domain-like	25	2	20	36	50	26	29	30
11	b.29	Concanavalin A-like lectins/glucanases	26	2	23	27	24	18	24	22
12	b.34	SH3-like barrel	42	3	0	29	0	20	-	24
13	b.40	OB-fold	78	5	22	24	24	24	23	24
14	b.82	Double-stranded α-helix	34	2	12	18	19	17	15	17
15	b.121	Nucleoplasmin-like	42	3	52	52	51	47	52	49
		α/β
16	c.1	TIM barrel	145	9	44	27	57	65	50	38
17	c.2	NAD(P)-binding Rossmann-fold domains	77	5	34	31	30	32	32	32
18	c.3	FAD/NAD(P)-binding domain	31	2	10	16	13	11	11	13
19	c.23	Flavodoxin-like	55	3	11	5	17	8	13	7
20	c.26	Adenine nucleotide a hydrolase-like	34	2	12	29	14	22	13	25
21	c.37	P-loop containing nucleoside triphosphate hydrolases	95	6	43	34	42	53	43	41
22	c.47	Thioredoxin fold	32	2	9	19	38	10	15	13
23	c.55	Ribonuclease H-like motif	49	3	4	6	11	8	6	7
24	c.66	S-adenosyl-L-methionine-dependent methyltransferases	34	2	29	29	31	21	30	24
25	c.69	α/β-Hydrolases	37	2	35	41	39	34	37	37
		α + β
26	d.15	β-Grasp, ubiquitin-like	42	3	5	21	40	18	9	19
27	d.17	Cystatin-like	25	2	0	8	-	4	-	5
28	d.58	Ferredoxin-like	118	7	32	7	17	25	22	11
		small
29	g.3	Knottins	80	5	98	89	72	82	83	85
30	g.41	Rubredoxin-like	28	2	11	71	75	32	19	44

ISSN: 1471-2105