Efficacy of different protein descriptors in predicting protein functional families

BMC Bioinformatics

Table 2 Summary of datasets statistics, including size of training, testing and independent evaluation sets, and average sequence length.

	Total		Training		Testing		Independent testing		Average sequence size
	P	N	P	N	P	N	P	N
EC2.4	3304	14373	1382	5068	1022	5859	900	3446	460
GPCR	2819	21515	1580	7389	717	7333	522	6793	498
TC8.A	229	23096	94	7962	72	7962	63	7172	483
Chlorophyll	999	22997	356	7928	333	7928	310	7141	480
Lipid	2192	11537	850	5779	707	4483	635	1275	312
rRNA	5855	13770	2004	5246	1940	4953	1911	3571	376

ISSN: 1471-2105