Improving classification in protein structure databases using text mining

BMC Bioinformatics

Table 4 REGS352 and PDB145 datasets

Superfamily	Sequences	REGS352 Families	REGS352 References	PDB145 Families	PDB145 References
Amidohydrolase	87	26	73	11	41
Crotonase	50	16	36	7	14
Enolase	85	9	66	8	39
Haloacid Dehalogenase	104	19	93	10	30
VOC	95	17	84	7	21
TOTAL	421	87	352	43	145

Distribution of the gold dataset sequences and the derived datasets REGS352 and PDB145 among the five superfamilies of the gold dataset. (Brown et al ., 2006)

ISSN: 1471-2105