Rigorous assessment and integration of the sequence and structure based features to predict hot spots

BMC Bioinformatics

Table 2 The results of different models with self-consistency test on training set

Features	P	R	F1	AUC
ASA	0.67	0.70	0.68	0.72
BC	0.64	0.36	0.46	0.61
Phy	0.66	0.63	0.64	0.72
ECS	0.60	0.23	0.33	0.59
SE	0.72	0.69	0.70	0.76
PSSM	0.72	0.63	0.67	0.75
ECS+SE	0.62	0.54	0.58	0.63
PSSM+ECS	0.78	0.74	0.76	0.86
PSSM+SE	0.84	0.71	0.77	0.88
Phy+ECS+SE	0.67	0.75	0.71	0.77
PSSM+ECS+SE	0.87	0.78	0.82	0.93
Phy+PSSM+ECS+SE	0.88	0.87	0.88	0.96
ASA+BC	0.63	0.61	0.62	0.69
Phy+ASA	0.65	0.73	0.69	0.75
Phy+BC	0.67	0.62	0.64	0.73
Phy+ASA+BC	0.68	0.67	0.68	0.77
Phy+ASA+BC+PSSM+ECS+SE	0.83	0.85	0.84	0.91

ASA denotes accessible surface area; BC denotes biochemical contacts; Phy means physicochemical features; ECS denotes evolutionary conservation score; SE means sequence entropy; and PSSM is the abbreviation of Position-Specific Scoring Matrix.

ISSN: 1471-2105