Prediction and analysis of protein solubility using a novel scoring card method with dipeptide composition

BMC Bioinformatics

Table 2 10 independent runs of the scoring card method on Sd957.

Exp.	Fitness	Training (%)	Test (%)	Sensitivity	Specificity	AUC	R	Threshold
1	0.905	83.159	81.675	0.640	0.879	0.893	0.954	463.746
2	0.903	83.420	83.246	0.740	0.865	0.894	0.940	473.867
3	0.906	83.681	85.864	0.760	0.894	0.897	0.943	461.951
4	0.906	84.465	84.293	0.740	0.879	0.894	0.953	463.787
5	0.900	82.507	83.246	0.780	0.851	0.883	0.968	455.756
6	0.900	83.943	86.911	0.820	0.887	0.884	0.962	457.543
7	0.902	83.943	84.293	0.720	0.887	0.888	0.959	464.317
8	0.899	83.159	83.770	0.680	0.894	0.885	0.957	464.933
9	0.901	82.507	83.246	0.760	0.858	0.885	0.966	460.600
10	0.902	82.898	83.246	0.720	0.872	0.885	0.970	457.866
Mean	0.902	83.368	83.979	0.736	0.877	0.889	0.957	462.437
Std. Dev.	0.003	0.646	1.485	0.051	0.015	0.005	0.010	5.132

ISSN: 1471-2105