BMC Bioinformatics

Table 1 The performance of models based on both positive dataset and negative 1 dataset using SVM as classifier

From: Incorporating support vector machine with sequential minimal optimization to identify anticancer peptides

Features	Training				Testing
Features	Weight	Sensitivity	Specificity	Accuracy	Sensitivity	Specificity	Accuracy
AAC	0.7	0.626	0.890	0.758	0.670	0.860	0.765
N5C5	0.7	0.665	0.866	0.766	0.640	0.850	0.745
k-space = 0	1.0	0.644	0.726	0.685	0.640	0.910	0.775
k-space = 1	1.0	0.639	0.704	0.672	0.610	0.930	0.770
k-space = 2	1.0	0.641	0.737	0.689	0.600	0.910	0.755
AAC + k-space = 0	0.9	0.693	0.907	0.800	0.690	0.900	0.795
AAC + N5C5	0.5	0.645	0.950	0.798	0.640	0.890	0.765
N5C5 + k-space = 0	0.9	0.678	0.907	0.792	0.630	0.860	0.745
AAC + N5C5 + k-space 0	0.5	0.641	0.978	0.810	0.610	0.910	0.760
PSSM	0.6	0.737	0.896	0.816	0.69	0.86	0.775

Back to article page

ISSN: 1471-2105

Contact us

General enquiries: journalsubmissions@springernature.com