Skip to main content

Table 4 Performance of models based on both positive dataset and negative 2 dataset using SMO as classifier

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

Features Training Testing
Sensitivity Specificity Accuracy MCC Sensitivity Specificity Accuracy MCC
AAC 0.896 0.931 0.914 0.828 0.930 0.932 0.932 0.786
N5C5 0.905 0.931 0.918 0.836 0.960 0.914 0.922 0.772
k-space = 0 0.890 0.929 0.909 0.819 0.940 0.944 0.943 0.819
k-space = 1 0.933 0.950 0.942 0.884 0.910 0.944 0.940 0.803
k-space = 2 0.924 0.942 0.933 0.866 0.910 0.956 0.948 0.825
AAC + k-space = 0 0.892 0.942 0.917 0.835 0.960 0.942 0.945 0.828
AAC + N5C5 0.918 0.920 0.919 0.838 0.960 0.946 0.948 0.836
N5C5 + k-space = 0 0.922 0.948 0.935 0.871 0.970 0.948 0.950 0.843
AAC + N5C5 + k-space 0 0.927 0.950 0.938 0.877 0.970 0.948 0.952 0.847
PSSM 0.950 0.948 0.949 0.898 0.940 0.930 0.932 0.789