Performance comparison of five single ML method-based models to predict malonylation sites for the three species using 10-fold cross-validation tests. Ten-fold cross-validation tests were randomly performed 10 times, and the reported performance is the average of the individual performances
| Species . | Method . | PRE . | SN . | SP . | F-value . | ACC . | MCC . |
|---|---|---|---|---|---|---|---|
| E. coli | RF | 0.787 ± 0.002 | 0.826 ± 0.004 | 0.776 ± 0.002 | 0.805 ± 0.002 | 0.801 ± 0.002 | 0.603 ± 0.004 |
| SVM | 0.813 ± 0.003 | 0.810 ± 0.003 | 0.813 ± 0.005 | 0.811 ± 0.002 | 0.812 ± 0.002 | 0.624 ± 0.004 | |
| LightGBM | 0.785 ± 0.004 | 0.815 ± 0.007 | 0.776 ± 0.005 | 0.799 ± 0.004 | 0.796 ± 0.004 | 0.592 ± 0.007 | |
| KNN | 0.826 ± 0.005 | 0.699 ± 0.003 | 0.853 ± 0.004 | 0.756 ± 0.003 | 0.776 ± 0.003 | 0.558 ± 0.006 | |
| LR | 0.792 ± 0.005 | 0.795 ± 0.005 | 0.791 ± 0.006 | 0.793 ± 0.004 | 0.793 ± 0.004 | 0.586 ± 0.009 | |
| M. musculus | RF | 0.818 ± 0.002 | 0.835 ± 0.003 | 0.815 ± 0.002 | 0.826 ± 0.002 | 0.825 ± 0.002 | 0.650 ± 0.003 |
| SVM | 0.833 ± 0.002 | 0.832 ± 0.002 | 0.833 ± 0.002 | 0.832 ± 0.002 | 0.832 ± 0.002 | 0.665 ± 0.004 | |
| LightGBM | 0.826 ± 0.002 | 0.836 ± 0.004 | 0.824 ± 0.003 | 0.830 ± 0.003 | 0.830 ± 0.002 | 0.659 ± 0.005 | |
| KNN | 0.848 ± 0.002 | 0.721 ± 0.004 | 0.871 ± 0.003 | 0.779 ± 0.002 | 0.796 ± 0.002 | 0.599 ± 0.003 | |
| LR | 0.822 ± 0.003 | 0.820 ± 0.003 | 0.822 ± 0.004 | 0.820 ± 0.002 | 0.821 ± 0.002 | 0.641 ± 0.005 | |
| H. sapiens | RF | 0.838 ± 0.002 | 0.830 ± 0.003 | 0.840 ± 0.002 | 0.834 ± 0.002 | 0.835 ± 0.002 | 0.670 ± 0.004 |
| SVM | 0.832 ± 0.002 | 0.825 ± 0.002 | 0.834 ± 0.002 | 0.828 ± 0.001 | 0.829 ± 0.001 | 0.659 ± 0.002 | |
| LightGBM | 0.837 ± 0.003 | 0.833 ± 0.004 | 0.838 ± 0.003 | 0.835 ± 0.003 | 0.835 ± 0.003 | 0.671 ± 0.005 | |
| KNN | 0.835 ± 0.002 | 0.752 ± 0.003 | 0.851 ± 0.002 | 0.791 ± 0.002 | 0.801 ± 0.002 | 0.606 ± 0.004 | |
| LR | 0.824 ± 0.002 | 0.819 ± 0.003 | 0.825 ± 0.002 | 0.821 ± 0.002 | 0.822 ± 0.002 | 0.644 ± 0.004 |
| Species . | Method . | PRE . | SN . | SP . | F-value . | ACC . | MCC . |
|---|---|---|---|---|---|---|---|
| E. coli | RF | 0.787 ± 0.002 | 0.826 ± 0.004 | 0.776 ± 0.002 | 0.805 ± 0.002 | 0.801 ± 0.002 | 0.603 ± 0.004 |
| SVM | 0.813 ± 0.003 | 0.810 ± 0.003 | 0.813 ± 0.005 | 0.811 ± 0.002 | 0.812 ± 0.002 | 0.624 ± 0.004 | |
| LightGBM | 0.785 ± 0.004 | 0.815 ± 0.007 | 0.776 ± 0.005 | 0.799 ± 0.004 | 0.796 ± 0.004 | 0.592 ± 0.007 | |
| KNN | 0.826 ± 0.005 | 0.699 ± 0.003 | 0.853 ± 0.004 | 0.756 ± 0.003 | 0.776 ± 0.003 | 0.558 ± 0.006 | |
| LR | 0.792 ± 0.005 | 0.795 ± 0.005 | 0.791 ± 0.006 | 0.793 ± 0.004 | 0.793 ± 0.004 | 0.586 ± 0.009 | |
| M. musculus | RF | 0.818 ± 0.002 | 0.835 ± 0.003 | 0.815 ± 0.002 | 0.826 ± 0.002 | 0.825 ± 0.002 | 0.650 ± 0.003 |
| SVM | 0.833 ± 0.002 | 0.832 ± 0.002 | 0.833 ± 0.002 | 0.832 ± 0.002 | 0.832 ± 0.002 | 0.665 ± 0.004 | |
| LightGBM | 0.826 ± 0.002 | 0.836 ± 0.004 | 0.824 ± 0.003 | 0.830 ± 0.003 | 0.830 ± 0.002 | 0.659 ± 0.005 | |
| KNN | 0.848 ± 0.002 | 0.721 ± 0.004 | 0.871 ± 0.003 | 0.779 ± 0.002 | 0.796 ± 0.002 | 0.599 ± 0.003 | |
| LR | 0.822 ± 0.003 | 0.820 ± 0.003 | 0.822 ± 0.004 | 0.820 ± 0.002 | 0.821 ± 0.002 | 0.641 ± 0.005 | |
| H. sapiens | RF | 0.838 ± 0.002 | 0.830 ± 0.003 | 0.840 ± 0.002 | 0.834 ± 0.002 | 0.835 ± 0.002 | 0.670 ± 0.004 |
| SVM | 0.832 ± 0.002 | 0.825 ± 0.002 | 0.834 ± 0.002 | 0.828 ± 0.001 | 0.829 ± 0.001 | 0.659 ± 0.002 | |
| LightGBM | 0.837 ± 0.003 | 0.833 ± 0.004 | 0.838 ± 0.003 | 0.835 ± 0.003 | 0.835 ± 0.003 | 0.671 ± 0.005 | |
| KNN | 0.835 ± 0.002 | 0.752 ± 0.003 | 0.851 ± 0.002 | 0.791 ± 0.002 | 0.801 ± 0.002 | 0.606 ± 0.004 | |
| LR | 0.824 ± 0.002 | 0.819 ± 0.003 | 0.825 ± 0.002 | 0.821 ± 0.002 | 0.822 ± 0.002 | 0.644 ± 0.004 |
Note: Performances are shown as mean ± standard deviation. For each species, the best performance (as measured by each metric) across different encoding methods is highlighted in bold for clarification. For each performance metric, the best performance value across different machine learning methods within a species is highlighted in bold for clarification. These highlights also apply to Tables 3 and 4.
Performance comparison of five single ML method-based models to predict malonylation sites for the three species using 10-fold cross-validation tests. Ten-fold cross-validation tests were randomly performed 10 times, and the reported performance is the average of the individual performances
| Species . | Method . | PRE . | SN . | SP . | F-value . | ACC . | MCC . |
|---|---|---|---|---|---|---|---|
| E. coli | RF | 0.787 ± 0.002 | 0.826 ± 0.004 | 0.776 ± 0.002 | 0.805 ± 0.002 | 0.801 ± 0.002 | 0.603 ± 0.004 |
| SVM | 0.813 ± 0.003 | 0.810 ± 0.003 | 0.813 ± 0.005 | 0.811 ± 0.002 | 0.812 ± 0.002 | 0.624 ± 0.004 | |
| LightGBM | 0.785 ± 0.004 | 0.815 ± 0.007 | 0.776 ± 0.005 | 0.799 ± 0.004 | 0.796 ± 0.004 | 0.592 ± 0.007 | |
| KNN | 0.826 ± 0.005 | 0.699 ± 0.003 | 0.853 ± 0.004 | 0.756 ± 0.003 | 0.776 ± 0.003 | 0.558 ± 0.006 | |
| LR | 0.792 ± 0.005 | 0.795 ± 0.005 | 0.791 ± 0.006 | 0.793 ± 0.004 | 0.793 ± 0.004 | 0.586 ± 0.009 | |
| M. musculus | RF | 0.818 ± 0.002 | 0.835 ± 0.003 | 0.815 ± 0.002 | 0.826 ± 0.002 | 0.825 ± 0.002 | 0.650 ± 0.003 |
| SVM | 0.833 ± 0.002 | 0.832 ± 0.002 | 0.833 ± 0.002 | 0.832 ± 0.002 | 0.832 ± 0.002 | 0.665 ± 0.004 | |
| LightGBM | 0.826 ± 0.002 | 0.836 ± 0.004 | 0.824 ± 0.003 | 0.830 ± 0.003 | 0.830 ± 0.002 | 0.659 ± 0.005 | |
| KNN | 0.848 ± 0.002 | 0.721 ± 0.004 | 0.871 ± 0.003 | 0.779 ± 0.002 | 0.796 ± 0.002 | 0.599 ± 0.003 | |
| LR | 0.822 ± 0.003 | 0.820 ± 0.003 | 0.822 ± 0.004 | 0.820 ± 0.002 | 0.821 ± 0.002 | 0.641 ± 0.005 | |
| H. sapiens | RF | 0.838 ± 0.002 | 0.830 ± 0.003 | 0.840 ± 0.002 | 0.834 ± 0.002 | 0.835 ± 0.002 | 0.670 ± 0.004 |
| SVM | 0.832 ± 0.002 | 0.825 ± 0.002 | 0.834 ± 0.002 | 0.828 ± 0.001 | 0.829 ± 0.001 | 0.659 ± 0.002 | |
| LightGBM | 0.837 ± 0.003 | 0.833 ± 0.004 | 0.838 ± 0.003 | 0.835 ± 0.003 | 0.835 ± 0.003 | 0.671 ± 0.005 | |
| KNN | 0.835 ± 0.002 | 0.752 ± 0.003 | 0.851 ± 0.002 | 0.791 ± 0.002 | 0.801 ± 0.002 | 0.606 ± 0.004 | |
| LR | 0.824 ± 0.002 | 0.819 ± 0.003 | 0.825 ± 0.002 | 0.821 ± 0.002 | 0.822 ± 0.002 | 0.644 ± 0.004 |
| Species . | Method . | PRE . | SN . | SP . | F-value . | ACC . | MCC . |
|---|---|---|---|---|---|---|---|
| E. coli | RF | 0.787 ± 0.002 | 0.826 ± 0.004 | 0.776 ± 0.002 | 0.805 ± 0.002 | 0.801 ± 0.002 | 0.603 ± 0.004 |
| SVM | 0.813 ± 0.003 | 0.810 ± 0.003 | 0.813 ± 0.005 | 0.811 ± 0.002 | 0.812 ± 0.002 | 0.624 ± 0.004 | |
| LightGBM | 0.785 ± 0.004 | 0.815 ± 0.007 | 0.776 ± 0.005 | 0.799 ± 0.004 | 0.796 ± 0.004 | 0.592 ± 0.007 | |
| KNN | 0.826 ± 0.005 | 0.699 ± 0.003 | 0.853 ± 0.004 | 0.756 ± 0.003 | 0.776 ± 0.003 | 0.558 ± 0.006 | |
| LR | 0.792 ± 0.005 | 0.795 ± 0.005 | 0.791 ± 0.006 | 0.793 ± 0.004 | 0.793 ± 0.004 | 0.586 ± 0.009 | |
| M. musculus | RF | 0.818 ± 0.002 | 0.835 ± 0.003 | 0.815 ± 0.002 | 0.826 ± 0.002 | 0.825 ± 0.002 | 0.650 ± 0.003 |
| SVM | 0.833 ± 0.002 | 0.832 ± 0.002 | 0.833 ± 0.002 | 0.832 ± 0.002 | 0.832 ± 0.002 | 0.665 ± 0.004 | |
| LightGBM | 0.826 ± 0.002 | 0.836 ± 0.004 | 0.824 ± 0.003 | 0.830 ± 0.003 | 0.830 ± 0.002 | 0.659 ± 0.005 | |
| KNN | 0.848 ± 0.002 | 0.721 ± 0.004 | 0.871 ± 0.003 | 0.779 ± 0.002 | 0.796 ± 0.002 | 0.599 ± 0.003 | |
| LR | 0.822 ± 0.003 | 0.820 ± 0.003 | 0.822 ± 0.004 | 0.820 ± 0.002 | 0.821 ± 0.002 | 0.641 ± 0.005 | |
| H. sapiens | RF | 0.838 ± 0.002 | 0.830 ± 0.003 | 0.840 ± 0.002 | 0.834 ± 0.002 | 0.835 ± 0.002 | 0.670 ± 0.004 |
| SVM | 0.832 ± 0.002 | 0.825 ± 0.002 | 0.834 ± 0.002 | 0.828 ± 0.001 | 0.829 ± 0.001 | 0.659 ± 0.002 | |
| LightGBM | 0.837 ± 0.003 | 0.833 ± 0.004 | 0.838 ± 0.003 | 0.835 ± 0.003 | 0.835 ± 0.003 | 0.671 ± 0.005 | |
| KNN | 0.835 ± 0.002 | 0.752 ± 0.003 | 0.851 ± 0.002 | 0.791 ± 0.002 | 0.801 ± 0.002 | 0.606 ± 0.004 | |
| LR | 0.824 ± 0.002 | 0.819 ± 0.003 | 0.825 ± 0.002 | 0.821 ± 0.002 | 0.822 ± 0.002 | 0.644 ± 0.004 |
Note: Performances are shown as mean ± standard deviation. For each species, the best performance (as measured by each metric) across different encoding methods is highlighted in bold for clarification. For each performance metric, the best performance value across different machine learning methods within a species is highlighted in bold for clarification. These highlights also apply to Tables 3 and 4.
This PDF is available to Subscribers Only
View Article Abstract & Purchase OptionsFor full access to this pdf, sign in to an existing account, or purchase an annual subscription.
