<p>Total 1783 cysteine sequences were applied in positive and negative data. Sn, sensitivity; Sp, specificity; Acc, accuracy; MCC, Matthews Correlation Coefficient.</p><p>Five-fold cross validation results on single SVM model trained with various features.</p
a<p>The overall recognition accuracy is 97.40±0.95%.</p>b<p>The class precision is the percentage of...
<p>AAC, Amino Acid Composition; DPC, Di Peptide Composition; N5AAC, Amino Acid Composition of 5 N-te...
<p>The Matthews correlation coefficient (MCC) is calculated according to <a href="http://www.ploscom...
<p>(a) Values for TPR, TNR, PPV, and NPV. (b) Values for MCC, BACC, AUC, and ACC.</p
<p>D: dimensionality; AUC: area under ROC curve; Spe: specificity; Pre: precision; Sen: sensitivity;...
<p>The generalized performance of the SVM model. We rebuilt the model for 100 times for the validati...
a<p>The 13 feature schemes were: where <i>k</i> = {<i>1</i>,<i>5</i>,<i>6</i>,<i>7</i>}, <i>g</i> =...
<p>The 10-fold cross-validation results of independent test by SVM algorithm with g = 0.005 and cuto...
<p>The results have been run 20 times for every feature construction by SVM algorithm with g = 0.005...
<p>The accuracy of SVM using just single propensity by the 2-level 10-fold cross validation scheme.<...
<p>Validation of the proposed method (SVMs with RBF kernel, using all described features) on experim...
<p>Comparison of predictive performances of single feature classes. All values are taken from SVM pr...
<p><i>Model<sub>ND</sub></i> is trained on <i>Positive<sub>H...
<p>The accuracy from 5-fold cross validation of SVM using EVSA and GDDA as kernel.</p
<p><b>Sn:</b> Sensitivity; <b>Sp:</b> Specificity; <b>Acc:</b> Accuracy; <b>MCC:</b> Matthew’s Corre...
a<p>The overall recognition accuracy is 97.40±0.95%.</p>b<p>The class precision is the percentage of...
<p>AAC, Amino Acid Composition; DPC, Di Peptide Composition; N5AAC, Amino Acid Composition of 5 N-te...
<p>The Matthews correlation coefficient (MCC) is calculated according to <a href="http://www.ploscom...
<p>(a) Values for TPR, TNR, PPV, and NPV. (b) Values for MCC, BACC, AUC, and ACC.</p
<p>D: dimensionality; AUC: area under ROC curve; Spe: specificity; Pre: precision; Sen: sensitivity;...
<p>The generalized performance of the SVM model. We rebuilt the model for 100 times for the validati...
a<p>The 13 feature schemes were: where <i>k</i> = {<i>1</i>,<i>5</i>,<i>6</i>,<i>7</i>}, <i>g</i> =...
<p>The 10-fold cross-validation results of independent test by SVM algorithm with g = 0.005 and cuto...
<p>The results have been run 20 times for every feature construction by SVM algorithm with g = 0.005...
<p>The accuracy of SVM using just single propensity by the 2-level 10-fold cross validation scheme.<...
<p>Validation of the proposed method (SVMs with RBF kernel, using all described features) on experim...
<p>Comparison of predictive performances of single feature classes. All values are taken from SVM pr...
<p><i>Model<sub>ND</sub></i> is trained on <i>Positive<sub>H...
<p>The accuracy from 5-fold cross validation of SVM using EVSA and GDDA as kernel.</p
<p><b>Sn:</b> Sensitivity; <b>Sp:</b> Specificity; <b>Acc:</b> Accuracy; <b>MCC:</b> Matthew’s Corre...
a<p>The overall recognition accuracy is 97.40±0.95%.</p>b<p>The class precision is the percentage of...
<p>AAC, Amino Acid Composition; DPC, Di Peptide Composition; N5AAC, Amino Acid Composition of 5 N-te...
<p>The Matthews correlation coefficient (MCC) is calculated according to <a href="http://www.ploscom...