Only BayesNet (BN), NaiveBayesUpdateable (NBU), RBFNetwork (RBFN), DecisionTable (DT), and J48 methods yield good results.
Comparisons between current results and those from analytical and other numerical methods yield good agreement.
While current machine learning-based methods yield good prediction accuracy, most of them suffer from two key problems: lack of interpretability and dealing with multiple locations.
In the current study, BP1 method yielded good quality DNA compared to BP2 method.
In our study, K method yielded good quality DNA than other five methods.
When predicting PPIs of Human dataset, the proposed method yielded good results of average accuracy, precision, sensitivity, and MCC of 96.30%, 99.59%, 92.63%, and 92.82% and the standard deviations are 0.10%, 0.29%, 0.44%, and 0.19%, respectively.
When predicting PPIs of Human dataset, the SVM-based method yielded good results with the average accuracy, precision, sensitivity, MCC, and AUC of 85.33%, 86.92%, 81.59%, 74.81%, and 93.15%, respectively.
The method yields good results for some validation parameters.
All results show that our method yields good sensitivity, accuracy and F1 score comparing with the existing methods.
From Table 8, it can be observed that our method yields good results similar to or even better than some other existing methods based on ensemble classifiers.
