Integration Strategy Is a Key Step in Network-Based Analysis and Dramatically Affects Network Topological Properties and Inferring Outcomes

Figure 1

Seven machine learning classifiers constructed by using the gold standard datasets. The gold standard datasets, positive protein-protein interactions in the DIP database, and negative protein-protein interactions in the NEGATOME database were used to construct the seven machine learning classifiers based on the following methods: Naive Bayes, Bayesian Networks, Logistic Regression, Support Vector Machine (SVM), Random Tree, Random Forest, and J48.