Skip to main content

Table 14 Overview of training features and performance of naïve Bayesian predictive models created from the String0.7 and Reactome networks, utilizing network-wide and target class-specific training, as in Table 11, and including additional non-graph parameters: disease association counts extracted from the DisGeNet database and GO terms associated with each protein

From: Centrality of drug targets in protein networks

  1. The inclusion of these features slightly enhanced the models’ performance (higher true positive Phase4 recall, reduced number of false positive ‘predicted’ targets)