The comparison of the nAnnoLyze method against the original AnnoLyze indicates that our network-based approach predicts drug-protein complexes with higher precision.

Moreover, the network-based paradigm implemented in nAnnoLyze allows for the integration of other types of additional information such as the diseases linked to the protein targets, which may eventually allow for drug indication predictions.

Others, named network-based approaches, exploit network properties to provide the drug target interactions and drug repositioning opportunities [11—18].

Here we introduce nAnnoLyze, a network-based version of the comparative docking method AnnoLyze [23].

Network-based prediction of DrugBank ligand and human target pairs

The most direct network-based scoring scheme is the neighbor counting method, where the annotation frequency in the immediate neighbors is ranked and assigned to the linked queries.

Thus, the similarity between PPI networks and CSNs suggested that this approach could be effective for network-based drug target inference.

In conclusion, we have developed a new network-based compound target identification method called CSNAP that can be used for large-scale profiling of hit compounds from chemical screens.

Target prediction accuracy comparison of network-based and ligand-based approaches.

The observation that disease associated proteins often interact with each other has fueled the development of network-based approaches to elucidate the molecular mechanisms of human disease.

The hypothesis that disease associated proteins tend to interact with each other in the human Interactome underlies all network-based prioritization methods.

In this paper, we propose a network-based methodology to uncover the disease module associated with a particular phenotype.