Table 2.

Network Based Drug Repositioning [14]

Name	Method	Network	Description	Key Findings	Advantage	Disadvantage
RNSA	Cluster	PPI	A global network algorithm to identify protein clusters on PPI network	Some complex proteins	This method considers both local and global information from networks. Overlap clusters can be detected as well.	Some information may be dropped as the cluster size is small
RRW	Cluster	PPI	An effective network cluster approach to identify protein clusters on a PPI network	Some complex proteins	This is a general method with high prediction accuracy.	It is a time costly and memory costly method that cannot detect overlap clusters
ClusterONE	Cluster	PPI	A global network algorithm to identify node clusters on network	Some complex proteins	This approach outperformed the other approaches including MCI, RRW, etc. both on weighted and unweighted PPI networks	There is not a standard gold value to evaluate clusters
	Cluster	Drug protein disease	A variant clusterONE algorithm to cluster nodes on heterogenous networks	(iloperidone, schizophrenia) Hypertension	This is an efficient cluster approach that integrates multiple databases	It Is difficult to distinguish between positive associations and negative associations on the network
	Cluster	Drug target disease	An algorithm to detect clusters on the network	(Vismodegib, Basal cell carcinoma) gorlin syndrome	This is a genera and highly robust approach	This approach loses weakly associate genes o diseases and drugs
MBiRW	Cluster	Drug disease	A bi random walk based algorithm	Levodopa, Parkinson disorder > Alzeihmer	Predictions of this approach are reliable	This approach needs to adopt more biological alternatives