. 2015 Sep 16;9:56. doi: 10.1186/s12918-015-0202-y

Table 1.

A classification of systematic drug synergy prediction models

Model type	Description	Inputs	Methods	Outputs
PPI network-based models	Evaluate drug synergy based on network topology relations of targets	Drug targets;	Complex network;	Synergistic drug combinations;
PPI network-based models		Protein interactions	Network pharmacology	Synergistic targets
Pathway-based models	Simulate the dynamic changes of pathway and identify synergy-specific pathway structures	Drug targets;	Ordinary differential equations;	Dose–response assessment of drug synergy;
		Pathway structures;	Network motif recognition	Synergy-specific
		Dynamic changes of each pathway component;		network motifs in pathways
		Drug interactions		network motifs in pathways
Drug similarity-based models	Construct classification models based on various drug similarities	Drug properties like targets, structures, indication, et al.	Similarity calculation;	Synergistic drug combinations;
			Feature selection;	Distinctive features for drug combination
			Classification model	Distinctive features for drug combination
Omic-based models	Apply “omic” data to calculate drug associations; or rebuild the synergy-dependent pathways	Responses to drugs in the form of “omic” data	Reverse engineering of biological networks;	Synergistic drug combinations;
			“Omic” data similarity calculation;	Biological networks;
			Classification model	Biological networks;