Table 4: Computational methods/algorithms for network pharmacology.

TypeMethod and algorithmDescriptionApplication#

Network baseddrugCIPHERA network-based method for drug-target identification based on three linear regression models which integrates drug therapeutic similarity, chemical similarity, and the relevance of targets on PPIs network, respectively [91]. H[91, 124, 132]
DMIMA distance-based mutual information model for indicating the relationship of herbs in TCM formulas [59]. H[59]
WNBIA weight network-based inference method for drug-target prediction by integrating drug similarity and known target similarity [93]. H[93]
CIPHERA computational framework based on a regression model which integrates PPIs, disease phenotype similarities, and gene-phenotype relationships [101]. D[101]
LMMAA reliable approach for constructing disease-related gene network, which combines literature mining and microarray analysis [102]. D[102]
ClustExA two-step method based on module identification in PPIs network by integrating the time-course microarray data for specific disease-related gene discovery [171]. D[171]
MICliqueIdentifying disease gene subsets by the combination of mutual information and clique analysis for biological networks [103]. D[103]
rcNetA coupling ridge regression model established based on the known phenotype-gene network for predicting the unknown ones by maximizing the coherence between them [172]. D[172]
WSMA similarity based method for weighted networks matching [104]. D[104]
SCANA structural clustering algorithm based on biological networks for functional modules discovery [173]. D[173]
CIPHER-HITA hitting-time-based method for predicting disease genes, which combined the modularity measure into the network inference [53]. I[53]
ComCIPHERAn efficient approach for identifying drug-gene-disease comodules underlying the gene closeness data [116]. I[116]
PPAPing-Pong algorithm: an efficient algorithm for predicting drug-gene associations based on multitypes of data [115]. I[115]
ISAIterative signature algorithm for searching the modules in heterogeneous network [118]. I[118]
NSSA network stratification strategy to analyze conglomerate networks [174]. I[174]

Machine learning/othersKNNK nearest neighbor algorithm: a classical supervised classification algorithm based on closest training samples in the feature space. H[81]
SVMSupport vector machine: a supervised kernel based classification algorithm based on the support vectors which are obtained after the training process by transforming original space into kernel space. B[8284, 96, 97, 175]
GIPGaussian Interaction profile: an efficient classification algorithm for predicting drug-target by constructing a kernel function from the known drug-target interaction profiles [176]. H[176]
RFRandom forest: an ensemble learning method for classification based on a multitude of trained decision trees. B[82, 83, 177]
Bayesian classifiersA popular supervised classification method based on probabilistic graphical model. B[8587, 98, 99]
SOMSelf-organizing maps: a unsupervised technology based on competition among the output neurons for assignment of the input vectors to map input observations to an output space represented by a grid of output neurons for similarity assessment. B[88, 89]
SEMSimilarity ensemble methods: usually based on several similarity index such as Tanimoto coefficient(Tc) [107, 108] or Jaccard coefficient (Jc) [109]. B[38, 110, 111]
PCAPrincipal component analysis: a classical data reduction technique for revealing the interrelationship among many variables by creating linear combinations of them into a few new variables to facilitate clustering and model analysis. B[100, 124, 178]

Application#: Hherb-related networks construction; Ddisease-related networks construction; Iintegrative analysis; Bboth herb- and- disease-related networks construction.