Table 4.

The methods for the prediction of drug targets.

Number	Model or method name	Description of the model	Reference
1	The ligand-based virtual screening (LBVS)	By comparing candidate ligands with the known drugs of a target protein	(Byvatov et al., 2003; Krejsa et al., 2003)
2	Structured-based virtual screening (SBVS)	Based on the available crystallographic structure of target	(Ballesteros and Palczewski, 2001)
3	Ligand-based approach	Based on the families or subfamilies of targets	(Huang et al., 2013b)
4	Target-based approach	Divide the receptors and pooled together the known ligands into clusters	(Nagamine and Sakakibara, 2007)
5	In silico model for predicting the drug–target interactions	By the integration of the amino acid sequences, two-dimensional chemical structures, and mass spectrometry data, as well as the chemical functional groups and biological features	(He et al., 2010)
6	The SysDT model	By the integration of artificial intelligence computing methods systems biology, chemical genomics, and structural genomics, which are based on two powerful methods, random forest (RF) and support vector machine (SVM)	(Yu et al., 2012)
7	Weighted ensemble similarity (WES) method	Based on the theory that the systematic features of ligands that could accurately reflect the ligand–receptor binding pattern	(Zheng et al., 2015)
8	Pred-binding method	Based on 1,589 Dragon descriptors of ligands and 1,080 protein descriptors, by SVM and RF	(Shar et al., 2016)