Computational Drug Discovery and Design

Training using machine learning algorithms

Selection of best

prediction model

Performance evaluation using K-fold cross

validation or Leave one out cross validation or

by training/testing set split

Confirmed Drug–target pairs (positive examples)

and unknown drug-target pairs (negative

examples)

Drug -features Target -features

Fig. 2Schematic representation of the steps for drug–target interaction prediction

Fig. 3The structure of an ARFF file

24 Abhigyan Nath et al.