The webserver iEzy-Drug was developed for predicting interaction between enzymes and drugs in the cellular networks. It has the following features: (i) each drug compound is formulated by a 2D fingerprint with a 258D feature vector; (ii) each enzyme formulated by the 480D Chou’s PseAAC generated with the grey PSSM and dipeptide composition; (iii) the prediction engine is operated by the SVM algorithm. The anticipated overall success rate in identifying interactive enzyme-drug pairs and non-interactive enzyme-drug pairs is about 91%.
To obtain the predicted result with the anticipated success rate, the entire sequence of a query enzyme rather than its fragment should be used as an input. A sequence with less than 50 amino acid residues is generally deemed as a fragment. Also, if the query protein sequence is known to be not a enzyme, stop the prediction because the result thus obtained will not make any sense.