The webserver iGPCR-Drug was developed for predicting interaction between GPCRs and drugs in the cellular networks. It has the following features: (i) each drug compound is formulated a 2D (dimensional) fingerprint via a 256D vector; (ii) each GPCR formulated by the PseAAC (pseudo amino acid composition) generated with the grey model theory; (iii) the prediction engine is operated by the fuzzy K-nearest neighbor algorithm. The anticipated overall success rate in identifying interactive GPCR-drug pairs and non-interactive GPCR-drug pairs is about 89%.
To obtain the predicted result with the anticipated success rate, the entire sequence of a query GPCR 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 GPCR, stop the prediction because the result thus obtained will not make any sense.