Computational Biology Research Center[CBRC]

released on 25th July, 2005

GRIFFIN HP ： http://griffin.cbrc.jp/

GRIFFIN (G-protein and Receptor Interaction Feature Finding INstrument) is GPCR - G-protein coupling selectivity prediction system including on the support vector machine (SVM), and the hidden Markov model (HMM). Based on our assumption that whole structural segments of ligand, GPCR and G-protein are essential to determine GPCR - G-protein coupling, various feature quantities were picked up from ligand, and GPCRs, G-protein complex structures and some of these parameters which are the most effective in selecting G-protein type were used as feature vectors in SVM. GRIFFIN predicts G-proteins by using the information of ligand molecular weight and GPCR sequence. The user can perform the computational experiment to monitor G-protein binding for orphan receptors whose ligands are still unknown. Applying this system to known GPCR sequences, each binding G-protein is predicted with high sensitivity and specificity (more than 85%, on average).