Functional classification of g-protein coupled receptors, based on their specific ligand coupling patterns

Authors:
Burcu Bakir;Osman Ugur Sezerman
Affiliations:
School of Biology, Georgia Institute of Technology, Atlanta;Sabanci University, Istanbul, Turkey
Venue:
EuroGP'06 Proceedings of the 2006 international conference on Applications of Evolutionary Computing
Year:
2006

Citing 7
Cited 1

C4.5: programs for machine learning

C4.5: programs for machine learning
The nature of statistical learning theory

The nature of statistical learning theory
Discovering Patterns and Subfamilies in Biosequences

Proceedings of the Fourth International Conference on Intelligent Systems for Molecular Biology
Asymptotic behaviors of support vector machines with Gaussian kernel

Neural Computation
Predicting GPCR--G-protein coupling using hidden Markov models

Bioinformatics
Families of membranous proteins can be characterized by the amino acid composition of their transmembrane domains

Bioinformatics
Classifying G-protein coupled receptors with bagging classification tree

Computational Biology and Chemistry

Classification of GPCRs Using Family Specific Motifs

IEEE/ACM Transactions on Computational Biology and Bioinformatics (TCBB)

Quantified Score

Hi-index	0.00

Visualization

Abstract

Functional identification of G-Protein Coupled Receptors (GPCRs) is one of the current focus areas of pharmaceutical research. Although thousands of GPCR sequences are known, many of them remain as orphan sequences (the activating ligand is unknown). Therefore, classification methods for automated characterization of orphan GPCRs are imperative. In this study, for predicting Level 2 subfamilies of Amine GPCRs, a novel method for obtaining fixed-length feature vectors, based on the existence of activating ligand specific patterns, has been developed and utilized for a Support Vector Machine (SVM)-based classification. Exploiting the fact that there is a non-promiscuous relationship between the specific binding of GPCRs into their ligands and their functional classification, our method classifies Level 2 subfamilies of Amine GPCRs with a high predictive accuracy of 97.02% in a ten-fold cross validation test. The presented machine learning approach, bridges the gulf between the excess amount of GPCR sequence data and their poor functional characterization.