An ensemble of support vector machines for predicting the membrane protein type directly from the amino acid sequence
- 22 April 2008
- journal article
- Published by Springer Nature in Amino Acids
- Vol. 35 (3) , 573-580
Abstract
Given a particular membrane protein, it is very important to know which membrane type it belongs to because this kind of information can provide clues for better understanding its function. In this work, we propose a system for predicting the membrane protein type directly from the amino acid sequence. The feature extraction step is based on an encoding technique that combines the physicochemical amino acid properties with the residue couple model. The residue couple model is a method inspired by Chou’s quasi-sequence-order model that extracts the features by utilizing the sequence order effect indirectly. A set of support vector machines, each trained using a different physicochemical amino acid property combined with the residue couple model, are combined by vote rule. The success rate obtained by our system on a difficult dataset, where the sequences in a given membrane type have a low sequence identity to any other proteins of the same membrane type, are quite high, indicating that the proposed method, where the features are extracted directly from the amino acid sequence, is a feasible system for predicting the membrane protein type.Keywords
This publication has 87 references indexed in Scilit:
- Structure and mechanism of the M2 proton channel of influenza A virusNature, 2008
- A machine learning approach for the identification of odorant binding proteins from sequence-derived propertiesBMC Bioinformatics, 2007
- The community structure of human cellular signaling networkJournal of Theoretical Biology, 2007
- DNA-nanotube-induced alignment of membrane proteins for NMR structure determinationProceedings of the National Academy of Sciences of the United States of America, 2007
- Large‐scale plant protein subcellular location predictionJournal of Cellular Biochemistry, 2006
- PLPD: reliable protein localization prediction from imbalanced and overlapped datasetsNucleic Acids Research, 2006
- Hum-PLoc: A novel ensemble classifier for predicting human protein subcellular localizationBiochemical and Biophysical Research Communications, 2006
- Prediction of protein structural classes using support vector machinesAmino Acids, 2006
- Prediction of protein cellular attributes using pseudo‐amino acid compositionProteins: Structure, Function, and Bioinformatics, 2001
- The Structure of the Potassium Channel: Molecular Basis of K + Conduction and SelectivityScience, 1998