Membrain: Improving the accuracy of predicting transmembrane helices

Abstract

Prediction of transmembrane helices (TMH) in α helical proteins provides valuable information about the protein topology when the high resolution structures are not available. Many prdictors have been developed based on either amino acid hydrophobicity scale or pure statistical approaches. While these predictors perform reasonably well in identifying the number of TMHs in protein, they are generally inaccurate in predicting the ends of TMHs, of TMHs of unusual length. To improve the accuracy of TMH detection, we developed a machine-learning based predictor, MemBrain, which integrates a number of modern bioinformatics approaches including sequence representation by multiple sequence alignment matrix, the optimized evidence-theoretic K-nearest neighbor prediction algorithm, fusion of multiple prediction window sizes, and classification by dynamic threshold. MemBrain demonstrates an overall improvement of about 20% in prediction accuracy, particularly, in predicting the ends of TMHs and TMHs that are shorter than 15 residues. It also has the capability to detect N-termal signal peptides. The MemBrain predictor is useful sequence-based analysis tool for functional and structural characterization of helical membrane protein; it is freely available at http://chou.med.harvard.edu/bioinf/MemBrain/. © 2008 Shen, Chou.