Premium
PRIMSIPLR: Prediction of inner‐membrane situated pore‐lining residues for alpha‐helical transmembrane proteins
Author(s) -
Nguyen Duy,
Helms Volkhard,
Lee PoHsien
Publication year - 2014
Publication title -
proteins: structure, function, and bioinformatics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.699
H-Index - 191
eISSN - 1097-0134
pISSN - 0887-3585
DOI - 10.1002/prot.24520
Subject(s) - transmembrane protein , computational biology , identification (biology) , membrane protein , transmembrane domain , support vector machine , software , biology , chemistry , membrane , data mining , computer science , biochemistry , artificial intelligence , botany , programming language , receptor
Transmembrane proteins such as transporters and channels mediate the passage of inorganic and organic substances across biological membranes through their central pore. Pore-lining residues (PLRs) that make direct contacts to the substrates have a crucial impact on the function of the protein and, hence, their identification is a key step in mechanistic studies. Here, we established a nonredundant data set containing the three-dimensional (3D) structures of 90 α-helical transmembrane proteins and annotated the PLRs of these proteins by a pore identification software. A support vector machine was then trained to distinguish PLRs from other residues based on the protein sequence alone. Using sixfold cross-validation, our best performing predictor gave a Matthews's correlation coefficient of 0.41 with an accuracy of 0.86, sensitivity of 0.61, and specificity of 0.89, respectively. We provide a novel software tool that will aid biomedical scientists working on transmembrane proteins with unknown 3D structures. Both standalone version and web service are freely available from the URL http://service.bioinformatik.uni-saarland.de/PRIMSIPLR/.