PuSH - Publikationsserver des Helmholtz Zentrums München

Accurate prediction of helix interactions and residue contacts in membrane proteins.

J. Struct. Biol. 194, 112-123 (2016)
Postprint DOI
Open Access Green
Accurate prediction of intra-molecular interactions from amino acid sequence is an important pre-requisite for obtaining high-quality protein models. Over the recent years, remarkable progress in this area has been achieved through the application of novel co-variation algorithms, which eliminate transitive evolutionary connections between residues. In this work we present a new contact prediction method for α-helical transmembrane proteins, MemConP, in which evolutionary couplings are combined with a machine learning approach. MemConP achieves a substantially improved accuracy (precision: 56.0%, recall: 17.5%, MCC: 0.288) compared to the use of either machine learning or co-evolution methods alone. The method also achieves 91.4% precision, 42.1% recall and a MCC of 0.490 in predicting helix-helix interactions based on predicted contacts. The approach was trained and rigorously benchmarked by cross-validation and independent testing on up-to-date non-redundant datasets of 90 and 30 experimental three dimensional structures, respectively. MemConP is a standalone tool that can be downloaded together with the associated training data from http://webclu.bio.wzw.tum.de/MemConP.
Altmetric
Weitere Metriken?
Zusatzinfos bearbeiten [➜Einloggen]
Publikationstyp Artikel: Journalartikel
Dokumenttyp Wissenschaftlicher Artikel
Schlagwörter Machine Learning ; Molecular Interactions ; Protein Structure Prediction ; Sequence Analysis; Transmembrane Proteins; Data-bank; Database; Coevolution; Tm
ISSN (print) / ISBN 1047-8477
e-ISSN 1047-8477
Zeitschrift Journal of Structural Biology
Quellenangaben Band: 194, Heft: 1, Seiten: 112-123 Artikelnummer: , Supplement: ,
Verlag Elsevier
Verlagsort San Diego
Begutachtungsstatus