Change search
ReferencesLink to record
Permanent link

Direct link
Using multi-data hidden Markov models trained on local neighborhoods of protein structure to predict residue-residue contacts.
The Linnaeus Centre for Bioinformatics, Uppsala University, Uppsala. (Stockholm Bioinformatics Center, Albanova, Stockholm University, 10691 Stockholm, Sweden)
Department of Biophysics, Faculty of Physics, University of Warsaw, Warsaw, Poland.
UC Davis Genome Centre, UC Davis, USA.
UC Davis Genome Centre, UC Davis, USA.
Show others and affiliations
2009 (English)In: Bioinformatics, ISSN 1367-4803, E-ISSN 1460-2059, Vol. 25, no 10, 1264-1270 p.Article in journal (Refereed) Published
Abstract [en]

MOTIVATION: Correct prediction of residue-residue contacts in proteins that lack good templates with known structure would take ab initio protein structure prediction a large step forward. The lack of correct contacts, and in particular long-range contacts, is considered the main reason why these methods often fail. RESULTS: We propose a novel hidden Markov model (HMM)-based method for predicting residue-residue contacts from protein sequences using as training data homologous sequences, predicted secondary structure and a library of local neighborhoods (local descriptors of protein structure). The library consists of recurring structural entities incorporating short-, medium- and long-range interactions and is general enough to reassemble the cores of nearly all proteins in the PDB. The method is tested on an external test set of 606 domains with no significant sequence similarity to the training set as well as 151 domains with SCOP folds not present in the training set. Considering the top 0.2 x L predictions (L = sequence length), our HMMs obtained an accuracy of 22.8% for long-range interactions in new fold targets, and an average accuracy of 28.6% for long-, medium- and short-range contacts. This is a significant performance increase over currently available methods when comparing against results published in the literature.

Place, publisher, year, edition, pages
2009. Vol. 25, no 10, 1264-1270 p.
National Category
Biological Sciences
URN: urn:nbn:se:umu:diva-22632DOI: 10.1093/bioinformatics/btp149PubMedID: 19289446OAI: diva2:217485
Available from: 2009-05-14 Created: 2009-05-14 Last updated: 2015-04-29Bibliographically approved

Open Access in DiVA

No full text

Other links

Publisher's full textPubMed

Search in DiVA

By author/editor
Hvidsten, Torgeir
By organisation
Department of Plant PhysiologyUmeå Plant Science Centre (UPSC)
In the same journal
Biological Sciences

Search outside of DiVA

GoogleGoogle Scholar
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Altmetric score

Total: 44 hits
ReferencesLink to record
Permanent link

Direct link