HAL will be down for maintenance from Friday, June 10 at 4pm through Monday, June 13 at 9am. More information
Skip to Main content Skip to Navigation
Conference papers

Knowledge-based consensus methods for secondary structure prediction of transmembrane beta-barrel proteins

Saad Sheikh 1, 2 van Du Tran 3, 1 Philippe Chassignet 1 Jean-Marc Steyaert 1
1 AMIB - Algorithms and Models for Integrative Biology
LIX - Laboratoire d'informatique de l'École polytechnique [Palaiseau], LRI - Laboratoire de Recherche en Informatique, UP11 - Université Paris-Sud - Paris 11, Inria Saclay - Ile de France
Abstract : Transmembrane β-barrel proteins are an important class of proteins that span the entire membrane and form a β-barrel structure. They play key roles in human body and are targeted by modern medicine. Computational and experimental difficulties in determining their structure have limited the number of resolved structures to a tiny percentage of the Protein Data Bank. As a result, over the years a number of methods based on different assumptions and models have been proposed. In this paper, we discuss consensus methods for combining results from different sources. We show how these methods can be used to improve the prediction power significantly and thus form the most accurate method for secondary structure prediction. We also discuss interpretation of basic social-choice theory axioms and results in the context of secondary structure prediction of proteins.
Complete list of metadata

Contributor : Frédéric Davesne Connect in order to contact the contributor
Submitted on : Tuesday, September 17, 2013 - 12:35:44 PM
Last modification on : Thursday, July 8, 2021 - 3:47:58 AM


  • HAL Id : hal-00862702, version 1


Saad Sheikh, van Du Tran, Philippe Chassignet, Jean-Marc Steyaert. Knowledge-based consensus methods for secondary structure prediction of transmembrane beta-barrel proteins. 4th International Conference on Bioinformatics and Computational Biology 2012 (BICoB 2012), Mar 2012, Las Vegas, NV, United States. pp.79--84. ⟨hal-00862702⟩



Record views