Tree-based consensus model for proline cis-trans isomerization prediction

Paul D. Yoo, Albert Y. Zomaya, Khalfan Alromaithi, Sara Alshamsi

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations

Abstract

Proline cis-trans isomerization plays a key role in the rate-determining steps of protein folding. Accurate prediction of proline cis-trans isomerization is of great importance for the understanding of protein folding, splicing, cell signaling, and transmembrane active transport in both the human body and animals. Our goal is to develop a state-of-The-Art proline cis-trans isomerization predictor with a biophysically-motivated consensus model through the use of evolutionary information only. The current computational predictors of proline cis-trans isomerization achieve about 70-73% accuracies through the use of evolutionary information as well as predicted protein secondary structure information. However, our methods that utilize support vector machine (SVM) and tree-based consensus model have achieved 76.72% and 81.5% accuracies, respectively, on the same proline dataset.

Original languageBritish English
Title of host publicationProceedings - IEEE 27th International Parallel and Distributed Processing Symposium Workshops and PhD Forum, IPDPSW 2013
PublisherIEEE Computer Society
Pages454-458
Number of pages5
ISBN (Print)9780769549798
DOIs
StatePublished - 2013
Event2013 IEEE 37th Annual Computer Software and Applications Conference, COMPSAC 2013 - Boston, MA, Japan
Duration: 22 Jul 201326 Jul 2013

Publication series

NameProceedings - IEEE 27th International Parallel and Distributed Processing Symposium Workshops and PhD Forum, IPDPSW 2013

Conference

Conference2013 IEEE 37th Annual Computer Software and Applications Conference, COMPSAC 2013
Country/TerritoryJapan
CityBoston, MA
Period22/07/1326/07/13

Keywords

  • consensus modeling
  • machine learning
  • proline cis-trans isomerization

Fingerprint

Dive into the research topics of 'Tree-based consensus model for proline cis-trans isomerization prediction'. Together they form a unique fingerprint.

Cite this