Functional annotation of proteins by a novel method using weight and feature selection

Jaehee Jung, Heung Ki Lee, Gangman Yi

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

Abstract

The definition of the automatic protein function means designating the function with the automation by utilizing the data that already revealed unknown protein function. The demand for analysis on the sequencing technology such as the next generation genome analysis (NGS) and the subsequent genome are on the rise; thus, the need for the method of predicting the protein function automatically has been more and more highlighted. As for the existing methods, the studies on the definition of function between the similar species based on the similarities of sequence have been primarily conducted. However, this paper aims to designate by automatically predicting the function of genome by utilizing InterPro (IPR) that can represent the properties of the protein family, which similarly groups the protein function. Moreover, the gene ontology (GO), which is the controlled vocabulary to describe the protein function comprehensively, is to be used. As for the data used in the experiment, the analysis on properties was conducted in the sparse state that is deflected to one side. Thus, this paper aims to analyze the prediction method for protein function automatically through selecting the features, assigning the data processing and weights and applying a variety of classification methods to overcome that property.

Original languageEnglish
Title of host publicationFrontier and Innovation in Future Computing and Communications
EditorsAlbert Zomaya, James J. Park, Hwa-Young Jeong, Mohammad Obaidat
PublisherSpringer Verlag
Pages785-797
Number of pages13
ISBN (Electronic)9789401787970
DOIs
StatePublished - 2014
Event2014 FTRA International Symposium on Frontier and Innovation in Future Computing and Communications, FCC 2014 - Auckland, New Zealand
Duration: 13 Jan 201416 Jan 2014

Publication series

NameLecture Notes in Electrical Engineering
Volume301
ISSN (Print)1876-1100
ISSN (Electronic)1876-1119

Conference

Conference2014 FTRA International Symposium on Frontier and Innovation in Future Computing and Communications, FCC 2014
Country/TerritoryNew Zealand
CityAuckland
Period13/01/1416/01/14

Keywords

  • Adaboosting
  • Functional annotation
  • Gene annotation
  • Gene ontology
  • GO
  • InterPro
  • IPR
  • SMO
  • SVM

Fingerprint

Dive into the research topics of 'Functional annotation of proteins by a novel method using weight and feature selection'. Together they form a unique fingerprint.

Cite this