Title

Prediction of Protein Subcellular Localization: A Machine Learning Approach

Publication Type

Report

Publication Date

2010

Abstract

Subcellular localization is a key functional characteristic of proteins. Optimally combining available information is one of the key challenges in today's knowledge-based subcellular localization prediction approaches. This study explores machine learning approaches for the prediction of protein subcellular localization that use resources concerning Gene Ontology and secondary structures. Using the spectrum kernel for feature representation of amino acid sequences and secondary structures, we explore an SVM-based learning method that classifies six subcellular localization sites: endoplasmic reticulum, extracellular, Golgi, membrane, mitochondria, and nucleus.

Discipline

Databases and Information Systems

Research Areas

Data Management and Analytics

Publication

Technical Report University of Minnesota Department of Computer Science and Engineering

Issue

TR10-4

First Page

1

Last Page

15

Publisher

University of Minnesota

City or Country

Minneapolis, MN

Additional URL

http://www.cs.umn.edu/research/technical_reports.php?page=report&report_id=10-014