Nuclear localization signal prediction based on sequential pattern mining

  • Authors:

  • Jhih-Rong Lin;Jianjun Hu

  • Affiliations:

  • University of South Carolina, Columbia, SC;University of South Carolina, Columbia, SC

  • Venue:
  • Proceedings of the ACM Conference on Bioinformatics, Computational Biology and Biomedicine
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

Abstract

Nuclear Localization Signals (NLS) are the most direct evidence for nuclear localization of proteins. Despite a couple of NLS prediction methods have been developed, the prediction performance is far from being satisfactory. In this study we proposed a sequential pattern mining based algorithm for identifying NLSs from protein sequences. The experiment results showed that our method can achieve better or comparable prediction performance than existing NLS prediction methods, which indicates that the motif residues discovered by our algorithm are effective features for predicting NLS.