• TUCS Publication Series
• How to Publish in TUCS Series
• Publication Search
• Publication Graph
• Publication Input
• Publication Input Guide
• JuFo Browser

Locality Kernels for Protein Classification

Evgeni Tsivtsivadze, Jorma Boberg, Tapio Salakoski, Locality Kernels for Protein Classification. In: Sridhar Hannenhalli Raffaele Giancarlo (Ed.), Algorithms in Bioinformatics, 7th International Workshop, Lecture Notes in Computer Science 4645, 2–11, Springer, 2007.

Abstract:

We propose kernels that take advantage of local correlations in sequential data and present their application to the protein classification problem. Our locality kernels measure protein sequence similarities within a small window constructed around matching amino acids. The kernels incorporate positional information of the amino acids inside the window and allow a range of position dependent similarity evaluations. We use these kernels with regularized least-squares algorithm (RLS) for protein classification on the SCOP database. Our experiments demonstrate that the locality kernels perform significantly better than the spectrum and the mismatch kernels. When used together with RLS, performance of the locality kernels is comparable with some state-of-the-art methods of protein classification and remote homology detection.

Files:

Full publication in PDF-format

BibTeX entry:

@INPROCEEDINGS{inpTsBoSa07a,
  title = {Locality Kernels for Protein Classification},
  booktitle = {Algorithms in Bioinformatics, 7th International Workshop},
  author = {Tsivtsivadze, Evgeni and Boberg, Jorma and Salakoski, Tapio},
  volume = {4645},
  number = {978-3-540-74125-1},
  series = {Lecture Notes in Computer Science},
  editor = {Raffaele Giancarlo, Sridhar Hannenhalli},
  publisher = {Springer},
  pages = {2–11},
  year = {2007},
  keywords = {kernel methods, protein classification},
}

Belongs to TUCS Research Unit(s): Turku BioNLP Group

Publication Forum rating of this publication: level 1

Edit publication