Header logo is

Protein homology detection using string alignment kernels




Remote homology detection between protein sequences is a central problem in computational biology. Discriminative methods involving support vector machines (SVM) are currently the most effective methods for the problem of superfamily recognition in the SCOP database. The performance of SVMs depend critically on the kernel function used to quantify the similarity between sequences. We propose new kernels for strings adapted to biological sequences, which we call local alignment kernels. These kernels measure the similarity between two sequences by summing up scores obtained from local alignments with gaps of the sequences. When tested in combination with SVM on their ability to recognize SCOP superfamilies on a benchmark dataset, the new kernels outperform state-of-the art methods for remote homology detection.

Author(s): Saigo, H. and Vert, J-P. and Ueda, N. and Akutsu, T.
Journal: Bioinformatics
Volume: 20
Number (issue): 11
Pages: 1682-1689
Year: 2004
Day: 0

Department(s): Empirical Inference
Bibtex Type: Article (article)

Digital: 0
DOI: 10.1093/bioinformatics/bth141
Organization: Max-Planck-Gesellschaft
School: Biologische Kybernetik

Links: Web


  title = {Protein homology detection using string alignment kernels},
  author = {Saigo, H. and Vert, J-P. and Ueda, N. and Akutsu, T.},
  journal = {Bioinformatics},
  volume = {20},
  number = {11},
  pages = {1682-1689},
  organization = {Max-Planck-Gesellschaft},
  school = {Biologische Kybernetik},
  year = {2004}