Partial profile alignment kernels for protein classification

Thanh Ngo, Rui Kuang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Remote homology detection and fold recognition are the central problems in protein classification. In real applications, kernel algorithms that are both accurate and efficient are required for classification of large databases. We explore a class of partial profile alignment kernels to be used with support vector machines (SVMs) for remote homology detection and fold recognition. While existing profile-based kernels use the whole profiles to determine the similarity between pairs of proteins, the partial profile alignment kernels are derived from part of the position specific scoring matrices (PSSMs) in the profiles for alignment. Specifically, at each position in the PSSM, only amino acids in the mutationneighborhood of the corresponding amino acid in the original protein sequence are considered for alignment to remove noise and improve computing efficiency. Our experiments on SCOP bench datasets show that the partial profile alignmentkernels achieved overall better classification results for both fold recognition and remote homology detection than profile kernels and profile-alignment kernels. In addition, our algorithm using only a fraction of the profiles saves the cost of computing the kernels significantly, compared to the full-profile alignment methods.

Original languageEnglish (US)
Title of host publication2009 IEEE International Workshop on Genomic Signal Processing and Statistics, GENSIPS 2009
DOIs
StatePublished - Oct 2 2009
Event2009 IEEE International Workshop on Genomic Signal Processing and Statistics, GENSIPS 2009 - Minneapolis, MN, United States
Duration: May 17 2009May 21 2009

Publication series

Name2009 IEEE International Workshop on Genomic Signal Processing and Statistics, GENSIPS 2009

Other

Other2009 IEEE International Workshop on Genomic Signal Processing and Statistics, GENSIPS 2009
CountryUnited States
CityMinneapolis, MN
Period5/17/095/21/09

Fingerprint Dive into the research topics of 'Partial profile alignment kernels for protein classification'. Together they form a unique fingerprint.

  • Cite this

    Ngo, T., & Kuang, R. (2009). Partial profile alignment kernels for protein classification. In 2009 IEEE International Workshop on Genomic Signal Processing and Statistics, GENSIPS 2009 [5174328] (2009 IEEE International Workshop on Genomic Signal Processing and Statistics, GENSIPS 2009). https://doi.org/10.1109/GENSIPS.2009.5174328