Skip to main navigation Skip to search Skip to main content

Visualization of Protein Structure Relationships Using Twin Kernel Embedding

Yi Guo, Junbin Gao, Paul Hing Kwan, Kevin Hou

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

In this paper, a recently proposed dimensionality reduction method called twin kernel embedding (TKE) is applied in 2-dimensional visualization of protein structure relationships. By matching the similarity measures of the input and the embedding spaces expressed by their respective kernels, TKE ensures that both local and global proximity information are preserved simultaneously. Experiments conducted on a subset of the structural classification of protein (SCOP) database confirmed the effectiveness of TKE in preserving the original relationships among protein structures in the lower dimensional embedding according to their similarities. This result is expected to benefit subsequent analyses of protein structures and their functions.
Original languageEnglish
Title of host publicationProceedings of the First International Conference on Bioinformatics and Biomedical Engineering (ICBBE 2007)
EditorsIEEE: Institute of Electrical, Electronics Engineers
Place of PublicationLos Alamitos, United States of America
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages1-4
ISBN (Print)1424411203
DOIs
Publication statusPublished - 2007
EventICBBE 2007: First International Conference on Bioinformatics and Biomedical Engineering - Wuhan, China
Duration: 6 Jul 20078 Jul 2007

Conference

ConferenceICBBE 2007: First International Conference on Bioinformatics and Biomedical Engineering
CityWuhan, China
Period6/07/078/07/07

Keywords

  • Pattern Recognition and Data Mining

Fingerprint

Dive into the research topics of 'Visualization of Protein Structure Relationships Using Twin Kernel Embedding'. Together they form a unique fingerprint.

Cite this