Abstract
Protein homology detection is a core problem in bioinformatics that helps annotate protein structural and functional features. It can be naturally formed as a mixed integer programming (MIP) problem with semi-supervised support vector machines (SVMs), which are accurate discriminative methods for classification. This article presents two new semidefinite programming (SDP) models for protein homology detection by using novel transformations of the MIP problem. Both models reduce the problem size significantly compared with the existing SDP models. Numerical experiments show that our first SDP model outperforms other methods in terms of misclassification errors for both synthetic data and the real data from the Protein Classification Benchmark Collection.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
