Universiti Teknologi Malaysia Institutional Repository

Enhancement of support vector machine for remote protein homology detection and fold recognition

M. M., Hilmi and S., Puteh and M. O., Razib (2009) Enhancement of support vector machine for remote protein homology detection and fold recognition. In: 5th Post-Graduate Annual Research Seminars( PARS’09), 2009, Faculty of Science and Information System, UTM.

Full text not available from this repository.

Official URL: https://www.semanticscholar.org/paper/Enhancement-...

Abstract

Remote protein homology detection and fold recognition refers to detection of structural homology in proteins where there are small or no similarity in the sequence. The issues arise on how to accurately classify remote protein homology and fold recognition in the context of Structural Classification of Proteins (SCOP) hierarchy database and incorporate biological knowledge at the same time. Homology-based methods have been developed to detect protein structural classes from protein primary sequence information which can be divided to three types: discriminative classifiers, generative models for protein families and pairwise sequence comparisons. We present a comprehensive method based on two-layer multiclass classifiers. The first layer is used detect up to superfamily and family in SCOP hierarchy by using optimized binary SVM classification rules directly to ROC-Area. The second layer uses discriminative SVM algorithm with a state-of-the-art string kernel based on PSI-BLAST profiles that used to leverage the unlabeled data. It will detect up to fold in SCOP hierarchy. We evaluated the results obtained using mean ROC and mean MRFP. Experimental results show that our approaches significantly improve the performance of protein remote protein homology detection for all three different datasets (SCOP 1.53, 1.67 and 1.73). We achieved 0.03% improvements in term of mean ROC in dataset SCOP 1.53, 1.17% in dataset SCOP 1.67 and 0.33% in dataset SCOP 1.73 when compared to the result produced by state-of-the-art methods.

Item Type:Conference or Workshop Item (Paper)
Subjects:Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions:Computer Science and Information System (Formerly known)
ID Code:16181
Deposited By: Mrs Liza Porijo
Deposited On:20 Oct 2011 09:50
Last Modified:19 Jul 2017 04:32

Repository Staff Only: item control page