Protein structural class determination using support vector machines

Işık, Zerrin and Yanıkoğlu, Berrin and Sezerman, Uğur (2004) Protein structural class determination using support vector machines. Lecture notes in computer science, 3280 . pp. 82-89. ISSN 0302-9743 (Print) 1611-3349 (Online)

[thumbnail of 3011800001044.pdf] PDF
Restricted to Repository staff only

Download (141kB) | Request a copy


Proteins can be classified into four structural classes (all-a, all-beta, alpha/beta, alpha+beta) according to their secondary structure composition. In this paper, we predict the structural class of a protein from its Amino Acid Composition (AAC) using Support Vector Machines (SVM). A protein can be represented by a 20 dimensional vector according to its AAC. In addition to the AAC, we have used another feature set, called the Trio Amino Acid Composition (Trio AAC) which takes into account the amino acid neighborhood information. We have tried both of these features, the AAC and the Trio AAC, in each case using a SVM as the classification tool, in predicting the structural class of a protein. According to the Jackknife test results, Trio AAC feature set shows better classification performance than the AAC feature.
Item Type: Article
Additional Information: 19th International Symposium, Kemer-Antalya, Turkey, October 27-29, 2004. Proceedings / Book: Computer and Information Sciences - ISCIS 2004 / Category: Artificial Intelligence and Machine Learning / ISBN: 978-3-540-23526-2
Subjects: Q Science > QA Mathematics > QA075 Electronic computers. Computer science
Divisions: Faculty of Engineering and Natural Sciences
Depositing User: Berrin Yanıkoğlu
Date Deposited: 19 Feb 2007 02:00
Last Modified: 26 Apr 2022 08:08

Actions (login required)

View Item
View Item