Please use this identifier to cite or link to this item:
|Title:||Mutli-features Predction of Protein Translational Modification Sites|
|Keywords:||post translational modification;Protein;classification|
|Citation:||IEEE/ACM Transactions on Computational Biology and Bioinformatics|
|Abstract:||— The post translational modification plays a significiant in the biological processings. The potential post translational modification is composed of the center sites and the adjacent amino acid residues which are fundamental protein sequence residues.It can be helpful to perform their biological function and contribute to understand the molecular mechanism that is the foundation of protein design and drug design. The existing algorithms of predicting modified sites often have some defects, such as stability and low accuracy. In this paper, combination of protein physical, chemical, statistical and biological properties have been ulitized as the features, a novel framework is proposed to predict protein post translational modification sites. The multi-layer neural network and support vector machine are invoked to predict the potential modified siteswith the selected features that include the amino acid residues composition, the E-H description of protein segments and several properties from the AAIndex database. Considering the redundant information, the features’ selection is proposed by the propocessing step in this research. The experimental results show that the proposed method has the ability to improving the accuracy in this classification issue.|
|Appears in Collections:||Dept of Life Sciences Research Papers|
Items in BURA are protected by copyright, with all rights reserved, unless otherwise indicated.