Designing predictors of halophilic and non-halophilic proteins using support vector machines

檔案

本條目沒有附加檔案。

日期

2013

期刊名稱

PROCEEDINGS OF THE 2013 IEEE SYMPOSIUM ON COMPUTATIONAL INTELLIGENCE IN BIOINFORMATICS AND COMPUTATIONAL BIOLOGY (CIBCB)

摘要

Finding the molecular features causes the halophilicity in the halostable organisms is helpful to understand the halophilic adaption. In this study, we proposed a prediction method for halophilic proteins by using a machine learning method. The stages of this study are six-fold. First, we establish a non-redundant dataset of the halophilic proteins, collected from NCBI, Uniprotkb and EMBL-EBI databases. The dataset consists of 245 positive and negative proteins with sequence identity < 25%. Second, the protein sequences are represented by three types of feature vector sets which include amino acid composition, dipeptide composition, and physicochemical properties. Third, we propose three classifiers based on support vector machine (SVM) to classify the halophilic proteins and non-halophilic proteins. Fourth, the independent test accuracies of the three efficient classifiers are larger than 83%. Fifth, an inheritable bi-objective combinatory genetic algorithm is utilized to select a set of 11 physicochemical properties (PCPs). Sixth, these abundant amino acids, high different dipeptides (amino acid pair) and 11 informative PCPs can support to analyze the halophilic and non-halophilic proteins.

所屬典藏

會議論文
顯示完整詮釋資料 統計資料