TY - JOUR A2 - Huang, Yanxin AU - Feng, Peng-Mian AU - Ding, Hui AU - Chen, Wei AU - Lin, Hao PY - 2013 DA - 2013/05/15 TI - Naïve Bayes Classifier with Feature Selection to Identify Phage Virion Proteins SP - 530696 VL - 2013 AB - Knowledge about the protein composition of phage virions is a key step to understand the functions of phage virion proteins. However, the experimental method to identify virion proteins is time consuming and expensive. Thus, it is highly desirable to develop novel computational methods for phage virion protein identification. In this study, a Naïve Bayes based method was proposed to predict phage virion proteins using amino acid composition and dipeptide composition. In order to remove redundant information, a novel feature selection technique was employed to single out optimized features. In the jackknife test, the proposed method achieved an accuracy of 79.15% for phage virion and nonvirion proteins classification, which are superior to that of other state-of-the-art classifiers. These results indicate that the proposed method could be as an effective and promising high-throughput method in phage proteomics research. SN - 1748-670X UR - https://doi.org/10.1155/2013/530696 DO - 10.1155/2013/530696 JF - Computational and Mathematical Methods in Medicine PB - Hindawi Publishing Corporation KW - ER -