Discrimination of outer membrane proteins using a <Emphasis Type="Italic">K</Emphasis>-nearest neighbor method |
| |
Authors: | C Yan J Hu Y Wang |
| |
Institution: | Department of Computer Science, Utah State University, Logan, UT 84322-4205, USA. charles.yan@usu.edu |
| |
Abstract: | Identification of outer membrane proteins (OMPs) from genome is an important task. This paper presents a k-nearest neighbor (K-NN) method for discriminating outer membrane proteins (OMPs). The method makes predictions based on a weighted Euclidean distance that is computed from residue composition. The method achieves 89.1% accuracy with 0.668 MCC (Matthews correlation coefficient) in discriminating OMPs and non-OMPs. The performance of the method is improved by including homologous information into the calculation of residue composition. The final method achieves an accuracy of 96.1%, with 0.873 MCC, 87.5% sensitivity, and 98.2% specificity. Comparisons with multiple recently published methods show that the method proposed in this study outperforms the others. |
| |
Keywords: | |
本文献已被 PubMed SpringerLink 等数据库收录! |
|