Computational and Mathematical Methods in Medicine
Volume 2012 (2012), Article ID 696190, 6 pages
Research Article

Identification of Novel Type III Effectors Using Latent Dirichlet Allocation

Department of Computer Science and Engineering, Information Engineering College, Shanghai Maritime University, 1550 Haigang Avenue, Shanghai 201306, China

Received 14 May 2012; Revised 7 August 2012; Accepted 12 August 2012

Academic Editor: Chunmei Liu

Copyright © 2012 Yang Yang. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.


Among the six secretion systems identified in Gram-negative bacteria, the type III secretion system (T3SS) plays important roles in the disease development of pathogens. T3SS has attracted a great deal of research interests. However, the secretion mechanism has not been fully understood yet. Especially, the identification of effectors (secreted proteins) is an important and challenging task. This paper adopts machine learning methods to identify type III secreted effectors (T3SEs). We extract features from amino acid sequences and conduct feature reduction based on latent semantic information by using latent Dirichlet allocation model. The experimental results on Pseudomonas syringae data set demonstrate the good performance of the new methods.