Type III secretion system (T3SSs) can be detected in lots of pathogenic bacteria, such as Dysentery bacillus, Salmonella Typhimurium, Vibrio cholera and Pathogenic E. coli, etc. The route of infection is T3SSs transfer a large number of Type III Secreted Effectors (T3SEs) to host cells, thereby blocking or adjusting the communication channels of the host cells. Therefore, accurate identification of T3SEs is the precondition for further study the pathogenic bacteria pathology. In this paper, a new T3SEs ensemble predictor was developed, which can accurately distinguish T3SEs from any unknown protein.


EP3 can identify T3SEs, accurately.The supported file formats are : Fasta



Instead of overfitting training model, a predictor without parameter optimization was exploited, which can automatically extract features, select features and calculate indicators. In the course of the experiment, methods and models are strictly trained and tested. Compared with other methods, EP3 demonstrate stronger superiority, such as without overfitting, strong robustness and powerful generalization. EP3 is designed to simplify the user (especially non-professional) access to T3SEs for further investigation, which will have a significant impact on understanding the pathogenesis of pathogenic bacteria. Based on the integration model that we raised, a web server had been set up to identify T3SE from non-T3SE.


  1. Xue, Li, et al. DeepT3: deep convolutional neural networks accurately identify Gram-negative bacterial type III secreted effectors using the N-terminal sequence. Bioinformatics, 2018.
  2. Wang, Jiawei, et al. Bastion3: a two-layer ensemble predictor of type III secreted effectors. Bioinformatics, 2018. 10.

all rights reserved@ 2019 | Quan Zou, Ph.D. & Professor
Last modified date:31/10/2019