SMOPredT4SE: An Effective Prediction of Bacterial Type IV Secreted Effectors Using SVM Training With SMO

Zihao Yan,Donghua Wang,Yanjuan Li,Dong Chen,Zhixia Teng

doi:10.1109/access.2020.2971091

Zihao Yan, Donghua Wang + Show 3 more

Open Access

PDF Available

https://doi.org/10.1109/access.2020.2971091

Copy DOI

Export

Save

Cite

Abstract
Highlights/Summary
Full-Text PDF
Similar Papers

Abstract

Listen

Various bacterial pathogens can deliver their secreted effectors to host cells via type IV secretion system (T4SS) and cause host diseases. Since T4SS secreted effectors (T4SEs) play important roles in the interaction between pathogens and host, identifying T4SEs is crucial to understanding of the pathogenic mechanism of T4SS. We established an effective predictor called SMOPredT4SE to identify T4SEs from protein sequences. SMOPredT4SE employed combination features of series correlation pseudo amino acid composition and position-specific scoring matrix to present protein sequences, and employed support vector machines (SVM) training with sequential minimal optimization (SMO) arithmetic to train the prediction model (To distinguish it from the traditional SVM, we will abbreviate it as SMO later). In the 5-fold cross-validation test, SMOPredT4SE's overall accuracy was 95.6%. Experiments on comparison with other feature, classifiers, and existing methods are conducted. Experimental results show the effectiveness of SMOPredT4SE in predicting T4SEs.

Highlights

Gram-negative bacteria are generally classified as bacteria that become red with gram staining, many of which are common bacteria that cause hospital infections
The results show that the combination of SC-PseAAC and position-specific scoring matrix (PSSM)-composition performed better than the other features and combinations
In this work, we propose a simple, efficient, and reliable experimental method for predicting gram-negative bacteria T4SS secreted effectors (T4SEs) based on machine learning algorithms

Summary

Introduction

Gram-negative bacteria are generally classified as bacteria that become red with gram staining, many of which are common bacteria that cause hospital infections. 100 years after the discovery of a bacterial ‘endotoxin’, 50 years after the introduction of antibiotics, and 25 years after the routine use of intensive care units to support septic shock patients, gram-negative infections continue to account for significant morbidity and mortality [3]. According to their outer membrane secretion mechanisms, gram-negative bacteria have been identified into eight different secretion systems (type I to type VIII) [4], all of which show differences. Due to the importance of T4SEs in biology, many experimental methods have been developed to identify them, such as genetic complementation, reporter protein fusion, and secretion

Methods

Results

Conclusion