Format

Send to

Choose Destination
Front Pharmacol. 2018 Aug 28;9:954. doi: 10.3389/fphar.2018.00954. eCollection 2018.

Prediction of Antitubercular Peptides From Sequence Information Using Ensemble Classifier and Hybrid Features.

Author information

1
Center for Computational Biology, Indraprastha Institute of Information Technology, New Delhi, India.
2
Bioinformatics Centre, CSIR-Institute of Microbial Technology, Chandigarh, India.

Abstract

Tuberculosis is one of the leading cause of death worldwide, particularly due to evolution of drug resistant strains. Antitubercular peptides may provide an alternate approach to combat antibiotic tolerance. Sequence analysis reveals that certain residues (e.g., Lysine, Arginine, Leucine, Tryptophan) are more prevalent in antitubercular peptides. This study describes the models developed for predicting antitubercular peptides by using sequence features of the peptides. We have developed support vector machine based models using different sequence features like amino acid composition, binary profile of terminus residues, dipeptide composition. Our ensemble classifiers that combines models based on amino acid composition and N5C5 binary pattern, achieves highest Acc of 73.20% with 0.80 AUROC on our main dataset. Similarly, the ensemble classifier achieved maximum Acc 75.62% with 0.83 AUROC on secondary dataset. Beside this, hybrid model achieves Acc of 75.87 and 78.54% with 0.83 and 0.86 AUROC on main and secondary dataset, respectively. In order to facilitate scientific community in designing of antitubercular peptides, we implement above models in a user friendly webserver (http://webs.iiitd.edu.in/raghava/antitbpred/).

KEYWORDS:

Mycobacterium; antimycobacterial therapy; antitubercular peptides; drug discovery; ensemble classifier; machine learning; tuberculosis

Supplemental Content

Full text links

Icon for Frontiers Media SA Icon for PubMed Central
Loading ...
Support Center