Abstract
Tuberculosis is killing millions of lives every year and on the blacklist of the most appalling public health problems. Recent findings suggest that secretory protein of Mycobacterium tuberculosis may serve the purpose of developing specific vaccines and drugs due to their antigenicity. Responding to global infectious disease, we focused on the identification of secretory proteins in Mycobacterium tuberculosis. A novel method called MycoSec was designed by incorporating g-gap dipeptide compositions into pseudo amino acid composition. Analysis of variance-based technique was applied in the process of feature selection and a total of 374 optimal features were obtained and used for constructing the final predicting model. In the jackknife test, MycoSec yielded a good performance with the area under the receiver operating characteristic curve of 0.93, demonstrating that the proposed system is powerful and robust. For user's convenience, the web server MycoSec was established and an obliging manual on how to use it was provided for getting around any trouble unnecessary.
Highlights
Mycobacterium tuberculosis (M. tuberculosis or MTB), known as acid-fast bacilli, is the causative pathogen of the contagious disease tuberculosis (TB)
To guarantee a good quality of data, proteins in Universal Protein Resource (UniProt) were collected confidently according to the following criteria: (I) only those from M. tuberculosis were considered; (II) only those reviewed and annotated by experts were chosen; (III) sequences with ambiguous residues, such as “B,” “X,” and “Z,” were discarded; (IV) sequences that were inferred from homologous proteins were eliminated; (V) sequences that were fragments of other proteins were excluded; (VI) sequences that have less than 16 amino acids were removed to meet the parameter (λ) requirement; (VII) sequences with the keyword “secreted” or “secretory vesicle” in the “subcellular location” column were regarded as secretory proteins, while sequences without these keywords were considered as nonsecretory proteins
In view of computational efficiency, fivefold cross-validation was firstly employed to cope with the prioritization of parameters, and once the optimal values were determined, the rigorous jackknife test was performed to evaluate the success rates of the feature set according to the four metrics defined in Performance Evaluation section
Summary
Mycobacterium tuberculosis (M. tuberculosis or MTB), known as acid-fast bacilli, is the causative pathogen of the contagious disease tuberculosis (TB). Recent researches suggest that secretory protein antigens can be used to detect antibodies in infected specimens [3]. It is a well-established fact that effector proteins are mostly secretory proteins that stimulate infection by manipulating the host response [4].
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
