Mycobacterium tuberculosis (Mtb) is critically responsible to make deadly tuberculosis (TB) disease of the human being. Among the 10 reasons for human deaths, TB is the foremost cause of them mentioned by the ‘Global TB report 2018’ issued by the World Health Organization (WHO). TB is universal health anxiety, mostly in developing countries. It is assessed that 44% TB covered by only three high-risk countries such as India, China, and Indonesia.
In this work, we have developed a novel predictor, iAntiTB (Identification of Anti-tubercular Peptides), by integrating sequence-based features through combining of Random Forest (RF) and Support Vector Machine (SVM) classifiers.
It is noted that, for predicting the anti-TB peptide the first and second negative datasets were retrieved from the non-anti-bacterial and anti-bacterial peptides, respectively.