iAtbP-Hyb-EnC: Prediction of antitubercular peptides via heterogeneous feature representation and genetic algorithm based ensemble learning model

• Published in: Computers in biology and medicine Vol. 137; p. 104778
• Main Authors: Akbar, Shahid, Ahmad, Ashfaq, Hayat, Maqsood, Rehman, Ateeq Ur, Khan, Salman, Ali, Farman
• Format: Journal Article
• Language: English
• Published: Oxford Elsevier Ltd 01.10.2021; Elsevier Limited
• Subjects: Algorithms; Amino acid composition; Amino acids; Antibiotics; Antitubercular peptides; Classification; Composite physiochemical properties; Datasets; Drug resistance; Ensemble classification; Ensemble learning; Feature extraction; Feature selection; Genetic algorithm; Genetic algorithms; k-fold cross-validation test; Machine learning; Model accuracy; Multidrug resistance; One-hot encoding; Peptides; Physiochemistry; Prediction models; Proteins; Representations; Selectivity; Source code; Training; Tuberculosis; Composite physiochemical properties; One-hot encoding; Ensemble classification; k-fold cross-validation test; Antitubercular peptides; Genetic algorithm
• ISSN: 0010-4825; 1879-0534
• DOI: 10.1016/j.compbiomed.2021.104778

Tuberculosis (TB) is a worldwide illness caused by the bacteria Mycobacterium tuberculosis. Owing to the high prevalence of multidrug-resistant tuberculosis, numerous traditional strategies for developing novel alternative therapies have been presented. The effectiveness and dependability of these procedures are not always consistent. Peptide-based therapy has recently been regarded as a preferable alternative due to its excellent selectivity in targeting specific cells without affecting the normal cells. However, due to the rapid growth of the peptide samples, predicting TB accurately has become a challenging task. To effectively identify antitubercular peptides, an intelligent and reliable prediction model is indispensable. An ensemble learning approach was used in this study to improve expected results by compensating for the shortcomings of individual classification algorithms. Initially, three distinct representation approaches were used to formulate the training samples: k-space amino acid composition, composite physiochemical properties, and one-hot encoding. The feature vectors of the applied feature extraction methods are then combined to generate a heterogeneous vector. Finally, utilizing individual and heterogeneous vectors, five distinct nature classification models were used to evaluate prediction rates. In addition, a genetic algorithm-based ensemble model was used to improve the suggested model's prediction and training capabilities. Using Training and independent datasets, the proposed ensemble model achieved an accuracy of 94.47% and 92.68%, respectively. It was observed that our proposed “iAtbP-Hyb-EnC” model outperformed and reported ~10% highest training accuracy than existing predictors. The “iAtbP-Hyb-EnC” model is suggested to be a reliable tool for scientists and might play a valuable role in academic research and drug discovery. The source code and all datasets are publicly available at https://github.com/Farman335/iAtbP-Hyb-EnC. •An Intelligent Computational model is developed for Prediction of Antitubercular peptides•A heterogeneous Vector representing three different feature encoding schemes are utilized.•Genetic Algorithm based Ensemble learning Approach is used to evaluate the model.•Obtained quite promising results than existing methods.