Machine Learning based Predictive Model for Screening Mycobacterium Tuberculosis Transcriptional Regulatory Protein Inhibitors from High-Throughput Screening Dataset
Journal Title: International Journal of Advanced Computer Science & Applications - Year 2017, Vol 8, Issue 12
Abstract
In view of the essential role played by dosRS in the survival of Mycobacterium in the infected granuloma cells, dosRS transcriptional regulatory proteins were considered as a validated target for high throughput screening (HTS). However, the cost and time factor involved in screening large compound libraries are an important hurdle in identifying lead compounds. Therefore, the use of computational machine learning techniques to build a predictive model for screening putative drug-like molecule has gained significance. In this regard, a target-based predictive model using machine learning approaches was built to develop fast and efficient virtual screening procedures to screen anti-dosRS molecules. In the present study, we have used various structural and physiochemical attributes of compounds from HTS dataset to train and build a chemoinformatics predictive model based on four state-of-art supervised classifiers (Random forest, SMO, J48, and Naïve Bayes). The trained model was applied to test dataset for validating the robustness, accuracy, and sensitivity of the predictive model in screening active anti-dosRS molecules. The Cost-Sensitive Classifier (CSC) with Random Forest (RF) algorithm based predictive model showed a high sensitivity (100%) and specificity (83.13%) to identify active and inactive molecules, respectively from assay dataset (ID: 1159583). CSC-RF proved to more robust and efficient in classifying active molecule from an imbalanced dataset with highest Balancing Classification Rate (BCR) (91.57%) and maximum Area under the Curve (AUC) value (0.999).
Authors and Affiliations
Syed Asif Hassan, Tabrej Khan
Keywords
Related Articles
- EP ID EP258304
- DOI 10.14569/IJACSA.2017.081215
- Views 105
- Downloads 0
Security Concerns in E-payment and the Law in Jordan
Recently communications and information technology became widely used in various aspects of life. The internet becomes the main network for information support. Using of internet enabled public and private organizations...
Use of Technology and Financial Literacy on SMEs Practices and Performance in Developing Economies
Micro, Small and Medium Enterprises (SMEs) practices in developing economies experience a unique set of challenges to attain their success. With a view of analyzing double impact of SME financial literacy and use of tech...
Mobile Software Testing: Thoughts, Strategies, Challenges, and Experimental Study
Mobile devices have become more pervasive in our daily lives, and are gradually replacing regular computers to perform traditional processes like Internet browsing, editing photos, playing videos and sound track, and rea...
Routing Optimization in WBAN using Bees Algorithm for Overcrowded Hajj Environment
Crowded places like Hajj environment in Makkah which host from 2 to 3 million on specific area and time can pose health challenges for pilgrims who need medical care. One of the solutions to overcome such difficulties is...
Automated Player Selection for a Sports Team using Competitive Neural Networks
The use of data analytics to constitute a winning team for the least cost has become the standard modus operandi in club leagues, beginning from Sabermetrics for the game of basketball. Our motivation is to implement thi...