1Professor, Department of Biomedical Engineering, Sri Shakthi Institute of Engineering and Technology, Coimbatore
2Assistant Professor, Department of Electronics and Instrumentation Engineering, Sri Sairam Engineering College, Chennai
3Assistant Professor, Department of Biomedical Engineering, Chennai Institute of Technology, Chennai
4Assistant Professor, Department of Electronics and Communication Engineering, Mahendra College of Engineering, Salem
5Assistant Professor, Department of Biomedical Engineering, Mahendra College of Engineering, Salem
In this study, we propose a novel machine learning-based simulation framework for evaluating biomedical compound efficacy under biosafety constraints. Focusing on antileprotic compounds, the system integrates QSAR-derived descriptors and a Random Forest surrogate model to predict inhibitory responses without requiring live Mycobacterium leprae cultures. The simulation achieved an R² of 0.87 and RMSE of 0.15, accurately estimating inhibition levels at multiple concentrations. A compound prioritization matrix was constructed using performance metrics, drug-likeness filters, and structural novelty scores. The framework demonstrates how signal-driven modeling and surrogate learning can accelerate screening processes in biomedical engineering where experimental validation is limited by infrastructure constraints.
Keywords: Simulation-based methodology, Surrogate models, Computational drug screening, QSAR, Random Forest Regression
How to cite this article: Rajalaxmi S, Rani NN, Abirami S, Kumar JS, Kala H. A Novel Simulation-Based Methodology for Evaluating Antileprotic Efficacy Using Surrogate Models in the Absence of Live Mycobacterium leprae Cultures. Int J Drug Deliv Technol. 2026;16(12s): 162-169. DOI: 10.25258/ijddt.16.12s.17
Source of support: Nil.
Conflict of interest: None