eSupervisor Detail

About me

I am a computational biology researcher specializing in AI-driven drug discovery and biomolecular interaction analysis. My work focuses on predicting RNA–ligand, DNA–ligand, and protein–ligand binding affinities using machine learning and structural bioinformatics. I aim to apply computational approaches to solve real-world biological and biomedical challenges.

Interests: My research interests lie at the intersection of artificial intelligence, computational biology, and drug discovery, with a primary focus on understanding and predicting biomolecular interactions. I am particularly interested in developing robust machine learning and deep learning models to predict binding affinities of RNA–ligand, DNA–ligand, and protein–ligand complexes. A central aspect of my work involves integrating structural bioinformatics with data-driven approaches to extract meaningful features from three-dimensional biomolecular structures, enabling accurate and generalizable predictive models. I actively work on designing scoring functions that can capture complex interaction patterns and improve the reliability of computational docking and virtual screening workflows. In addition to predictive modeling, I am deeply involved in molecular docking and molecular dynamics simulations to study the stability and behavior of biomolecular complexes under physiological conditions. I utilize simulation tools to analyze conformational changes, binding stability, and energetics, which further supports the development of more accurate AI-based prediction systems. My research also explores the application of graph-based and spatial learning techniques to better represent molecular interactions, aiming to enhance model interpretability and performance. Another important area of my research is the development of user-friendly computational tools and web servers that make advanced bioinformatics methods accessible to the broader scientific community. I am currently working on integrating multiple modules, including docking, scoring, virtual screening, and simulation analysis, into unified platforms that streamline the drug discovery process. I am also interested in extending these approaches to aptamer design, where I aim to predict and optimize nucleic acid sequences for improved binding with target proteins. Beyond molecular interactions, I am exploring the application of artificial intelligence in biomedical imaging, particularly for early disease detection. My work includes analyzing thermography and X-ray images for early-stage cancer prediction, with a focus on combining imaging data with clinical and molecular information to develop multi-modal predictive frameworks. This integrative approach aims to improve diagnostic accuracy and provide more comprehensive insights into disease progression. Overall, my research is driven by the goal of developing accurate, interpretable, and scalable computational methods that can bridge the gap between biological data and real-world biomedical applications. I am particularly motivated to contribute to advancements in precision medicine by leveraging AI to accelerate drug discovery, improve diagnostic tools, and enhance our understanding of complex biological systems.