About Me!

Hello! I’m a PhD candidate in Industrial Engineering at the University of Central Florida with a deep-seated passion for machine learning/deep learning, network science, and molecular modeling. My research focuses on utilizing geometric deep learning to advance molecular property prediction, drug discovery, and molecular generation. I’m particularly fascinated by how graph neural networks (GNNs) and transformer models can unlock insights into complex chemical structures, paving the way for innovative solutions in drug design and biophysics.

Research Interests

• Molecular Representation Learning: Developing and applying GNNs to enhance molecular property prediction, particularly using 2D and 3D molecular conformations to understand and predict quantum, chemical, and ADME properties.
• Graph Machine Learning & Network Science: Leveraging graph theory and machine learning to model complex interactions, including drug-protein interactions, influence maximization in social networks, and anomaly detection in large datasets.
• Time Series & Anomaly Detection: Applying temporal modeling techniques and hybrid approaches for real-time anomaly detection in various fields, from network science to acoustic pattern recognition.

Background

Previously, I worked as a Data Scientist at Air Arabia, where I applied machine learning to projects in revenue optimization and machine learning operations. I am also a Gold Microsoft Learn Student Ambassador, where I share my knowledge of AI and machine learning with the wider tech community. With hands-on experience in both industry and academia, I bring a unique, application-driven perspective to my research.

Achievements

• Graduate Research Fellowship, University of Central Florida: Awarded for outstanding contributions to research in industrial engineering and machine learning.
• DeepLearning.ai Mathematics for Machine Learning Specialization: Completed advanced coursework to enhance my understanding of machine learning foundations.
• Publications in leading venues, including ACM, focusing on deep learning applications in network science and anomaly detection.

Future Directions

I am actively exploring the intersection of molecular property prediction and geometric deep learning, with a focus on developing interpretable AI models for drug discovery. My goal is to advance the understanding of how 3D molecular data can improve the accuracy and applicability of predictive models in pharmaceuticals, biology, and chemistry.

Feel free to explore my site to learn more about my work, publications, and ongoing projects. You can also reach out to me on LinkedIn or GitHub to connect and collaborate!