03/11/2024
By Kwok Fan Chow

The Kennedy College of Science, Department of Chemistry, invites you to attend a Ph.D. Dissertation defense by Solene Bechelli entitled “Bridging Computational Models and Pharmaceutical Applications: Predictive Algorithms for Lead Compound Identification and Molecular Property Analysis.”

Degree: Doctoral
Location: Olney, Room 518
Date: Monday, March 25, 2024
Time: Noon

Committee Chair: Prof. Jerome Delhommelle, Department of Chemistry, University of Massachusetts Lowell

Committee Members:

  • Prof. Juan Artes Vivancos, Department of Chemistry, University of Massachusetts Lowell
  • Prof. Olof Ramstrom, Department of Chemistry, University of Massachusetts Lowell
  • Prof. James Whitten, Department of Chemistry, University of Massachusetts Lowell

Abstract:
This dissertation explores applications of artificial intelligence (AI) to drug discovery, highlighting the role of machine learning in advancing pharmaceutical research. It centers on deploying sophisticated algorithms to streamline molecular docking processes and improve the prediction of molecular properties.

The research first examines the integration of AI in molecular docking—a critical step in drug discovery that simulates interactions between ligands and target proteins. By adopting state-of-the-art deep learning techniques, it introduces an optimized docking approach that not only minimizes computational costs but also ensures high levels of accuracy in predicting ligand-protein binding affinities. This advancement offers significant implications for the efficient design of new drugs, marking a notable improvement over traditional methods.

Subsequently, the dissertation tackles the inefficiencies in conventional drug discovery processes by showcasing the transformative potential of AI. It underscores the importance of accurate prediction of molecular properties—such as bioactivity, toxicity, and pharmacokinetics—in the early stages of drug development. Through the development of innovative machine learning models, the study achieves remarkable predictive capabilities, thereby streamlining the selection process for viable drug candidates with unprecedented precision.

Throughout the dissertation, the efficacy and versatility of the proposed AI-driven solutions are validated via detailed case studies and comparisons with existing methods. These investigations reinforce the value of AI in enhancing drug discovery, contributing to a significant reduction in time and resources required for the development of new therapeutic agents. This research represents a vital step forward in the quest for more effective and efficient drug discovery processes, offering promising avenues for the advancement of precision medicine in the pharmaceutical sector.

All interested students and faculty members are invited to attend.