Digital twins for drug repurposing by integrating mathematical modelling and machine learning: bridging the gap between in silico and real-world data

The rapid development of computational approaches has revolutionised the field of drug discovery and repurposing. Here I will show a practical application of digital twins built by the synergistic combination of mathematical modelling of the cell and machine learning techniques to identify potential drug candidates for repurposing and subsequently validate their efficacy using real-world data. After discussing the inherent challenges associated with traditional drug discovery methods and the need for alternative approaches I will introduce the concept of digital twins, virtual replicas of real biological systems, which leverage mathematical models to capture the intricacies of cellular behaviour and response to drugs. By integrating machine learning algorithms, these digital twins can be trained on vast datasets to predict drug effectiveness and identify promising candidates for repurposing. Moreover, I will emphasise the importance of validating these predictions with real-world data, obtained from biomedical databases, to ensure reliability and efficacy. The presentation aims to showcase the power of integrating mathematical modelling, digital twins, and machine learning for drug repurposing, paving the way for accelerated and cost-effective drug discovery processes.

Who is this course for?

The goal of PerMedCoE is to provide an efficient and sustainable entry point to the HPC/Exascale-upgraded methodology to translate omics analyses into actionable models of cellular functions of medical relevance.

Outcomes

By the end of this webinar, you will be able to:

• Cite the limitations of traditional drug discovery methods
• Describe the advantages of digital twins for drug repurposing