Modeling cellular uptake via the IFITM pathway for data-driven drug design

The field of drug discovery is rapidly advancing with the help of data-driven approaches to molecular engineering.

These methods require large amounts of data to accurately predict the complex relationships between molecular structure and biological function.

One key research area is multi-target therapeutic modalities, which simultaneously interact with multiple disease targets to achieve synergistic effects and improve therapeutic outcomes. However, designing these modalities is challenging, especially when it comes to predicting their cellular.

The proposed project will develop an integrated molecular dynamics simulations and machine learning framework for modeling cellular uptake via the IFITM pathway, recently established as a means of cellular uptake for large modalities.

The framework will be used to design novel protein degraders and lead to a better understanding of their cellular uptake mechanism.

The results of this work will help experimental labs save time and money focusing on the synthesis and testing of molecules likely to be cell permeable, and lead to an improved drug design workflow for large modalities. The proposed PhD project has significant impact potential in the field of multi-target therapeutic modalities.

It will provide a much-needed tool for the design of cell permeable drugs that do not follow traditional drug design principles, enabling the discovery of therapies for previously "undruggable" proteins.