Machine-learning guided experimental approaches for developing a robust nanoscale delivery platform for the treatment of pancreatic cancer

点击翻译按钮获取中文摘要

Pancreatic cancer is currently the fourth leading cause of cancer related deaths and is projected to be the second leading cause of cancer related deaths by 2030. The disease also has amongst the poorest prognosis across cancers. The cancer is particularly hard to target due to the tumour microenvironment and the presence of a dense stroma that makes targeted drug delivery quite challenging. In this regard, metal-organic frameworks have emerged as promising drug delivery candidates owing to the modularity of their constituents, high drug loading capacities, slow drug release times and ease of surface functionalisation. That being said, there are several gaps that need to be filled before these materials are considered serious candidates at a clinical level. This project is aimed at tackling several unanswered questions in order to translate laboratory scale results to the clinical level. It will involve leveraging machine learning approaches to gain insights into the bio-compatibility of these materials, using molecular simulations to understand their stability, using statistical approaches to understand the interaction of these materials with therapeutic molecules and generative modeling to enhance their utility for drug delivery applications. Based on these computational approaches, shortlisted MOFs will be synthesised, characterised and tested, with a primary focus on the delivery of synthetic peptides that target relevant oncogenes in pancreatic cancer cells.