Tailoring therapies: a frontier approach to pancreatic cancer with AI-driven multiomics profiling

Abstract

Pancreatic cancer is often diagnosed at an advanced stage when treatment options are limited. Being one of the deadliest cancers that mandates longer medication and treatment phases, there is an inevitable need to have the knowledge of drug response of anti-pancreatic cancer drugs before it is recommended for a patient. AI-driven drug response prediction has proven potential to personalize treatment strategies, improve therapeutic outcomes, and reduce adverse effects and treatment costs for cancer patients. In this research work, we have accounted for the use of different drug descriptors and their core structures known as scaffolds along with three cell line features, chromatin profiling, reverse phase protein array, and metabolomics data to build a feature engineered dataset for drug response prediction tested on various computational learning models. The 53 unique drugs against 18 unique pancreatic cancer cell lines were taken as the raw dataset. The initial dataset having a large dimension was feature selected using an ensemble method derived from five different techniques. The dataset was evaluated on various computational methods and an accuracy of 89% was achieved using the TabNet architecture. Furthermore, the common scaffolds that were persistently found among the drugs that possess high IC50-valued drug clusters were also recorded.