This talk covers the progress of the Personalised Immunotherapy Program to implement a multi-omic biomarker program for immunotherapy treated patients with metastatic melanoma. The Personalised Immunotherapy Program (PIP) is a multicenter clinical initiative leveraging multi-omic biomarkers and machine learning to identify patients unlikely to respond to immunotherapy. PIP has developed and validated predictive models in a retrospective setting, followed by prospective evaluation in the PIP-PREDICT clinical observational study.
The program analysed data from 250 tumor biopsies of melanoma patients treated with anti-PD-1 monotherapy or combination anti-PD-1/anti-CTLA-4 therapy. This analysis integrated somatic mutations, gene expression, and spatial tumor immune profiling. The talk will focus on the development and performance of these multi-omic models in predicting resistance to immune checkpoint blockade. Additionally, it will delve into how high-dimensional spatial tissue imaging is being used to elucidate the mechanisms of resistance identified by PIP.