APPLICATION NOTE
AI-enabled hit selection of drug screening on human pancreatic cancer organoids
Pancreatic ductal carcinoma (PDAC) is a highly aggressive cancer and the 4th leading cause of cancer mortality in the United States.
Despite advances in understanding PDAC mechanisms, effective therapies are still lacking. Patient-derived organoids (PDOs) are promising models for ex vivo testing, as they retain tumor histopathology and cancer gene mutations. However, challenges like manual cell culture processes, time-consuming imaging protocols and lack of automation capabilities hinder their use in screening applications.
To overcome these challenges, we set up a compound screening workflow with PDOs using the Gri3D® platform from SUN bioscience and pancreatic cancer patient-derived organoids (PDOs). These organoids were exposed to various anti-cancer compounds at different doses and monitored using high-content confocal imaging. An automated, AI-based workflow was also developed to detect organoids and extract phenotypic features, which were then analyzed using machine-learning techniques. The data showed significant cytotoxicity effects of certain compounds—similar to the positive control—and demonstrates the feasibility of performing drug screening using a robust and unbiased data analysis method.
