AI-driven discovery and validation of a GIPC1 PDZ domain inhibitor for pancreatic ductal adenocarcinoma.

Pancreatic ductal adenocarcinoma (PDAC) remains highly aggressive, with a five-year survival rate under 13.3%, due to late diagnosis, rapid progression, and therapeutic resistance, highlighting the need for advanced treatments. GAIP-interacting protein C terminus 1 (GIPC1), a scaffolding protein overexpressed in PDAC, drives tumor growth and chemoresistance but has remained "undruggable" due to its PDZ domain. Using advanced computational modeling, machine learning, and predictive analytics, we identified a selective and specific small molecule inhibitor of GIPC1 (GIPCi) targeting its PDZ domain. Binding of GIPCi with GIPC1 protein itself was confirmed via hydrogen-deuterium exchange mass spectrometry (HDX-MS). Preclinical studies showed that GIPCi alone or in combination with gemcitabine (GEM) significantly suppressed tumor growth and improved survival in PDAC models by blocking key pro-tumorigenic pathways. These findings demonstrate the power of AI-driven drug discovery and rigorous validation in unlocking advanced therapeutic targets for treatment-resistant cancers like PDAC.