Predictive Oncology Develops Novel Approach to Identifying Clinically Viable Abandoned Drugs

Core Insights - Predictive Oncology Inc. has made significant advancements in biomarker discovery and drug repurposing through the integration of active machine learning and a biobank of live-cell tumor specimens [1][2] - The company’s innovative approach has successfully identified three compounds for further exploration in tumor indications that have not been previously examined [3][4] Drug Discovery and Development - The efficient screening process identified Afuresertib, Alisertib, and Entinostat as promising candidates for ovarian and colon tumors, with Alisertib and Entinostat outperforming standard care drugs [4][6] - Afuresertib is an Akt inhibitor previously studied in various cancers, while Alisertib is a selective Aurora A inhibitor showing strong responses in ovarian and colon tumors [5][6] - Entinostat, an HDAC1/3 inhibitor, demonstrated strong responses in colon tumor models and is currently in clinical trials for combination therapy [7] Methodology and Future Directions - The company’s AI platform, PEDAL, predicts with 92% accuracy whether a tumor sample will respond to specific drug compounds, enhancing drug/tumor type selection for testing [10] - The next logical step involves applying this methodology to other publicly available abandoned drugs, potentially creating partnership opportunities with pharmaceutical companies [9]