|
Pittsburgh-headquartered Predictive Oncology Inc, a company on the cutting-edge of the rapidly growing use of artificial intelligence and machine learning to expedite early drug discovery and enable drug development for the benefit of cancer patients globally, is moving to leverage its vast biobank of more than 150,000 heterogenous live cell tumour samples and drug response data to aggressively pursue novel drug discovery, biomarker discovery and drug repurposing using artificial intelligence (AI) and machine learning (ML).
Earlier this week, Regeneron Pharmaceuticals announced its acquisition of 23andMe for $256 million, marking a strategic step in the industry-wide shift toward data-driven drug discovery. The move highlights the enduring value of 23andMe’s vast genomic database and its proven track record in therapeutic development partnerships.
23andMe houses one of the world’s largest and most comprehensive longitudinal genomic datasets, with many customers having consented to ongoing health tracking. This unique trove of real-world health data offers powerful insights into disease progression, treatment efficacy, and patient stratification - making it a highly valuable resource for precision drug development.
A testament to this value is 23andMe’s previous $300 million partnership with GlaxoSmithKline in 2018, which was later extended in an all-cash deal. The continuation signaled strong confidence in the utility of 23andMe’s data to inform drug discovery efforts and guide clinical decisions.
With this acquisition, Regeneron is expected to integrate 23andMe’s consumer genomic and health data into its own R&D pipeline. The company aims to strengthen its capabilities in areas such as target identification, biomarker discovery, and clinical trial optimization, aligning with a broader trend across the biopharma landscape: the convergence of artificial intelligence, real-world data, and predictive analytics to improve therapeutic outcomes.
“We recently achieved a major milestone in AI-enabled cancer drug discovery,” said Raymond Vennare, chairman and CEO of Predictive Oncology. “Using compounds sourced from the Natural Products Discovery Core at the University of Michigan, we successfully developed predictive tumor response models for 21 previously untested molecules. These models are targeted at some of the most common cancer types, including breast, colon, and ovarian cancers.
“What makes this advancement particularly significant is that these compounds had no prior response data - making this a clear demonstration of AI’s ability not just to enhance but to lead in early-stage drug discovery. Predictive Oncology’s proprietary active machine learning platform was able to model tumor response across diverse cancer types using insights derived from its biobank of over 150,000 tumor samples spanning 137 cancer indications.”
The combination of artificial intelligence, machine learning and empirical validation allows the company to test drug response in silico before confirming them in vitro in their CLIA laboratory, which has been proven to dramatically accelerate timelines and improve the Probability of Technical Success (PTS) in drug development.
“Our ability to combine artificial intelligence and machine learning with live cell tumor samples and real-world drug response data allows us to expedite early-stage drug discovery and de-risk downstream drug development. This strategic first-mover advantage enables our partners to accelerate timelines, reduce R&D risk, and maximize ROI. This proprietary AI/ML platform and robust scientific methodology is the cornerstone of our business development efforts in oncology drug discovery and repurposing,” Vennare concluded.
Not unlike Regeneron’s acquisition of 23andMe, Predictive Oncology’s AI-driven breakthroughs reflect a broader transformation in life sciences. The integration of genomics, machine learning, and real-world biological data is no longer an emerging trend - it’s now a foundational force driving the future of precision medicine.
About Predictive Oncology’s scientifically validated AI platform, PEDAL, is able to predict with 92% accuracy if a tumor sample will respond to a certain drug compound, allowing for a more informed selection of drug/tumor type combinations for subsequent in-vitro testing. Together with the company’s vast biobank of more than 150,000 assay-capable heterogenous human tumor samples, Predictive Oncology offers its academic and industry partners one of the industry’s broadest AI-based drug discovery solutions, further complimented by its wholly owned CLIA laboratory facility.
|