SandboxAQ and iOncologi announced a strategic collaboration to jointly develop, validate, and commercialize a novel high-fidelity mRNA vaccine for glioblastoma, the most common and aggressive malignant brain tumor in adults. The partnership combines SandboxAQ's proven software and biologics technology for drug candidate identification and lead optimization with iOncologi's deep tech immunotherapy design and clinical expertise to overcome longstanding barriers in brain cancer treatment.
Addressing Critical Unmet Medical Need
Glioblastoma represents one of the most challenging cancers to treat, with patients typically surviving less than two years due to limited treatment options. This aggressive cancer accounts for about 15% of all primary brain tumors, affecting approximately 300,000 new cases and causing more than 200,000 deaths worldwide each year, according to the World Health Organization.
"Glioblastoma's rapid progression and high mortality rate make it one of the most devastating cancers in the world," said Jack Hidary, CEO of SandboxAQ. "Our collaboration with iOncologi aims to create a new and effective treatment for this challenging condition, pairing the most comprehensive oncology datasets with advanced quantitative AI tools and simulation techniques, greatly accelerating the drug discovery process."
AI-Powered Drug Discovery Platform
The joint program aims to deliver a lead therapeutic candidate into the clinic within 18 months by combining SandboxAQ's AQBioSim platform for drug discovery and optimization with iOncologi's leadership in immunotherapy design and clinical execution. SandboxAQ's AQBioSim platform uses Large Quantitative Models (LQMs) grounded in physics and chemistry to rapidly identify potential drug candidates, simulate molecular behavior and design new potential drug molecules, in the same way as other generative models might output text or images.
SandboxAQ's generative chemistry AI model has been shown to design new molecules with better binding characteristics than the next best technologies, such as large-scale virtual screening, and it does this 100 times faster and at lower cost. The technology has proven its ability to rapidly identify and design molecules that address some of the most challenging diseases including Alzheimer's and Parkinson's.
"SandboxAQ's Large Quantitative Models and AI simulation techniques have proven their ability to rapidly identify and design molecules that address some of the most challenging diseases including Alzheimer's and Parkinson's," said Nadia Harhen, General Manager of AI Simulation and head of the AQBioSim division at SandboxAQ. "By adapting the technology stack to oncology, we believe we can make a significant impact where traditional approaches and other advanced technologies have failed."
Precision Immunotherapy Approach
iOncologi specializes in precision immunotherapies that reprogram and redirect the immune system to target tumors previously considered untreatable, particularly those shielded by the blood-brain barrier or cloaked in immune tolerance. The company focuses on integrating immune intelligence, mRNA engineering, and drug delivery platforms into universal and adaptable, patient-specific treatment models.
"iOncologi is reimagining cancer immunotherapy by integrating immune intelligence, mRNA engineering, and drug delivery platforms into universal and adaptable, patient-specific treatment models," said Dr. Edgardo Rodriguez-Lebron, CEO of iOncologi. "By combining this with SandboxAQ's ability to model and rapidly optimize molecules across vast chemical and biological spaces, we are well-positioned to advance a truly transformative therapeutic for glioblastoma, and eventually for other treatment-resistant solid tumors."
Broader Cancer Research Initiative
In June, SandboxAQ also announced a collaboration with Stand Up To Cancer® (SU2C) to support SU2C-funded cancer research projects. Leveraging LQMs, the initiative aims to accelerate the development of new treatments, including supporting efforts to detect hard-to-diagnose and treat cancers, and leverage predictive modeling to optimize treatment response and monitor potential recurrence.
