QIMR Berghofer and Qubigen Report Promising Experimental Validation Results in Ongoing AI-Driven Cancer Discovery Collaboration
- 5 hours ago
- 2 min read
Qubigen is pleased to share encouraging progress from its ongoing collaboration with QIMR Berghofer. The partnership combines QIMR Berghofer’s expertise in translational cancer biology with Qubigen’s privacy-preserving Federated AI platform to identify novel small-molecule candidates targeting tumorigenesis and cancer progression. The project is now advancing from computational discovery and early experimental validation into the AI optimization and hit-to-lead acceleration phase, with multiple compounds identified from Qubigen’s advanced computational modeling techniques.
From Computational Discovery to Experimental Validation
Using the Qubigen Federated AI platform, we have applied advanced computational modeling to identify an initial set of candidate compounds against a challenging protein–protein interaction implicated in inflammation and tumor growth in cancers. The compounds were subsequently tested experimentally across two complementary assay systems to evaluate both protein interaction and cell-based functional activity.
The validation studies demonstrated several promising outcomes:
Multiple compounds showed measurable inhibitory activity
Approximately 10 of the 34 predicted compounds interfered with target binding in biochemical assays
5 hit compounds demonstrated overlapping activity in both binding and functional assays
Validation Across Complementary Assays
Prof. Nils Halberg, Group leader at QIMR said that “The overlap observed between the biochemical and functional assays was particularly encouraging, as it provided increased confidence in the biological relevance of several of the identified compounds.”
“This stage of the collaboration is particularly exciting because we are now seeing predictions from our computational modeling translate into experimentally validation,” said Dr. Jonathan Hall, CEO of Qubigen. “One of the key challenges in early-stage therapeutic discovery is identifying which signals are worth advancing further. These results provide strong support for continued optimization and translational follow-up.”
The convergence of results across complementary assay systems strengthens confidence that the computationally identified compounds are engaging biologically relevant mechanisms. QIMR Berghofer researchers conducted both binding inhibition and functional assays across two cell lines, with overlapping activity providing an important foundation for potential next-stage optimization efforts.
Exploring the Next Phase of Optimization
The project highlights the growing role of AI-enabled workflows in supporting early-stage translational research programs, particularly in areas that are scientifically promising and cutting-edge, prior to large-scale commercial development or pharmaceutical investment.
Discussions are now underway regarding potential follow-on optimization studies, including:
Federated AI-guided compound optimization and novel candidate generation
Druglikeness (ADMET) assessment
Synthesis feasibility evaluation
By integrating computational modeling, privacy-preserving Federated AI workflows, and synthesis feasibility AI, the collaboration aims to accelerate the transition from biological insight to viable therapeutic candidates. The project also demonstrates the value of close collaboration between computational and experimental research teams in advancing difficult oncology discovery programs efficiently and cost-effectively.
Qubigen looks forward to supporting the next phase of the collaboration as the project advances toward further optimization, translational funding opportunities, and future therapeutic development pathways.
Qubigen - Accelerate Drug Design Without Exposing Secrets
Qubigen builds and hosts powerful, privacy-preserving AI Engines, turning discrete client-specific data into a competitive edge.
Whether you're advancing active programs, reviving dormant data, or starting from scratch, Qubigen’s secure Federated AI and quantum chemistry platform can help you identify, optimize, and accelerate the path to promising lead drug candidates. Get in touch to explore how we can support your next development.