Turbine, a leading AI-powered drug discovery company, has announced a strategic collaboration with pharmaceutical giant AstraZeneca to revolutionize antibody-drug conjugate (ADC) discovery through virtual disease modeling. The partnership, announced on October 9, 2025, aims to address key challenges in ADC development by leveraging Turbine's platform to predict response mechanisms, inform ADC positioning, and significantly reduce the need for costly large-scale cell line screening.
Addressing ADC Discovery Challenges
ADCs represent a promising class of targeted cancer therapies that deliver potent drug payloads directly to tumor cells. However, the discovery process faces significant bottlenecks due to the complexity of identifying effective payloads across diverse tumor types and patient populations. Traditional approaches require extensive screening of hundreds of cell lines and patient-derived xenografts (PDXs), creating substantial time and cost barriers.
The collaboration between Turbine and AstraZeneca directly tackles these in vitro challenges through an innovative lab-in-the-loop approach. Rather than conducting broad experimental screening, Turbine's platform will recommend strategically chosen subsets of cell lines for testing, then predict outcomes across thousands of in silico models using AstraZeneca's comprehensive ADC datasets, including both single-agent and combination studies.
Virtual Experimentation Platform
Turbine's Simulated Cell™ platform virtualizes biological experiments at scale, offering capabilities that extend beyond traditional screening methods. The platform models not only cell survival but also changes in gene expression, providing crucial mechanistic insights into why cells respond to or resist treatment. This approach enhances clinical translatability by delivering deeper understanding of therapeutic mechanisms that current experimental screening approaches may typically lack.
"By implementing a lab-in-the-loop approach, we can move beyond broad experimental screening toward a more efficient, targeted strategy that selects the ADC combinations most likely to succeed in patients," said Daniel Veres, MD, PhD, CSO and Co-Founder of Turbine. "This also lays the groundwork for deeper integration of our Virtual Lab into discovery workflows, helping ensure that the right experiments are run to generate the greatest impact for patients."
Building on Previous Success
This collaboration builds upon previous successful partnerships between Turbine and AstraZeneca. The companies have previously worked together using Turbine's platform to identify and understand mechanisms of resistance to therapy in hematological cancers and to predict combination synergy and relevant biomarker candidates involving DNA Damage Repair mechanisms.
Technology Platform and Validation
Turbine has spent the last decade developing virtual disease models designed to become second only to actual patients in predicting drug response. The platform enables scientists to run billions of virtual experiments to uncover risk, design smarter trials, and scale decisions across entire pipelines. By simulating how cells and tissues behave under treatment, the technology helps pharmaceutical companies identify therapeutic opportunities more efficiently while reducing late-stage clinical failures caused by poor efficacy.
The platform's effectiveness has been validated through partnerships with major pharmaceutical companies including Bayer, MSD, and AstraZeneca, supporting nearly 30 research programs. Backed by investors including Accel and MSD Global Health Innovation Fund, Turbine aims to democratize predictive simulations across the drug discovery community.
Long-term Vision
The collaboration represents a significant step toward bringing discovery processes closer to clinical outcomes. While initially focused on cell line models, the long-term vision extends the same approach to patient-derived models and ultimately clinical care. This progression could fundamentally transform how ADC discovery is conducted, moving from resource-intensive broad screening to precision-guided development strategies that maximize the likelihood of clinical success.
