AI in Precision Oncology: From Protein Folding to Clinical Operations

Chadi Nabhan, MD, MBA, FACP, hematologist-oncologist and the chief medical officer and head of strategy at Ryght.AI, explores the intersection of artificial intelligence (AI) and precision medicine, expanding on the insights regarding the future of oncological care.

Nabhan observes that while AI is a frequent topic of conversation, its current integration into the precision oncology ecosystem is still in its early, foundational stages. Depending on a stakeholder's position—whether they are a pharmaceutical sponsor, a biotech innovator, or a clinical researcher—the application of AI varies significantly, though its primary goal remains the acceleration of life-saving interventions.

Accelerating Drug Discovery and R&D

For pharmaceutical companies and biotech firms, Nabhan notes that AI has become an indispensable tool in research and development (R&D). By utilizing machine learning algorithms to screen for specific genetic or molecular targets, these organizations can expedite the identification of the "perfect target" for new drug candidates. This predictive power allows researchers to bypass months of traditional trial-and-error in the lab.

A cornerstone of this technological leap is the ability to understand and predict protein folding. Nabhan highlights the revolutionary impact of AlphaFold2, an AI platform that has fundamentally changed how scientists view protein structures. To illustrate the gravity of this achievement, Nabhan points out that the pioneers behind AlphaFold were awarded the Nobel Prize in Chemistry in 2024, signaling that AI is no longer a peripheral tech interest but a core pillar of modern chemistry and biology.

Streamlining Clinical Administration

Beyond the laboratory, Nabhan identifies a massive opportunity for AI to optimize the "bureaucratic bottlenecks" of clinical trials. The administrative burden of drafting protocols and Informed Consent Forms often delays patient access to new treatments. Traditionally, navigating the complexities of institutional review board approvals could take up to 6 months. Nabhan suggests that AI could feasibly compress that timeline into a single week, dramatically increasing the efficiency of the clinical trial pipeline.

The Untapped Horizon

Despite these advancements, Nabhan maintains a grounded perspective, asserting that the medical community is currently only "scratching the surface." While the early wins in protein modeling and administrative efficiency are impressive, Nabhan believes the full potential of AI in oncology has yet to be realized. The future holds even greater promise as these tools move from specialized R&D applications into broader, more integrated clinical roles.