WALTHAM, Mass. — BostonGene has entered into a strategic collaboration with Daiichi Sankyo to integrate artificial intelligence–driven multimodal analytics into the development of an antibody drug conjugate program, with the goal of accelerating clinical decision-making and improving patient selection strategies.
Under the collaboration, BostonGene’s AI platform will be embedded into the core of the drug development process to move beyond traditional exploratory biomarker analysis and deliver decision-ready translational insights. The effort is aimed at helping prioritize development pathways, refine translational positioning, and identify patient populations most likely to benefit from the investigational therapy.
“Success in modern drug development is no longer defined by data volume, but by the speed and accuracy with which we translate biological complexity into clinical outcomes,” said Nathan Fowler, MD, Chief Medical Officer at BostonGene. “Our work with Daiichi Sankyo is focused on accelerating learning cycles, lowering the cost of uncertainty, and differentiating this medicine earlier by identifying where it will most likely benefit patients with cancer.”
BostonGene’s approach uses digital twin representations generated from hundreds of thousands of multiomic and histopathologic patient profiles. Through this analysis, the platform identifies biological signatures and efficacy-associated mechanisms that distinguish responders from non-responders. These insights are intended to support the definition of molecular subgroups and allow benchmarking of the investigational therapy against approved treatments and existing standards of care.
The company said the collaboration will also help clarify asset differentiation by uncovering unique therapeutic profiles and biological advantages. In addition, the analyses are designed to provide insights into resistance pathways and tumor microenvironment dynamics, supporting more informed future trial design and clinical positioning.
BostonGene said the collaboration reflects a broader push within oncology drug development to use AI-driven analytics to better manage biological complexity and improve the efficiency and precision of clinical development programs.
