Waiv Enters Collaboration with Daiichi Sankyo to Deliver AI-Derived Biomarkers for ADC Program

Key Takeaways

• Waiv will use AI to discover ADC biomarkers from limited patient data
• Platform analyzes H&E and IHC whole-slide images for tumor microenvironment
• Collaboration targets early‑phase trials, aiming to predict response before later phases
• Foundation models trained on hundreds of thousands of pathology images
• Outputs are interpretable, supporting clinical decision‑making

Pulse Analysis

Antibody‑drug conjugates represent a fast‑growing class of targeted cancer therapies, yet their development is hampered by the difficulty of identifying reliable biomarkers in early‑stage trials. Traditional biomarker pipelines often require large patient cohorts, which are impractical for ADCs that target niche indications. By leveraging artificial intelligence to extract predictive signals directly from pathology slides, companies can overcome sample‑size constraints and make more informed go/no‑go decisions, ultimately reducing the risk and cost associated with late‑stage failures.

Waiv’s platform distinguishes itself through a suite of foundation models built on an extensive, multinational image repository. These models are fine‑tuned for low‑data settings, enabling the analysis of both hematoxylin‑and‑eosin (H&E) and immunohistochemistry (IHC) stained slides to characterize the tumor microenvironment and uncover novel histopathological features. The end‑to‑end workflow—from slide digitization to interpretable biomarker reports—aligns with regulatory expectations for transparency, positioning Waiv’s outputs as viable candidates for clinical validation and eventual diagnostic deployment.

The partnership with Daiichi Sankyo illustrates a broader industry shift toward AI‑driven drug development. Early integration of computational pathology can accelerate patient stratification, shorten trial durations, and improve the likelihood of regulatory approval for ADC candidates. As more pharmaceutical firms adopt similar collaborations, the competitive landscape may favor those who can swiftly translate AI‑derived insights into actionable clinical tools, reshaping the economics of oncology R&D and delivering targeted therapies to patients faster.