Akoya Biosciences (AKYA) investor relations material

AI strategy and clinical application

• AI-powered profiling of trillions of immune cell data points identified key predictors of cancer recurrence risk, focusing on spatial proteogenomics and single-cell analysis.

• Developed a strategy to reduce massive datasets to a clinically actionable five-gene immune scoring system, achieving superior predictive accuracy (AUC 0.82) for liver cancer recurrence compared to existing clinical factors.

• AI models were designed to be explainable and human-in-the-loop, allowing domain experts to validate and interpret results at the single-cell level.

• The immune scoring system stratifies patients into high and low risk, guiding potential adjuvant treatment and improving clinical trial recruitment efficiency.

• The approach is being extended to H&E 2.0 and 3.0 versions, aiming for automated, cloud-based clinical translation.

Validation and mechanistic insights

• Findings were validated across RNA, protein, ex vivo, and in vivo models, confirming the role of NK cells and CD8 T cells in tumor immune response.

• Ex vivo 3D bioprinting and live imaging demonstrated NK cell penetration and tumor killing, modulated by SPON2 and interferon gamma.

• Spatial mass spectrometry (deep visual proteomics) was used to validate and discover additional protein markers, contributing to the concept of spatial dark proteomics.

• The immune scoring system was shown to be robust, requiring at least one or two markers and regions for optimal performance.

Future directions and broader impact

• Ongoing work includes generalizing the scoring system for broader multiplex IF/IHC clinical use and automating image quantification.

• The AI-driven approach is being applied to global health projects in Africa and Southeast Asia, aiming to improve access and outcomes in remote areas.

• The team encourages early-career scientists to persist, work sincerely, and embrace transparent communication in research.