Foundational Patent Strengthens AI Moat Across Multimodal Data Standardization, Disease Stratification and Gene Mapping

Lunai Bioworks, Inc. (NASDAQ: LNAI), an AI-driven biotechnology company advancing precision therapeutics in central nervous system (CNS) disorders and oncology, as well as solutions for biodefense, announced the issuance of U.S. Patent No. 12,369,861, titled "Methods, Systems, and Frameworks for Debiasing Data in Drug Discovery Predictions."

Lunai Bioworks is focused on strengthening its core technology platform, expanding its defensible intellectual property moat, and building scalable AI infrastructure capable of supporting long-term pharmaceutical collaborations. The issuance of this patent and the advancement of additional applications represent tangible execution against that strategy.

"Precision disease subtyping begins with clean, standardized multimodal data," said David Weinstein, Chief Executive Officer of Lunai Bioworks. "This patent protects the critical first step in our closed-loop AI architecture, increasing confidence in biomarker discovery, disease stratification, and gene network mapping across our CNS and biodefense programs. Strengthening our AI infrastructure moat is central to our long-term value creation strategy."

The newly issued patent protects the foundational first step of Lunai's proprietary closed-loop disease reverse engineering platform, multimodal data standardization and structural bias removal prior to predictive modeling.

AI-driven drug discovery models are only as reliable as the data they ingest. Hidden dataset bias and fragmentation across genomic, clinical, imaging, and phenotypic sources can distort biomarker discovery and reduce translational reliability. Lunai's patented architecture systematically detects, standardizes, and removes structural bias across multimodal inputs before downstream artificial intelligence modeling begins.

By protecting this core data layer, Lunai strengthens its ability to accurately identify biologically coherent patient subtypes and trace those subtypes to the gene networks most strongly associated with each disease type.