Lunit SCOPE GP

Lunit SCOPE GP is an AI-powered digital pathology solution designed to predict actionable tumor characteristics—including gene mutations and target protein expression—directly from a single H&E slide. Built for biopharma companies, translational researchers, and clinical trial teams, it enables faster, more scalable, and cost-effective pre-screening and biomarker discovery without requiring additional tissue samples or lengthy turnaround times.

By leveraging Lunit's proprietary large-scale foundation models, SCOPE GP supports the development of customized pre-screening tools, co-mutation screening strategies, and advanced genomic signature analysis. It is intended for research use only and is not for use in diagnostic procedures or decisions.

Core Capabilities

• Genotype prediction from H&E slides: Assess tumor genomics faster and less invasively by predicting genotype directly from a single H&E slide—no extra tissue required and virtually zero turnaround time.
• Co-mutation screening: Use AI-powered analysis to identify multiple co-mutations from a single slide, such as EGFR and KRAS G12C, to accelerate and streamline clinical research workflows.
• Genomic signature prediction: Generate AI-derived genomic signatures from H&E slides to support discovery of novel biomarkers, therapy response indicators, and resistance mechanisms, including TGFβ signatures.
• Customized pre-screening tool development: Build custom pre-screening tools tailored to specific research needs, with the flexibility to choose between high-sensitivity or high-specificity models for improved predictive power.
• Trial enrollment enrichment: Apply AI-based pre-screening from H&E to enrich target patient populations, enabling more efficient and faster clinical trial enrollment.

Key Product Features

• Genotype prediction probability score for each analyzed slide
• Visualization of the genotype-predicted area within the tissue
• Flexibility to configure the tool as either a rule-out or rule-in test depending on study design
• Powered by Lunit's data-efficient foundation model, enabling rapid development of new prediction models with reduced data requirements and shorter development turnaround times

Case Study: Co-Development with AstraZeneca

• Lunit and AstraZeneca are co-developing an AI tool using Lunit SCOPE Genotype Predictor to analyze H&E slides and rapidly assess the likelihood of NSCLC driver mutations, including EGFR, ALK, ROS1, MET, KRAS, HER2, and others.
• This cost-effective screening approach can deliver results before molecular testing, helping research teams prioritize high-probability samples for faster and more efficient workflows.
• Lunit has presented related AI research on EGFR mutation prediction in NSCLC at AACR 2025 in collaboration with AstraZeneca, and a global multi-cohort validation study on AI-based EGFR mutation prediction from H&E images in NSCLC has been published.

Designed for Biopharma Innovation

• Supports end-to-end companion diagnostic (CDx) development with mature regulatory capabilities
• Compatible with a broad range of scanners and file types
• Scalable deployment across digital pathology platforms and CRO partner networks
• Helps biopharma companies scale oncology R&D, advance biomarker strategies, and optimize clinical trials

Lunit SCOPE GP is part of a broader suite of AI pathology solutions from Lunit, which also includes tools for HER2 analysis, IHC-based biomarker development, PD-L1 TPS scoring, and tumor microenvironment immune phenotyping. The platform's deep clinical evidence base, CRO partnerships, and broad scanner compatibility make it a versatile choice for teams seeking to integrate AI-driven genomic insights into their oncology research programs.