Multimodal AI curator integrated into CancerVision workflow demonstrates strong performance across real-world specimens while reducing expert review time

Inocras Inc., a bioinformatics-led company harnessing the power of whole-genome data and proprietary analytics to deliver curated insights, today announced that it will present the first public results from its multimodal agentic AI framework for automating variant curation and clinical interpretation of cancer whole-genome sequencing (WGS) analysis at the Association for Molecular Pathology (AMP) 2026 Annual Meeting & Expo, taking place November 10–14 in Seattle.

Developed to address a key scalability bottleneck in clinical Cancer WGS analysis, the AI framework is a preview of Inocras’s CancerVision™ workflow innovation. In its latest evaluation, the framework achieved 99.5% agreement with expert curation among accepted calls, while deferring 10.2% of candidate variants for expert review. It also demonstrated 98.4% reproducibility across all candidate variants in repeated analyses with identical inputs and settings and is projected to reduce expert review time by more than half.

“Whole-genome sequencing offers a comprehensive view of cancer genomes, but interpreting the volume of data can be challenging,” said Jehee Suh, CEO of Inocras. “Our AI framework aims to streamline this process, making WGS more practical for clinical use by reducing curation workload while maintaining expert oversight.”

Unlike approaches based primarily on genomic annotations, Inocras’s new AI framework combines multiple types of evidence that expert curators traditionally assess. The agent can perform a structured review of candidate driver variants using genomic annotations and sequencing metrics and, when additional evidence is needed, can visually inspect sequencing read alignments and retrieve internal knowledge base, expert-curated historical cases.

Inocras is continuing to accumulate additional real-world performance evidence while continuously refining the agent through expert feedback. Human experts retain responsibility for the review and sign-off on all clinical reports.

“Variant curation is becoming an increasingly important rate-limiting step as WGS moves toward broader clinical adoption,” said WonChul Lee, CIO and Head of the Innovation Lab at Inocras. “By combining multimodal reasoning, historical expert knowledge, and continuous feedback, our AI framework will be able to automate routine decisions while directing expert attention to the cases that require it most.”

Inocras’s AMP presentation, “A Multimodal Agentic AI Framework for Scalable Variant Curation and Clinical Interpretation of Cancer Whole-Genome Sequencing,” will be presented by Hansol Park of Inocras’s Data-Centric AI team.

Oral Presentation

• Session: Platform Presentations of Selected Informatics Abstracts I
• Date: Thursday, November 12, 2026
• Time: 2:30–2:45 PM
• Presentation: I024 — A Multimodal Agentic AI Framework for Scalable Variant Curation and Clinical Interpretation of Cancer Whole-Genome Sequencing
• Location: Room 608–609, Level 6, Arch Building, Seattle Convention Center, 705 Pike St., Seattle, WA

Poster Presentation

• Poster Number: I024
• Abstract Number: 2465932
• Category: Informatics
• Poster Display Dates: November 12–14, 2026
• Presentation Date: Friday, November 13, 2026
• Presentation Time: 9:15–10:15 AM
• Location: Expo Hall, Seattle Convention Center

About Inocras

Inocras is a bioinformatics-led company redefining precision health through whole genome data and proprietary analytics. Its oncology and rare disease platforms integrate comprehensive whole-genome data with advanced automation to deliver curated and actionable insights at scale that accelerate discovery and diagnostics to improve patient care.

Inocras operates a CLIA/CAP-certified laboratory and partners with leading hospitals, pharmaceutical companies, and research institutions worldwide. For more information, visit inocras.com.

View source version on businesswire.com: https://www.businesswire.com/news/home/20261109381648/en/

"Our AI framework aims to streamline this process, making WGS more practical for clinical use by reducing curation workload while maintaining expert oversight."