Clyra Bio provides a decision-support platform that helps oncology translational and clinical development teams define patient populations and biomarker strategies before trials begin, then identify response and resistance biomarkers to guide later development phases. The platform integrates molecular, cellular, clinical, and outcome data into decision-specific workflows, with an initial focus on osteosarcoma using both human and canine comparative oncology evidence.
- Artificial Intelligence
- Data & Analytics
- Biotechnology
- Drug Discovery & Therapeutics
- Healthcare Technology
- Software Only
Funding
Funding not disclosed
Founders
Product
Problem
Oncology programs struggle with heterogeneous patient populations, small cohorts, fragmented datasets, and biomarkers that do not translate cleanly into development strategy. More data does not automatically produce a better decision when evidence is not organized around the specific question a program needs to answer.
Solution
Clyra Bio provides a platform that organizes molecular, cellular, clinical, and outcome evidence around the specific development decision a program needs to make. The platform supports decision-specific workflows that frame the decision, assemble relevant human and program data, model tumor states and patient subgroups, and translate findings into a population, biomarker, or next-phase strategy with assumptions and limitations made explicit. It is built for oncology translational and clinical development teams and starts with osteosarcoma, a rare and heterogeneous cancer that is difficult to study in large prospective cohorts. Clyra also incorporates naturally occurring canine osteosarcoma as a complementary source of longitudinal evidence while keeping species-specific differences explicit.
Target Audience
Primary customers are biopharma oncology translational and clinical development teams who need to define patient populations, biomarker strategies, and next-phase development decisions for their drug programs.
Features
- Multimodal cohort characterization integrating genomics, transcriptomics, single-cell data, spatial data, pathology, clinical characteristics, treatment context, and survival outcomes
- Tumor-state and subgroup discovery that identifies biologically distinct populations hidden by conventional disease classifications
- Biomarker prioritization and validation comparing candidates across cohorts, modalities, and biological contexts
- Response and resistance analysis identifying features associated with sensitivity, non-response, adaptation, and recurrence when treatment-linked data are available
- Structured decision packages including population definition, prevalence and heterogeneity analysis, prioritized biomarker strategy, inclusion and exclusion logic, and validation plans
- Workflow that makes assumptions and limitations explicit for each translational recommendation