Make the world's toxicology and drug safety data accessible, connected, and useful.
Founder & CEO
Sara is a computational biologist with more than 15 years of experience applying data science and machine learning to biomedical research and drug development. Prior to founding FlashPath, she founded QuantBio, a computational biology company that helped biotechnology companies accelerate drug discovery, select indications, and characterize therapeutic targets through the integration and analysis of large-scale biomedical datasets. QuantBio was acquired by Tempus AI, where Sara subsequently served as Director of Translational Research. Earlier in her career, she was faculty at the University of North Carolina at Chapel Hill.
Co-Founder & Chief Operating Officer
Ryan is a biotechnology executive and genomic scientist with extensive experience building and leading scientific and technology organizations across genomics, diagnostics, and precision medicine. He previously served as SVP of Genomics R&D at Tempus AI, where he led research and development efforts across genomic technologies and applications. Prior to Tempus, Ryan was VP of Scientific Research at Illumina, where he helped advance new genomic technologies and their application to research and medicine.
Chief Scientific Officer
Jordan is a computational biologist and drug development scientist with experience spanning drug discovery, translational research, and clinical development. Prior to joining FlashPath, he led oncology early-development bioinformatics at Gilead Sciences, applying computational and translational approaches to support clinical development programs. He previously led computational biology at Arda Therapeutics, where he worked at the intersection of large-scale biological data, target discovery, and therapeutic development.
High-quality, cleaned foundations specifically designed for toxicology and safety assessment.
Solutions that support predictive modeling, translational insights, and chemical exploration.
Systems that allow scientists to move faster and transition from legacy files to scalable insights.
Drug development has generated decades of valuable safety data, but much of that evidence remains fragmented across study reports, regulatory documents, databases, drug labels, and organizations. As a result, knowledge that already exists can be difficult to find, connect, and reuse.
FlashPath changes that.
We are building tools that connect evidence across the entire drug development lifecycle: from preclinical studies and regulatory interpretation to clinical outcomes and post-market experience.
Our goal is to make what we already know more useful for understanding the findings of today and predicting what may happen next.
Cleaning and structuring toxicology data with domain expertise and full transparency.
Building models on strong, harmonized foundations rather than patchwork datasets.
Minimizing new testing by maximizing the value of existing data and prior studies.
Infrastructure designed for everything from exploratory analysis to model-informed drug development.
Safety evidence is a complex network, not a collection of isolated findings.
A preclinical observation can be connected to other findings in the same study, similar findings across compounds and species, regulatory conclusions, clinical adverse events, and real-world outcomes. Looking across drugs, drug classes, and chemical composition can reveal even broader patterns.
FlashPath brings these relationships together so scientists can move across the evidence and see connections that are difficult to recognize when each source is considered independently.
Evidence should never be a black box.
Every scientific insight should be grounded in evidence that can be examined, traced, and challenged. FlashPath preserves the connection between structured data and its original sources, giving scientists the ability to verify findings and understand the context behind them.
FlashPath helps scientists compare similar drugs and compounds, evaluate findings across species and doses, inform dose selection and study design, understand regulatory precedent, and use historical controls where appropriate. By making existing evidence easier to apply, we aim to reduce unnecessary animal testing while supporting rigorous safety decisions.