🎉 We’re Joining the 2025 Bronco Ventures Accelerator!
We’re excited to share that OmicXHealth has been selected to join the 2025 Bronco Ventures Accelerator (BVA7) at Santa Clara University!
This marks another major milestone in our journey. Over the past year, we’ve built a clinically validated, patent-pending platform for early cancer detection using AI/ML models trained on cfDNA methylation data. With the support of Bronco Ventures, we’re now entering the next phase: preparing for clinical launch and scaling our solution to reach those who need it most.
As part of the accelerator, we’ll work closely with mentors, investors, and fellow founders across the SCU ecosystem to refine our go-to-market strategy and strengthen our business foundation. We're particularly grateful for the opportunity to gain feedback from experienced healthcare and tech leaders as we grow.
Thank you to the Bronco Ventures team for believing in our mission — and congratulations to the other startups joining this year’s cohort. We look forward to learning, collaborating, and pushing the boundaries of what's possible in digital health.
Stay tuned for more updates as we progress through the accelerator and prepare for Demo Day in October!
Our Story One Year In
From Personal Loss to a Platform for Early Cancer Detection
In June 2024, after losing yet another relative to liver cancer—just weeks after diagnosis—I decided to ask a simple but urgent question: Why aren’t cancers caught earlier, when something could still be done?
This wasn’t the first loss. Too many of my extended family members had passed from cancer—often within weeks of their diagnosis. That pattern haunted me. What if early cancer detection could be as simple as a blood test—like how we screen for cholesterol or liver function today?
As a computer science and engineering professional with 25+ years in the software industry, I’ve spent my career solving complex data problems. This time, I chose to apply that experience to an urgent health problem. After exploring recent breakthroughs in DNA methylation and AI/ML, I launched a feasibility project to explore whether a proof of concept, early cancer detection test could be built using existing public data.
That idea became OmicXHealth, and the past year has taken it from concept to clinical validation.
🔬 From PoC to Platform: The Journey so far
We started with a feasibility study. With the help of cancer genomics expert Dr. Elena Tomas Bort, we surveyed public bisulfite sequencing datasets across various cancers. Hepatocellular carcinoma (HCC) emerged as a compelling proof-of-concept—not only because of personal urgency, but because it lacks good screening standards today.
Our team—including bioinformatics consultant Paul Gaudin—built a preprocessing pipeline to clean, align, and format raw sequencing data from multiple independent studies. The challenge? Each dataset used a different assay and targeted different methylation markers. There was minimal overlap.
That’s when the insight struck: instead of one universal model, we would build multiple high-accuracy models, each tailored to its dataset, and use a meta-classifier to route samples based on assay signature. This architecture—validated using an independent fourth dataset—delivered strong performance, confirming that our platform could generalize across assays and patients.
Dr. Ryan Koehler, a computational biologist advisor, helped ensure scientific rigor and reproducibility of our approach. Together, we built the foundation for OmicXScreen, a modular platform designed to scale to multi-cancer detection.
One Year of Progress: Key Milestones
✅ Feasibility completed (July 2024)
Established our technical pipeline and selected HCC as the proof-of-concept cancer type based on unmet clinical need and dataset availability.
✅ Preprocessing completed (October 2024)
Public datasets chosen and raw sequenced data cleaned and preprocessed for model training/validation.
✅ Models built and validated across datasets (December 2024)
Achieved high accuracy within and across datasets—proving a generalizable approach was possible despite assay differences.
✅ Attended RESI and JPM Healthcare Conference (January 2025)
Pitched the platform to early-stage investors and advisors; gained feedback confirming need for additional clinical validation and regulatory clarity.
✅ Provisional patent filed (March 2025)
Filed for IP protection on our “sequence-once, analyze-many-times” architecture supporting modular, multi-cancer detection.
✅ Preprints published (Research Square – March 2025; bioRxiv – June 2025); manuscript submitted to JCO Clinical Cancer Informatics
Shared early results with the scientific community and submitted for peer-reviewed publication.
✅ Completed NCI STEP (January–April 2025),
Mentored by Dr. Katharine Korunes. Refined our commercialization plan and learned how to align SBIR applications with translational expectations.
✅ Completed NSF I-Corps Regional Program (April–May 2025)
UC Berkeley Node. Coached by Chris DeNoia. Conducted ~20 customer discovery interviews with hepatologists, researchers, and payers; validated need for a personalized, multi-cancer test.
✅ Clinical validation planned (April 2025)
Biobank samples identified; Zymo Research selected as sequencing partner Established the operational foundation for clinical validation using retrospective plasma samples.
✅ Joined AdvaMed (June 2025)
Engaging with regulatory and reimbursement experts to guide CLIA LDT launch and long-term payer strategy.
✅ Invited to present at MHSRS 2025 (August 2025)
Selected to share findings at the DoD’s flagship medical research conference in a breakout session on novel diagnostics.
🚀 What’s Next
​
We’re now gearing up for clinical validation of OmicXScreen, with plans to launch as a CLIA-certified Laboratory Developed Test (LDT) in early 2026—starting with liver cancer and cirrhosis.
​
But this is just the beginning. Our modular AI/ML platform will enable personalized, multi-cancer screening from a single blood draw, tailored to individual risk factors and clinical context. We believe this can move cancer detection upstream—where it belongs—into preventive care and primary care workflows.
​
Thank you for following our journey. More to come.
Mythili Subharam
Founder/CEO
June 2025