Epigene Labs Announces Breakthrough Expansion in AI-Powered Omic Data Curation, Reaching 2 Million Cancer Profiles

Dec 2, 2025

Unveiling a New Data Foundation for Precision Medicine R&D

Epigene Labs today announced a major advancement in its AI-powered data curation platform, achieving a twentyfold increase in curated cancer omic profiles within the past year. This breakthrough brings the company’s total curated data catalog to nearly 2 million cancer molecular profiles, including over 600,000 patient-derived profiles spanning genomics, transcriptomics, and epigenomics.

 

This accomplishment positions Epigene Labs alongside the most advanced data-centric biopharma technology companies and marks a defining moment for the future of precision medicine.

A Milestone Seven Years in the Making

Since its founding, Epigene Labs has focused on transforming fragmented public omic data into unified, richly annotated disease atlases that power oncology research and drug development. The company’s latest expansion reflects seven years of scientific innovation and engineering advances, culminating in a dramatic acceleration in both scale and productivity.

 

Over the past twelve months, Epigene Labs:

 

  • Expanded its curated cancer omic data by 20x
  • Increased operational productivity by 50x
  • Processed more datasets this year than in the previous six years combined

Setting a New Standard for Disease Atlas Construction

With this release, Epigene Labs is unveiling its first comprehensive mapping of the cancer research data of the predominant public omic data repository, NCBI’s Gene Expression Omnibus (GEO). This mapping covers 21 data elements, including information on:

 

  • Omics and sequencing technology
  • Indication: primary site, biopsy site, histological type, stage, grade, tumor type
  • Sample origin: donor type, sample type
  • Treatment: prior treatment, therapy type
  • Clinical outcome: overall survival time, overall survival status, progression-free survival time, progression-free survival status
  • Demographics: sex, age, biological origin
  • Geographical origin
 

Built on top of this foundational data, Epigene Labs’ disease atlases reach scales up to ten times larger than current industry references. These atlases enable multidimensional insights into cancer biology, spanning biomarker discovery, pathway analysis, tumor microenvironment characterization, and cross-disease comparisons.

A Platform Built for Biopharma at Scale

The new data volume empowers Epigene Labs to support large-scale collaborations with leading biopharma organizations. 

 

Key applications include:

 

  • Private data marketplaces integrating public, consortium, commercial, and clinical-trial data
  • Secure multi-cloud architectures and cloud-to-cloud data bridges
  • Streamlined exploration through the company’s user-friendly web app
  • A forthcoming notebook environment for advanced computational users
 

The company is also preparing to launch an off-the-shelf data product line tailored to smaller biotechs and academic research groups.

Expanding Beyond Oncology

Epigene’s curation framework generalizes seamlessly across therapeutic areas. The company is already conducting early explorations into immunology and neurology, leveraging the shared core metadata and sample descriptors that underpin its oncology platform.

Quotes

“Reaching 2 million curated cancer omic profiles is a defining moment for Epigene Labs. It validates seven years of scientific rigor, strategic pragmatism, and relentless engineering. More importantly, it opens the door to a new era where disease biology can be explored at a level of resolution and scale that was previously out of reach. This breakthrough will accelerate precision medicine research and development in oncology, and beyond.” commented Akpéli Nordor, Co-founder and CEO of Epigene Labs.

About Epigene Labs

Epigene Labs creates intelligence-augmenting solutions to accelerate precision oncology research and drug development. 

 

By harnessing artificial intelligence and next-generation bioinformatics, its mCUBE platform integrates fragmented multi-omic datasets into comprehensive disease atlases with unprecedented depth and breadth. As a result, mCUBE has significantly impacted various R&D programs on immuno-oncology — often reducing months of research to mere days. Applications include target discovery, biomarker identification, and patient selection at leading cancer research institutes and biopharmaceutical companies. 

 

Based in Paris and Boston, Epigene Labs was initially incubated at the Harvard Innovation Labs and later launched in France with the backing of prominent European investors.

Media Contacts

Lucie Jankovsky

Communication & Marketing Manager

[email protected]