The company’s transformer model interprets up to one billion DNA fragments in each blood sample, capturing molecular context at a scale hundreds of times greater than leading LLMs and demonstrating strong clinical validation
With $6.7 million seed led by Felicis Ventures and Illumina Ventures, Hepta advances liquid biopsy platforms beyond oncology
FOSTER CITY, Calif.–(BUSINESS WIRE)–Hepta, a biotechnology company using transformer-based AI to read the cell-free DNA (cfDNA) epigenome and detect organ-specific signals of chronic disease, today emerged from stealth with $6.7 million in seed funding led by Felicis Ventures and Illumina Ventures, with participation from SeaX Ventures, Alumni Ventures, and AME Cloud Ventures. The company also revealed clinical data showing its AI-powered epigenetics platform can identify patients with metabolic dysfunction-associated steatohepatitis (MASH, formerly known as NASH) with significant fibrosis with a diagnostic AUC of 0.86, cutting false positives threefold compared to standard blood tests.
Founded by former Illumina, Grail and Google leaders, Hepta is applying the technological, genomic and commercialization expertise that made liquid biopsy possible in oncology to the far larger field of chronic disease, clinically demonstrating for the first time that epigenetic patterns in circulating cell-free DNA (cfDNA) mirror liver-tissue biology in metabolic dysfunction-associated steatohepatitis (MASH).
MASH, a progressive form of metabolic dysfunction‑associated steatotic liver disease (MASLD, formerly known as NAFLD or non-alcoholic fatty liver disease), affects more than 20 million Americans, yet less than 1% are diagnosed today. Current testing methods, unchanged for two decades, cannot scale to meet this need. Invasive biopsies and specialized imaging like FibroScan exist in fewer than 10% of primary care settings. Blood tests like FIB-4 produce false positives in over half of patients in low-prevalence populations. As the first MASH therapies reach the market with at least seven more in late-stage trials, physicians need tools that work where patients actually are. Hepta’s blood-based test promises to deliver tissue-level insight from a simple blood draw, bringing specialist-grade precision to routine care.
Hepta has developed a first-of-its-kind liquid-biopsy-native transformer model optimized for cfDNA analysis. Unlike conventional oncology assays that focus on high-signal ctDNA fragments or limited gene panels, this architecture analyzes the epigenetic patterns across all the molecules in the blood sample in a single pass, capturing contextual relationships among up to a billion molecular interactions. The company’s patented platform leverages the attention mechanism, the core innovation behind large language models like GPT, scaling it to one billion unique molecules per sample. This allows the model to track how every observed molecule interacts with every other molecule, uncovering subtle, disease-specific biological patterns.
“Traditional liquid biopsy methods work for cancer by typically looking for rare but distinct mutations, chromosomal copy number variations, or rather unique epigenetic changes,” said Soheil Damangir, Ph.D., Co-founder and CTO, who previously led AI research at Grail and Google. “Chronic diseases such as MASH create no such signals, but rather subtle methylation shifts across millions of genomic sites. The technical challenge is detecting complex diseases like MASH, where signals are far fainter than in cancer. We built a transformer that processes all billion molecular interactions simultaneously. That’s how we find patterns that are invisible to methods that analyze the genome in far smaller segments.”
“Hepta is extending the power of liquid biopsy beyond oncology to reveal organ-level biology in chronic disease,” said Hamed Amini, Ph.D., Co-founder and CEO of Hepta. “Our team, which developed next generation sequencing technologies at Illumina and built and scaled the first generation of liquid biopsy platforms at Grail, has now demonstrated that a simple blood draw can replicate tissue-level biology. This establishes a foundation for non-invasive diagnostics that can guide precision therapies in chronic diseases, starting with MASH, a systemic metabolic disease and a global epidemic affecting tens of millions in the US alone, where access to care is tragically limited by invasive, outdated or highly specialized tools. Beyond detection, our platform holds potential as a single source for guiding therapy and monitoring response.”
The company’s MASH Atlas dataset, developed in collaboration with Duke University and other leading hepatology centers, shows high concordance between cfDNA methylation and liver tissue methylation and gene expression. This further confirms the ability of this technology to act as a true liquid biopsy of the liver, providing a new lens to detect and study the disease as well as discover novel therapeutic targets.
“The concordance between cfDNA and liver tissue signals is strong, mechanistically consistent and biologically grounded. If implemented at scale, this approach can expand access to accurate liver diagnostics and care beyond tertiary centers,” said Anna Mae Diehl, M.D., Florence McAlister Distinguished Professor of Medicine at Duke University.
“This test provides a novel way to address a major unmet clinical need to have a liquid biopsy and identify who needs to be treated among patients with suspected MASH,” said Rohit Loomba, M.D., M.H.Sc. Hepta’s Chief Medical & Scientific Advisor and Director of the MASLD Research Center at UC San Diego. “The improved diagnostic accuracy above and beyond routinely available clinical tests, such as FIB-4, enables immediate clinical action. This is especially important with MASH drugs finally arriving, where an accurate blood test could increase patient access by multiple folds.”
Aydin Senkut, Founder and Managing Partner at Felicis Ventures, added: “Hepta’s technical rigor and data quality stand out even among later-stage companies. The science is strong, the market opportunity is clear, and we are proud to be early investors.”
Hepta’s approach not only detects disease but also supports longitudinal intelligence, akin to repeated testing for conditions like diabetes, but less frequently, to track subtle shifts over time. The company plans to present its data at upcoming conferences, including The Liver Meeting, the premier annual conference for the American Association for the Study of Liver Disease (AASLD), and is expanding clinical data while engaging pharma partners.
The funding will accelerate dataset expansion, platform scaling, regulatory milestones and commercialization to bring Hepta’s assay to clinical use.
About Hepta
Hepta detects chronic disease early by using cfDNA epigenetic analysis and AI to deliver accurate, non-invasive diagnostics at population scale. Founded by former Illumina, Grail and Google scientists, the company is backed by Felicis Ventures, Illumina Ventures, SeaX Ventures, Alumni Ventures, and AME Cloud Ventures. Hepta is proving that blood-based epigenetic biomarkers can replace invasive biopsies, enabling earlier and more accessible detection of diseases like MASH and laying the foundation for future applications across chronic diseases. For more information, visit www.hepta.bio.
Contacts
Media Contact
Patrick Schmidt
Consort Partners for Hepta
[email protected]
