In a study of 229 patients, an AI-based liquid biopsy matched magnetic resonance elastography in identifying patients with fibrosis stages associated with eligibility for approved MASH treatments.

Hepta, a Foster City, California-based liquid biopsy company, announced research showing that its LiquidTransformer technology matched magnetic resonance elastography (MRE) for identifying treatment-eligible fibrosis in patients with metabolic dysfunction-associated steatohepatitis (MASH), using a routine blood draw. The findings are among six studies Hepta is presenting at The Liver Meeting, hosted by the American Association for the Study of Liver Diseases Nov 5 to 9 in Denver.

MASH is a progressive liver disease involving inflammation and scarring that can advance to cirrhosis and liver failure. Approved therapies target patients with moderate-to-advanced fibrosis, stages F2 to F3, so staging determines who qualifies. According to Hepta, that staging currently requires an invasive liver biopsy or imaging that many patients cannot easily reach. MRE is the most accurate noninvasive method for staging liver fibrosis. However, it requires an MRI scanner equipped with elastography hardware and software, trained technologists, and expert interpretation, which concentrates its availability in specialist centers and clinical trials.

Validation in Madrigal’s MASH Program

In an independent cohort of 229 biopsy-confirmed participants from Madrigal Pharmaceuticals’ MASH program, LiquidTransformer matched MRE for identifying treatment-eligible fibrosis. It also outperformed FibroScan, Pro-C3, FAST, and MAST in head-to-head comparison. Madrigal makes Rezdiffra, the first approved MASH therapy. Hepta says its test’s advantage held at the boundary between mild and significant fibrosis, where the treatment decision falls and conventional tests lose accuracy. The work was designated a Poster of Distinction (Abstract 2303).

“Seeing a blood test approach the diagnostic accuracy of MRE and beat VCTE and ELF at determining treatment eligibility is a real step forward, as that is an important unmet need given the wider availability and access of a blood test,” says Rohit Loomba, MD, of UC San Diego and Hepta’s chief medical and scientific advisor, in a release. “Further studies are underway to validate these findings.”

A separate study (Abstract 2322) evaluated the targeted assay intended for Hepta’s first commercial test. Across three cohorts, including Akero Therapeutics’ SYNCHRONY program, a panel covering less than 1% of the genome retained the diagnostic performance of whole-methylome analysis. Hepta says this supports the cost-effective deep sequencing a practical test requires. Akero is a Novo Nordisk company.

Why a Different AI Architecture

Hepta argues that cell-free DNA tests built for cancer are poorly suited to chronic disease. Tumors can leave distinctive abnormalities concentrated in particular genomic regions. Chronic liver disease, by contrast, produces much subtler changes spread across the genome as liver cells lose function, inflammation develops, and scar tissue forms. LiquidTransformer reads methylation patterns across hundreds of millions of cell-free DNA fragments at once. It pairs them with a curated liver disease atlas to connect what appears in blood to what is happening in the organ.

“We are making the liver as readable from blood as a tumor is today, with our first commercial test identifying patients who qualify for MASH treatment,” says Hamed Amini, PhD, co-founder and CEO of Hepta, in a release. “Since the technology is organ- and disease-agnostic, our ambition is to expand this capability to other organs and indications beyond the liver.”

The company also has a paper accepted to the main track of the 2026 Conference on Neural Information Processing Systems. Titled “Why Cancer cfDNA Models Fail on Chronic Disease: A Geometric Information-Theoretic Bound and Its Architectural Implications,” it was authored by Hepta’s Fereshteh Abedini and Soheil Damangir. The analysis spanned 9,432 tissue samples across 14 cancer types and 26 chronic diseases. According to Hepta, it shows that adding more data or building larger models on older architectures cannot close the gap. The paper will be presented December 6 to 13.

Hepta also reported results beyond fibrosis staging:

  • Liver pathway activity. In an oral presentation by Anna Mae Diehl, MD, of Duke University (Abstract 0205), researchers measured biological changes in liver tissue and then tested whether blood could recover them. LiquidTransformer identified 17 of the top 20 disease-related pathway changes that conventional blood cell-free DNA analysis largely missed. As fibrosis advanced, the blood readout also detected liver cells losing their characteristic identity and bile-duct cell populations expanding.
  • PPAR biology. In collaboration with Inventiva, whose pan-PPAR candidate lanifibranor is in phase 3, researchers analyzed Hepta’s MASH atlas and identified coordinated methylation changes across the PPAR family. Different family members were associated with different aspects of disease (Abstract 1052).
  • Drug response. In the 52-week SAMARA trial of 35 participants receiving semaglutide or placebo, LiquidTransformer detected molecular changes consistent with drug activity even though an MRI-based response measure did not distinguish the treatment groups (Abstract 3485).
  • Steatotic liver disease subtypes. In a study of 60 participants, the technology distinguished MASLD, alcohol-related liver disease, and MetALD, in which the two coexist. MetALD carried its own signature of immune activation and scarring rather than sitting midway between the other two. The study (Abstract 3004) also received a Poster of Distinction.

The sample sizes in the drug response and subtype studies are small, and Hepta describes the work as early. All four presenters at The Liver Meeting serve as advisors to Hepta. Hepta’s first diagnostic, designed to identify patients eligible for MASH treatment, remains in development.

ID 173861891 © Chernetskaya | Dreamstime.com