An AI-powered blood take a look at that analyzes DNA fragments could detect silent liver disease long before symptoms begin.
Scientists at the Johns Hopkins Kimmel Cancer Center have developed an artificial intelligence (AI) powered liquid biopsy that may identify liver fibrosis and cirrhosis long before symptoms appear. The test studies genome-wide patterns of cell-free DNA (cfDNA) fragments circulating in the bloodstream, including repetitive DNA regions across the genome, to uncover signs of disease and broader chronic health problems.
The findings were published in Science Translational Medicine and were supported in part by the National Institutes of Health. According to the researchers, this is the first large-scale application of fragmentome technology, originally explored in cancer research, for detecting chronic diseases unrelated to cancer.
How DNA Fragment Patterns Reveal Disease
Liquid biopsies based on cfDNA are already used in cancer detection, but researchers have only recently begun exploring whether the same technology could identify other illnesses. For the new study, scientists analyzed whole-genome sequencing data from 1,576 people with liver disease and other health conditions. They examined how DNA fragments varied in size and how they were distributed throughout the genome.
The study also included repetitive DNA regions that had not previously been well characterized. In each sample, researchers evaluated about 40 million DNA fragments across thousands of genomic locations, creating one of the largest datasets ever used for a liquid biopsy approach.
Machine learning tools sorted through these massive datasets to identify fragmentation patterns linked to disease. Using those signals, the team developed an AI classification system capable of detecting early liver disease, advanced fibrosis, and cirrhosis with high sensitivity.
“This builds directly on our earlier fragmentome work in cancer, but now using AI and genome-wide fragmentation profiles of cell-free DNA to focus on chronic diseases,” says Victor Velculescu, M.D., Ph.D., co-director of the cancer genetics and epigenetics program at the Johns Hopkins Kimmel Cancer Center and co-senior author of the study. “For many of these illnesses, early detection could make a profound difference, and liver fibrosis and cirrhosis are important examples. Liver fibrosis is reversible in early its stages, but if left undetected, it can progress to cirrhosis and ultimately increase the risk of liver cancer.”
Why the Fragmentome Approach Is Different
Most liquid biopsy methods search for mutations associated with cancer. This technique instead studies the fragmentome, which reflects how DNA fragments are broken apart, packaged and spread throughout the genome. Researchers say this broader analysis may make the method useful for identifying diseases beyond cancer, including conditions that may later increase cancer risk. The study was also co-led by Robert Scharpf, Ph.D., professor of oncology, and Jill Phallen, Ph.D., assistant professor of oncology.
“The fact that we are not looking for individual mutations is what makes this study so powerful,” says first author Akshaya Annapragada, an M.D./Ph.D. student working in the Velculescu lab. “We are analyzing the entire fragmentome, which contains a tremendous amount of information about a person’s physiologic state. The scale of these data, coupled with machine learning, enables development of specific classifiers for many different health conditions.”
Early Detection Could Help Millions
Velculescu says an estimated 100 million people in the United States have liver conditions that place them at increased risk for cirrhosis and liver cancer. Existing blood tests for fibrosis often fail to detect disease early, and current testing methods identify cirrhosis only about half the time. Imaging technologies such as specialized ultrasound and magnetic resonance scans can help, but these tools are not always widely available.
“Many individuals at risk don’t know they have liver disease,” Velculescu says. “If we can intervene earlier — before fibrosis progresses to cirrhosis or cancer — the impact could be substantial.”
He says earlier detection could also help doctors identify and treat underlying conditions before cancer develops.
Study Grew From Earlier Cancer Research
The project began after a 2023 Cancer Discovery study examining liver cancer fragmentomes. While reviewing patient data, researchers noticed that some individuals with fibrosis or cirrhosis had mostly normal fragmentation profiles but still showed subtle disease-related DNA signals. That finding led the team to investigate whether liver fibrosis and cirrhosis produced distinct fragmentome patterns.
In another part of the research involving 570 people with suspected serious illness, scientists developed a fragmentation comorbidity index. The index separated individuals with high and low Charlson Comorbidity Index scores, a standard tool used to estimate how additional health conditions affect mortality risk. Researchers found that the fragmentome-based index independently predicted overall survival and, in some cases, outperformed traditional inflammatory markers. Certain fragmentation patterns were also associated with poorer clinical outcomes.
“The fragmentome can serve as a foundation for building different classifiers for different diseases, and importantly, these classifiers are disease-specific and do not cross-react,” Annapragada says. “A liver fibrosis classifier is distinct from a cancer classifier. This is a unique, disease-specific test built from the same underlying platform.”
Potential Beyond Liver Disease
The researchers also identified fragmentome signals associated with cardiovascular, inflammatory, and neurodegenerative conditions in people considered at high risk for these diseases. However, the study did not include enough patients to build separate classifiers for each illness. The team says these findings suggest the technology could eventually have much broader applications, which will be explored in future research.
The liver fibrosis assay described in the study is still a prototype and is not yet available as a clinical test. Researchers say the next phase of work will focus on validating and improving the liver disease classifier and studying fragmentome signatures linked to other chronic conditions.
Reference: “Cell-free DNA fragmentomes for noninvasive detection of liver cirrhosis and other diseases” by Akshaya V. Annapragada, Zachariah H. Foda, Hope Orjuela, Carter Norton, Shashikant Koul, Noushin Niknafs, Sarah Short, Keerti Boyapati, Adrianna Bartolomucci, Dimitrios Mathios, Michael Noë, Chris Cherry, Jacob Carey, Alessandro Leal, Bryan Chesnick, Nicholas C. Dracopoli, Jamie E. Medina, Nicholas A. Vulpescu, Daniel C. Bruhm, Sarah Bacus, Vilmos Adleff, Amy K. Kim, Stephen B. Baylin, Gregory D. Kirk, Andrei Sorop, Razvan Iacob, Speranta Iacob, Liana Gheorghe, Simona Dima, Manuel Ramírez-Zea, Katherine A. McGlynn, Claus L. Feltoft, Julia S. Johansen, John Groopman, Jillian Phallen, Robert B. Scharpf and Victor E. Velculescu, 4 March 2026, Science Translational Medicine.
DOI: 10.1126/scitranslmed.adw2603
In addition to Velculescu, Annapragada, Scharpf and Phallen, the study included Zachariah Foda, Hope Orjuela, Carter Norton, Shashikant Koul, Noushin Niknafs, Sarah Short, Keerti Boyapati, Adrianna Bartolomucci, Dimitrios Mathios, Michael Noe, Chris Cherry, Jacob Carey, Alessandro Leal, Bryan Chesnick, Nic Dracopoli, Jamie Medina, Nicholas Vulpescu, Daniel Bruhm, Sarah Bacus, Vilmos Adleff, Amy Kim, Stephen Baylin, Gregory Kirk, Andrei Sorop, Razvan Iacob, Speranta Iacob, Liana Gheorghe, Simona Dima, Katherine McGlynn, Manuel Ramirez-Zea, Claus Feltoft, Julia Johansen and John Groopman.
Funding support came in part from the Dr. Miriam and Sheldon G. Adelson Medical Research Foundation, SU2C in-Time Lung Cancer Interception Dream Team Grant, Stand Up to Cancer-Dutch Cancer Society International Translational Cancer Research Dream Team Grant, the Gray Foundation, The Honorable Tina Brozman Foundation, the Commonwealth Foundation, the Mark Foundation for Cancer Research, the Danaher Foundation and ARCS Metro Washington Chapter, the Family of Dan Y. Zhang AACR Scholar in Training Award, the Cole Foundation and National Institutes of Health grants CA121113, CA006973, CA233259, CA062924, CA271896, T32GM136577, T32GM148383 and DA036297.
The researchers disclosed several competing interests related to companies and patents connected to cell free DNA analysis and disease detection technologies.
Annapragada, Scharpf, Phallen and Foda are co-founders of Artemyx. Annaprada, Foda, Bruhm, Medina, Adleff, Mathios, Phallen and Scharpf are inventors on patent applications submitted by The Johns Hopkins University related to cell-free DNA analyses. Annaprada, Foda, Bruhm, Adleff, Phallen and Scharpf are inventors on patent applications submitted by The Johns Hopkins University related to cfDNA and disease detection that have been licensed to Delfi Diagnostics and Artemyx. Cherry is the founder and owner of CMCC Consulting. Phallen, Adleff and Scharpf are founders of Delfi Diagnostics, and Adleff and Scharpf are consultants for this organization. Velculescu is a founder of Delfi Diagnostics and Artemyx, serves on the board of directors for both organizations, as an officer for Artemyx, and owns Delfi Diagnostics and Artemyx stock, which are subject to certain restrictions under university policy. Additionally, The Johns Hopkins University owns equity in Delfi Diagnostics. Velculescu divested his equity in Personal Genome Diagnostics to LabCorp in February 2022. Velculescu is an inventor on patent applications submitted by The Johns Hopkins University related to cancer genomic and cell-free DNA analyses that have been licensed to one or more entities, including Delfi Diagnostics, Artemyx, LabCorp, Qiagen, Sysmex, Agios, Genzyme, Esoterix, Ventana and ManaT Bio. Under the terms of these license agreements, the university and inventors are entitled to fees and royalty distributions. Velculescu is an adviser to Viron Therapeutics and Epitope. These arrangements have been reviewed and approved by The Johns Hopkins University in accordance with its conflict-of-interest policies.
Never miss a breakthrough: Join the SciTechDaily newsletter.
Follow us on Google and Google News.
