Obesity can affect far more than body weight or fat storage. A new study shows how artificial intelligence may help scientists see those wider changes across the body in unprecedented detail.
The study, published in Nature, describes a new AI-powered platform called MouseMapper that allows researchers to map disease-related changes throughout the entire mouse body at cellular resolution. Using the tool, researchers found widespread inflammation and changes in nerve structure in mice with obesity, including previously unrecognized changes in facial sensory nerves.
The findings do not show that the same whole-body changes happen in the same way in living people with obesity. However, researchers also found related molecular signals in human tissue, suggesting that some obesity-linked nerve changes may be shared across species.
Obesity is often discussed in terms of metabolism, blood sugar, cholesterol or excess fat. But it can also affect immune activity, nerves and tissue structure across multiple organ systems. That broader view matters because obesity is linked to higher risk of type 2 diabetes, cardiovascular disease, stroke, neuropathy and some cancers.
Until now, researchers have had limited tools for studying those changes across the entire body at high resolution.
A team led by Ali Ertürk, director of the Institute for Biological Intelligence at Helmholtz Munich and a professor at Ludwig Maximilians University Munich, developed MouseMapper to analyze whole-body biological imaging data. The platform uses deep-learning algorithms to automatically identify 31 organs and tissue types, while also mapping nerves and immune cells.
“MouseMapper is built on a foundation model, which means it generalizes far beyond the data it was originally trained on,” said Ying Chen, co-first author of the study.
To create the whole-body maps, researchers labeled nerves and immune cells in mice with fluorescent markers. They then used tissue-clearing techniques to make the animals transparent while preserving the fluorescent signals. Specialized light-sheet microscopy allowed the team to capture three-dimensional images of whole mice, creating large datasets with tens of millions of cellular structures.
MouseMapper then analyzed the data, identifying nerves, immune-cell clusters and anatomical regions across the body. That allowed researchers to see where inflammation and structural changes were occurring without choosing one organ or tissue in advance.
To study obesity, the researchers fed mice a high-fat diet that induced obesity and metabolic dysfunction. When they applied MouseMapper, they found widespread changes in immune-cell organization and nerve structure across the body, including in fat, muscle, liver and peripheral nerves.
One notable finding involved the trigeminal nerve, a major facial nerve involved in sensation and movement. In mice with obesity, some sensory branches of the nerve had fewer endings and branches, suggesting a loss of normal nerve structure. Behavioral experiments also showed the mice responded less to sensory stimulation than lean mice.
The researchers then examined the trigeminal ganglion, which contains the cell bodies of facial sensory neurons. Using spatial proteomics, they identified molecular changes related to nerve remodeling and inflammation.
Some of those same molecular signatures were also found in trigeminal tissue from people with obesity. That does not make the study a human clinical trial, but it does suggest that at least part of what researchers observed in mice may be relevant to human biology.
“We revealed previously unknown structural and molecular changes in the trigeminal ganglion and its facial branches, and the same molecular signature was conserved in human tissue. This kind of finding simply cannot emerge from studying one organ at a time,” said Dr. Doris Kaltenecker, senior scientist at the Institute for Diabetes and Cancer at Helmholtz Munich and first author of the study.
The platform may also have uses beyond obesity research. The researchers said MouseMapper could help study diseases that affect multiple body systems at once, including diabetes, cancer, neurodegenerative diseases and autoimmune disorders.
That is one reason the study is as much about technology as it is about obesity. MouseMapper gives scientists a way to study disease as a whole-body process, rather than looking only at one organ or one pathway.
“Our goal is to create a comprehensive framework for understanding how diseases affect the body as an interconnected system,” Ertürk said. “Our long-term vision is to build truly realistic digital twins of mice in health and disease: cell-level atlases that we can query, perturb and screen in silico computationally. That would let us pinpoint the earliest changes a disease causes, design interventions to prevent them, and accelerate the discovery of new treatments while reducing the number of physical experiments we need to run.”
The findings should not be read as a simple message about diet or weight loss. The study did not test a diet treatment, weight-loss program or medication to see whether the nerve and immune changes could be prevented or reversed.
Instead, the study adds to a growing understanding that obesity is a systemic condition involving multiple tissues and biological pathways. It also shows how new AI tools may help researchers identify changes that would be difficult to detect by studying one organ at a time.
The study was supported by several research organizations and foundations, including the European Research Council, the German Research Foundation, the German Federal Ministry of Education and Research, the Vascular Dementia Research Foundation, the Nomis Foundation, the Else-Kröner-Fresenius-Stiftung, the Edith-Haberland-Wagner Stiftung, the Helmut Horten Foundation, the European Foundation for the Study of Diabetes and Novo Nordisk A/S Programme for Diabetes Research in Europe and the China Scholarship Council.