AI toolset reveals the link between pulmonary fibrosis and aging

The new research paper was published in Volumes 17 and Issue 8. Aging-us entitled “AI-driven toolset for IPF and aging research and pulmonary fibrosis associates accelerated aging,” August 8, 2025.

In this study, researchers Fedor Galkin, Shan Chen, Alex Aliper, Alex Zhavoronkov, and Feng Ren used artificial intelligence (AI) to investigate similarities between idiopathic pulmonary fibrosis (IPF), severe lung disease, and aging processes. Their findings indicate that IPF is a distinct biological condition shaped by age-related dysfunction rather than simply accelerated aging. This insight could lead to new approaches on how scientists and clinicians deal with this complex disease.

IPF mainly affects individuals over the age of 60. It causes scarring of lung tissue, making breathing difficult and often leads to respiratory failure. Current treatments can slow the disease, but rarely stop or reverse its progression. Researchers used AI to identify covalent biological features between aging and fibrosis and to find new potential targets for treatment.

The team has developed a “proteomic aging clock” based on protein data from more than 55,000 participants in the UK Biobank. This AI-driven tool accurately measures biological age and found that severe COVID-19 patients at high risk of pulmonary fibrosis also showed signs of accelerated aging. This suggests that fibrosis leaves a detectable biological trace and supports the use of aging clocks in the study of age-related diseases.

“For aging watch training, I used the UK Biobank Collection of the 55319 Proteome Olink NPX Profile annotated for age and gender.”

We also developed a custom AI model IPF-P3GPT to compare the gene activity of aged lungs and IPF lungs. Some genes were active in both, but many showed opposite behavior. In fact, more than half of the shared genes had the opposite effect. This means that IPF not only speeds up aging, but also disrupts the body's normal aging pathway.

This study identified a unique molecular signature that distinguishes IPF from normal aging. Both involve inflammation and tissue remodeling, but IPF promotes more damage changes in lung structure and repair systems. This difference can lead to the development of drugs targeting fibrosis without affecting normal aging.

By combining AI with large-scale biological data, this study also introduces a powerful set of tools to investigate other age-related conditions such as liver and renal fibrosis. These models support personalized treatments, expand understanding of the relationship between aging and disease, and open up new directions for treatment development.