Idiopathic pulmonary fibrosis (IPF) is a chronic and progressive lung disease characterized by the excessive accumulation of extracellular matrix components, leading to a gradual decline in lung function and, ultimately, respiratory failure. Predominantly affecting individuals over the age of 60, IPF is believed to share underlying biological pathways with the aging process. Understanding these common mechanisms is crucial for developing innovative longevity therapies with the potential to benefit people worldwide.
Recently, researchers at Insilico Medicine published a study in Aging that investigates the aging-related mechanisms in IPF using artificial intelligence (AI) approaches. The research establishes novel connections between aging biology and IPF pathogenesis while demonstrating the potential of AI-guided approaches in therapeutic development for age-related diseases.
To advance this research, the team developed two specialized deep learning models: fibrosis-aware aging clock, a pathway-aware proteomic aging clock trained on UK Biobank proteomics data, and IPF-Precious3GPT, an omics transformer that generates differential gene expression profiles from text prompts.
The aging clock shows great performance in cross-validation that predicts biological age with high accuracy (R²=0.84, MAE=2.68 years). Researchers then applied the model to the Olink dataset and used a linear regression method to assess the effect of disease severity on the pace of aging. The results showed that patients with severe infections—who are likely to develop lung fibrosis—had significantly higher predicted biological ages compared to healthy controls, suggesting that the trained clock carries biological relevance in fibrotic cases.
Analysis with the IPF-P3GPT generative model revealed both shared and unique gene expression patterns between aging lungs and fibrotic disease, highlighting that IPF is not just accelerated aging but entails unique pathological processes. The study further identified four key pathways (TGF-ß signaling, oxidative stress, inflammation, ECM remodeling) as central to both IPF and aging, but involved differently at the gene level.
Moving forward, Insilico's research team will expand on these findings by validating the AI models on dedicated IPF patient cohorts and extending the approach to other fibrotic and age-related diseases. The team also envisions using their tools for drug discovery, biomarker identification, and personalized medicine strategies across the spectrum of aging and chronic disease.
Harnessing state-of-the-art AI and automation technologies, Insilico has significantly improved the efficiency of preclinical drug development, setting a benchmark for AI-driven drug R&D.While traditional early-stage drug discovery typically requires 2.5 to 4 years, Insilico has nominated 20 preclinical candidates with an average timeline—from project initiation to preclinical candidate (PCC) nomination—of just 12 to 18 months per program, with only 60 to 200 molecules synthesized and tested in each program.
Since founding in 2014, Insilico has published over 200 peer-reviewed papers. Leveraging sustained scientific breakthroughs at the intersection of biotechnology, artificial intelligence, and automation, Insilico ranked Top 100 global corporate institutions in Nature Index's "2025 Research Leaders: global corporate institutions for biological sciences and natural sciences publications".
[1] Galkin F, Chen S, Aliper A, Zhavoronkov A, Ren F. AI-driven toolset for IPF and aging research associates lung fibrosis with accelerated aging. Aging (Albany NY). 2025 Aug 8; . https://doi.org/10.18632/aging.206295
About Insilico Medicine
