| Title: | A foundational model encodes deep phenotyping data and enables diverse downstream applications |
| Journal: | npj Digital Medicine |
| Published: | 14 May 2026 |
| Pubmed: | https://pubmed.ncbi.nlm.nih.gov/42135472/ |
| DOI: | https://doi.org/10.1038/s41746-026-02736-w |
| URL: | https://www.nature.com/articles/s41746-026-02736-w_reference.pdf |
Publication 20039
WARNING: the interactive features of this website use CSS3, which your browser does not support. To use the full features of this website, please update your browser.
Abstract
Deep phenotyping data are essential for understanding disease mechanisms and individual health trajectories. However, its unprecedented scale and complexity pose significant analytical challenges that conventional approaches struggle to address. Here, we introduce ukbFound, a foundation model that encoded thousands of individual-level traits into language-like sequences. By incorporating domain-specific tokenization, position-free embedding, and interpretable reasoning, ukbFound effectively captures latent disease-trait relationships from 502,118 UK Biobank individuals. We demonstrate its versatility in three downstream applications. In disease stratification, ukbFound identifies distinct patient subgroups in 289 diseases, with 53/289 (18.3%) showing FDR-significant prognostic differences. Notably, ukbFound reveals two subgroups in chronic obstructive pulmonary disease distinguished by unique basophil count distributions, suggesting a novel indicator for lung function decline. In multimorbidity network analysis, ukbFound uncovers previously unreported associations (e.g., low platelet disorder and gout) and disease communities with shared etiological mechanisms. In disease prediction, ukbFound identified high-risk individuals based solely on lifestyle and dietary data, outperforming ten benchmark models by ΔAUC gains of +0.03 to +0.16. Notably, the highest-risk group showed 17.5-fold greater odds of developing gout up to 8 years in advance. Collectively, ukbFound provides a scalable and interpretable framework for modeling deep phenotyping data and advancing precision medicine.</p>
13 Authors
- Qiyang Hong
- Cong Wang
- Wenqian Wu
- Yuyan Li
- Xinti Sun
- Zigeng Huang
- Jixin Wang
- Mengyan Zhang
- Peixing Wan
- Xiaolin Ni
- Erkang Yi
- Junling Pang
- Erping Long
1 Application
| Application ID | Title |
|---|---|
| 150455 | Dissecting the genetic underpinnings of comorbidities via functional genomics |
Enabling scientific discoveries that improve human health