Interpretable machine learning-guided single-cell mapping deciphers multi-lineage pancreatic dysregulation in type 2 diabetes
This study presents a machine learning-based single-cell framework that systematically maps pancreatic cellular alterations in diabetes. The identified novel signatures, stellate activation dynamics, and beta cell maturation trajectories may serve as potential targets for diabetic management and pancreatic cancer risk stratification.
Authors
- Xueqin Xie (ORCID: https://orcid.org/0000-0002-7807-9930)
- Jian Hua Huang (ORCID: https://orcid.org/0000-0003-3282-8892)
- Hao Lv (ORCID: https://orcid.org/0000-0002-7580-0155)
- Wei Su (ORCID: https://orcid.org/0000-0001-5958-6366)
- Hao Lin (ORCID: https://orcid.org/0000-0001-6265-2862)
- Fanny Dao (ORCID: https://orcid.org/0000-0001-5285-6044)
- Yuhe R. Yang (ORCID: https://orcid.org/0000-0003-2321-4653)
- Changchun Wu (ORCID: https://orcid.org/0009-0003-9864-2756)
- Zheng Shi
Institutions
- Nanyang Technological University (SG)
- Chengdu Medical College (CN)
- Sichuan Cancer Hospital (CN)
- Chengdu University (CN)
- First Affiliated Hospital of Chengdu Medical College (CN)
Publication Details
- Journal
- Cardiovascular Diabetology
- Published
- 2025-07-24
- DOI
- https://doi.org/10.1186/s12933-025-02865-8
- Citations
- 4
- Primary Topic
- Single-cell and spatial transcriptomics
- Type
- article
- Field-Weighted Citation Impact
- 3.22
Funders
- National Natural Science Foundation of China
- China Postdoctoral Science Foundation