A deep learning‐based deconvolution framework identifies human brain cell‐type specific expression quantitative trait loci (eQTLs) and pathobiology in Alzheimer’s disease
Lijun Dou, Jielin Xu, Yuan Hou, Feixiong Cheng · 2025
Read A deep learning‐based deconvolution framework identifies human brain cell‐type specific expression quantitative trait loci (eQTLs) and pathobiology in Alzheimer’s disease by Lijun Dou, Jielin Xu, Yuan Hou, Feixiong Cheng (2025) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-11709395.txt.
Description
Lijun Dou, Jielin Xu, Yuan Hou, and Feixiong Cheng use deep learning to extract cell-level genetic signals from ordinary bulk brain data. Their study came out in 2025. The question is which genetic variants change gene activity in which brain cell types, a clue to how Alzheimer's risk variants act.
True single-cell data are costly and hard to match with genotypes at scale. Their framework estimates each cell type's expression from cheap bulk samples, then links it to genome data from the same donors. They found tens of thousands of cell-specific regulatory variants across eight brain cell types. Many matched results from real single-cell studies. One Alzheimer's risk variant was tied to genes it regulates in excitatory neurons. The method promises cell-level insight without cell-level cost.
Catalog record
| CREATOR | Lijun Dou, Jielin Xu, Yuan Hou, Feixiong Cheng |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 3 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |