PreSiBOGNN: Multi‐Modal Graph Neural Network for Prediction of Cognitive Improvement in Medication Usage in UK Biobank
Dhawal Priyadarshi, Heng Huang, Nathan J Sahelijo, Reza Shirkavand, Gyungah R Jun · 2025
Read PreSiBOGNN: Multi‐Modal Graph Neural Network for Prediction of Cognitive Improvement in Medication Usage in UK Biobank by Dhawal Priyadarshi, Heng Huang, Nathan J Sahelijo, Reza Shirkavand, Gyungah R Jun (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-11713926.txt.
Description
Dhawal Priyadarshi and four co-authors built a graph learning system to forecast which drugs might lift thinking in Alzheimer's disease in a 2025 paper. New drug work for the disease is costly, so reusing known drugs is an appealing shortcut. Their system links genes, proteins, drugs, and patients in stacked graphs.
Data came from a large British health bank, with drug, clinic, and gene records for over forty-eight thousand people who took two thinking tests. Layers were joined by links from drug and protein databases. A chain of attention steps passed facts along the layers, ending in per-person forecasts of thinking change. Two ways of pooling the layers were compared. The authors aim the tool at patient-level drug matching.
Catalog record
| CREATOR | Dhawal Priyadarshi, Heng Huang, Nathan J Sahelijo, Reza Shirkavand, Gyungah R Jun |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 3 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |