Transfer learning enhances clinical utility of polygenic scores with small, phenotypically refined cohorts
YuChung Lin, Christoph Patrick Beier, Zuzana Sobiskova, Khalid Hamandi, Tommy Stödberg, Ching Ching Ng, Danielle M Andrade, Marte Roa Syvertsen, Elena Gardella, Alessandro Orsini, Choong Yi Fong, Jana Zarubova, Michaela Kajsová, Kheng Seang Lim, Kaja Kristine Selmer, Emanuele Cerulli Irelli, Guido Rubboli, Pasquale Striano, BIOJUME Consortium, Deb K Pal, Lisa J Strug · 2026
Read Transfer learning enhances clinical utility of polygenic scores with small, phenotypically refined cohorts by YuChung Lin, Christoph Patrick Beier, Zuzana Sobiskova, Khalid Hamandi, Tommy Stödberg, Ching Ching Ng, Danielle M Andrade, Marte Roa Syvertsen, Elena Gardella, Alessandro Orsini, Choong Yi Fong, Jana Zarubova, Michaela Kajsová, Kheng Seang Lim, Kaja Kristine Selmer, Emanuele Cerulli Irelli, Guido Rubboli, Pasquale Striano, BIOJUME Consortium, Deb K Pal, Lisa J Strug (2026) 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/PMC13322190.txt.
Description
YuChung Lin and co-authors borrow strength from large gene studies to sharpen risk scores for small patient groups in a 2026 study. Polygenic scores need huge data sets, which blurs fine clinical types, while small well defined cohorts alone are too weak. Their external score framework blends target cohort evidence with genetic correlation to a larger source study.
Simulations showed gains across a range of genetic links between source and target traits. Applied work refined an epilepsy score to separate juvenile myoclonic epilepsy from sister types and used a large ADHD study to predict impulsivity in that group. A cystic fibrosis cohort test predicted diabetes linked to the disease, with checks for platform artefacts.
Catalog record
| CREATOR | YuChung Lin, Christoph Patrick Beier, Zuzana Sobiskova, Khalid Hamandi, Tommy Stödberg, Ching Ching Ng, Danielle M Andrade, Marte Roa Syvertsen, Elena Gardella, Alessandro Orsini, Choong Yi Fong, Jana Zarubova, Michaela Kajsová, Kheng Seang Lim, Kaja Kristine Selmer, Emanuele Cerulli Irelli, Guido Rubboli, Pasquale Striano, BIOJUME Consortium, Deb K Pal, Lisa J Strug |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 77324 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |