Sample-Specific Generalized Cross-Validation for Gene Network Analysis of Cytarabine Response in Cancer Cell Lines
Jooee Oh, Heewon Park · 2026
Read Sample-Specific Generalized Cross-Validation for Gene Network Analysis of Cytarabine Response in Cancer Cell Lines by Jooee Oh, Heewon Park (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/pmc-13607853.txt.
Description
Jooee Oh and Heewon Park present a faster way to choose settings when building a personal gene network for each cancer sample, in a 2026 paper. Such networks can expose why one tumor answers a drug and another does not. The network builder they use depends heavily on its tuning settings, and standard cross-checking is slow and grades all samples together rather than one by one.
Their criterion, doubleS-GCV, grades each sample on its own and cuts the computing load sharply. In simulated tests it picked the right genes and rebuilt networks well, beating four classic grading rules. Applied to a large drug-response dataset, it found gene networks specific to sensitivity to the drug cytarabine, with candidate marker genes that earlier studies support. The networks also shifted shape in a nonlinear way as sensitivity changed.
Catalog record
| CREATOR | Jooee Oh, Heewon Park |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 45 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |