Nearest template prediction: a single-sample-based flexible class prediction with confidence assessment.
Hoshida Y. · 2010
Read Nearest template prediction: a single-sample-based flexible class prediction with confidence assessment. by Hoshida Y. (2010) 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/europmc-pmc2990751.txt.
Description
Hoshida presented nearest template prediction, a method for classifying a single patient's gene activity profile, in a 2010 article. Gene signature tests had stalled before reaching clinics because measurements vary between labs and platforms, and most methods judge batches rather than individuals.
Given only a list of signature genes and one sample, the method assigns a class and computes a confidence score for that call. Tests showed it working across platforms, across species, and with several classes at once, without tuning settings for each dataset. That flexibility targets the practical barriers holding back bedside use.
Catalog record
| CREATOR | Hoshida Y. |
|---|---|
| YEAR | 2010 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 31 KB |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |