Comparing Artificial Neural Networks, General Linear Models and Support Vector Machines in Building Predictive Models for Small Interfering RNAs
Kyle A. McQuisten, Andrew S. Peek · 2009
Read Comparing Artificial Neural Networks, General Linear Models and Support Vector Machines in Building Predictive Models for Small Interfering RNAs by Kyle A. McQuisten, Andrew S. Peek (2009) 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/plos-pone-0007522.txt.
Description
Kyle McQuisten and Andrew Peek published a comparison study in PLOS ONE in 2009 on designing small interfering RNAs. These short RNA pieces can silence a chosen gene inside cells. Not every design works equally well, though. Machine learning tools promise to predict which ones will succeed. The authors pitted three approaches against each other: artificial neural networks, general linear models, and support vector machines.
Each method was tested on how well it predicted effective siRNAs. The head-to-head comparison also weighed the feature sets fed into the models. For researchers, the value is practical guidance. Choosing the right predictor means fewer wasted experiments on designs that fail. The study turns a crowded field of algorithms into clearer advice for anyone building gene-silencing tools.
Catalog record
| CREATOR | Kyle A. McQuisten, Andrew S. Peek |
|---|---|
| YEAR | 2009 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 61 KB |
| LICENSE | Creative Commons Attribution License |
| RIGHTS | CC BY |
| SOURCE | PLOS ONE |
Source: https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0007522