Naslov
Enhanced analytical power of SDS-PAGE using machine learning algorithms

Autori
Supek, Fran ; Peharec, Petra ; Krsnik-Rasol, Marijana ; Šmuc, Tomislav

Izvornik
Proteomics (1615-9853) 8 (2008), 1; 28-31

Vrsta, podvrsta i kategorija rada
Radovi u časopisima, članak, znanstveni

Ključne riječi
support vector machines ; principal component analysis ; one dimensional gel electrophoresis ; data mining ; differential protein expression

Sažetak
We aim to demonstrate that a complex plant tissue protein mixture can be reliably 'fingerprinted’ by running conventional one-dimensional SDS-PAGE in bulk and analyzing gel banding patterns using machine learning methods. An unsupervised approach to filter noise and systemic biases (principal component analysis) was coupled to state-of-the-art supervised methods for classification (support vector machines) and attribute ranking (ReliefF) to improve tissue discrimination, visualization and recognition of important gel regions.

Izvorni jezik
Engleski

Znanstvena područja
Biologija, Računarstvo, Biotehnologija

POVEZANOST RADA