Protein subcellular location prediction is one of the most difficult multiclass prediction problems in modern computational biology. Many methods have been proposed in the literature to solve this problem, but all the existing approaches are affected by some limitations. In this contribution we propose a novel method for protein subcellular location prediction that performs multiclass classification by combining kernel classifiers through DDAG. Each base classifier, called K-TIPCAC, projects the points on a Fisher subspace estimated on the training data by means of a novel technique. Experimental results clearly indicated that DDAG K-TIPCAC performs equally, if not better, than state-of-the-art ensemble methods for protein subcellular location.
DDAG K-TIPCAC : an ensemble method for protein subcellular localization / A. Rozza, G. Lombardi, M. Re, E. Casiraghi, G. Valentini - In: SUEMA 2010 Proceedings / [a cura di] O. Okun, M. Re, G. Valentini. - [s.l] : ECML, 2010 Sep. - pp. 75-84 (( convegno ECML SUEMA 2010 workshop : supervised and unsupervised ensemble methods and their applications tenutosi a Barcelona nel 2010.
|Titolo:||DDAG K-TIPCAC : an ensemble method for protein subcellular localization|
|Parole Chiave:||bioinformatics ; protein subcellular location prediction ; Fisher subspace ; ensemble of classifiers|
|Settore Scientifico Disciplinare:||Settore INF/01 - Informatica|
|Data di pubblicazione:||set-2010|
|Tipologia:||Book Part (author)|
|Appare nelle tipologie:||03 - Contributo in volume|