Classifying Protein-Protein Interaction Type based on Association Pattern with Adjusted Support

Huang-Cheng Kuo, Ming-Yi Tai

Abstract


Proteins carry out their functions by means of interaction. There are two major types of protein-protein interaction (PPI): obligate interaction and transient interaction. In this paper, residues with geographical information on the binding sites are used to discover association patterns for classifying protein interaction type. We use the support of a frequent pattern as its inference power. However, due to the number of transient examples are much less than the number of obligate examples, therefore there needs adjustment on the imbalance. Three methods of applying association pattern to classify PPI type are designed. In the experiment, there are almost same results for three methods. And we reduce effect which is correct rate decreased by data type imbalance.

Keywords


Protein-Protein Interaction; Association Pattern Based Classification; Type Imbalance

Full Text:

PDF


Lululemon Black Friday cheap nfl jerseys Lululemon factory Outlet ny Black Friday discount tiffany outlet wholesale soccer jerseys online oakley black friday cheap nhl jerseys china cheap nfl jerseys north face black friday sale cheap nfl jerseys online Jordans Black Friday Sale 2015 Cheap Moncler Cyber Monday moncler outlet cheap soccer jerseys moncler outlet black friday cheap authentic nfl jerseys north face cyber monday Louboutin Black Friday canada wholesale cheap nfl jerseys lululemon cyber monday 2015 cheap nfl jerseys from china 2015 Cheap Moncler Black Friday Sale Moncler Cyber Monday 2015 cheap jerseys Lululemon Cyber Monday Sale jordans cyber monday deals 2015 cheap nike nfl jerseys Black Friday deals Lululemon 2015 jordan black friday 2015 Moncler Jackets Black Friday Sale 2015 Louboutin Pas Cher Black Friday 2015 Canada Lululemon north face black friday cheap wholesale soccer jerseys