Amir Ahooye Atashin - Department of Computer Engineering Ferdowsi University of Mashhad Mashhad, Iran
Parsa Bagherzadeh - Department of Computer Engineering Ferdowsi University of Mashhad Mashhad, Iran
Kamaledin Giasi-Shirazi - Department of Computer Engineering Ferdowsi University of Mashhad Mashhad, Iran

In this paper, a new method for PPI (protein-protein interaction) prediction is proposed. In PPI prediction, a reliable and sufficient number of training samples is not available, but a large number of unlabeled samples is in hand. In the proposed method, the denoising auto encoders are employed for learning robust features. The obtained robust features are used in order to train a classifier with a better performance. The experimental results demonstrate the capabilities of the proposed method.

Protein-protein interaction; Denoising auto encoder; Robust features; Unlabelled data;