A two-stage learning method for protein-protein interaction prediction

TL;DR

This paper introduces a two-stage learning approach for protein-protein interaction prediction that leverages denoising autoencoders to learn robust features from unlabeled data, improving classifier performance.

Contribution

It proposes a novel two-stage method combining denoising autoencoders and classifiers to enhance PPI prediction with limited labeled data.

Findings

The method outperforms traditional classifiers on PPI datasets.

Robust features learned improve prediction accuracy.

Effective use of unlabeled data enhances model performance.

Abstract

In this paper, a new method for PPI (proteinprotein 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;