COLoR - Coordinated On-Line Rankers for Network Reconstruction

TL;DR

This paper introduces COLoR, an online ranking algorithm that predicts protein-protein interactions by training interconnected models, improving over traditional SVMs but slightly underperforming compared to local classifiers.

Contribution

The paper presents a novel online ranking approach for PPI prediction that leverages interconnected models and passive aggressive learning.

Findings

Ranking algorithm outperforms classic SVM in PPI prediction.

Performance is slightly below local supervised methods.

Effective in predicting interactions in the post synaptic density network.

Abstract

Predicting protein interactions is one of the more interesting challenges of the post-genomic era. Many algorithms address this problem as a binary classification problem: given two proteins represented as two vectors of features, predict if they interact or not. Importantly however, computational predictions are only one component of a larger framework for identifying PPI. The most promising candidate pairs can be validated experimentally by testing if they physical bind to each other. Since these experiments are more costly and error prone, the computational predictions serve as a filter, aimed to produce a small number of highly promising candidates. Here we propose to address this problem as a ranking problem: given a network with known interactions, rank all unknown pairs based on the likelihood of their interactions. In this paper we propose a ranking algorithm that trains multiple inter-connected models using a passive aggressive on-line approach. We show good results predicting protein-protein interactions for post synaptic density PPI network. We compare the precision of the ranking algorithm with local classifiers and classic support vector machine. Though the ranking algorithm outperforms the classic SVM classification, its performance is inferior compared to the local supervised method.