An application of topological graph clustering to protein function prediction

TL;DR

This paper introduces a topological graph clustering method using semisupervised learning to predict protein functions in yeast, demonstrating comparable or superior performance to existing techniques.

Contribution

It applies topological data analysis to biological networks for protein function prediction, offering a novel approach that enhances prediction accuracy.

Findings

Achieves comparable or better results than current methods

Validates the effectiveness of topological data analysis in biological networks

Provides a new tool for protein function annotation

Abstract

We use a semisupervised learning algorithm based on a topological data analysis approach to assign functional categories to yeast proteins using similarity graphs. This new approach to analyzing biological networks yields results that are as good as or better than state of the art existing approaches.