Reconstruction of biological networks by supervised machine learning approaches

TL;DR

This paper reviews supervised machine learning methods for reconstructing biological networks from genomic data, demonstrating their effectiveness across various network types with state-of-the-art results.

Contribution

It provides a comprehensive overview of recent supervised learning strategies for biological network inference, highlighting their application and performance.

Findings

Effective reconstruction of metabolic networks

Successful inference of protein-protein interaction networks

Accurate modeling of regulatory networks

Abstract

We review a recent trend in computational systems biology which aims at using pattern recognition algorithms to infer the structure of large-scale biological networks from heterogeneous genomic data. We present several strategies that have been proposed and that lead to different pattern recognition problems and algorithms. The strenght of these approaches is illustrated on the reconstruction of metabolic, protein-protein and regulatory networks of model organisms. In all cases, state-of-the-art performance is reported.