Supervised, semi-supervised and unsupervised inference of gene regulatory networks
Molecular Networks
2013-01-08 v1 Quantitative Methods
Machine Learning
Abstract
Inference of gene regulatory network from expression data is a challenging task. Many methods have been developed to this purpose but a comprehensive evaluation that covers unsupervised, semi-supervised and supervised methods, and provides guidelines for their practical application, is lacking. We performed an extensive evaluation of inference methods on simulated expression data. The results reveal very low prediction accuracies for unsupervised techniques with the notable exception of the z-score method on knock-out data. In all other cases the supervised approach achieved the highest accuracies and even in a semi-supervised setting with small numbers of only positive samples, outperformed the unsupervised techniques.
Keywords
Cite
@article{arxiv.1301.1083,
title = {Supervised, semi-supervised and unsupervised inference of gene regulatory networks},
author = {Stefan R. Maetschke and Piyush B. Madhamshettiwar and Melissa J. Davis and Mark A. Ragan},
journal= {arXiv preprint arXiv:1301.1083},
year = {2013}
}