Supervised, semi-supervised and unsupervised inference of gene regulatory networks

作者：Maetschke Stefan R; Madhamshettiwar Piyush B; Davis Melissa J; Ragan Mark A^*

来源：Briefings in Bioinformatics, 2014, 15(2): 195-211.

DOI：10.1093/bib/bbt034

• gene regulatory networks
• simulation
• gene expression data
• machine learning

We performed an extensive evaluation of inference methods on simulated and experimental expression data. The results reveal low prediction accuracies for unsupervised techniques with the notable exception of the Z-SCORE method on knockout 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.

• 出版日期2014-3