EnGRaiN is a supervised machine learning method to construct ensemble networks. To benefit from the typical accuracy advantages of supervised learning methods while taking into account the impossibility of knowing true networks for training, we devised a method that uses small training datasets of true positives and true negatives among gene pairs. The datasets used to evaluate the performance of EnGaiN include (i) simulated datasets generated from Yeast networks and (ii) A. thaliana gene expression datasets.

Funding: This work is supported in part by the National Science Foundation under IIS-1841351 Related publication DOI: 10.1093/bioinformatics/btab829