Table 7 Comparing the performance of DEEPLYESSENTIAL and Ning et al. and Nigatu et al. on their respective datasets [16, 35]; numbers in boldface indicate the best performance
From: DeeplyEssential: a deep neural network for predicting essential genes in microbes
Method | Clustering method | AUC |
|---|---|---|
Ning et al. 2014 | CD-HIT | 0.758 |
DeeplyEssential | OrthoMCL | 0.818 |
Nigatu et al. 2017 | Kullback-Leibler divergence | 0.650 |
DeeplyEssential | OrthoMCL | 0.840 |