Figure 1
From: Identifying essential genes in bacterial metabolic networks with machine learning methods
The workflow. Essentiality data for an organism was taken from an experimental genome wide knock-out screen. It was used to train the machine learning system using features that based on the topology of the metabolic network and genomic and transcriptomic data. The trained classifier was then applied to another organism (query organism) for which the essentiality for each gene in the metabolism was predicted.