Gene distribution in the functional categories of the JCVI-CMR ontology.

Only categories used to train the classifier are shown. Mix category regroups the noisy subcategories. The original column refers to the complete J. Craig Venter Institute Comprehensive Microbial Resource (JCVI-CMR). The training column refers to the dataset used to train the classifier. The classified column refers to the “Unknown function” and “Unclassified” genes that were classified by LitProf- Gene Classifier with confidence≥0.7. There is no significant difference between the original and training datasets (p>0.05 in paired t-test; confidence level of 95%).