Skip to main content
Fig. 3 | BMC Bioinformatics

Fig. 3

From: MetageNN: a memory-efficient neural network taxonomic classifier robust to sequencing errors and missing genomes

Fig. 3

Results at the genus level of taxonomic classification methods applied to ONT data. Bar plots (error bars represent standard deviation across ONT bacterial isolates) showing results for MetaMaps, Kraken2, GeNet, MEGAN-LR, MMseqs2 and MetageNN. Average values of sensitivity, precision and F1 are shown on the top along with statistical significance bars on top, where * stands for digits after the decimal p-value point i.e., “****” signifies 1e−4. a Results aggregating all ONT isolates tested. b Results for the “Species in the database” dataset. c Results for the “Species out of the database” dataset. Bottom: Results stratified by the number of species sharing the same genus. Results for d “exactly one”, e “two or three” and f “more than three” groups based on the “Species out of the database” dataset

Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us