@article{mbs:/content/journal/mgen/10.1099/mgen.0.000685, author = "Schwengers, Oliver and Jelonek, Lukas and Dieckmann, Marius Alfred and Beyvers, Sebastian and Blom, Jochen and Goesmann, Alexander", title = "Bakta: rapid and standardized annotation of bacterial genomes via alignment-free sequence identification", journal= "Microbial Genomics", year = "2021", volume = "7", number = "11", pages = "", doi = "https://doi.org/10.1099/mgen.0.000685", url = "https://www.microbiologyresearch.org/content/journal/mgen/10.1099/mgen.0.000685", publisher = "Microbiology Society", issn = "2057-5858", type = "Journal Article", keywords = "whole-genome sequencing", keywords = "bacteria", keywords = "metagenome-assembled genomes", keywords = "plasmids ", keywords = "genome annotation", eid = "000685", abstract = "Command-line annotation software tools have continuously gained popularity compared to centralized online services due to the worldwide increase of sequenced bacterial genomes. However, results of existing command-line software pipelines heavily depend on taxon-specific databases or sufficiently well annotated reference genomes. Here, we introduce Bakta, a new command-line software tool for the robust, taxon-independent, thorough and, nonetheless, fast annotation of bacterial genomes. Bakta conducts a comprehensive annotation workflow including the detection of small proteins taking into account replicon metadata. The annotation of coding sequences is accelerated via an alignment-free sequence identification approach that in addition facilitates the precise assignment of public database cross-references. Annotation results are exported in GFF3 and International Nucleotide Sequence Database Collaboration (INSDC)-compliant flat files, as well as comprehensive JSON files, facilitating automated downstream analysis. We compared Bakta to other rapid contemporary command-line annotation software tools in both targeted and taxonomically broad benchmarks including isolates and metagenomic-assembled genomes. We demonstrated that Bakta outperforms other tools in terms of functional annotations, the assignment of functional categories and database cross-references, whilst providing comparable wall-clock runtimes. Bakta is implemented in Python 3 and runs on MacOS and Linux systems. It is freely available under a GPLv3 license at https://github.com/oschwengers/bakta. An accompanying web version is available at https://bakta.computational.bio.", }