@article{mbs:/content/journal/mgen/10.1099/mgen.0.000850, author = "Volk, Denis and Yang-Turner, Fan and Didelot, Xavier and Crook, Derrick W. and Wyllie, David", title = "Catwalk: identifying closely related sequences in large microbial sequence databases", journal= "Microbial Genomics", year = "2022", volume = "8", number = "6", pages = "", doi = "https://doi.org/10.1099/mgen.0.000850", url = "https://www.microbiologyresearch.org/content/journal/mgen/10.1099/mgen.0.000850", publisher = "Microbiology Society", issn = "2057-5858", type = "Journal Article", keywords = "bacterial genomics", keywords = "microbial relatedness", keywords = "outbreak detection", eid = "000850", abstract = "There is a need to identify microbial sequences that may form part of transmission chains, or that may represent importations across national boundaries, amidst large numbers of SARS-CoV-2 and other bacterial or viral sequences. Reference-based compression is a sequence analysis technique that allows both a compact storage of sequence data and comparisons between sequences. Published implementations of the approach are being challenged by the large sample collections now being generated. Our aim was to develop a fast software detecting highly similar sequences in large collections of microbial genomes, including millions of SARS-CoV-2 genomes. To do so, we developed Catwalk, a tool that bypasses bottlenecks in the generation, comparison and in-memory storage of microbial genomes generated by reference mapping. It is a compiled solution, coded in Nim to increase performance. It can be accessed via command line, rest api or web server interfaces. We tested Catwalk using both SARS-CoV-2 and Mycobacterium tuberculosis genomes generated by prospective public-health sequencing programmes. Pairwise sequence comparisons, using clinically relevant similarity cut-offs, took about 0.39 and 0.66 μs, respectively; in 1 s, between 1 and 2 million sequences can be searched. Catwalk operates about 1700 times faster than, and uses about 8 % of the RAM of, a Python reference-based compression and comparison tool in current use for outbreak detection. Catwalk can rapidly identify close relatives of a SARS-CoV-2 or M. tuberculosis genome amidst millions of samples.", }