@article {Wong060657, author = {Adam Chun-Nin Wong and Patrick Ng and Angela E. Douglas}, title = {16SpeB: Towards defining bacterial species boundaries by intra-species gene sequence identity}, elocation-id = {060657}, year = {2016}, doi = {10.1101/060657}, publisher = {Cold Spring Harbor Laboratory}, abstract = {Summary 16SpeB (16S rRNA-based Species Boundary) is a package of Perl programs that evaluates total sequence variation of a bacterial species at the levels of the whole 16S rRNA sequences or single hypervariable (V) regions, using publicly-available sequences. The 16SpeB pipelines filter sequences from duplicated strains and of low quality, extracts a V region of interest using general primer sequences, and calculates sequence percentage identity (\%ID) through all possible pairwise alignments.Results The minimum \%ID of 16S rRNA gene sequences for 15 clinically-important bacterial species, as determined by 16SpeB, ranged from 82.6\% to 99.8\%. The relationship between minimum \%ID of V2/V6 regions and full-gene sequences varied among species, indicating that \%ID species limits should be resolved independently for each region of the 16S rRNA gene and bacterial species.Availability 16SpeB and user manual are freely available for download from: https://github.com/pnpnpn/16SpeB. A video tutorial is available at: https://youtu.be/Vd6YmMhyBiAContact cw442{at}cornell.eduSupplementary information Supplementary data are available at Bioinformatics online.}, URL = {https://www.biorxiv.org/content/early/2016/06/24/060657}, eprint = {https://www.biorxiv.org/content/early/2016/06/24/060657.full.pdf}, journal = {bioRxiv} }