@article {Moshiri261354, author = {Niema Moshiri}, title = {TreeCluster: Massively scalable transmission clustering using phylogenetic trees}, elocation-id = {261354}, year = {2018}, doi = {10.1101/261354}, publisher = {Cold Spring Harbor Laboratory}, abstract = {Background The ability to infer transmission clusters from molecular data is critical to designing and evaluating viral control strategies. Viral sequencing datasets are growing rapidly, but standard methods of transmission cluster inference do not scale well beyond thousands of sequences.Results I present TreeCluster, a cross-platform tool that performs transmission cluster inference on a given phylogenetic tree orders of magnitude faster than existing inference methods and supports multiple clustering optimization functions.Conclusions TreeCluster is a freely-available cross-platform open source Python 3 tool for inferring transmission clusters from phylogenetic trees. Code, usage information, and in-depth descriptions of the implemented clustering modes are available publicly at the following repository:https://github.com/niemasd/TreeClusterAbbreviationsGTRGeneral Time ReversibleHIVHuman Immunodeficiency VirusLANLLos Alamos National LaboratorypolDNA polymerase geneSHShimodaira-HasegawaTN93Tamura-Nei 93}, URL = {https://www.biorxiv.org/content/early/2018/02/21/261354}, eprint = {https://www.biorxiv.org/content/early/2018/02/21/261354.full.pdf}, journal = {bioRxiv} }