Please cite swarm as follows:
- Mahé F, Rognes T, Quince C, de Vargas C, Dunthorn M. (2014) Swarm: robust and fast clustering method for amplicon-based studies. PeerJ 2:e593 <http://dx.doi.org/10.7717/peerj.593>
- Mahé F, Rognes T, Quince C, de Vargas C, Dunthorn M. (2015) Swarm v2: highly-scalable and high-resolution amplicon clustering. PeerJ 3:e1420 <https://doi.org/10.7717/peerj.1420>
- Mahé F, Czech L, Stamatakis A, Quince C, de Vargas C, Dunthorn M, Rognes T. (2021) Swarm v3: towards tera-scale amplicon clustering. Bioinformatics <https://doi.org/10.1093/bioinformatics/btab493>

Bibtex format:

@article{10.7717/peerj.593,
 title = {Swarm: robust and fast clustering method for amplicon-based studies},
 author = {Mahé, Frédéric and Rognes, Torbjørn and Quince, Christopher and de Vargas, Colomban and Dunthorn, Micah},
 year = {2014},
 month = {9},
 keywords = {Environmental diversity, Barcoding, Molecular operational taxonomic units},
 abstract = {Popular \textit{de novo} amplicon clustering methods suffer from two fundamental flaws: arbitrary global clustering thresholds, and input-order dependency induced by centroid selection. Swarm was developed to address these issues by first clustering nearly identical amplicons iteratively using a local threshold, and then by using clusters’ internal structure and amplicon abundances to refine its results. This fast, scalable, and input-order independent approach reduces the influence of clustering parameters and produces robust operational taxonomic units.},
 volume = {2},
 pages = {e593},
 journal = {PeerJ},
 issn = {2167-8359},
 url = {http://dx.doi.org/10.7717/peerj.593},
 doi = {10.7717/peerj.593}
}

@article{10.7717/peerj.1420,
 title = {Swarm v2: highly-scalable and high-resolution amplicon clustering},
 author = {Mahé, Frédéric and Rognes, Torbjørn and Quince, Christopher and de Vargas, Colomban and Dunthorn, Micah},
 year = {2015},
 month = {12},
 keywords = {Environmental diversity, Barcoding, Molecular operational taxonomic units},
 abstract = {Previously we presented Swarm v1, a novel and open source amplicon clustering program that produced fine-scale molecular operational taxonomic units (OTUs), free of arbitrary global clustering thresholds and input-order dependency. Swarm v1 worked with an initial phase that used iterative single-linkage with a local clustering threshold (\textit{d}), followed by a phase that used the internal abundance structures of clusters to break chained OTUs. Here we present Swarm v2, which has two important novel features: (1) a new algorithm for \textit{d} = 1 that allows the computation time of the program to scale linearly with increasing amounts of data; and (2) the new fastidious option that reduces under-grouping by grafting low abundant OTUs (e.g., singletons and doubletons) onto larger ones. Swarm v2 also directly integrates the clustering and breaking phases, dereplicates sequencing reads with \textit{d} = 0, outputs OTU representatives in fasta format, and plots individual OTUs as two-dimensional networks.},
 volume = {3},
 pages = {e1420},
 journal = {PeerJ},
 issn = {2167-8359},
 url = {https://doi.org/10.7717/peerj.1420},
 doi = {10.7717/peerj.1420}
}

@article{Mahe2021,
 title = {{Swarm v3: towards tera-scale amplicon clustering}},
 author = {Mah{\'{e}}, Fr{\'{e}}d{\'{e}}ric and Czech, Lucas and Stamatakis, Alexandros and Quince, Christopher and de Vargas, Colomban and Dunthorn, Micah and Rognes, Torbj{\o}rn},
 year = {2021},
 month = {jul},
 abstract = {Motivation: Previously we presented swarm, an open-source amplicon clustering program that produces fine-scale molecular operational taxonomic units (OTUs) that are free of arbitrary global clustering thresholds. Here we present swarm v3 to address issues of contemporary datasets that are growing towards tera-byte sizes. Results: When compared to previous swarm versions, swarm v3 has modernized C++ source code, reduced memory footprint by up to 50{\%}, optimized CPU-usage and multithreading (more than 7 times faster with default parameters), and it has been extensively tested for its robustness and logic.},
 journal = {Bioinformatics},
 url = {https://doi.org/10.1093/bioinformatics/btab493},
 doi = {10.1093/BIOINFORMATICS/BTAB493}
}
