references.bib

@misc{bushnell2014bbmap,  title={BBMap: a fast, accurate, splice-aware aligner}, 
  author={Bushnell, Brian}, 
  year={2014}
 }


@article{kamvar2014poppr,
  title={Poppr: an R package for genetic analysis of populations with clonal, partially clonal, and/or sexual reproduction},
  author={Kamvar, Zhian N and Tabima, Javier F and Gr{\"u}nwald, Niklaus J},
  journal={PeerJ},
  volume={2},
  pages={e281},
  year={2014},
  publisher={PeerJ Inc.}
}

@article{brown2016sourmash, title={sourmash: a library for MinHash sketching of DNA}, 
 author={Brown, C Titus and Irber, Luiz}, 
 journal={Journal of open source software}, 
 volume={1}, 
 number={5}, 
 pages={27}, 
 year={2016}
}

@article{sayers2022database, title={Database resources of the national center for biotechnology information}, 
 author={Sayers, Eric W and Bolton, Evan E and Brister, J Rodney and Canese, Kathi and Chan, Jessica and Comeau, Donald C and Connor, Ryan and Funk, Kathryn and Kelly, Chris and Kim, Sunghwan and others}, 
 journal={Nucleic acids research}, 
 volume={50}, 
 number={D1}, 
 pages={D20}, 
 year={2022}, 
 publisher={Oxford University Press}
}

@article{sayers2022database, title={Database resources of the national center for biotechnology information}, 
 author={Sayers, Eric W and Bolton, Evan E and Brister, J Rodney and Canese, Kathi and Chan, Jessica and Comeau, Donald C and Connor, Ryan and Funk, Kathryn and Kelly, Chris and Kim, Sunghwan and others}, 
 journal={Nucleic acids research}, 
 volume={50}, 
 number={D1}, 
 pages={D20}, 
 year={2022}, 
 publisher={Oxford University Press}
}

@article{crusoe2015khmer, title={The khmer software package: enabling efficient nucleotide sequence analysis}, 
 author={Crusoe, Michael R and Alameldin, Hussien F and Awad, Sherine and Boucher, Elmar and Caldwell, Adam and Cartwright, Reed and Charbonneau, Amanda and Constantinides, Bede and Edvenson, Greg and Fay, Scott and others}, 
 journal={F1000Research}, 
 volume={4}, 
 year={2015}, 
 publisher={Faculty of 1000 Ltd}
}

@article{chen2023ultrafast, title={Ultrafast one-pass FASTQ data preprocessing, quality control, and deduplication using fastp}, 
 author={Chen, Shifu}, 
 journal={Imeta}, 
 volume={2}, 
 number={2}, 
 pages={e107}, 
 year={2023}, 
 publisher={Wiley Online Library}
}

@article{li2009fast, title={Fast and accurate short read alignment with Burrows--Wheeler transform}, 
 author={Li, Heng and Durbin, Richard}, 
 journal={bioinformatics}, 
 volume={25}, 
 number={14}, 
 pages={1754--1760}, 
 year={2009}, 
 publisher={Oxford University Press}
}

@misc{Picard2019toolkit,  title = {Picard toolkit}, 
  year = {2019}, 
  publisher = {Broad Institute}, 
  journal = {Broad Institute, GitHub repository}, 
  howpublished = {\url{https://broadinstitute.github.io/picard/}}
}

@article{eggertsson2017graphtyper, title={Graphtyper enables population-scale genotyping using pangenome graphs}, 
 author={Eggertsson, Hannes P and Jonsson, Hakon and Kristmundsdottir, Snaedis and Hjartarson, Eirikur and Kehr, Birte and Masson, Gisli and Zink, Florian and Hjorleifsson, Kristjan E and Jonasdottir, Aslaug and Jonasdottir, Adalbjorg and others}, 
 journal={Nature genetics}, 
 volume={49}, 
 number={11}, 
 pages={1654--1660}, 
 year={2017}, 
 publisher={Nature Publishing Group US New York}
}

@article{manni2021busco, title={BUSCO update: novel and streamlined workflows along with broader and deeper phylogenetic coverage for scoring of eukaryotic, prokaryotic, and viral genomes}, 
 author={Manni, Mos{\`e} and Berkeley, Matthew R and Seppey, Mathieu and Sim{\~a}o, Felipe A and Zdobnov, Evgeny M}, 
 journal={Molecular biology and evolution}, 
 volume={38}, 
 number={10}, 
 pages={4647--4654}, 
 year={2021}, 
 publisher={Oxford University Press}
}

@article{dylus2024inference, title={Inference of phylogenetic trees directly from raw sequencing reads using Read2Tree}, 
 author={Dylus, David and Altenhoff, Adrian and Majidian, Sina and Sedlazeck, Fritz J and Dessimoz, Christophe}, 
 journal={Nature Biotechnology}, 
 volume={42}, 
 number={1}, 
 pages={139--147}, 
 year={2024}, 
 publisher={Nature Publishing Group US New York}
}

@article{prjibelski2020using, title={Using SPAdes de novo assembler}, 
 author={Prjibelski, Andrey and Antipov, Dmitry and Meleshko, Dmitry and Lapidus, Alla and Korobeynikov, Anton}, 
 journal={Current protocols in bioinformatics}, 
 volume={70}, 
 number={1}, 
 pages={e102}, 
 year={2020}, 
 publisher={Wiley Online Library}
}

@article{kolmogorov2019assembly, title={Assembly of long, error-prone reads using repeat graphs}, 
 author={Kolmogorov, Mikhail and Yuan, Jeffrey and Lin, Yu and Pevzner, Pavel A}, 
 journal={Nature biotechnology}, 
 volume={37}, 
 number={5}, 
 pages={540--546}, 
 year={2019}, 
 publisher={Nature Publishing Group US New York}
}

@article{schwengers2021bakta, title={Bakta: rapid and standardized annotation of bacterial genomes via alignment-free sequence identification}, 
 author={Schwengers, Oliver and Jelonek, Lukas and Dieckmann, Marius Alfred and Beyvers, Sebastian and Blom, Jochen and Goesmann, Alexander}, 
 journal={Microbial genomics}, 
 volume={7}, 
 number={11}, 
 pages={000685}, 
 year={2021}, 
 publisher={Microbiology Society}
}

@article{bayliss2019pirate, title={PIRATE: A fast and scalable pangenomics toolbox for clustering diverged orthologues in bacteria}, 
 author={Bayliss, Sion C and Thorpe, Harry A and Coyle, Nicola M and Sheppard, Samuel K and Feil, Edward J}, 
 journal={Gigascience}, 
 volume={8}, 
 number={10}, 
 pages={giz119}, 
 year={2019}, 
 publisher={Oxford University Press}
}

@article{nguyen2015iq, title={IQ-TREE: a fast and effective stochastic algorithm for estimating maximum-likelihood phylogenies}, 
 author={Nguyen, Lam-Tung and Schmidt, Heiko A and Von Haeseler, Arndt and Minh, Bui Quang}, 
 journal={Molecular biology and evolution}, 
 volume={32}, 
 number={1}, 
 pages={268--274}, 
 year={2015}, 
 publisher={Oxford University Press}
}

@article{katoh2002mafft, title={MAFFT: a novel method for rapid multiple sequence alignment based on fast Fourier transform}, 
 author={Katoh, Kazutaka and Misawa, Kazuharu and Kuma, Kei-ichi and Miyata, Takashi}, 
 journal={Nucleic acids research}, 
 volume={30}, 
 number={14}, 
 pages={3059--3066}, 
 year={2002}, 
 publisher={Oxford University Press}
}

@article{ewels2016multiqc, title={MultiQC: summarize analysis results for multiple tools and samples in a single report}, 
 author={Ewels, Philip and Magnusson, M{\aa}ns and Lundin, Sverker and K{\"a}ller, Max}, 
 journal={Bioinformatics}, 
 volume={32}, 
 number={19}, 
 pages={3047--3048}, 
 year={2016}, 
 publisher={Oxford University Press}
}

@article{mikheenko2018versatile, title={Versatile genome assembly evaluation with QUAST-LG}, 
 author={Mikheenko, Alla and Prjibelski, Andrey and Saveliev, Vladislav and Antipov, Dmitry and Gurevich, Alexey}, 
 journal={Bioinformatics}, 
 volume={34}, 
 number={13}, 
 pages={i142--i150}, 
 year={2018}, 
 publisher={Oxford University Press}
}

@article{shen2016seqkit, title={SeqKit: a cross-platform and ultrafast toolkit for FASTA/Q file manipulation}, 
 author={Shen, Wei and Le, Shuai and Li, Yan and Hu, Fuquan}, 
 journal={PloS one}, 
 volume={11}, 
 number={10}, 
 pages={e0163962}, 
 year={2016}, 
 publisher={Public Library of Science San Francisco, CA USA}
}

@book{van2020genomics,   title={Genomics in the cloud: using Docker, GATK, and WDL in Terra}, 
  author={Van der Auwera, Geraldine A and O'Connor, Brian D}, 
  year={2020}, 
  publisher={O'Reilly Media}
}

@article{garrison2022spectrum, title={A spectrum of free software tools for processing the VCF variant call format: vcflib, bio-vcf, cyvcf2, hts-nim and slivar}, 
 author={Garrison, Erik and Kronenberg, Zev N and Dawson, Eric T and Pedersen, Brent S and Prins, Pjotr}, 
 journal={PLoS computational biology}, 
 volume={18}, 
 number={5}, 
 pages={e1009123}, 
 year={2022}, 
 publisher={Public Library of Science San Francisco, CA USA}
}

@article{danecek2021twelve, title={Twelve years of SAMtools and BCFtools}, 
 author={Danecek, Petr and Bonfield, James K and Liddle, Jennifer and Marshall, John and Ohan, Valeriu and Pollard, Martin O and Whitwham, Andrew and Keane, Thomas and McCarthy, Shane A and Davies, Robert M and others}, 
 journal={Gigascience}, 
 volume={10}, 
 number={2}, 
 pages={giab008}, 
 year={2021}, 
 publisher={Oxford University Press}
}

@article{di2017nextflow, title={Nextflow enables reproducible computational workflows}, 
 author={Di Tommaso, Paolo and Chatzou, Maria and Floden, Evan W and Barja, Pablo Prieto and Palumbo, Emilio and Notredame, Cedric}, 
 journal={Nature biotechnology}, 
 volume={35}, 
 number={4}, 
 pages={316--319}, 
 year={2017}, 
 publisher={Nature Publishing Group}
}

@article{ewels2020nf, title={The nf-core framework for community-curated bioinformatics pipelines}, 
 author={Ewels, Philip A and Peltzer, Alexander and Fillinger, Sven and Patel, Harshil and Alneberg, Johannes and Wilm, Andreas and Garcia, Maxime Ulysse and Di Tommaso, Paolo and Nahnsen, Sven}, 
 journal={Nature biotechnology}, 
 volume={38}, 
 number={3}, 
 pages={276--278}, 
 year={2020}, 
 publisher={Nature Publishing Group US New York}
}

@article{kurtzer2017singularity, title={Singularity: Scientific containers for mobility of compute}, 
 author={Kurtzer, Gregory M and Sochat, Vanessa and Bauer, Michael W}, 
 journal={PloS one}, 
 volume={12}, 
 number={5}, 
 pages={e0177459}, 
 year={2017}, 
 publisher={Public Library of Science San Francisco, CA USA}
}

@article{da2017biocontainers, title={BioContainers: an open-source and community-driven framework for software standardization}, 
 author={da Veiga Leprevost, Felipe and Gr{\"u}ning, Bj{\"o}rn A and Alves Aflitos, Saulo and R{\"o}st, Hannes L and Uszkoreit, Julian and Barsnes, Harald and Vaudel, Marc and Moreno, Pablo and Gatto, Laurent and Weber, Jonas and others}, 
 journal={Bioinformatics}, 
 volume={33}, 
 number={16}, 
 pages={2580--2582}, 
 year={2017}, 
 publisher={Oxford University Press}
}

@article{qin2014proposed, title={A proposed genus boundary for the prokaryotes based on genomic insights}, 
 author={Qin, Qi-Long and Xie, Bin-Bin and Zhang, Xi-Ying and Chen, Xiu-Lan and Zhou, Bai-Cheng and Zhou, Jizhong and Oren, Aharon and Zhang, Yu-Zhong}, 
 journal={Journal of bacteriology}, 
 volume={196}, 
 number={12}, 
 pages={2210--2215}, 
 year={2014}, 
 publisher={Am Soc Microbiol}
}

@Manual{Rbase, title = {R: A Language and Environment for Statistical Computing},
author = {{R Core Team}},
organization = {R Foundation for Statistical Computing},
address = {Vienna, Austria},
year = {2021},
url = {https://www.R-project.org/}
}

@article{gruning2018bioconda, title={Bioconda: sustainable and comprehensive software distribution for the life sciences},
  author={Gr{\"u}ning, Bj{\"o}rn and Dale, Ryan and Sj{\"o}din, Andreas and Chapman, Brad A and Rowe, Jillian and Tomkins-Tinch, Christopher H and Valieris, Renan and K{\"o}ster, Johannes and Bioconda Team},
  journal={Nature methods},
  volume={15},
  number={7},
  pages={475--476},
  year={2018},
  publisher={Nature Publishing Group US New York}
}

@misc{anaconda, title = {Anaconda Software Distribution},
  url={https://docs.anaconda.com/},
  journal={Anaconda Documentation},
  version={Vers. 2-2.4.0}, 
  publisher={Anaconda Inc.},
  year={2020}
}

@misc{andrews2010fastqc,
  title={FastQC: a quality control tool for high throughput sequence data},
  author={Andrews, Simon and others},
  year={2010},
  publisher={Cambridge, United Kingdom}
}

@article{danecek2011variant,
  title={The variant call format and VCFtools},
  author={Danecek, Petr and Auton, Adam and Abecasis, Goncalo and Albers, Cornelis A and Banks, Eric and DePristo, Mark A and Handsaker, Robert E and Lunter, Gerton and Marth, Gabor T and Sherry, Stephen T and others},
  journal={Bioinformatics},
  volume={27},
  number={15},
  pages={2156--2158},
  year={2011},
  publisher={Oxford University Press}
}

@article{li2011tabix,
  title={Tabix: fast retrieval of sequence features from generic TAB-delimited files},
  author={Li, Heng},
  journal={Bioinformatics},
  volume={27},
  number={5},
  pages={718--719},
  year={2011},
  publisher={Oxford University Press}
}

 @article{anaconda,

    author = {Anaconda Software Distribution},
    title = {Computer software},
    journal = {Vers.},
    year = {2016},
    month = {November},
    volume = {4},
    pages = {2-2},

}