refs.bib

@article{mardis2017dna,
  title={DNA sequencing technologies: 2006--2016},
  author={Mardis, Elaine R},
  journal={Nature protocols},
  volume={12},
  number={2},
  pages={213},
  year={2017},
  publisher={Nature Publishing Group}
}
@article{buermans2014next,
  title={Next generation sequencing technology: advances and applications},
  author={Buermans, HPJ and Den Dunnen, JT},
  journal={Biochimica et Biophysica Acta (BBA)-Molecular Basis of Disease},
  volume={1842},
  number={10},
  pages={1932--1941},
  year={2014},
  publisher={Elsevier}
}
@article{giardine2005galaxy,
  title={Galaxy: a platform for interactive large-scale genome analysis},
  author={Giardine, Belinda and Riemer, Cathy and Hardison, Ross C and Burhans, Richard and Elnitski, Laura and Shah, Prachi and Zhang, Yi and Blankenberg, Daniel and Albert, Istvan and Taylor, James and others},
  journal={Genome research},
  volume={15},
  number={10},
  pages={1451--1455},
  year={2005},
  publisher={Cold Spring Harbor Lab}
}
@article{depristo2011framework,
  title={A framework for variation discovery and genotyping using next-generation DNA sequencing data},
  author={DePristo, Mark A and Banks, Eric and Poplin, Ryan and Garimella, Kiran V and Maguire, Jared R and Hartl, Christopher and Philippakis, Anthony A and Del Angel, Guillermo and Rivas, Manuel A and Hanna, Matt and others},
  journal={Nature genetics},
  volume={43},
  number={5},
  pages={491},
  year={2011},
  publisher={Nature Publishing Group}
}
@article{anders2015htseq,
  title={HTSeq—a Python framework to work with high-throughput sequencing data},
  author={Anders, Simon and Pyl, Paul Theodor and Huber, Wolfgang},
  journal={Bioinformatics},
  volume={31},
  number={2},
  pages={166--169},
  year={2015},
  publisher={Oxford University Press}
}
@article{kumar2016mega7,
  title={MEGA7: molecular evolutionary genetics analysis version 7.0 for bigger datasets},
  author={Kumar, Sudhir and Stecher, Glen and Tamura, Koichiro},
  journal={Molecular biology and evolution},
  volume={33},
  number={7},
  pages={1870--1874},
  year={2016},
  publisher={Society for Molecular Biology and Evolution}
}
@article{tamura2011mega5,
  title={MEGA5: molecular evolutionary genetics analysis using maximum likelihood, evolutionary distance, and maximum parsimony methods},
  author={Tamura, Koichiro and Peterson, Daniel and Peterson, Nicholas and Stecher, Glen and Nei, Masatoshi and Kumar, Sudhir},
  journal={Molecular biology and evolution},
  volume={28},
  number={10},
  pages={2731--2739},
  year={2011},
  publisher={Oxford University Press}
}
@article{pratas2014xs,
  title={XS: a FASTQ read simulator},
  author={Pratas, Diogo and Pinho, Armando J and Rodrigues, Jo{\~a}o MOS},
  journal={BMC research notes},
  volume={7},
  number={1},
  pages={40},
  year={2014},
  publisher={BioMed Central}
}
@incollection{zhang2016overview,
  title={Overview of sequence data formats},
  author={Zhang, Hongen},
  booktitle={Statistical Genomics},
  pages={3--17},
  year={2016},
  publisher={Springer}
}
@article{liu2012comparison,
  title={Comparison of next-generation sequencing systems},
  author={Liu, Lin and Li, Yinhu and Li, Siliang and Hu, Ni and He, Yimin and Pong, Ray and Lin, Danni and Lu, Lihua and Law, Maggie},
  journal={BioMed Research International},
  volume={2012},
  year={2012},
  publisher={Hindawi Publishing Corporation}
}
@article{brouwer2016current,
  title={Current opportunities and challenges of next generation sequencing (NGS) of DNA; determining health and disease},
  author={Brouwer, CPJM and Vu, Thuy Duong and Zhou, Miaomiao and Cardinali, Gianluigi and Welling, Mick M and van de Wiele, Nathalie and Robert, Vincent},
  journal={British Biotechnology Journal},
  volume={13},
  number={4},
  year={2016},
  publisher={Sciencedomain International}
}
@article{cock2009sanger,
  title={The Sanger FASTQ file format for sequences with quality scores, and the Solexa/Illumina FASTQ variants},
  author={Cock, Peter JA and Fields, Christopher J and Goto, Naohisa and Heuer, Michael L and Rice, Peter M},
  journal={Nucleic acids research},
  volume={38},
  number={6},
  pages={1767--1771},
  year={2009},
  publisher={Oxford University Press}
}
@article{price2017simulome,
  title={Simulome: a genome sequence and variant simulator},
  author={Price, Adam and Gibas, Cynthia},
  journal={Bioinformatics},
  volume={33},
  number={12},
  pages={1876--1878},
  year={2017},
  publisher={Oxford University Press}
}
@article{huang2011art,
  title={ART: a next-generation sequencing read simulator},
  author={Huang, Weichun and Li, Leping and Myers, Jason R and Marth, Gabor T},
  journal={Bioinformatics},
  volume={28},
  number={4},
  pages={593--594},
  year={2011},
  publisher={Oxford University Press}
}
@article{escalona2016comparison,
  title={A comparison of tools for the simulation of genomic next-generation sequencing data},
  author={Escalona, Merly and Rocha, Sara and Posada, David},
  journal={Nature Reviews Genetics},
  volume={17},
  number={8},
  pages={459},
  year={2016},
  publisher={Nature Publishing Group}
}
@article{baruzzo2017simulation,
  title={Simulation-based comprehensive benchmarking of RNA-seq aligners},
  author={Baruzzo, Giacomo and Hayer, Katharina E and Kim, Eun Ji and Di Camillo, Barbara and FitzGerald, Garret A and Grant, Gregory R},
  journal={Nature methods},
  volume={14},
  number={2},
  pages={135},
  year={2017},
  publisher={Nature Publishing Group}
}
@article{hosseini2016survey,
  title={A survey on data compression methods for biological sequences},
  author={Hosseini, Morteza and Pratas, Diogo and Pinho, Armando},
  journal={Information},
  volume={7},
  number={4},
  pages={56},
  year={2016},
  publisher={Multidisciplinary Digital Publishing Institute}
}
@inproceedings{pratas2016efficient,
  title={Efficient compression of genomic sequences},
  author={Pratas, Diogo and Pinho, Armando J and Ferreira, Paulo JSG},
  booktitle={2016 Data Compression Conference (DCC)},
  pages={231--240},
  year={2016},
  organization={IEEE}
}
@article{hernaez2019genomic,
  title={Genomic Data Compression},
  author={Hernaez, Mikel and Pavlichin, Dmitri and Weissman, Tsachy and Ochoa, Idoia},
  journal={Annual Review of Biomedical Data Science},
  volume={2},
  year={2019},
  publisher={Annual Reviews}
}
@article{liu2017high,
  title={High-speed and high-ratio referential genome compression},
  author={Liu, Yuansheng and Peng, Hui and Wong, Limsoon and Li, Jinyan},
  journal={Bioinformatics},
  volume={33},
  number={21},
  pages={3364--3372},
  year={2017},
  publisher={Oxford University Press}
}
@article{ochoa2014idocomp,
  title={iDoComp: a compression scheme for assembled genomes},
  author={Ochoa, Idoia and Hernaez, Mikel and Weissman, Tsachy},
  journal={Bioinformatics},
  volume={31},
  number={5},
  pages={626--633},
  year={2014},
  publisher={Oxford University Press}
}
@article{deorowicz2015gdc,
  title={GDC 2: Compression of large collections of genomes},
  author={Deorowicz, Sebastian and Danek, Agnieszka and Niemiec, Marcin},
  journal={Scientific reports},
  volume={5},
  pages={11565},
  year={2015},
  publisher={Nature Publishing Group}
}
@article{hosseini2019ac,
  title={AC: A Compression Tool for Amino Acid Sequences},
  author={Hosseini, Morteza and Pratas, Diogo and Pinho, Armando J},
  journal={Interdisciplinary Sciences: Computational Life Sciences},
  pages={1--9},
  year={2019},
  publisher={Springer}
}
@article{nalbantoglu2010data,
  title={Data compression concepts and algorithms and their applications to bioinformatics},
  author={Nalbantoglu, {\"O}zkan and Russell, David and Sayood, Khalid},
  journal={Entropy},
  volume={12},
  number={1},
  pages={34--52},
  year={2010},
  publisher={Molecular Diversity Preservation International}
}
@inproceedings{pratas2018compression,
  title={Compression of amino acid sequences},
  author={Pratas, Diogo and Hosseini, Morteza and Pinho, Armando J},
  booktitle={International Conference on Practical Applications of Computational Biology \& Bioinformatics},
  pages={105--113},
  year={2018},
  organization={Springer}
}
@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}
}
@article{droop2016fqtools,
  title={fqtools: an efficient software suite for modern FASTQ file manipulation},
  author={Droop, Alastair P},
  journal={Bioinformatics},
  volume={32},
  number={12},
  pages={1883--1884},
  year={2016},
  publisher={Oxford University Press}
}
@article{afgan2018galaxy,
  title={The Galaxy platform for accessible, reproducible and collaborative biomedical analyses: 2018 update},
  author={Afgan, Enis and Baker, Dannon and Batut, B{\'e}r{\'e}nice and Van Den Beek, Marius and Bouvier, Dave and {\v{C}}ech, Martin and Chilton, John and Clements, Dave and Coraor, Nate and Gr{\"u}ning, Bj{\"o}rn A and others},
  journal={Nucleic acids research},
  volume={46},
  number={W1},
  pages={W537--W544},
  year={2018},
  publisher={Oxford University Press}
}
@article{blankenberg2010manipulation,
  title={Manipulation of FASTQ data with Galaxy},
  author={Blankenberg, Daniel and Gordon, Assaf and Von Kuster, Gregory and Coraor, Nathan and Taylor, James and Nekrutenko, Anton and Galaxy Team},
  journal={Bioinformatics},
  volume={26},
  number={14},
  pages={1783--1785},
  year={2010},
  publisher={Oxford University Press}
}
@article{goecks2010galaxy,
  title={Galaxy: a comprehensive approach for supporting accessible, reproducible, and transparent computational research in the life sciences},
  author={Goecks, Jeremy and Nekrutenko, Anton and Taylor, James},
  journal={Genome biology},
  volume={11},
  number={8},
  pages={R86},
  year={2010},
  publisher={BioMed Central}
}
@article{van2013fastq,
  title={From FastQ data to high-confidence variant calls: the genome analysis toolkit best practices pipeline},
  author={Van der Auwera, Geraldine A and Carneiro, Mauricio O and Hartl, Christopher and Poplin, Ryan and Del Angel, Guillermo and Levy-Moonshine, Ami and Jordan, Tadeusz and Shakir, Khalid and Roazen, David and Thibault, Joel and others},
  journal={Current protocols in bioinformatics},
  volume={43},
  number={1},
  pages={11--10},
  year={2013},
  publisher={Wiley Online Library}
}
@article{gordon2010fastx,
  title={Fastx-toolkit},
  author={Gordon, Assaf and Hannon, GJ and others},
  journal={FASTQ/A short-reads preprocessing tools (unpublished) http://hannonlab. cshl. edu/fastx\_toolkit},
  volume={5},
  year={2010}
}