bibliography.bib

@book{durbin1998biological,
  title={Biological sequence analysis: probabilistic models of proteins and nucleic acids},
  author={Durbin, Richard and Eddy, Sean R and Krogh, Anders and Mitchison, Graeme},
  year={1998},
  publisher={Cambridge university press}
}
@article{soneson2013comparison,
  title={A comparison of methods for differential expression analysis of RNA-seq data},
  author={Soneson, Charlotte and Delorenzi, Mauro},
  journal={BMC bioinformatics},
  volume={14},
  number={1},
  pages={91},
  year={2013},
  publisher={BioMed Central}
}
@article{daley2013predicting,
  title={Predicting the molecular complexity of sequencing libraries},
  author={Daley, Timothy and Smith, Andrew D},
  journal={Nature methods},
  volume={10},
  number={4},
  pages={325},
  year={2013},
  publisher={Nature Publishing Group}
}
@article{delignette2015fitdistrplus,
  title={fitdistrplus: An R package for fitting distributions},
  author={Delignette-Muller, Marie Laure and Dutang, Christophe and others},
  journal={Journal of Statistical Software},
  volume={64},
  number={4},
  pages={1--34},
  year={2015}
}
@article{sun2018findgse,
  title={findGSE: estimating genome size variation within human and Arabidopsis using k-mer frequencies},
  author={Sun, Hequan and Ding, Jia and Piedno{\"e}l, Mathieu and Schneeberger, Korbinian},
  journal={Bioinformatics},
  volume={34},
  number={4},
  pages={550--557},
  year={2018},
  publisher={Oxford University Press}
}
@article{marccais2011fast,
  title={A fast, lock-free approach for efficient parallel counting of occurrences of k-mers},
  author={Mar{\c{c}}ais, Guillaume and Kingsford, Carl},
  journal={Bioinformatics},
  volume={27},
  number={6},
  pages={764--770},
  year={2011},
  publisher={Oxford University Press}
}
@incollection{liu2000bioprospector,
  title={BioProspector: discovering conserved DNA motifs in upstream regulatory regions of co-expressed genes},
  author={Liu, Xiaole and Brutlag, Douglas L and Liu, Jun S},
  booktitle={Biocomputing 2001},
  pages={127--138},
  year={2000},
  publisher={World Scientific}
}
@article{zhang2014these,
  title={These are not the k-mers you are looking for: efficient online k-mer counting using a probabilistic data structure},
  author={Zhang, Qingpeng and Pell, Jason and Canino-Koning, Rosangela and Howe, Adina Chuang and Brown, C Titus},
  journal={PloS one},
  volume={9},
  number={7},
  year={2014},
  publisher={Public Library of Science}
}
@misc{jones2015fastqtools,
  title={dcjones/fastq-tools}, url={https://github.com/dcjones/fastq-tools},
  journal={GitHub},
  author={Jones, Daniel C},
  year={2015}
}
@article{huang2012art,
  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={2012},
  publisher={Oxford University Press}
}
@book{cullen1999probabilistic,
  title={Probabilistic techniques in exposure assessment: a handbook for dealing with variability and uncertainty in models and inputs},
  author={Cullen, Alison C and Frey, H Christopher and Frey, Christopher H},
  year={1999},
  publisher={Springer Science \& Business Media}
}
@article{anders2010differential,
  title={Differential expression analysis for sequence count data},
  author={Anders, Simon and Huber, Wolfgang},
  journal={Nature Precedings},
  pages={1--1},
  year={2010},
  publisher={Nature Publishing Group}
}
@article{love2014moderated,
  title={Moderated estimation of fold change and dispersion for RNA-seq data with DESeq2},
  author={Love, Michael I and Huber, Wolfgang and Anders, Simon},
  journal={Genome biology},
  volume={15},
  number={12},
  pages={550},
  year={2014},
  publisher={Springer}
}
@misc{tange2018ole,
  title={Ole Tange, Mar. 2018},
  author={Tange, O and Parallel, GNU},
  year={2018}
}
@article{sanner1999python,
  title={Python: a programming language for software integration and development},
  author={Sanner, Michel F and others},
  journal={J Mol Graph Model},
  volume={17},
  number={1},
  pages={57--61},
  year={1999}
}
@article{harris2020array,
  title={Array programming with NumPy},
  author={Harris, Charles R and Millman, K Jarrod and van der Walt, St{\'e}fan J and Gommers, Ralf and Virtanen, Pauli and Cournapeau, David and Wieser, Eric and Taylor, Julian and Berg, Sebastian and Smith, Nathaniel J and others},
  journal={Nature},
  volume={585},
  number={7825},
  pages={357--362},
  year={2020},
  publisher={Nature Publishing Group}
}
@article{virtanen2020scipy,
  title={SciPy 1.0: fundamental algorithms for scientific computing in Python},
  author={Virtanen, Pauli and Gommers, Ralf and Oliphant, Travis E and Haberland, Matt and Reddy, Tyler and Cournapeau, David and Burovski, Evgeni and Peterson, Pearu and Weckesser, Warren and Bright, Jonathan and others},
  journal={Nature methods},
  volume={17},
  number={3},
  pages={261--272},
  year={2020},
  publisher={Nature Publishing Group}
}
@article{pedregosa2011scikit,
  title={Scikit-learn: Machine learning in Python},
  author={Pedregosa, Fabian and Varoquaux, Ga{\"e}l and Gramfort, Alexandre and Michel, Vincent and Thirion, Bertrand and Grisel, Olivier and Blondel, Mathieu and Prettenhofer, Peter and Weiss, Ron and Dubourg, Vincent and others},
  journal={the Journal of machine Learning research},
  volume={12},
  pages={2825--2830},
  year={2011},
  publisher={JMLR. org}
}
@article{cock2009biopython,
  title={Biopython: freely available Python tools for computational molecular biology and bioinformatics},
  author={Cock, Peter JA and Antao, Tiago and Chang, Jeffrey T and Chapman, Brad A and Cox, Cymon J and Dalke, Andrew and Friedberg, Iddo and Hamelryck, Thomas and Kauff, Frank and Wilczynski, Bartek and others},
  journal={Bioinformatics},
  volume={25},
  number={11},
  pages={1422--1423},
  year={2009},
  publisher={Oxford University Press}
}
@article{mckinney2011pandas,
  title={pandas: a foundational Python library for data analysis and statistics},
  author={McKinney, Wes and others},
  journal={Python for High Performance and Scientific Computing},
  volume={14},
  number={9},
  year={2011},
  publisher={Seattle}
}
@inproceedings{mckinney2010matplotlib,
  title={Data structures for statistical computing in python},
  author={McKinney, Wes and others},
  booktitle={Proceedings of the 9th Python in Science Conference},
  volume={445},
  pages={51--56},
  year={2010},
  organization={Austin, TX}
}
@article{luczak2019survey,
  title={A survey and evaluations of histogram-based statistics in alignment-free sequence comparison},
  author={Luczak, Brian B and James, Benjamin T and Girgis, Hani Z},
  journal={Briefings in Bioinformatics},
  volume={20},
  number={4},
  pages={1222--1237},
  year={2019},
  publisher={Oxford University Press}
}
@book{ferreira2017primer,
  title={A primer on process mining: Practical skills with python and graphviz},
  author={Ferreira, Diogo R},
  year={2017},
  publisher={Springer}
}

@article{zhou2015high,
  title={High-throughput metagenomic technologies for complex microbial community analysis: open and closed formats},
  author={Zhou, Jizhong and He, Zhili and Yang, Yunfeng and Deng, Ye and Tringe, Susannah G and Alvarez-Cohen, Lisa},
  journal={MBio},
  volume={6},
  number={1},
  pages={10--1128},
  year={2015},
  publisher={Am Soc Microbiol}
}

@article{xiong2012generation,
  title={Generation and analysis of a mouse intestinal metatranscriptome through Illumina based RNA-sequencing},
  author={Xiong, Xuejian and Frank, Daniel N and Robertson, Charles E and Hung, Stacy S and Markle, Janet and Canty, Angelo J and McCoy, Kathy D and Macpherson, Andrew J and Poussier, Philippe and Danska, Jayne S and others},
  journal={PloS one},
  volume={7},
  number={4},
  pages={e36009},
  year={2012},
  publisher={Public Library of Science San Francisco, USA}
}

@article{rognes2016vsearch,
  title={VSEARCH: a versatile open source tool for metagenomics},
  author={Rognes, Torbj{\o}rn and Flouri, Tom{\'a}{\v{s}} and Nichols, Ben and Quince, Christopher and Mah{\'e}, Fr{\'e}d{\'e}ric},
  journal={PeerJ},
  volume={4},
  pages={e2584},
  year={2016},
  publisher={PeerJ Inc.}
}
@article{fonseca2012tools,
  title={Tools for mapping high-throughput sequencing data},
  author={Fonseca, Nuno A and Rung, Johan and Brazma, Alvis and Marioni, John C},
  journal={Bioinformatics},
  volume={28},
  number={24},
  pages={3169--3177},
  year={2012},
  publisher={Oxford University Press}
}
@article{altschul1997gapped,
  title={Gapped BLAST and PSI-BLAST: a new generation of protein database search programs},
  author={Altschul, Stephen F and Madden, Thomas L and Sch{\"a}ffer, Alejandro A and Zhang, Jinghui and Zhang, Zheng and Miller, Webb and Lipman, David J},
  journal={Nucleic acids research},
  volume={25},
  number={17},
  pages={3389--3402},
  year={1997},
  publisher={Oxford University Press}
}
@article{eddy2004did,
  title={Where did the BLOSUM62 alignment score matrix come from?},
  author={Eddy, Sean R},
  journal={Nature biotechnology},
  volume={22},
  number={8},
  pages={1035--1036},
  year={2004},
  publisher={Nature Publishing Group}
}
@article{roberts2004reducing,
  title={Reducing storage requirements for biological sequence comparison},
  author={Roberts, Michael and Hayes, Wayne and Hunt, Brian R and Mount, Stephen M and Yorke, James A},
  journal={Bioinformatics},
  volume={20},
  number={18},
  pages={3363--3369},
  year={2004},
  publisher={Oxford University Press}
}

@article{thompson1999comprehensive,
  title={A comprehensive comparison of multiple sequence alignment programs},
  author={Thompson, Julie D and Plewniak, Fr{\'e}d{\'e}ric and Poch, Olivier},
  journal={Nucleic acids research},
  volume={27},
  number={13},
  pages={2682--2690},
  year={1999},
  publisher={Oxford University Press}
}
@article{zielezinski2017alignment,
  title={Alignment-free sequence comparison: benefits, applications, and tools},
  author={Zielezinski, Andrzej and Vinga, Susana and Almeida, Jonas and Karlowski, Wojciech M},
  journal={Genome biology},
  volume={18},
  number={1},
  pages={186},
  year={2017},
  publisher={Springer}
}
@article{anvar2014determining,
  title={Determining the quality and complexity of next-generation sequencing data without a reference genome},
  author={Anvar, Seyed Yahya and Khachatryan, Lusine and Vermaat, Martijn and van Galen, Michiel and Pulyakhina, Irina and Ariyurek, Yavuz and Kraaijeveld, Ken and den Dunnen, Johan T and de Knijff, Peter and Ac’t Hoen, Peter and others},
  journal={Genome biology},
  volume={15},
  number={12},
  pages={555},
  year={2014},
  url={doi:10.1186/s13059-014-0555-3},
  publisher={Springer}
}
@article{subramanian2003neutral,
  title={Neutral substitutions occur at a faster rate in exons than in noncoding DNA in primate genomes},
  author={Subramanian, Sankar and Kumar, Sudhir},
  journal={Genome research},
  volume={13},
  number={5},
  pages={838--844},
  year={2003},
  publisher={Cold Spring Harbor Lab}
}
@article{sved1990expected,
  title={The expected equilibrium of the CpG dinucleotide in vertebrate genomes under a mutation model.},
  author={Sved, John and Bird, Adrian},
  journal={Proceedings of the National Academy of Sciences},
  volume={87},
  number={12},
  pages={4692--4696},
  year={1990},
  publisher={National Acad Sciences}
}
@article{csHuros2007reconsidering,
  title={Reconsidering the significance of genomic word frequencies},
  author={Cs{\H{u}}r{\"o}s, Mikl{\'o}s and No{\'e}, Laurent and Kucherov, Gregory},
  journal={Trends in Genetics},
  volume={23},
  number={11},
  pages={543--546},
  year={2007},
  publisher={Elsevier}
}
@article{acquisti2007nullomers,
  title={Nullomers: really a matter of natural selection?},
  author={Acquisti, Claudia and Poste, George and Curtiss, David and Kumar, Sudhir},
  journal={PloS one},
  volume={2},
  number={10},
  pages={e1022},
  year={2007},
  publisher={Public Library of Science}
}
@article{patro2017salmon,
  title={Salmon provides fast and bias-aware quantification of transcript expression},
  author={Patro, Rob and Duggal, Geet and Love, Michael I and Irizarry, Rafael A and Kingsford, Carl},
  journal={Nature methods},
  volume={14},
  number={4},
  pages={417--419},
  year={2017},
  publisher={Nature Publishing Group}
}
@article{bray2016near,
  title={Near-optimal probabilistic RNA-seq quantification},
  author={Bray, Nicolas L and Pimentel, Harold and Melsted, P{\'a}ll and Pachter, Lior},
  journal={Nature biotechnology},
  volume={34},
  number={5},
  pages={525--527},
  year={2016},
  publisher={Nature Publishing Group}
}
@article{li2008maq,
  title={Maq: Mapping and assembly with qualities},
  author={Li, Heng and Ruan, J and Durbin, R},
  journal={Version 0.6},
  volume={3},
  year={2008}
}
@article{srivastava2016rapmap,
  title={RapMap: a rapid, sensitive and accurate tool for mapping RNA-seq reads to transcriptomes},
  author={Srivastava, Avi and Sarkar, Hirak and Gupta, Nitish and Patro, Rob},
  journal={Bioinformatics},
  volume={32},
  number={12},
  pages={i192--i200},
  year={2016},
  publisher={Oxford University Press}
}
@article{patro2014sailfish,
  title={Sailfish enables alignment-free isoform quantification from RNA-seq reads using lightweight algorithms},
  author={Patro, Rob and Mount, Stephen M and Kingsford, Carl},
  journal={Nature biotechnology},
  volume={32},
  number={5},
  pages={462--464},
  year={2014},
  publisher={Nature Publishing Group}
}
@article{simpson2014exploring,
  title={Exploring genome characteristics and sequence quality without a reference},
  author={Simpson, Jared T},
  journal={Bioinformatics},
  volume={30},
  number={9},
  pages={1228--1235},
  year={2014},
  publisher={Oxford University Press}
}
@article{caporaso2011moving,
  title={Moving pictures of the human microbiome},
  author={Caporaso, J Gregory and Lauber, Christian L and Costello, Elizabeth K and Berg-Lyons, Donna and Gonzalez, Antonio and Stombaugh, Jesse and Knights, Dan and Gajer, Pawel and Ravel, Jacques and Fierer, Noah and others},
  journal={Genome biology},
  volume={12},
  number={5},
  pages={1--8},
  year={2011},
  publisher={BioMed Central}
}
@inproceedings{fernandes2018graph,
  title={Graph Databases Comparison: AllegroGraph, ArangoDB, InfiniteGraph, Neo4J, and OrientDB.},
  author={Fernandes, Diogo and Bernardino, Jorge},
  booktitle={DATA},
  pages={373--380},
  year={2018}
}
@article{gunasekera2021evaluating,
  title={Evaluating coverage bias in next-generation sequencing of Escherichia coli},
  author={Gunasekera, Samantha and Abraham, Sam and Stegger, Marc and Pang, Stanley and Wang, Penghao and Sahibzada, Shafi and O’Dea, Mark},
  journal={Plos one},
  volume={16},
  number={6},
  pages={e0253440},
  year={2021},
  publisher={Public Library of Science San Francisco, CA USA}
}

@book{durbin1998biological,
  title={Biological sequence analysis: probabilistic models of proteins and nucleic acids},
  author={Durbin, Richard and Eddy, Sean R and Krogh, Anders and Mitchison, Graeme},
  year={1998},
  publisher={Cambridge university press}
}
@article{soneson2013comparison,
  title={A comparison of methods for differential expression analysis of RNA-seq data},
  author={Soneson, Charlotte and Delorenzi, Mauro},
  journal={BMC bioinformatics},
  volume={14},
  number={1},
  pages={91},
  year={2013},
  publisher={BioMed Central}
}
@article{daley2013predicting,
  title={Predicting the molecular complexity of sequencing libraries},
  author={Daley, Timothy and Smith, Andrew D},
  journal={Nature methods},
  volume={10},
  number={4},
  pages={325},
  year={2013},
  publisher={Nature Publishing Group}
}
@article{delignette2015fitdistrplus,
  title={fitdistrplus: An R package for fitting distributions},
  author={Delignette-Muller, Marie Laure and Dutang, Christophe and others},
  journal={Journal of Statistical Software},
  volume={64},
  number={4},
  pages={1--34},
  year={2015}
}
@article{sun2018findgse,
  title={findGSE: estimating genome size variation within human and Arabidopsis using k-mer frequencies},
  author={Sun, Hequan and Ding, Jia and Piedno{\"e}l, Mathieu and Schneeberger, Korbinian},
  journal={Bioinformatics},
  volume={34},
  number={4},
  pages={550--557},
  year={2018},
  publisher={Oxford University Press}
}
@article{marccais2011fast,
  title={A fast, lock-free approach for efficient parallel counting of occurrences of k-mers},
  author={Mar{\c{c}}ais, Guillaume and Kingsford, Carl},
  journal={Bioinformatics},
  volume={27},
  number={6},
  pages={764--770},
  year={2011},
  publisher={Oxford University Press}
}
@incollection{liu2000bioprospector,
  title={BioProspector: discovering conserved DNA motifs in upstream regulatory regions of co-expressed genes},
  author={Liu, Xiaole and Brutlag, Douglas L and Liu, Jun S},
  booktitle={Biocomputing 2001},
  pages={127--138},
  year={2000},
  publisher={World Scientific}
}
@article{zhang2014these,
  title={These are not the k-mers you are looking for: efficient online k-mer counting using a probabilistic data structure},
  author={Zhang, Qingpeng and Pell, Jason and Canino-Koning, Rosangela and Howe, Adina Chuang and Brown, C Titus},
  journal={PloS one},
  volume={9},
  number={7},
  year={2014},
  publisher={Public Library of Science}
}
@misc{jones2015fastqtools,
  title={dcjones/fastq-tools}, url={https://github.com/dcjones/fastq-tools},
  journal={GitHub},
  author={Jones, Daniel C},
  year={2015}
}
@article{huang2012art,
  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={2012},
  publisher={Oxford University Press}
}
@book{cullen1999probabilistic,
  title={Probabilistic techniques in exposure assessment: a handbook for dealing with variability and uncertainty in models and inputs},
  author={Cullen, Alison C and Frey, H Christopher and Frey, Christopher H},
  year={1999},
  publisher={Springer Science \& Business Media}
}
@article{anders2010differential,
  title={Differential expression analysis for sequence count data},
  author={Anders, Simon and Huber, Wolfgang},
  journal={Nature Precedings},
  pages={1--1},
  year={2010},
  publisher={Nature Publishing Group}
}
@article{love2014moderated,
  title={Moderated estimation of fold change and dispersion for RNA-seq data with DESeq2},
  author={Love, Michael I and Huber, Wolfgang and Anders, Simon},
  journal={Genome biology},
  volume={15},
  number={12},
  pages={550},
  year={2014},
  publisher={Springer}
}
@misc{tange2018ole,
  title={Ole Tange, Mar. 2018},
  author={Tange, O and Parallel, GNU},
  year={2018}
}
@article{sanner1999python,
  title={Python: a programming language for software integration and development},
  author={Sanner, Michel F and others},
  journal={J Mol Graph Model},
  volume={17},
  number={1},
  pages={57--61},
  year={1999}
}
@article{harris2020array,
  title={Array programming with NumPy},
  author={Harris, Charles R and Millman, K Jarrod and van der Walt, St{\'e}fan J and Gommers, Ralf and Virtanen, Pauli and Cournapeau, David and Wieser, Eric and Taylor, Julian and Berg, Sebastian and Smith, Nathaniel J and others},
  journal={Nature},
  volume={585},
  number={7825},
  pages={357--362},
  year={2020},
  publisher={Nature Publishing Group}
}
@article{virtanen2020scipy,
  title={SciPy 1.0: fundamental algorithms for scientific computing in Python},
  author={Virtanen, Pauli and Gommers, Ralf and Oliphant, Travis E and Haberland, Matt and Reddy, Tyler and Cournapeau, David and Burovski, Evgeni and Peterson, Pearu and Weckesser, Warren and Bright, Jonathan and others},
  journal={Nature methods},
  volume={17},
  number={3},
  pages={261--272},
  year={2020},
  publisher={Nature Publishing Group}
}
@article{pedregosa2011scikit,
  title={Scikit-learn: Machine learning in Python},
  author={Pedregosa, Fabian and Varoquaux, Ga{\"e}l and Gramfort, Alexandre and Michel, Vincent and Thirion, Bertrand and Grisel, Olivier and Blondel, Mathieu and Prettenhofer, Peter and Weiss, Ron and Dubourg, Vincent and others},
  journal={the Journal of machine Learning research},
  volume={12},
  pages={2825--2830},
  year={2011},
  publisher={JMLR. org}
}
@article{cock2009biopython,
  title={Biopython: freely available Python tools for computational molecular biology and bioinformatics},
  author={Cock, Peter JA and Antao, Tiago and Chang, Jeffrey T and Chapman, Brad A and Cox, Cymon J and Dalke, Andrew and Friedberg, Iddo and Hamelryck, Thomas and Kauff, Frank and Wilczynski, Bartek and others},
  journal={Bioinformatics},
  volume={25},
  number={11},
  pages={1422--1423},
  year={2009},
  publisher={Oxford University Press}
}
@article{mckinney2011pandas,
  title={pandas: a foundational Python library for data analysis and statistics},
  author={McKinney, Wes and others},
  journal={Python for High Performance and Scientific Computing},
  volume={14},
  number={9},
  year={2011},
  publisher={Seattle}
}
@inproceedings{mckinney2010matplotlib,
  title={Data structures for statistical computing in python},
  author={McKinney, Wes and others},
  booktitle={Proceedings of the 9th Python in Science Conference},
  volume={445},
  pages={51--56},
  year={2010},
  organization={Austin, TX}
}
@article{luczak2019survey,
  title={A survey and evaluations of histogram-based statistics in alignment-free sequence comparison},
  author={Luczak, Brian B and James, Benjamin T and Girgis, Hani Z},
  journal={Briefings in Bioinformatics},
  volume={20},
  number={4},
  pages={1222--1237},
  year={2019},
  publisher={Oxford University Press}
}
@article{fonseca2012tools,
  title={Tools for mapping high-throughput sequencing data},
  author={Fonseca, Nuno A and Rung, Johan and Brazma, Alvis and Marioni, John C},
  journal={Bioinformatics},
  volume={28},
  number={24},
  pages={3169--3177},
  year={2012},
  publisher={Oxford University Press}
}
@article{eddy2004did,
  title={Where did the BLOSUM62 alignment score matrix come from?},
  author={Eddy, Sean R},
  journal={Nature biotechnology},
  volume={22},
  number={8},
  pages={1035--1036},
  year={2004},
  publisher={Nature Publishing Group}
}
@article{roberts2004reducing,
  title={Reducing storage requirements for biological sequence comparison},
  author={Roberts, Michael and Hayes, Wayne and Hunt, Brian R and Mount, Stephen M and Yorke, James A},
  journal={Bioinformatics},
  volume={20},
  number={18},
  pages={3363--3369},
  year={2004},
  publisher={Oxford University Press}
}

@article{thompson1999comprehensive,
  title={A comprehensive comparison of multiple sequence alignment programs},
  author={Thompson, Julie D and Plewniak, Fr{\'e}d{\'e}ric and Poch, Olivier},
  journal={Nucleic acids research},
  volume={27},
  number={13},
  pages={2682--2690},
  year={1999},
  publisher={Oxford University Press}
}
@article{zielezinski2017alignment,
  title={Alignment-free sequence comparison: benefits, applications, and tools},
  author={Zielezinski, Andrzej and Vinga, Susana and Almeida, Jonas and Karlowski, Wojciech M},
  journal={Genome biology},
  volume={18},
  number={1},
  pages={186},
  year={2017},
  publisher={Springer}
}
@article{anvar2014determining,
  title={Determining the quality and complexity of next-generation sequencing data without a reference genome},
  author={Anvar, Seyed Yahya and Khachatryan, Lusine and Vermaat, Martijn and van Galen, Michiel and Pulyakhina, Irina and Ariyurek, Yavuz and Kraaijeveld, Ken and den Dunnen, Johan T and de Knijff, Peter and Ac’t Hoen, Peter and others},
  journal={Genome biology},
  volume={15},
  number={12},
  pages={555},
  year={2014},
  publisher={Springer}
}
@article{subramanian2003neutral,
  title={Neutral substitutions occur at a faster rate in exons than in noncoding DNA in primate genomes},
  author={Subramanian, Sankar and Kumar, Sudhir},
  journal={Genome Research},
  volume={13},
  number={5},
  pages={838--844},
  year={2003},
  publisher={Cold Spring Harbor Lab}
}
@article{sved1990expected,
  title={The expected equilibrium of the CpG dinucleotide in vertebrate genomes under a mutation model.},
  author={Sved, John and Bird, Adrian},
  journal={Proceedings of the National Academy of Sciences, PNAS},
  volume={87},
  number={12},
  pages={4692--4696},
  year={1990},
  publisher={National Acad Sciences}
}
@article{csHuros2007reconsidering,
  title={Reconsidering the significance of genomic word frequencies},
  author={Cs{\H{u}}r{\"o}s, Mikl{\'o}s and No{\'e}, Laurent and Kucherov, Gregory},
  journal={Trends in Genetics},
  volume={23},
  number={11},
  pages={543--546},
  year={2007},
  publisher={Elsevier}
}
@article{acquisti2007nullomers,
  title={Nullomers: really a matter of natural selection?},
  author={Acquisti, Claudia and Poste, George and Curtiss, David and Kumar, Sudhir},
  journal={PloS one},
  volume={2},
  number={10},
  pages={e1022},
  year={2007},
  publisher={Public Library of Science}
}
@article{patro2017salmon,
  title={Salmon provides fast and bias-aware quantification of transcript expression},
  author={Patro, Rob and Duggal, Geet and Love, Michael I and Irizarry, Rafael A and Kingsford, Carl},
  journal={Nature methods},
  volume={14},
  number={4},
  pages={417--419},
  year={2017},
  publisher={Nature Publishing Group}
}
@article{bray2016near,
  title={Near-optimal probabilistic RNA-seq quantification},
  author={Bray, Nicolas L and Pimentel, Harold and Melsted, P{\'a}ll and Pachter, Lior},
  journal={Nature biotechnology},
  volume={34},
  number={5},
  pages={525--527},
  year={2016},
  publisher={Nature Publishing Group}
}
@article{li2008maq,
  title={Maq: Mapping and assembly with qualities},
  author={Li, Heng and Ruan, J and Durbin, R},
  journal={Version 0.6},
  volume={3},
  year={2008}
}
@article{srivastava2016rapmap,
  title={RapMap: a rapid, sensitive and accurate tool for mapping RNA-seq reads to transcriptomes},
  author={Srivastava, Avi and Sarkar, Hirak and Gupta, Nitish and Patro, Rob},
  journal={Bioinformatics},
  volume={32},
  number={12},
  pages={i192--i200},
  year={2016},
  publisher={Oxford University Press}
}
@article{patro2014sailfish,
  title={Sailfish enables alignment-free isoform quantification from RNA-seq reads using lightweight algorithms},
  author={Patro, Rob and Mount, Stephen M and Kingsford, Carl},
  journal={Nature biotechnology},
  volume={32},
  number={5},
  pages={462--464},
  year={2014},
  publisher={Nature Publishing Group}
}
@article{simpson2014exploring,
  title={Exploring genome characteristics and sequence quality without a reference},
  author={Simpson, Jared T},
  journal={Bioinformatics},
  volume={30},
  number={9},
  pages={1228--1235},
  year={2014},
  publisher={Oxford University Press}
}
@article{caporaso2011moving,
  title={Moving pictures of the human microbiome},
  author={Caporaso, J Gregory and Lauber, Christian L and Costello, Elizabeth K and Berg-Lyons, Donna and Gonzalez, Antonio and Stombaugh, Jesse and Knights, Dan and Gajer, Pawel and Ravel, Jacques and Fierer, Noah and others},
  journal={Genome biology},
  volume={12},
  number={5},
  pages={1--8},
  year={2011},
  publisher={BioMed Central}
}
@article{bailey2009meme,
  title={MEME SUITE: tools for motif discovery and searching},
  author={Bailey, Timothy L and Boden, Mikael and Buske, Fabian A and Frith, Martin and Grant, Charles E and Clementi, Luca and Ren, Jingyuan and Li, Wilfred W and Noble, William S},
  journal={Nucleic acids research},
  volume={37},
  number={suppl\_2},
  pages={W202--W208},
  year={2009},
  publisher={Oxford University Press}
}

@inproceedings{fernandes2018graph,
  title={Graph Databases Comparison: AllegroGraph, ArangoDB, InfiniteGraph, Neo4J, and OrientDB.},
  author={Fernandes, Diogo and Bernardino, Jorge},
  booktitle={DATA},
  pages={373--380},
  year={2018}
}
@article{gunasekera2021evaluating,
  title={Evaluating coverage bias in next-generation sequencing of Escherichia coli},
  author={Gunasekera, Samantha and Abraham, Sam and Stegger, Marc and Pang, Stanley and Wang, Penghao and Sahibzada, Shafi and O’Dea, Mark},
  journal={Plos one},
  volume={16},
  number={6},
  pages={e0253440},
  year={2021},
  publisher={Public Library of Science San Francisco, CA USA}
}

@article{anvar2014determining,
  title={Determining the quality and complexity of next-generation sequencing data without a reference genome},
  author={Anvar, Seyed Yahya and Khachatryan, Lusine and Vermaat, Martijn and van Galen, Michiel and Pulyakhina, Irina and Ariyurek, Yavuz and Kraaijeveld, Ken and den Dunnen, Johan T and de Knijff, Peter and ’t Hoen, Peter AC and others},
  journal={Genome biology},
  volume={15},
  pages={1--15},
  year={2014},
  publisher={Springer}
}
@article{swain2022interpreting,
  title={Interpreting alignment-free sequence comparison: what makes a score a good score?},
  author={Swain, Martin T and Vickers, Martin},
  journal={NAR genomics and bioinformatics},
  volume={4},
  number={3},
  pages={lqac062},
  year={2022},
  publisher={Oxford University Press}
}
@article{wu1997measure,
  title={A measure of DNA sequence dissimilarity based on Mahalanobis distance between frequencies of words},
  author={Wu, Tiee-Jian and Burke, John P and Davison, Daniel B},
  journal={Biometrics},
  pages={1431--1439},
  year={1997},
  publisher={JSTOR}
}
@article{blaisdell1986measure,
  title={A measure of similarity of sets of sequences not requiring sequence alignment},
  author={Blaisdell, B. Edwin},
  journal={Proc. Nat. Acad. Sci. USA},
  volume={83},
  pages={5155-5159},
  year={1986},
  month={July},
  publisher={National Academy of Sciences}
}
@article{kantorovitz2007statistical,
  title={A statistical method for alignment-free comparison of regulatory sequences},
  author={Kantorovitz, Miriam R and Robinson, Gene E and Sinha, Saurabh},
  journal={Bioinformatics},
  volume={23},
  number={13},
  pages={i249--i255},
  year={2007},
  publisher={Oxford University Press}
}
@article{lippert2002distributional,
  title={Distributional regimes for the number of k-word matches between two random sequences},
  author={Lippert, Ross A and Huang, Haiyan and Waterman, Michael S},
  journal={Proceedings of the National Academy of Sciences},
  volume={99},
  number={22},
  pages={13980--13989},
  year={2002},
  publisher={National Acad Sciences}
}
@article{marcais2012jellyfish,
  title={Jellyfish: A fast k-mer counter},
  author={Marcais, G and Kingsford, C},
  journal={Tutorialis e Manuais},
  volume={1},
  number={1-8},
  pages={1038},
  year={2012}
}


@software{Jellyfish,
  author={Marcais, G and Kingsford, C},
  title={Jellyfish},
  url={https://github.com/gmarcais/Jellyfish},
  version={2.3.1},
  date={12/6/2023}
}

@comment   url={https://kpal.readthedocs.io/en/latest/method.html},
@comment Thanks so much, your work inspired me from the get-go and I hope I never come across the wrong way.
@comment All honesty, your paper was a real eye opener and thanks so much. Regards
@software{kPAL,
  author={Anvar, Seyed Yahya},
  title={kmer profile analysis library (kPAL)},
  url={https://github.com/LUMC/kPAL},
  version={2.1},
  date={11/21/2014}
  }

@software{kmerdb,
  author={Matt Ralston},
  title={kmerdb},
  url={https://github.com/MatthewRalston/kmerdb},
  version={0.8.5},
  date = {8/7/2024}
}



@software{NumPy,
  author={Harris, Charles R and Millman, K Jarrod and van der Walt, St{\'e}fan J and Gommers, Ralf and Virtanen, Pauli and Cournapeau, David and Wieser, Eric and Taylor, Julian and Berg, Sebastian and Smith, Nathaniel J and others},
  title={NumPy},
  url = {https://github.com/numpy/numpy},
  version = {2.0},
  date = {2020}
  }

 @Comment + Sergio Valqui, Ben Morris, Carlos Peña, João Rodrigues, Chris Rands, Rob Miller,Francesco Gastaldello, and others},
@software{BioPython,
  author={Cock, Peter JA and Antao, Tiago and Chang, Jeffrey T and Chapman, Brad A and Cox, Cymon J and Dalke, Andrew and Friedberg, Iddo and Hamelryck, Thomas and Kauff, Frank and Wilczynski, Bartek, Wibowo Arindrarto, Eric Talevich, Christian Brueffer, et al.}
  title={BioPython},
  url={https://biopython.org},
  version={1.81},
  date={02/12/2023}
}

@software{SciPy,
  author={Virtanen, Pauli and Gommers, Ralf and Oliphant, Travis E and Haberland, Matt and Reddy, Tyler and Cournapeau, David and Burovski, Evgeni and Peterson, Pearu and Weckesser, Warren and Bright, Jonathan and others},
  title={SciPy}
  url={https://scipy.org},
  version={1.11.4},
  date={11/18/2024}
}


@software{scikit-learn,
  author={Pedregosa, Fabian and Varoquaux, Ga{\"e}l and Gramfort, Alexandre and Michel, Vincent and Thirion, Bertrand and Grisel, Olivier and Blondel, Mathieu and Prettenhofer, Peter and Weiss, Ron and Dubourg, Vincent and others},
  title={Scikit-learn},
  url={https://github.com/scikit-learn/scikit-learn},
  version={1.5.1},
  date={07/03/2024}
}
@software{Python,
  author={Sanner, Michel F},
  title={Python Programming Language},
  url={https://python.org},
  version={3.12.4},
  date={6/6/2024}
}

@software{khmer,
  author={Zhang, Qingpeng},
  title={khmer: In-memory nucleotide sequence k-mer counting, filtering, graph traversal and more }
  url={https://github.com/dib-lab/khmer},
  version={2.1.2},
  date={7/3/2017}
}