references.bib

@Article{tidyverse,
  title = {Welcome to the {tidyverse}},
  author = {Hadley Wickham and Mara Averick and Jennifer Bryan and Winston Chang and Lucy D'Agostino McGowan and Romain François and Garrett Grolemund and Alex Hayes and Lionel Henry and Jim Hester and Max Kuhn and Thomas Lin Pedersen and Evan Miller and Stephan Milton Bache and Kirill Müller and Jeroen Ooms and David Robinson and Dana Paige Seidel and Vitalie Spinu and Kohske Takahashi and Davis Vaughan and Claus Wilke and Kara Woo and Hiroaki Yutani},
  year = {2019},
  journal = {Journal of Open Source Software},
  volume = {4},
  number = {43},
  pages = {1686},
  doi = {10.21105/joss.01686},
}
@Manual{rmarkdown1,
  title = {rmarkdown: Dynamic Documents for R},
  author = {JJ Allaire and Yihui Xie and Christophe Dervieux and Jonathan McPherson and Javier Luraschi and Kevin Ushey and Aron Atkins and Hadley Wickham and Joe Cheng and Winston Chang and Richard Iannone},
  year = {2024},
  note = {R package version 2.28},
  url = {https://github.com/rstudio/rmarkdown},
}

@Book{rmarkdown2,
  title = {R Markdown: The Definitive Guide},
  author = {Yihui Xie and J.J. Allaire and Garrett Grolemund},
  publisher = {Chapman and Hall/CRC},
  address = {Boca Raton, Florida},
  year = {2018},
  isbn = {9781138359338},
  url = {https://bookdown.org/yihui/rmarkdown},
}

@Book{rmarkdown3,
  title = {R Markdown Cookbook},
  author = {Yihui Xie and Christophe Dervieux and Emily Riederer},
  publisher = {Chapman and Hall/CRC},
  address = {Boca Raton, Florida},
  year = {2020},
  isbn = {9780367563837},
  url = {https://bookdown.org/yihui/rmarkdown-cookbook},
}

@Manual{tweetrmd,
  title = {tweetrmd: Embed Tweets in R Markdown},
  author = {Garrick Aden-Buie},
  year = {2024},
  note = {R package version 0.0.10, commit c683b537a4a5234ee750fff234d21e4e9c201ba8},
  url = {https://github.com/gadenbuie/tweetrmd},
}

@Manual{renv,
  title = {renv: Project Environments},
  author = {Kevin Ushey and Hadley Wickham},
  year = {2023},
  note = {R package version 1.0.3},
  url = {https://CRAN.R-project.org/package=renv},
}

@Manual{dplyr,
  title = {dplyr: A Grammar of Data Manipulation},
  author = {Hadley Wickham and Romain François and Lionel Henry and Kirill Müller and Davis Vaughan},
  year = {2023},
  note = {R package version 1.1.4, https://github.com/tidyverse/dplyr},
  url = {https://dplyr.tidyverse.org},
}

@software{Allaire_Quarto_2024,
author = {Allaire, J.J. and Teague, Charles and Scheidegger, Carlos and Xie, Yihui and Dervieux, Christophe},
doi = {10.5281/zenodo.5960048},
month = feb,
title = {{Quarto}},
url = {https://github.com/quarto-dev/quarto-cli},
version = {1.4},
year = {2024}
}

@misc{1.membershipofworkinggroup2.termsofreference,
	title = {Report of the DORA working group},
	author = {1. Membership of Working Group 2. Terms of reference, },
	url = {https://www.imperial.ac.uk/media/imperial-college/research-and-innovation/public/DORA-working-group-recommendations-2017.pdf}
}

@ARTICLE{wickham2014,
  title    = "Tidy Data",
  author   = "Wickham, Hadley",
  abstract = "A huge amount of effort is spent cleaning data to get it ready
              for analysis, but there has been little research on how to make
              data cleaning as easy and effective as possible. This paper
              tackles a small, but important, component of data cleaning: data
              tidying. Tidy datasets are easy to manipulate, model and
              visualize, and have a specific structure: each variable is a
              column, each observation is a row, and each type of observational
              unit is a table. This framework makes it easy to tidy messy
              datasets because only a small set of tools are needed to deal
              with a wide range of un-tidy datasets. This structure also makes
              it easier to develop tidy tools for data analysis, tools that
              both input and output tidy datasets. The advantages of a
              consistent data structure and matching tools are demonstrated
              with a case study free from mundane data manipulation chores.",
  journal  = "Journal of Statistical Software, Articles",
  volume   =  59,
  number   =  10,
  pages    = "1--23",
  year     =  2014,
  url      = "https://vita.had.co.nz/papers/tidy-data.pdf",
}

@Manual{knitr1,
  title = {knitr: A General-Purpose Package for Dynamic Report Generation in R},
  author = {Yihui Xie},
  year = {2024},
  note = {R package version 1.48},
  url = {https://yihui.org/knitr/},
}

@Book{knitr2,
  title = {Dynamic Documents with {R} and knitr},
  author = {Yihui Xie},
  publisher = {Chapman and Hall/CRC},
  address = {Boca Raton, Florida},
  year = {2015},
  edition = {2nd},
  note = {ISBN 978-1498716963},
  url = {https://yihui.org/knitr/},
}

@InCollection{knitr3,
  booktitle = {Implementing Reproducible Computational Research},
  editor = {Victoria Stodden and Friedrich Leisch and Roger D. Peng},
  title = {knitr: A Comprehensive Tool for Reproducible Research in {R}},
  author = {Yihui Xie},
  publisher = {Chapman and Hall/CRC},
  year = {2014},
  note = {ISBN 978-1466561595},
}

@article{kableExtra,
	title = {kableExtra: Construct Complex Table with 'kable' and Pipe Syntax},
	author = {Zhu, Hao},
	year = {2021},
	date = {2021},
	url = {https://CRAN.R-project.org/package=kableExtra}
}

@book{rand2023,
	title = {Data Analysis in R for Becoming a Bioscientist},
	author = {Rand, Emma},
	year = {2023},
	month = {05},
	date = {2023-05},
	url = {https://3mmarand.github.io/R4BABS/}
}


@Manual{readxl,
  title = {readxl: Read Excel Files},
  author = {Hadley Wickham and Jennifer Bryan},
  year = {2023},
  note = {R package version 1.4.3, https://github.com/tidyverse/readxl},
  url = {https://readxl.tidyverse.org},
}


@Manual{R-core,
  title = {R: A Language and Environment for Statistical Computing},
  author = {{R Core Team}},
  organization = {R Foundation for Statistical Computing},
  address = {Vienna, Austria},
  year = {2024},
  url = {https://www.R-project.org/},
}

@misc{allison_horst,
    title = {Data Science Illustrations},
    author = {Allison Horst},
    year = {2023},
    url = {https://allisonhorst.com/allison-horst},
  }
@article{tukey1949,
	title = {Comparing Individual Means in the Analysis of Variance},
	author = {Tukey, John W.},
	year = {1949},
	date = {1949},
	journal = {Biometrics},
	pages = {99--114},
	volume = {5},
	number = {2},
	doi = {10.2307/3001913},
	url = {https://www.jstor.org/stable/3001913},
	note = {Publisher: [Wiley, International Biometric Society]}
}

@article{nestorowa2016,
  title = {A Single-Cell Resolution Map of Mouse Hematopoietic Stem and Progenitor Cell Differentiation},
  author = {Nestorowa, Sonia and Hamey, Fiona K. and Pijuan Sala, Blanca and Diamanti, Evangelia and Shepherd, Mairi and Laurenti, Elisa and Wilson, Nicola K. and Kent, David G. and G{\"o}ttgens, Berthold},
  year = {2016},
  month = aug,
  journal = {Blood},
  volume = {128},
  number = {8},
  pages = {e20-e31},
  issn = {0006-4971},
  doi = {10.1182/blood-2016-05-716480},
  urldate = {2022-11-21},
  abstract = {Maintenance of the blood system requires balanced cell fate decisions by hematopoietic stem and progenitor cells (HSPCs). Because cell fate choices are executed at the individual cell level, new single-cell profiling technologies offer exciting possibilities for mapping the dynamic molecular changes underlying HSPC differentiation. Here, we have used single-cell RNA sequencing to profile more than 1600 single HSPCs, and deep sequencing has enabled detection of an average of 6558 protein-coding genes per cell. Index sorting, in combination with broad sorting gates, allowed us to retrospectively assign cells to 12 commonly sorted HSPC phenotypes while also capturing intermediate cells typically excluded by conventional gating. We further show that independently generated single-cell data sets can be projected onto the single-cell resolution expression map to directly compare data from multiple groups and to build and refine new hypotheses. Reconstruction of differentiation trajectories reveals dynamic expression changes associated with early lymphoid, erythroid, and granulocyte-macrophage differentiation. The latter two trajectories were characterized by common upregulation of cell cycle and oxidative phosphorylation transcriptional programs. By using external spike-in controls, we estimate absolute messenger RNA (mRNA) levels per cell, showing for the first time that despite a general reduction in total mRNA, a subset of genes shows higher expression levels in immature stem cells consistent with active maintenance of the stem-cell state. Finally, we report the development of an intuitive Web interface as a new community resource to permit visualization of gene expression in HSPCs at single-cell resolution for any gene of choice.}
}


@book{nationalacademiesofsciences2019,
	title = {Understanding Reproducibility and Replicability},
	author = {National Academies of Sciences, Engineering and Medicine,  and Policy,  and Affairs, Global and Committee on Science, {Engineering, Medicine} and Public Policy,  and Board on Research Data,  and Information,  and Division on Engineering,  and Physical Sciences,  and Committee on Applied,  and Statistics, Theoretical and Board on Mathematical Sciences,  and Analytics,  and Division on Earth,  and Life Studies,  and Nuclear,  and Radiation Studies Board,  and Division of Behavioral,  and Social Sciences,  and Education,  and Committee on National Statistics,  and Board on Behavioral, Cognitive and Sensory Sciences,  and Committee on Reproducibility,  and Replicability, },
	year = {2019},
	month = {05},
	date = {2019-05-07},
	publisher = {National Academies Press (US)},
	url = {https://www.ncbi.nlm.nih.gov/books/NBK547546/}
}

@book{community2022,
	title = {The Turing Way: A handbook for reproducible, ethical and collaborative research},
	author = {Community, The Turing Way},
	year = {2022},
	month = {07},
	date = {2022-07-27},
	publisher = {Zenodo},
	doi = {10.5281/ZENODO.3233853},
	url = {https://zenodo.org/record/3233853}
}

@article{baggerly2009,
	title = {DERIVING CHEMOSENSITIVITY FROM CELL LINES: FORENSIC BIOINFORMATICS AND REPRODUCIBLE RESEARCH IN HIGH-THROUGHPUT BIOLOGY},
	author = {Baggerly, Keith A and Coombes, Kevin R},
	year = {2009},
	date = {2009},
	journal = {Ann. Appl. Stat.},
	pages = {1309--1334},
	volume = {3},
	number = {4},
	url = {http://www.jstor.org/stable/27801549},
	note = {Publisher: Institute of Mathematical Statistics}
}

@techreport{oecdglobalscienceforum2020,
	title = {Building digital workforce capacity and skills for data-intensive science},
	author = {OECD Global Science Forum, },
	year = {2020},
	month = {06},
	date = {2020-06-19},
	url = {http://www.oecd.org/officialdocuments/publicdisplaydocumentpdf/?cote=DSTI/STP/GSF(2020)6/FINAL&docLanguage=En}
}

@Manual{sessioninfo,
    title = {sessioninfo: R Session Information},
    author = {Hadley Wickham and Winston Chang and Robert Flight and Kirill Müller and Jim Hester},
    year = {2021},
    note = {R package version 1.2.2, 
https://r-lib.github.io/sessioninfo/},
    url = {https://github.com/r-lib/sessioninfo#readme},
  }

@book{ostblomjoel2019,
	title = {session{\_}info},
	author = {{Ostblom, Joel}, },
	year = {2019},
	date = {2019},
	url = {https://gitlab.com/joelostblom/session_info}
}

@article{markowetz2015,
	title = {Five selfish reasons to work reproducibly},
	author = {Markowetz, Florian},
	year = {2015},
	month = {12},
	date = {2015-12-08},
	journal = {Genome Biol.},
	pages = {274},
	volume = {16},
	doi = {10.1186/s13059-015-0850-7},
	url = {http://dx.doi.org/10.1186/s13059-015-0850-7}
}

@book{bryan,
	title = {What They Forgot to Teach You About R},
	author = {Bryan, Jennifer and Hester, Jim and Pileggi, Shannon and Aja, E. David},
	url = {https://rstats.wtf/}
}

@article{sandve2013,
	title = {Ten simple rules for reproducible computational research},
	author = {Sandve, Geir Kjetil and Nekrutenko, Anton and Taylor, James and Hovig, Eivind},
	year = {2013},
	month = {10},
	date = {2013-10},
	journal = {PLoS Comput. Biol.},
	pages = {e1003285},
	volume = {9},
	number = {10},
	doi = {10.1371/journal.pcbi.1003285},
	url = {http://dx.doi.org/10.1371/journal.pcbi.1003285}
}

@article{wilson2017,
	title = {Good enough practices in scientific computing},
	author = {Wilson, Greg and Bryan, Jennifer and Cranston, Karen and Kitzes, Justin and Nederbragt, Lex and Teal, Tracy K},
	year = {2017},
	month = {06},
	date = {2017-06},
	journal = {PLoS Comput. Biol.},
	pages = {e1005510},
	volume = {13},
	number = {6},
	doi = {10.1371/journal.pcbi.1005510},
	url = {http://dx.doi.org/10.1371/journal.pcbi.1005510}
}

@article{bryan2018,
	title = {Excuse Me, Do You Have a Moment to Talk About Version Control?},
	author = {Bryan, Jennifer},
	year = {2018},
	month = {01},
	date = {2018-01-02},
	journal = {Am. Stat.},
	pages = {20--27},
	volume = {72},
	number = {1},
	doi = {10.1080/00031305.2017.1399928},
	url = {https://doi.org/10.1080/00031305.2017.1399928},
	note = {Publisher: Taylor & Francis}
}

@misc{rand_statistically_2022,
	title = {Statistically useful experimental design},
	url = {https://cloud-span.github.io/experimental_design00-overview/},
	abstract = {The Statistically useful experimental design module is a 2 - 3 hour workshop about designing ‘omics experiments. We consider: what influences platform choice and what influences design when platform choice is fixed replication and controls sequence coverage and depth Type I and Type II errors and multiple testing correction The site infrastructure is based on The Carpentries This course not not require any software or coding. Some principles of design will be presented followed by discussion of their application using three case studies. There will also be an opportunity for participants to discuss their own designs. This module assumes no experience with designing omics’ experiments but some previous experience experimental design and statistical analysis - such as would be covered in an undergraduate bioscience degreee - would be useful. The module is designed for a 2 - 3 hour workshop.},
	author = {Rand, Emma and Forrester, Sarah},
	year = {2022},
}

@Article{DESeq2,
  title = {Moderated estimation of fold change and dispersion for RNA-seq data with DESeq2},
  author = {Michael I. Love and Wolfgang Huber and Simon Anders},
  year = {2014},
  journal = {Genome Biology},
  doi = {10.1186/s13059-014-0550-8},
  volume = {15},
  issue = {12},
  pages = {550},
}

@Article{scran,
  author = {Aaron T. L. Lun and Davis J. McCarthy and John C. Marioni},
  title = {A step-by-step workflow for low-level analysis of single-cell RNA-seq data with Bioconductor},
  journal = {F1000Res.},
  year = {2016},
  volume = {5},
  pages = {2122},
  doi = {10.12688/f1000research.9501.2}
}

@article{fs,
	title = {fs: Cross-Platform File System Operations Based on 'libuv'},
	author = {Hester, Jim and Wickham, Hadley and {Csárdi}, {Gábor}},
	year = {2023},
	date = {2023}
}

@Manual{conflicted,
  title = {conflicted: An Alternative Conflict Resolution Strategy},
  author = {Hadley Wickham},
  year = {2023},
  note = {R package version 1.2.0, https://github.com/r-lib/conflicted},
  url = {https://conflicted.r-lib.org/},
}

@article{düren2022,
	title = {Depth normalization of small RNA sequencing: using data and biology to select a suitable method},
	author = {{Düren}, Yannick and Lederer, Johannes and Qin, Li-Xuan},
	year = {2022},
	month = {06},
	date = {2022-06-10},
	journal = {Nucleic Acids Research},
	pages = {e56},
	volume = {50},
	number = {10},
	doi = {10.1093/nar/gkac064},
	url = {https://doi.org/10.1093/nar/gkac064}
}

@article{bullard2010,
	title = {Evaluation of statistical methods for normalization and differential expression in mRNA-Seq experiments},
	author = {Bullard, James H. and Purdom, Elizabeth and Hansen, Kasper D. and Dudoit, Sandrine},
	year = {2010},
	month = {02},
	date = {2010-02-18},
	journal = {BMC Bioinformatics},
	pages = {94},
	volume = {11},
	number = {1},
	doi = {10.1186/1471-2105-11-94},
	url = {https://doi.org/10.1186/1471-2105-11-94}
}

@article{lytal2020,
	title = {Normalization Methods on Single-Cell RNA-seq Data: An Empirical Survey},
	author = {Lytal, Nicholas and Ran, Di and An, Lingling},
	year = {2020},
	date = {2020},
	journal = {Frontiers in Genetics},
	volume = {11},
	url = {https://www.frontiersin.org/articles/10.3389/fgene.2020.00041}
}

@article{abrams2019,
	title = {A protocol to evaluate RNA sequencing normalization methods},
	author = {Abrams, Zachary B. and Johnson, Travis S. and Huang, Kun and Payne, Philip R. O. and Coombes, Kevin},
	year = {2019},
	month = {12},
	date = {2019-12-20},
	journal = {BMC Bioinformatics},
	pages = {679},
	volume = {20},
	number = {24},
	doi = {10.1186/s12859-019-3247-x},
	url = {https://doi.org/10.1186/s12859-019-3247-x}
}

@article{vallejos2017,
	title = {Normalizing single-cell RNA sequencing data: challenges and opportunities},
	author = {Vallejos, Catalina A. and Risso, Davide and Scialdone, Antonio and Dudoit, Sandrine and Marioni, John C.},
	year = {2017},
	month = {06},
	date = {2017-06},
	journal = {Nature Methods},
	pages = {565--571},
	volume = {14},
	number = {6},
	doi = {10.1038/nmeth.4292},
	url = {https://www.nature.com/articles/nmeth.4292/},
	note = {Number: 6
Publisher: Nature Publishing Group},
	langid = {en}
}

@article{evans2017,
	title = {Selecting between-sample RNA-Seq normalization methods from the perspective of their assumptions},
	author = {Evans, Ciaran and Hardin, Johanna and Stoebel, Daniel M},
	year = {2017},
	month = {02},
	date = {2017-02-27},
	journal = {Briefings in Bioinformatics},
	pages = {776--792},
	volume = {19},
	number = {5},
	doi = {10.1093/bib/bbx008},
	url = {https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6171491/},
	note = {PMID: 28334202
PMCID: PMC6171491}
}

@article{robinson2010,
	title = {edgeR: a Bioconductor package for differential expression analysis of digital gene expression data},
	author = {Robinson, Mark D. and McCarthy, Davis J. and Smyth, Gordon K.},
	year = {2010},
	month = {01},
	date = {2010-01-01},
	journal = {Bioinformatics},
	pages = {139--140},
	volume = {26},
	number = {1},
	doi = {10.1093/bioinformatics/btp616},
	url = {https://www.ncbi.nlm.nih.gov/pmc/articles/PMC2796818/},
	note = {PMID: 19910308
PMCID: PMC2796818}
}

@Article{edgeR,
    author = {Yunshun Chen and Lizhong Chen and Aaron T L Lun and Pedro Baldoni and Gordon K Smyth},
    title = {edgeR 4.0: powerful differential analysis of sequencing data with expanded functionality and improved support for small counts and larger datasets},
    year = {2024},
    journal = {bioRxiv},
    doi = {10.1101/2024.01.21.576131},
  }

@article{mccarthy2012,
	title = {Differential expression analysis of multifactor RNA-Seq experiments with respect to biological variation},
	author = {McCarthy, Davis J. and Chen, Yunshun and Smyth, Gordon K.},
	year = {2012},
	month = {05},
	date = {2012-05-01},
	journal = {Nucleic Acids Research},
	pages = {4288--4297},
	volume = {40},
	number = {10},
	doi = {10.1093/nar/gks042},
	url = {https://doi.org/10.1093/nar/gks042}
}

@techreport{chen2016,
	title = {From reads to genes to pathways: differential expression analysis of RNA-Seq experiments using Rsubread and the edgeR quasi-likelihood pipeline},
	author = {Chen, Yunshun and Lun, Aaron T. L. and Smyth, Gordon K.},
	year = {2016},
	month = {08},
	date = {2016-08-02},
	doi = {10.12688/f1000research.8987.2},
	url = {https://f1000research.com/articles/5-1438},
	note = {DOI: 10.12688/f1000research.8987.2
Type: article},
	langid = {en}
}

@article{ritchie2015,
	title = {limma powers differential expression analyses for RNA-sequencing and microarray studies},
	author = {Ritchie, Matthew E. and Phipson, Belinda and Wu, Di and Hu, Yifang and Law, Charity W. and Shi, Wei and Smyth, Gordon K.},
	year = {2015},
	month = {04},
	date = {2015-04-20},
	journal = {Nucleic Acids Research},
	pages = {e47},
	volume = {43},
	number = {7},
	doi = {10.1093/nar/gkv007},
	url = {https://doi.org/10.1093/nar/gkv007}
}

@article{benjamini1995,
	title = {Controlling the False Discovery Rate: A Practical and Powerful Approach to Multiple Testing},
	author = {Benjamini, Yoav and Hochberg, Yosef},
	year = {1995},
	date = {1995},
	journal = {J. R. Stat. Soc. Series B Stat. Methodol.},
	pages = {289--300},
	volume = {57},
	number = {1},
	url = {http://www.jstor.org/stable/2346101},
	note = {Publisher: [Royal Statistical Society, Wiley]}
}

@article{fisher2023,
	title = {Xenbase: key features and resources of the Xenopus model organism knowledgebase},
	author = {Fisher, Malcolm and James-Zorn, Christina and Ponferrada, Virgilio and Bell, Andrew J and Sundararaj, Nivitha and Segerdell, Erik and Chaturvedi, Praneet and Bayyari, Nadia and Chu, Stanley and Pells, Troy and Lotay, Vaneet and Agalakov, Sergei and Wang, Dong Zhuo and Arshinoff, Bradley I and Foley, Saoirse and Karimi, Kamran and Vize, Peter D and Zorn, Aaron M},
	year = {2023},
	month = {05},
	date = {2023-05-02},
	journal = {Genetics},
	pages = {iyad018},
	volume = {224},
	number = {1},
	doi = {10.1093/genetics/iyad018},
	url = {https://doi.org/10.1093/genetics/iyad018}
}

@article{birney2004,
	title = {An Overview of Ensembl},
	author = {Birney, Ewan and Andrews, T. Daniel and Bevan, Paul and Caccamo, Mario and Chen, Yuan and Clarke, Laura and Coates, Guy and Cuff, James and Curwen, Val and Cutts, Tim and Down, Thomas and Eyras, Eduardo and Fernandez-Suarez, Xose M. and Gane, Paul and Gibbins, Brian and Gilbert, James and Hammond, Martin and Hotz, Hans-Rudolf and Iyer, Vivek and Jekosch, Kerstin and Kahari, Andreas and Kasprzyk, Arek and Keefe, Damian and Keenan, Stephen and Lehvaslaiho, Heikki and McVicker, Graham and Melsopp, Craig and Meidl, Patrick and Mongin, Emmanuel and Pettett, Roger and Potter, Simon and Proctor, Glenn and Rae, Mark and Searle, Steve and Slater, Guy and Smedley, Damian and Smith, James and Spooner, Will and Stabenau, Arne and Stalker, James and Storey, Roy and Ureta-Vidal, Abel and Woodwark, K. Cara and Cameron, Graham and Durbin, Richard and Cox, Anthony and Hubbard, Tim and Clamp, Michele},
	year = {2004},
	month = {05},
	date = {2004-05},
	journal = {Genome Research},
	pages = {925--928},
	volume = {14},
	number = {5},
	doi = {10.1101/gr.1860604},
	url = {https://www.ncbi.nlm.nih.gov/pmc/articles/PMC479121/},
	note = {PMID: 15078858
PMCID: PMC479121}
}


@article{smedley2009,
	title = {BioMart {\textendash} biological queries made easy},
	author = {Smedley, Damian and Haider, Syed and Ballester, Benoit and Holland, Richard and London, Darin and Thorisson, Gudmundur and Kasprzyk, Arek},
	year = {2009},
	month = {01},
	date = {2009-01-14},
	journal = {BMC Genomics},
	pages = {22},
	volume = {10},
	number = {1},
	doi = {10.1186/1471-2164-10-22},
	url = {https://doi.org/10.1186/1471-2164-10-22}
}

@Article{biomaRt1,
  title = {Mapping identifiers for the integration of genomic datasets with the R/Bioconductor package biomaRt},
  author = {Steffen Durinck and Paul T. Spellman and Ewan Birney and Wolfgang Huber},
  journal = {Nature Protocols},
  year = {2009},
  volume = {4},
  pages = {1184--1191},
}

@Article{biomaRt2,
  title = {BioMart and Bioconductor: a powerful link between biological databases and microarray data analysis},
  author = {Steffen Durinck and Yves Moreau and Arek Kasprzyk and Sean Davis and Bart {De Moor} and Alvis Brazma and Wolfgang Huber},
  journal = {Bioinformatics},
  year = {2005},
  volume = {21},
  pages = {3439--3440},
}

@book{rand2021,
	title = {Data Science strand of BIO00058M},
	author = {Rand, Emma},
	year = {2021},
	month = {09},
	date = {2021-09},
	doi = {10.5281/zenodo.5527705},
	url = {https://github.com/3mmaRand/BIO00058M-Data-science-2020}
}

@Manual{BiocManager,
  title = {BiocManager: Access the Bioconductor Project Package Repository},
  author = {Martin Morgan and Marcel Ramos},
  year = {2024},
  note = {R package version 1.30.25},
  url = {https://bioconductor.github.io/BiocManager/},
}
  
@Manual{ggrepel,
  title = {ggrepel: Automatically Position Non-Overlapping Text Labels with
'ggplot2'},
  author = {Kamil Slowikowski},
  year = {2024},
  note = {R package version 0.9.5, https://github.com/slowkow/ggrepel},
  url = {https://ggrepel.slowkow.com/},
}

@Article{heatmaply,
  author = {{Galili} and {Tal} and {O'Callaghan} and {Alan} and {Sidi} and {Jonathan} and {Sievert} and {Carson}},
  title = {heatmaply: an R package for creating interactive cluster heatmaps for online publishing},
  journal = {Bioinformatics},
  year = {2017},
  doi = {10.1093/bioinformatics/btx657},
  url = {https://academic.oup.com/bioinformatics/article-pdf/doi/10.1093/bioinformatics/btx657/21358327/btx657.pdf},
}


@article{martin2023,
	title = {Ensembl 2023},
	author = {Martin, Fergal J and Amode, M Ridwan and Aneja, Alisha and Austine-Orimoloye, Olanrewaju and Azov, {Andrey G} and Barnes, If and Becker, Arne and Bennett, Ruth and Berry, Andrew and Bhai, Jyothish and Bhurji, {Simarpreet Kaur} and Bignell, Alexandra and Boddu, Sanjay and {Branco Lins}, Paulo R and Brooks, Lucy and Ramaraju, Shashank Budhanuru and Charkhchi, Mehrnaz and Cockburn, Alexander and {Da Rin Fiorretto}, Luca and Davidson, Claire and Dodiya, Kamalkumar and Donaldson, Sarah and {El Houdaigui}, Bilal and {El Naboulsi}, Tamara and Fatima, Reham and Giron, Carlos Garcia and Genez, Thiago and Ghattaoraya, Gurpreet S and Martinez, Jose Gonzalez and Guijarro, Cristi and Hardy, Matthew and Hollis, Zoe and Hourlier, Thibaut and Hunt, Toby and Kay, Mike and Kaykala, Vinay and Le, Tuan and Lemos, Diana and Marques-Coelho, Diego and {Marugán}, {José Carlos} and Merino, {Gabriela Alejandra} and Mirabueno, {Louisse Paola} and Mushtaq, Aleena and Hossain, {Syed Nakib} and Ogeh, Denye N and Sakthivel, Manoj Pandian and Parker, Anne and Perry, Malcolm and {Pili{\v{z}}ota}, Ivana and Prosovetskaia, Irina and {Pérez-Silva}, {José G} and Salam, {Ahamed Imran Abdul} and Saraiva-Agostinho, Nuno and Schuilenburg, Helen and Sheppard, Dan and Sinha, Swati and Sipos, Botond and Stark, William and Steed, Emily and Sukumaran, Ranjit and Sumathipala, Dulika and Suner, Marie-Marthe and Surapaneni, Likhitha and Sutinen, {Kyösti} and Szpak, Michal and Tricomi, {Francesca Floriana} and {Urbina-Gómez}, David and Veidenberg, Andres and Walsh, {Thomas A} and Walts, Brandon and Wass, Elizabeth and Willhoft, Natalie and Allen, Jamie and Alvarez-Jarreta, Jorge and Chakiachvili, Marc and Flint, Bethany and Giorgetti, Stefano and Haggerty, Leanne and Ilsley, {Garth R} and Loveland, {Jane E} and Moore, Benjamin and Mudge, {Jonathan M} and Tate, John and Thybert, David and Trevanion, {Stephen J} and Winterbottom, Andrea and Frankish, Adam and Hunt, Sarah E and Ruffier, Magali and Cunningham, Fiona and Dyer, Sarah and Finn, {Robert D} and Howe, {Kevin L} and Harrison, Peter W and Yates, Andrew D and Flicek, Paul},
	year = {2023},
	month = {01},
	date = {2023-01-06},
	journal = {Nucleic Acids Research},
	pages = {D933--D941},
	volume = {51},
	number = {D1},
	doi = {10.1093/nar/gkac958},
	url = {https://doi.org/10.1093/nar/gkac958}
}


@article{marwick2018,
	title = {Packaging Data Analytical Work Reproducibly Using R (and Friends)},
	author = {Marwick, Ben and Boettiger, Carl and Mullen, Lincoln},
	year = {2018},
	month = {01},
	date = {2018-01-02},
	journal = {The American Statistician},
	pages = {80--88},
	volume = {72},
	number = {1},
	doi = {10.1080/00031305.2017.1375986},
	url = {https://doi.org/10.1080/00031305.2017.1375986},
	note = {Publisher: Taylor & Francis
{\_}eprint: https://doi.org/10.1080/00031305.2017.1375986}
}

@article{rule2019,
	title = {Ten simple rules for writing and sharing computational analyses in Jupyter Notebooks},
	author = {Rule, Adam and Birmingham, Amanda and Zuniga, Cristal and Altintas, Ilkay and Huang, Shih-Cheng and Knight, Rob and Moshiri, Niema and Nguyen, Mai H. and Rosenthal, Sara Brin and {Pérez}, Fernando and Rose, Peter W.},
	editor = {Lewitter, Fran},
	year = {2019},
	month = {07},
	date = {2019-07-25},
	journal = {PLOS Computational Biology},
	pages = {e1007007},
	volume = {15},
	number = {7},
	doi = {10.1371/journal.pcbi.1007007},
	url = {http://dx.doi.org/10.1371/journal.pcbi.1007007},
	langid = {en}
}

@Article{GenomicRanges,
  title = {Software for Computing and Annotating Genomic Ranges},
  author = {Michael Lawrence and Wolfgang Huber and Herv\'e Pag\`es and Patrick Aboyoun and Marc Carlson and Robert Gentleman and Martin Morgan and Vincent Carey},
  year = {2013},
  journal = {{PLoS} Computational Biology},
  volume = {9},
  issue = {8},
  doi = {10.1371/journal.pcbi.1003118},
  url = {http://www.ploscompbiol.org/article/info%3Adoi%2F10.1371%2Fjournal.pcbi.1003118},
}

@article{bernal_transcriptome_2012,
	title = {Transcriptome sequencing identifies {SPL7}-regulated copper acquisition genes {FRO4}/{FRO5} and the copper dependence of iron homeostasis in {Arabidopsis}},
	volume = {24},
	issn = {1532-298X},
	doi = {10.1105/tpc.111.090431},
	abstract = {The transition metal copper (Cu) is essential for all living organisms but is toxic when present in excess. To identify Cu deficiency responses comprehensively, we conducted genome-wide sequencing-based transcript profiling of Arabidopsis thaliana wild-type plants and of a mutant defective in the gene encoding SQUAMOSA PROMOTER BINDING PROTEIN-LIKE7 (SPL7), which acts as a transcriptional regulator of Cu deficiency responses. In response to Cu deficiency, FERRIC REDUCTASE OXIDASE5 (FRO5) and FRO4 transcript levels increased strongly, in an SPL7-dependent manner. Biochemical assays and confocal imaging of a Cu-specific fluorophore showed that high-affinity root Cu uptake requires prior FRO5/FRO4-dependent Cu(II)-specific reduction to Cu(I) and SPL7 function. Plant iron (Fe) deficiency markers were activated in Cu-deficient media, in which reduced growth of the spl7 mutant was partially rescued by Fe supplementation. Cultivation in Cu-deficient media caused a defect in root-to-shoot Fe translocation, which was exacerbated in spl7 and associated with a lack of ferroxidase activity. This is consistent with a possible role for a multicopper oxidase in Arabidopsis Fe homeostasis, as previously described in yeast, humans, and green algae. These insights into root Cu uptake and the interaction between Cu and Fe homeostasis will advance plant nutrition, crop breeding, and biogeochemical research.},
	language = {eng},
	number = {2},
	journal = {The Plant Cell},
	author = {Bernal, María and Casero, David and Singh, Vasantika and Wilson, Grandon T. and Grande, Arne and Yang, Huijun and Dodani, Sheel C. and Pellegrini, Matteo and Huijser, Peter and Connolly, Erin L. and Merchant, Sabeeha S. and Krämer, Ute},
	month = feb,
	year = {2012},
	pmid = {22374396},
	pmcid = {PMC3315244},
	keywords = {Arabidopsis, Arabidopsis Proteins, Copper, DNA-Binding Proteins, FMN Reductase, Gene Expression Regulation, Plant, Gene Knockdown Techniques, High-Throughput Nucleotide Sequencing, Homeostasis, Iron, Plant Roots, Plants, Genetically Modified, RNA, Plant, Transcription Factors, Transcriptome},
	pages = {738--761},
}


@article{yates_ensembl_2022,
	title = {Ensembl {Genomes} 2022: an expanding genome resource for non-vertebrates},
	volume = {50},
	issn = {0305-1048},
	shorttitle = {Ensembl {Genomes} 2022},
	url = {https://doi.org/10.1093/nar/gkab1007},
	doi = {10.1093/nar/gkab1007},
	abstract = {Ensembl Genomes (https://www.ensemblgenomes.org) provides access to non-vertebrate genomes and analysis complementing vertebrate resources developed by the Ensembl project (https://www.ensembl.org). The two resources collectively present genome annotation through a consistent set of interfaces spanning the tree of life presenting genome sequence, annotation, variation, transcriptomic data and comparative analysis. Here, we present our largest increase in plant, metazoan and fungal genomes since the project's inception creating one of the world's most comprehensive genomic resources and describe our efforts to reduce genome redundancy in our Bacteria portal. We detail our new efforts in gene annotation, our emerging support for pangenome analysis, our efforts to accelerate data dissemination through the Ensembl Rapid Release resource and our new AlphaFold visualization. Finally, we present details of our future plans including updates on our integration with Ensembl, and how we plan to improve our support for the microbial research community. Software and data are made available without restriction via our website, online tools platform and programmatic interfaces (available under an Apache 2.0 license). Data updates are synchronised with Ensembl's release cycle.},
	number = {D1},
	urldate = {2024-10-03},
	journal = {Nucleic Acids Research},
	author = {Yates, Andrew D and Allen, James and Amode, Ridwan M and Azov, Andrey G and Barba, Matthieu and Becerra, Andrés and Bhai, Jyothish and Campbell, Lahcen I and Carbajo Martinez, Manuel and Chakiachvili, Marc and Chougule, Kapeel and Christensen, Mikkel and Contreras-Moreira, Bruno and Cuzick, Alayne and Da Rin Fioretto, Luca and Davis, Paul and De Silva, Nishadi H and Diamantakis, Stavros and Dyer, Sarah and Elser, Justin and Filippi, Carla V and Gall, Astrid and Grigoriadis, Dionysios and Guijarro-Clarke, Cristina and Gupta, Parul and Hammond-Kosack, Kim E and Howe, Kevin L and Jaiswal, Pankaj and Kaikala, Vinay and Kumar, Vivek and Kumari, Sunita and Langridge, Nick and Le, Tuan and Luypaert, Manuel and Maslen, Gareth L and Maurel, Thomas and Moore, Benjamin and Muffato, Matthieu and Mushtaq, Aleena and Naamati, Guy and Naithani, Sushma and Olson, Andrew and Parker, Anne and Paulini, Michael and Pedro, Helder and Perry, Emily and Preece, Justin and Quinton-Tulloch, Mark and Rodgers, Faye and Rosello, Marc and Ruffier, Magali and Seager, James and Sitnik, Vasily and Szpak, Michal and Tate, John and Tello-Ruiz, Marcela K and Trevanion, Stephen J and Urban, Martin and Ware, Doreen and Wei, Sharon and Williams, Gary and Winterbottom, Andrea and Zarowiecki, Magdalena and Finn, Robert D and Flicek, Paul},
	month = jan,
	year = {2022},
	pages = {D996--D1003},
}


@article{rogers_chromosome_2011,
	title = {Chromosome and gene copy number variation allow major structural change between species and strains of {Leishmania}},
	volume = {21},
	issn = {1549-5469},
	doi = {10.1101/gr.122945.111},
	abstract = {Leishmania parasites cause a spectrum of clinical pathology in humans ranging from disfiguring cutaneous lesions to fatal visceral leishmaniasis. We have generated a reference genome for Leishmania mexicana and refined the reference genomes for Leishmania major, Leishmania infantum, and Leishmania braziliensis. This has allowed the identification of a remarkably low number of genes or paralog groups (2, 14, 19, and 67, respectively) unique to one species. These were found to be conserved in additional isolates of the same species. We have predicted allelic variation and find that in these isolates, L. major and L. infantum have a surprisingly low number of predicted heterozygous SNPs compared with L. braziliensis and L. mexicana. We used short read coverage to infer ploidy and gene copy numbers, identifying large copy number variations between species, with 200 tandem gene arrays in L. major and 132 in L. mexicana. Chromosome copy number also varied significantly between species, with nine supernumerary chromosomes in L. infantum, four in L. mexicana, two in L. braziliensis, and one in L. major. A significant bias against gene arrays on supernumerary chromosomes was shown to exist, indicating that duplication events occur more frequently on disomic chromosomes. Taken together, our data demonstrate that there is little variation in unique gene content across Leishmania species, but large-scale genetic heterogeneity can result through gene amplification on disomic chromosomes and variation in chromosome number. Increased gene copy number due to chromosome amplification may contribute to alterations in gene expression in response to environmental conditions in the host, providing a genetic basis for disease tropism.},
	language = {eng},
	number = {12},
	journal = {Genome Research},
	author = {Rogers, Matthew B. and Hilley, James D. and Dickens, Nicholas J. and Wilkes, Jon and Bates, Paul A. and Depledge, Daniel P. and Harris, David and Her, Yerim and Herzyk, Pawel and Imamura, Hideo and Otto, Thomas D. and Sanders, Mandy and Seeger, Kathy and Dujardin, Jean-Claude and Berriman, Matthew and Smith, Deborah F. and Hertz-Fowler, Christiane and Mottram, Jeremy C.},
	month = dec,
	year = {2011},
	pmid = {22038252},
	pmcid = {PMC3227102},
	keywords = {Base Sequence, Chromosomes, Gene Dosage, Gene Expression Regulation, Genes, Protozoan, Leishmania, Molecular Sequence Data, Polymorphism, Single Nucleotide, Species Specificity},
	pages = {2129--2142},
	file = {Full Text:C\:\\Users\\er13\\Zotero\\storage\\8M8LFUR6\\Rogers et al. - 2011 - Chromosome and gene copy number variation allow ma.pdf:application/pdf},
}