book.bib

@website{AlexsLemonade2022,
  url = {https://github.com/AlexsLemonade/training-modules},
  title = {Alex's Lemonade Training Modules},
  authors = {Josh Shapiro, Candace Savonen, Jaclyn Taroni, Chante Bethell},
  year = {2022},
}

@article{Alföldi_Lindblad-Toh_2013,
  title={Comparative genomics as a tool to understand evolution and disease},
  volume={23},
  ISSN={1088-9051, 1549-5469},
  url={https://genome.cshlp.org/content/23/7/1063},
  DOI={10.1101/gr.157503.113},
  abstractNote={When the human genome project started, the major challenge was how to sequence a 3 billion letter code in an organized and cost-effective manner. When completed, the project had laid the foundation for a huge variety of biomedical fields through the production of a complete human genome sequence, but also had driven the development of laboratory and analytical methods that could produce large amounts of sequencing data cheaply. These technological developments made possible the  sequencing of many more vertebrate genomes, which have been necessary for the interpretation of the human genome. They have also enabled large-scale studies of vertebrate genome evolution, as well as comparative and human medicine. In this review, we give examples of evolutionary analysis using a wide variety of time frames—from the comparison of populations within a species to the comparison of species separated by at least 300 million years. Furthermore, we anticipate discoveries related to evolutionary mechanisms, adaptation, and disease to quickly accelerate in the coming years.},
  note={Company: Cold Spring Harbor Laboratory Press
      Distributor: Cold Spring Harbor Laboratory Press
      Institution: Cold Spring Harbor Laboratory Press
      Label: Cold Spring Harbor Laboratory Press
      publisher: Cold Spring Harbor Lab
      PMID: 23817047},
  number={7},
  journal={Genome Research},
  author={Alföldi, Jessica and Lindblad-Toh, Kerstin},
  year={2013},
  month=jul,
  pages={1063–1068},
  language={en}
}


@article{Aljanahi2018,
	title = {An {Introduction} to the {Analysis} of {Single}-{Cell} {RNA}-{Sequencing} {Data}},
	volume = {10},
	issn = {23290501},
	url = {https://linkinghub.elsevier.com/retrieve/pii/S2329050118300664},
	doi = {10.1016/j.omtm.2018.07.003},
	language = {en},
	urldate = {2022-10-05},
	journal = {Molecular Therapy - Methods \& Clinical Development},
	author = {AlJanahi, Aisha A. and Danielsen, Mark and Dunbar, Cynthia E.},
	month = sep,
	year = {2018},
	pages = {189--196},
}

@article{Alonge2022,
  title={Automated assembly scaffolding using RagTag elevates a new tomato system for high-throughput genome editing},
  volume={23},
  ISSN={1474-760X},
  url={https://doi.org/10.1186/s13059-022-02823-7},
  DOI={10.1186/s13059-022-02823-7},
  abstractNote={Advancing crop genomics requires efficient genetic systems enabled by high-quality personalized genome assemblies. Here, we introduce RagTag, a toolset for automating assembly scaffolding and patching, and we establish chromosome-scale reference genomes for the widely used tomato genotype M82 along with Sweet-100, a new rapid-cycling genotype that we developed to accelerate functional genomics and genome editing in tomato. This work outlines strategies to rapidly expand genetic systems and genomic resources in other plant species.},
  number={1},
  journal={Genome Biology},
  author={Alonge, Michael and Lebeigle, Ludivine and Kirsche, Melanie and Jenike, Katie and Ou, Shujun and Aganezov, Sergey and Wang, Xingang and Lippman, Zachary B. and Schatz, Michael C. and Soyk, Sebastian},
  year={2022},
  month=dec,
  pages={258}
}


@article{Amezquita2020,
	title = {Orchestrating single-cell analysis with {Bioconductor}},
	volume = {17},
	copyright = {2019 Springer Nature America, Inc.},
	issn = {1548-7105},
	url = {https://www.nature.com/articles/s41592-019-0654-x},
	doi = {10.1038/s41592-019-0654-x},
	abstract = {Recent technological advancements have enabled the profiling of a large number of genome-wide features in individual cells. However, single-cell data present unique challenges that require the development of specialized methods and software infrastructure to successfully derive biological insights. The Bioconductor project has rapidly grown to meet these demands, hosting community-developed open-source software distributed as R packages. Featuring state-of-the-art computational methods, standardized data infrastructure and interactive data visualization tools, we present an overview and online book (https://osca.bioconductor.org) of single-cell methods for prospective users.},
	language = {en},
	number = {2},
	urldate = {2022-10-05},
	journal = {Nature Methods},
	author = {Amezquita, Robert A. and Lun, Aaron T. L. and Becht, Etienne and Carey, Vince J. and Carpp, Lindsay N. and Geistlinger, Ludwig and Marini, Federico and Rue-Albrecht, Kevin and Risso, Davide and Soneson, Charlotte and Waldron, Levi and Pagès, Hervé and Smith, Mike L. and Huber, Wolfgang and Morgan, Martin and Gottardo, Raphael and Hicks, Stephanie C.},
	month = feb,
	year = {2020},
	keywords = {Genomic analysis, Software},
	pages = {137--145},
}

@article{Angerer2017,
	title = {Single cells make big data: {New} challenges and opportunities in transcriptomics},
	volume = {4},
	issn = {24523100},
	shorttitle = {Single cells make big data},
	url = {https://linkinghub.elsevier.com/retrieve/pii/S245231001730077X},
	doi = {10.1016/j.coisb.2017.07.004},
	language = {en},
	urldate = {2022-10-05},
	journal = {Current Opinion in Systems Biology},
	author = {Angerer, Philipp and Simon, Lukas and Tritschler, Sophie and Wolf, F. Alexander and Fischer, David and Theis, Fabian J.},
	month = aug,
	year = {2017},
	pages = {85--91},
}

@article{Audano2019,
  title={Characterizing the Major Structural Variant Alleles of the Human Genome},
  volume={176},
  ISSN={00928674},
  url={https://linkinghub.elsevier.com/retrieve/pii/S0092867418316337},
  DOI={10.1016/j.cell.2018.12.019},
  abstractNote={In order to provide a comprehensive resource for human structural variants (SVs), we generated longread sequence data and analyzed SVs for fifteen human genomes. We sequence resolved 99,604 insertions, deletions, and inversions including 2,238 (1.6 Mbp) that are shared among all discovery genomes with an additional 13,053 (6.9 Mbp) present in the majority, indicating minor alleles or errors in the reference. Genotyping in 440 additional genomes confirms the most common SVs in unique euchromatin are now sequence resolved. We report a ninefold SV bias toward the last 5 Mbp of human chromosomes with nearly 55% of all VNTRs (variable number of tandem repeats) mapping to this portion of the genome. We identify SVs affecting coding and noncoding regulatory loci improving annotation and interpretation of functional variation. These data provide the framework to construct a canonical human reference and a resource for developing advanced representations capable of capturing allelic diversity.},
  number={3},
  journal={Cell},
  author={Audano, Peter A. and Sulovari, Arvis and Graves-Lindsay, Tina A. and Cantsilieris, Stuart and Sorensen, Melanie and Welch, AnneMarie E. and Dougherty, Max L. and Nelson, Bradley J. and Shah, Ankeeta and Dutcher, Susan K. and Warren, Wesley C. and Magrini, Vincent and McGrath, Sean D. and Li, Yang I. and Wilson, Richard K. and Eichler, Evan E.},
  year={2019},
  month=jan,
  pages={663-675.e19},
  language={en}
}


@article{BaranGale2018,
	title = {Experimental design for single-cell {RNA} sequencing},
	volume = {17},
	issn = {2041-2649, 2041-2657},
	url = {https://academic.oup.com/bfg/article/17/4/233/4604806},
	doi = {10.1093/bfgp/elx035},
	language = {en},
	number = {4},
	urldate = {2022-10-05},
	journal = {Briefings in Functional Genomics},
	author = {Baran-Gale, Jeanette and Chandra, Tamir and Kirschner, Kristina},
	month = jul,
	year = {2018},
	pages = {233--239},
}

@article{Booth2013,
  doi = {10.1038/nprot.2013.115},
  url = {https://doi.org/10.1038/nprot.2013.115},
  year = {2013},
  month = sep,
  publisher = {Springer Science and Business Media {LLC}},
  volume = {8},
  number = {10},
  pages = {1841--1851},
  author = {Michael J Booth and Tobias W B Ost and Dario Beraldi and Neil M Bell and Miguel R Branco and Wolf Reik and Shankar Balasubramanian},
  title = {Oxidative bisulfite sequencing of 5-methylcytosine and 5-hydroxymethylcytosine},
  journal = {Nature Protocols}
}

@ARTICLE{Bolyen2019,
  title    = "Reproducible, interactive, scalable and extensible microbiome
              data science using {QIIME} 2",
  author   = "Bolyen, Evan and Rideout, Jai Ram and Dillon, Matthew R and
              Bokulich, Nicholas A and Abnet, Christian C and Al-Ghalith,
              Gabriel A and Alexander, Harriet and Alm, Eric J and Arumugam,
              Manimozhiyan and Asnicar, Francesco and Bai, Yang and Bisanz,
              Jordan E and Bittinger, Kyle and Brejnrod, Asker and Brislawn,
              Colin J and Brown, C Titus and Callahan, Benjamin J and
              Caraballo-Rodr{\'\i}guez, Andr{\'e}s Mauricio and Chase, John and
              Cope, Emily K and Da Silva, Ricardo and Diener, Christian and
              Dorrestein, Pieter C and Douglas, Gavin M and Durall, Daniel M
              and Duvallet, Claire and Edwardson, Christian F and Ernst,
              Madeleine and Estaki, Mehrbod and Fouquier, Jennifer and
              Gauglitz, Julia M and Gibbons, Sean M and Gibson, Deanna L and
              Gonzalez, Antonio and Gorlick, Kestrel and Guo, Jiarong and
              Hillmann, Benjamin and Holmes, Susan and Holste, Hannes and
              Huttenhower, Curtis and Huttley, Gavin A and Janssen, Stefan and
              Jarmusch, Alan K and Jiang, Lingjing and Kaehler, Benjamin D and
              Kang, Kyo Bin and Keefe, Christopher R and Keim, Paul and Kelley,
              Scott T and Knights, Dan and Koester, Irina and Kosciolek, Tomasz
              and Kreps, Jorden and Langille, Morgan G I and Lee, Joslynn and
              Ley, Ruth and Liu, Yong-Xin and Loftfield, Erikka and Lozupone,
              Catherine and Maher, Massoud and Marotz, Clarisse and Martin,
              Bryan D and McDonald, Daniel and McIver, Lauren J and Melnik,
              Alexey V and Metcalf, Jessica L and Morgan, Sydney C and Morton,
              Jamie T and Naimey, Ahmad Turan and Navas-Molina, Jose A and
              Nothias, Louis Felix and Orchanian, Stephanie B and Pearson,
              Talima and Peoples, Samuel L and Petras, Daniel and Preuss, Mary
              Lai and Pruesse, Elmar and Rasmussen, Lasse Buur and Rivers, Adam
              and Robeson, Michael S and Rosenthal, Patrick and Segata, Nicola
              and Shaffer, Michael and Shiffer, Arron and Sinha, Rashmi and
              Song, Se Jin and Spear, John R and Swafford, Austin D and
              Thompson, Luke R and Torres, Pedro J and Trinh, Pauline and
              Tripathi, Anupriya and Turnbaugh, Peter J and Ul-Hasan, Sabah and
              van der Hooft, Justin J J and Vargas, Fernando and
              V{\'a}zquez-Baeza, Yoshiki and Vogtmann, Emily and von Hippel,
              Max and Walters, William and Wan, Yunhu and Wang, Mingxun and
              Warren, Jonathan and Weber, Kyle C and Williamson, Charles H D
              and Willis, Amy D and Xu, Zhenjiang Zech and Zaneveld, Jesse R
              and Zhang, Yilong and Zhu, Qiyun and Knight, Rob and Caporaso, J
              Gregory",
  journal  = "Nat. Biotechnol.",
  volume   =  37,
  number   =  8,
  pages    = "852--857",
  month    =  aug,
  year     =  2019,
  keywords = "Microbiome, Software"
}


@misc{Bruning2021,
	title = {Comparative {Analysis} of common alignment tools for single cell {RNA} sequencing},
	copyright = {© 2021, Posted by Cold Spring Harbor Laboratory. The copyright holder for this pre-print is the author. All rights reserved. The material may not be redistributed, re-used or adapted without the author's permission.},
	url = {https://www.biorxiv.org/content/10.1101/2021.02.15.430948v2},
	doi = {10.1101/2021.02.15.430948},
	abstract = {With the rise of single cell RNA sequencing new bioinformatic tools became available to handle specific demands, such as quantifying unique molecular identifiers and correcting cell barcodes. Here, we analysed several datasets with the most common alignment tools for scRNA-seq data. We evaluated differences in the whitelisting, gene quantification, overall performance and potential variations in clustering or detection of differentially expressed genes.
We compared the tools Cell Ranger 5, STARsolo, Kallisto and Alevin on three published datasets for human and mouse, sequenced with different versions of the 10X sequencing protocol.
Striking differences have been observed in the overall runtime of the mappers. Besides that Kallisto and Alevin showed variances in the number of valid cells and detected genes per cell. Kallisto reported the highest number of cells, however, we observed an overrepresentation of cells with low gene content and unknown celtype. Conversely, Alevin rarely reported such low content cells.
Further variations were detected in the set of expressed genes. While STARsolo, Cell Ranger 5 and Alevin released similar gene sets, Kallisto detected additional genes from the Vmn and Olfr gene family, which are likely mapping artifacts. We also observed differences in the mitochondrial content of the resulting cells when comparing a prefiltered annotation set to the full annotation set that includes pseudogenes and other biotypes.
Overall, this study provides a detailed comparison of common scRNA-seq mappers and shows their specific properties on 10X Genomics data.
Key messagesMapping and gene quantifications are the most resource and time intensive steps during the analysis of scRNA-Seq data.The usage of alternative alignment tools reduces the time for analysing scRNA-Seq data.Different mapping strategies influence key properties of scRNA-SEQ e.g. total cell counts or genes per cellA better understanding of advantages and disadvantages for each mapping algorithm might improve analysis results.},
	language = {en},
	urldate = {2022-10-05},
	publisher = {bioRxiv},
	author = {Brüning, Ralf Schulze and Tombor, Lukas and Schulz, Marcel H. and Dimmeler, Stefanie and John, David},
	month = mar,
	year = {2021},
}

@article{Byrska-Bishop2022,
  title={High-coverage whole-genome sequencing of the expanded 1000 Genomes Project cohort including 602 trios},
  volume={185},
  ISSN={0092-8674, 1097-4172},
  url={https://www.cell.com/cell/abstract/S0092-8674(22)00991-6},
  DOI={10.1016/j.cell.2022.08.004},
  number={18},
  journal={Cell},
  publisher={Elsevier},
  author={Byrska-Bishop, Marta and Evani, Uday S. and Zhao, Xuefang and Basile, Anna O. and Abel, Haley J. and Regier, Allison A. and Corvelo, André and Clarke, Wayne E. and Musunuri, Rajeeva and Nagulapalli, Kshithija and Fairley, Susan and Runnels, Alexi and Winterkorn, Lara and Lowy, Ernesto and Eichler, Evan E. and Korbel, Jan O. and Lee, Charles and Marschall, Tobias and Devine, Scott E. and Harvey, William T. and Zhou, Weichen and Mills, Ryan E. and Rausch, Tobias and Kumar, Sushant and Alkan, Can and Hormozdiari, Fereydoun and Chong, Zechen and Chen, Yu and Yang, Xiaofei and Lin, Jiadong and Gerstein, Mark B. and Kai, Ye and Zhu, Qihui and Yilmaz, Feyza and Xiao, Chunlin and Flicek, Paul and Germer, Soren and Brand, Harrison and Hall, Ira M. and Talkowski, Michael E. and Narzisi, Giuseppe and Zody, Michael C.},
  year={2022},
  month=sep,
  pages={3426-3440.e19},
  language={English}
}


@article{Conesa2016,
  doi = {10.1186/s13059-016-0881-8},
  url = {https://doi.org/10.1186/s13059-016-0881-8},
  year = {2016},
  month = jan,
  publisher = {Springer Science and Business Media {LLC}},
  volume = {17},
  number = {1},
  author = {Ana Conesa and Pedro Madrigal and Sonia Tarazona and David Gomez-Cabrero and Alejandra Cervera and Andrew McPherson and Micha{\l} Wojciech Szcze{\'{s}}niak and Daniel J. Gaffney and Laura L. Elo and Xuegong Zhang and Ali Mortazavi},
  title = {A survey of best practices for {RNA}-seq data analysis},
  journal = {Genome Biology}
}

@article{Chen2018,
  doi = {10.1146/annurev-biodatasci-080917-013452},
  url = {https://doi.org/10.1146/annurev-biodatasci-080917-013452},
  year = {2018},
  month = jul,
  publisher = {Annual Reviews},
  volume = {1},
  number = {1},
  pages = {29--51},
  author = {Xi Chen and Sarah A. Teichmann and Kerstin B. Meyer},
  title = {From Tissues to Cell Types and Back: Single-Cell Gene Expression Analysis of Tissue Architecture},
  journal = {Annual Review of Biomedical Data Science}
}

@article{Ding2020,
  doi = {10.1038/s41587-020-0465-8},
  url = {https://doi.org/10.1038/s41587-020-0465-8},
  year = {2020},
  month = apr,
  publisher = {Springer Science and Business Media {LLC}},
  volume = {38},
  number = {6},
  pages = {737--746},
  author = {Jiarui Ding and Xian Adiconis and Sean K. Simmons and Monika S. Kowalczyk and Cynthia C. Hession and Nemanja D. Marjanovic and Travis K. Hughes and Marc H. Wadsworth and Tyler Burks and Lan T. Nguyen and John Y. H. Kwon and Boaz Barak and William Ge and Amanda J. Kedaigle and Shaina Carroll and Shuqiang Li and Nir Hacohen and Orit Rozenblatt-Rosen and Alex K. Shalek and Alexandra-Chlo{\'{e}} Villani and Aviv Regev and Joshua Z. Levin},
  title = {Systematic comparison of single-cell and single-nucleus {RNA}-sequencing methods},
  journal = {Nature Biotechnology}
}

@article{Eichler_2019,
  title={Genetic Variation, Comparative Genomics, and the Diagnosis of Disease},
  volume={381},
  ISSN={0028-4793},
  url={https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6681822/},
  DOI={10.1056/NEJMra1809315},
  number={1},
  journal={The New England journal of medicine},
  author={Eichler, Evan E.},
  year={2019},
  month=jul,
  pages={64–74}
}


@article{Ermini_Driguez_2024,
  title={The Application of Long-Read Sequencing to Cancer},
  volume={16},
  rights={http://creativecommons.org/licenses/by/3.0/},
  ISSN={2072-6694},
  url={https://www.mdpi.com/2072-6694/16/7/1275},
  DOI={10.3390/cancers16071275},
  abstractNote={Cancer is a multifaceted disease arising from numerous genomic aberrations that have been identified as a result of advancements in sequencing technologies. While next-generation sequencing (NGS), which uses short reads, has transformed cancer research and diagnostics, it is limited by read length. Third-generation sequencing (TGS), led by the Pacific Biosciences and Oxford Nanopore Technologies platforms, employs long-read sequences, which have marked a paradigm shift in cancer research. Cancer genomes often harbour complex events, and TGS, with its ability to span large genomic regions, has facilitated their characterisation, providing a better understanding of how complex rearrangements affect cancer initiation and progression. TGS has also characterised the entire transcriptome of various cancers, revealing cancer-associated isoforms that could serve as biomarkers or therapeutic targets. Furthermore, TGS has advanced cancer research by improving genome assemblies, detecting complex variants, and providing a more complete picture of transcriptomes and epigenomes. This review focuses on TGS and its growing role in cancer research. We investigate its advantages and limitations, providing a rigorous scientific analysis of its use in detecting previously hidden aberrations missed by NGS. This promising technology holds immense potential for both research and clinical applications, with far-reaching implications for cancer diagnosis and treatment.},
  number={77},
  journal={Cancers},
  publisher={Multidisciplinary Digital Publishing Institute},
  author={Ermini, Luca and Driguez, Patrick},
  year={2024},
  month=jan,
  pages={1275},
  language={en}
}

@website{GeneticDiversity,
  url={https://kids.frontiersin.org/articles/10.3389/frym.2021.656168}, abstractNote={All living things on Earth contain a unique code within them, called DNA. DNA is organised into genes, similar to the way letters are organised into words. Genes give our bodies instructions on how to function. However, the exact DNA code is different even between individuals within the same species. We call this genetic diversity. Genetic diversity causes differences in the shape of bird beaks, in the flavours of tomatoes, and even in the colour of your hair! Genetic diversity is important because it gives species a better chance of survival. However, genetic diversity can be lost when populations get smaller and isolated, which decreases a species’ ability to adapt and survive. In this article, we explore the importance of genetic diversity, discuss how it is formed and maintained in wild populations, how it is lost and why that is dangerous, and what we can do to conserve it.},
  journal={Frontiers for Young Minds},
  title = {What is Genetic Diversity and Why Does it Matter?},
  language={en}
}

@article{Gershman2022,
  title={Epigenetic patterns in a complete human genome},
  volume={376},
  url={https://www.science.org/doi/10.1126/science.abj5089},
  DOI={10.1126/science.abj5089},
  abstractNote={The completion of a telomere-to-telomere human reference genome, T2T-CHM13, has resolved complex regions of the genome, including repetitive and homologous regions. Here, we present a high-resolution epigenetic study of previously unresolved sequences, representing entire acrocentric chromosome short arms, gene family expansions, and a diverse collection of repeat classes. This resource precisely maps CpG methylation (32.28 million CpGs), DNA accessibility, and short-read datasets (166,058 previously unresolved chromatin immunoprecipitation sequencing peaks) to provide evidence of activity across previously unidentified or corrected genes and reveals clinically relevant paralog-specific regulation. Probing CpG methylation across human centromeres from six diverse individuals generated an estimate of variability in kinetochore localization. This analysis provides a framework with which to investigate the most elusive regions of the human genome, granting insights into epigenetic regulation.},
  number={6588},
  journal={Science},
  publisher={American Association for the Advancement of Science},
  author={Gershman, Ariel and Sauria, Michael E. G. and Guitart, Xavi and Vollger, Mitchell R. and Hook, Paul W. and Hoyt, Savannah J. and Jain, Miten and Shumate, Alaina and Razaghi, Roham and Koren, Sergey and Altemose, Nicolas and Caldas, Gina V. and Logsdon, Glennis A. and Rhie, Arang and Eichler, Evan E. and Schatz, Michael C. and O’Neill, Rachel J. and Phillippy, Adam M. and Miga, Karen H. and Timp, Winston},
  year={2022},
  month=apr,
  pages={eabj5089}
}

@article{Gershman2023,
  title={Genomic insights into metabolic flux in hummingbirds},
  volume={33},
  ISSN={1088-9051, 1549-5469},
  url={https://genome.cshlp.org/content/33/5/703},
  DOI={10.1101/gr.276779.122},
  abstractNote={Hummingbirds are very well adapted to sustain efficient and rapid metabolic shifts. They oxidize ingested nectar to directly fuel flight when foraging but have to switch to oxidizing stored lipids derived from ingested sugars during the night or long-distance migratory flights. Understanding how this organism moderates energy turnover is hampered by a lack of information regarding how relevant enzymes differ in sequence, expression, and regulation. To explore these questions, we generated a chromosome-scale genome assembly of the ruby-throated hummingbird (A. colubris) using a combination of long- and short-read sequencing, scaffolding it using existing assemblies. We then used hybrid long- and short-read RNA sequencing of liver and muscle tissue in fasted and fed metabolic states for a comprehensive transcriptome assembly and annotation. Our genomic and transcriptomic data found positive selection of key metabolic genes in nectivorous avian species and deletion of critical genes (SLC2A4, GCK) involved in glucostasis in other vertebrates. We found expression of a fructose-specific version of SLC2A5 putatively in place of insulin-sensitive SLC2A5, with predicted protein models suggesting affinity for both fructose and glucose. Alternative isoforms may even act to sequester fructose to preclude limitations from transport in metabolism. Finally, we identified differentially expressed genes from fasted and fed hummingbirds, suggesting key pathways for the rapid metabolic switch hummingbirds undergo.},
  note={Company: Cold Spring Harbor Laboratory Press
        Distributor: Cold Spring Harbor Laboratory Press
        Institution: Cold Spring Harbor Laboratory Press
        Label: Cold Spring Harbor Laboratory Press
        publisher: Cold Spring Harbor Lab
        PMID: 37156619},
  number={5},
  journal={Genome Research},
  author={Gershman, Ariel and Hauck, Quinn and Dick, Morag and Jamison, Jerrica M. and Tassia, Michael and Agirrezabala, Xabier and Muhammad, Saad and Ali, Raafay and Workman, Rachael E. and Valle, Mikel and Wong, G. William and Welch, Kenneth C. and Timp, Winston},
  year={2023},
  month=may,
  pages={703–714},
  language={en}
}

@article{Govindarajan2012,
  title={Microarray and its applications},
  volume={4},
  ISSN={0976-4879},
  url={https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3467903/},
  DOI={10.4103/0975-7406.100283},
  abstractNote={Microarray is one of the most recent advances being used for cancer research; it provides assistance in pharmacological approach to treat various diseases including oral lesions. Microarray helps in analyzing large amount of samples which have either been recorded previously or new samples; it even helps to test the incidence of a particular marker in tumors. Till recently, microarray’s usage in dentistry has been very limited, but in future, as the technology becomes affordable, there may be increase in its usage. Here, we discuss the various techniques and applications of microarray or DNA chip.},
  number={Suppl 2},
  journal={Journal of Pharmacy & Bioallied Sciences},
  author={Govindarajan, Rajeshwar and Duraiyan, Jeyapradha and Kaliyappan, Karunakaran and Palanisamy, Murugesan},
  year={2012},
  month=aug,
  pages={S310–S312}
}


@article{Kochmanski2019,
  author={Kochmanski, Joseph and Savonen, Candace and Bernstein, Alison I.},
  article={A Novel Application of Mixed Effects Models for Reconciling Base-Pair Resolution 5-Methylcytosine and 5-Hydroxymethylcytosine Data in Neuroepigenetics},
	journalL={Frontiers in Genetics},
	volume={10},
	year={2019},
	url={https://www.frontiersin.org/articles/10.3389/fgene.2019.00801},
	doi={10.3389/fgene.2019.00801},
  issn={1664-8021},
}

@ARTICLE{Caporaso2010,
  title    = "{QIIME} allows analysis of high-throughput community sequencing
              data",
  author   = "Caporaso, J Gregory and Kuczynski, Justin and Stombaugh, Jesse
              and Bittinger, Kyle and Bushman, Frederic D and Costello,
              Elizabeth K and Fierer, Noah and Pe{\~n}a, Antonio Gonzalez and
              Goodrich, Julia K and Gordon, Jeffrey I and Huttley, Gavin A and
              Kelley, Scott T and Knights, Dan and Koenig, Jeremy E and Ley,
              Ruth E and Lozupone, Catherine A and McDonald, Daniel and Muegge,
              Brian D and Pirrung, Meg and Reeder, Jens and Sevinsky, Joel R
              and Turnbaugh, Peter J and Walters, William A and Widmann, Jeremy
              and Yatsunenko, Tanya and Zaneveld, Jesse and Knight, Rob",
  journal  = "Nat. Methods",
  volume   =  7,
  number   =  5,
  pages    = "335--336",
  month    =  may,
  year     =  2010,
  language = "en"
}


@website{Hadfield2016,
  url={https://bitesizebio.com/13542/what-everyone-should-know-about-rna-seq/},
  author = {James Hadfield},
  year={2016},
  month=jul,
  language={en-US}
}

@article{Hansen2010,
  title={Biases in Illumina transcriptome sequencing caused by random hexamer priming},
  volume={38},
  ISSN={0305-1048},
  url={https://doi.org/10.1093/nar/gkq224},
  DOI={10.1093/nar/gkq224},
  abstractNote={Generation of cDNA using random hexamer priming induces biases in the nucleotide composition at the beginning of transcriptome sequencing reads from the Illumina Genome Analyzer. The bias is independent of organism and laboratory and impacts the uniformity of the reads along the transcriptome. We provide a read count reweighting scheme, based on the nucleotide frequencies of the reads, that mitigates the impact of the bias.},
  number={12},
  journal={Nucleic Acids Research},
  author={Hansen, Kasper D. and Brenner, Steven E. and Dudoit, Sandrine},
  year={2010},
  month=jul,
  pages={e131}
}


@article{Hicks2017,
  doi = {10.1093/biostatistics/kxx053},
  url = {https://doi.org/10.1093/biostatistics/kxx053},
  year = {2017},
  month = nov,
  publisher = {Oxford University Press ({OUP})},
  volume = {19},
  number = {4},
  pages = {562--578},
  author = {Stephanie C Hicks and F William Townes and Mingxiang Teng and Rafael A Irizarry},
  title = {Missing data and technical variability in single-cell {RNA}-sequencing experiments},
  journal = {Biostatistics}
}

@article{Hindorff2009,
  title={Potential etiologic and functional implications of genome-wide association loci for human diseases and traits},
  volume={106},
  url={https://www.pnas.org/doi/full/10.1073/pnas.0903103106},
  DOI={10.1073/pnas.0903103106},
  abstractNote={We have developed an online catalog of SNP-trait associations from published genome-wide association studies for use in investigating genomic characteristics of trait/disease-associated SNPs (TASs). Reported TASs were common [median risk allele frequency 36%, interquartile range (IQR) 21%−53%] and were associated with modest effect sizes [median odds ratio (OR) 1.33, IQR 1.20–1.61]. Among 20 genomic annotation sets, reported TASs were significantly overrepresented only in nonsynonymous sites [OR = 3.9 (2.2−7.0), p = 3.5 × 10−7] and 5kb-promoter regions [OR = 2.3 (1.5−3.6), p = 3 × 10−4] compared to SNPs randomly selected from genotyping arrays. Although 88% of TASs were intronic (45%) or intergenic (43%), TASs were not overrepresented in introns and were significantly depleted in intergenic regions [OR = 0.44 (0.34−0.58), p = 2.0 × 10−9]. Only slightly more TASs than expected by chance were predicted to be in regions under positive selection [OR = 1.3 (0.8−2.1), p = 0.2]. This new online resource, together with bioinformatic predictions of the underlying functionality at trait/disease-associated loci, is well-suited to guide future investigations of the role of common variants in complex disease etiology.},
  number={23},
  journal={Proceedings of the National Academy of Sciences},
  publisher={Proceedings of the National Academy of Sciences},
  author={Hindorff, Lucia A. and Sethupathy, Praveen and Junkins, Heather A. and Ramos, Erin M. and Mehta, Jayashri P. and Collins, Francis S. and Manolio, Teri A.},
  year={2009},
  month=jun,
  pages={9362–9367}
}

@article{Hodges2007,
  doi = {10.1038/ng.2007.42},
  url = {https://doi.org/10.1038/ng.2007.42},
  year = {2007},
  month = nov,
  publisher = {Springer Science and Business Media {LLC}},
  volume = {39},
  number = {12},
  pages = {1522--1527},
  author = {Emily Hodges and Zhenyu Xuan and Vivekanand Balija and Melissa Kramer and Michael N Molla and Steven W Smith and Christina M Middle and Matthew J Rodesch and Thomas J Albert and Gregory J Hannon and W Richard McCombie},
  title = {Genome-wide in situ exon capture for selective resequencing},
  journal = {Nature Genetics}
}

@article{Karczewski2020,
  doi = {10.1038/s41586-020-2308-7},
  url = {https://www.nature.com/articles/s41586-020-2308-7#change-history},
  year = {2020},
  month = {May},
  journal = {Nature},
  language = {en},
  author = {Konrad J. Karczewski and Laurent C. Francioli and Grace Tiao and Beryl B. Cummings and Jessica Alföldi and Qingbo Wang and Ryan L. Collins and Kristen M. Laricchia and Andrea Ganna and Daniel P. Birnbaum and Laura D. Gauthier and Harrison Brand and Matthew Solomonson and Nicholas A. Watts and Daniel Rhodes and Moriel Singer-Berk and Eleina M. England and Eleanor G. Seaby and Jack A. Kosmicki, and Raymond K. Walters and Katherine Tashman and Yossi Farjoun and Eric Banks and Timothy Poterba and Arcturus Wang and Cotton Seed and Nicola Whiffin and Jessica X. Chong and Kaitlin E. Samocha and Emma Pierce-Hoffman and Zachary Zappala and Anne H. O'Donnell-Luria and Eric Vallabh Minikel and ben Weisburd and Monkol Lek and James S. Ware and Christopher Vittal and Irina M. Armean and Louis Bergelson and Kristian Cibulskis and Kristen M Connolly and Miguel Covarrubias and Stacey Donnelly and Steven Ferriera and Stacey Gabriel and Jeff Gentry and Namrata Gupta and Thibault Jeandet and Diane Kaplan and Christopher Llanwarne and Ruchi Munshi and Sam Novod and Nikelle Petrillo and David Roazen and Valentin Ruano-Rubio and Andrea Saltzman and Molly Schleicher and Jose Soto and Kathleen Tibbetts and Charlotte Tolonen and Gordon Wade and Michael E. Talkowski and and Genome Aggregation Database Consortium and Benjamin M. Neale and Mark J. Daly and Daniel G. MacArthur},
  title = {The mutational constraint spectrum quantified from variation in 141,456 humans},
  volume = {581}
}

@article{Kellis2014,
  title={Defining functional DNA elements in the human genome},
  volume={111},
  url={https://www.pnas.org/doi/10.1073/pnas.1318948111},
  DOI={10.1073/pnas.1318948111},
  abstractNote={With the completion of the human genome sequence, attention turned to identifying and annotating its functional DNA elements. As a complement to genetic and comparative genomics approaches, the Encyclopedia of DNA Elements Project was launched to contribute maps of RNA transcripts, transcriptional regulator binding sites, and chromatin states in many cell types. The resulting genome-wide data reveal sites of biochemical activity with high positional resolution and cell type specificity that facilitate studies of gene regulation and interpretation of noncoding variants associated with human disease. However, the biochemically active regions cover a much larger fraction of the genome than do evolutionarily conserved regions, raising the question of whether nonconserved but biochemically active regions are truly functional. Here, we review the strengths and limitations of biochemical, evolutionary, and genetic approaches for defining functional DNA segments, potential sources for the observed differences in estimated genomic coverage, and the biological implications of these discrepancies. We also analyze the relationship between signal intensity, genomic coverage, and evolutionary conservation. Our results reinforce the principle that each approach provides complementary information and that we need to use combinations of all three to elucidate genome function in human biology and disease.},
  number={17},
  journal={Proceedings of the National Academy of Sciences},
  publisher={Proceedings of the National Academy of Sciences},
  author={Kellis, Manolis and Wold, Barbara and Snyder, Michael P. and Bernstein, Bradley E. and Kundaje, Anshul and Marinov, Georgi K. and Ward, Lucas D. and Birney, Ewan and Crawford, Gregory E. and Dekker, Job and Dunham, Ian and Elnitski, Laura L. and Farnham, Peggy J. and Feingold, Elise A. and Gerstein, Mark and Giddings, Morgan C. and Gilbert, David M. and Gingeras, Thomas R. and Green, Eric D. and Guigo, Roderic and Hubbard, Tim and Kent, Jim and Lieb, Jason D. and Myers, Richard M. and Pazin, Michael J. and Ren, Bing and Stamatoyannopoulos, John A. and Weng, Zhiping and White, Kevin P. and Hardison, Ross C.},
  year={2014},
  month=apr,
  pages={6131–6138}
}


@article{Lafzi2018,
	title = {Tutorial: guidelines for the experimental design of single-cell {RNA} sequencing studies},
	volume = {13},
	copyright = {2018 Springer Nature Limited},
	issn = {1750-2799},
	shorttitle = {Tutorial},
	url = {https://www.nature.com/articles/s41596-018-0073-y},
	doi = {10.1038/s41596-018-0073-y},
	abstract = {Single-cell RNA sequencing is at the forefront of high-resolution phenotyping experiments for complex samples. Although this methodology requires specialized equipment and expertise, it is now widely applied in research. However, it is challenging to create broadly applicable experimental designs because each experiment requires the user to make informed decisions about sample preparation, RNA sequencing and data analysis. To facilitate this decision-making process, in this tutorial we summarize current methodological and analytical options, and discuss their suitability for a range of research scenarios. Specifically, we provide information about best practices for the separation of individual cells and provide an overview of current single-cell capture methods at different cellular resolutions and scales. Methods for the preparation of RNA sequencing libraries vary profoundly across applications, and we discuss features important for an informed selection process. An erroneous or biased analysis can lead to misinterpretations or obscure biologically important information. We provide a guide to the major data processing steps and options for meaningful data interpretation. These guidelines will serve as a reference to support users in building a single-cell experimental framework—from sample preparation to data interpretation—that is tailored to the underlying research context.},
	language = {en},
	number = {12},
	urldate = {2022-10-05},
	journal = {Nature Protocols},
	author = {Lafzi, Atefeh and Moutinho, Catia and Picelli, Simone and Heyn, Holger},
	month = dec,
	year = {2018},
	keywords = {Gene expression, RNA sequencing},
	pages = {2742--2757},
}

@article{Li_Durbin_2024,
  title={Genome assembly in the telomere-to-telomere era},
  rights={2024 Springer Nature Limited},
  ISSN={1471-0064},
  url={https://www.nature.com/articles/s41576-024-00718-w},
  DOI={10.1038/s41576-024-00718-w},
  abstractNote={Genome sequences largely determine the biology and encode the history of an organism, and de novo assembly — the process of reconstructing the genome sequence of an organism from sequencing reads — has been a central problem in bioinformatics for four decades. Until recently, genomes were typically assembled into fragments of a few megabases at best, but now technological advances in long-read sequencing enable the near-complete assembly of each chromosome — also known as telomere-to-telomere assembly — for many organisms. Here, we review recent progress on assembly algorithms and protocols, with a focus on how to derive near-telomere-to-telomere assemblies. We also discuss the additional developments that will be required to resolve remaining assembly gaps and to assemble non-diploid genomes.},
  journal={Nature Reviews Genetics},
  publisher={Nature Publishing Group},
  author={Li, Heng and Durbin, Richard},
  year={2024},
  month=apr,
  pages={1–13},
  language={en}
}

@article{Love2016,
  title={Modeling of RNA-seq fragment sequence bias reduces systematic errors in transcript abundance estimation},
  volume={34},
  ISSN={1087-0156},
  url={https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5143225/},
  DOI={10.1038/nbt.3682},
  number={12},
  journal={Nature biotechnology},
  author={Love, Michael I. and Hogenesch, John B. and Irizarry, Rafael A.},
  year={2016},
  month=dec,
  pages={1287–1291}
}

@website{bias-blog,
  title={RNA-seq fragment sequence bias},
  url={https://mikelove.wordpress.com/2016/09/26/rna-seq-fragment-sequence-bias/},
  abstractNote={Our paper was just published describing a new method for modeling and correcting fragment sequence bias for estimation of transcript abundances from RNA-seq: “Modeling of RNA-seq fragment seq…},
  journal={Mike Love’s blog},
  author={Mike Love},
  year={2016},
  month=sep,
  language={en}
}


@article{Luecken2019,
	title = {Current best practices in single‐cell {RNA}‐seq analysis: a tutorial},
	volume = {15},
	issn = {1744-4292, 1744-4292},
	shorttitle = {Current best practices in single‐cell {RNA}‐seq analysis},
	url = {https://onlinelibrary.wiley.com/doi/10.15252/msb.20188746},
	doi = {10.15252/msb.20188746},
	language = {en},
	number = {6},
	urldate = {2022-10-05},
	journal = {Molecular Systems Biology},
	author = {Luecken, Malte D and Theis, Fabian J},
	month = jun,
	year = {2019},
}

@article{Mantione2014,
  author  = {Mantione, K. J.  and Kream, R. M.  and Kuzelova, H.  and Ptacek, R.  and Raboch, J.  and Samuel, J. M.  and Stefano, G. B. },
  title   = {Comparing bioinformatic gene expression profiling methods: microarray and {RNA-Seq}},
  journal = {Medical Science Monitor Basic Research},
  year    = {2014},
  volume  = {20},
  pages   = {138--142},
  month   = {Aug},
  doi     = {10.12659/MSMBR.892101},
  url     = {https://pubmed.ncbi.nlm.nih.gov/25149683/}
}

@article{Mamanova2010,
  doi = {10.1038/nmeth.1419},
  url = {https://doi.org/10.1038/nmeth.1419},
  year = {2010},
  month = jan,
  publisher = {Springer Science and Business Media {LLC}},
  volume = {7},
  number = {2},
  pages = {111--118},
  author = {Lira Mamanova and Alison J Coffey and Carol E Scott and Iwanka Kozarewa and Emily H Turner and Akash Kumar and Eleanor Howard and Jay Shendure and Daniel J Turner},
  title = {Target-enrichment strategies for next-generation sequencing},
  journal = {Nature Methods}
}

@article{Miller2023,
  title={Chromosome-level genome and the identification of sex chromosomes in Uloborus diversus},
  volume={12},
  ISSN={2047-217X},
  url={https://doi.org/10.1093/gigascience/giad002},
  DOI={10.1093/gigascience/giad002},
  abstractNote={The orb web is a remarkable example of animal architecture that is observed in families of spiders that diverged over 200 million years ago. While several genomes exist for araneid orb-weavers, none exist for other orb-weaving families, hampering efforts to investigate the genetic basis of this complex behavior. Here we present a chromosome-level genome assembly for the cribellate orb-weaving spider Uloborus diversus. The assembly reinforces evidence of an ancient arachnid genome duplication and identifies complete open reading frames for every class of spidroin gene, which encode the proteins that are the key structural components of spider silks. We identified the 2 X chromosomes for U. diversus and identify candidate sex-determining loci. This chromosome-level assembly will be a valuable resource for evolutionary research into the origins of orb-weaving, spidroin evolution, chromosomal rearrangement, and chromosomal sex determination in spiders.},
  journal={GigaScience},
  author={Miller, Jeremiah and Zimin, Aleksey V and Gordus, Andrew},
  year={2023},
  month=jan,
  pages={giad002}
}


@website{NHGRIfactsheet2022,
  year = {2022},
  title = {Genomic Data Science},
  url = {https://www.genome.gov/about-genomics/fact-sheets/Genomic-Data-Science},
  author = {NHGRI}
}

@website{NHGRIGlossary2024,
  year = {2024},
  title = {Genome},
  url = {https://www.genome.gov/genetics-glossary/Genome},
  author = {NHGRI}
}

@website{NHSFrost2022,
  year = {2022},
  title = {Constitutional (germline) vs somatic (tumour) variants},
  url = {https://www.genomicseducation.hee.nhs.uk/genotes/knowledge-hub/constitutional-germline-vs-somatic-tumour-variants/},
  author = {Dr Amy Frost},
  publisher = {NHS}
}

@article{Nurk2022,
  title={The complete sequence of a human genome},
  volume={376},
  url={https://www.science.org/doi/10.1126/science.abj6987},
  DOI={10.1126/science.abj6987},
  abstractNote={Since its initial release in 2000, the human reference genome has covered only the euchromatic fraction of the genome, leaving important heterochromatic regions unfinished. Addressing the remaining 8% of the genome, the Telomere-to-Telomere (T2T) Consortium presents a complete 3.055 billion–base pair sequence of a human genome, T2T-CHM13, that includes gapless assemblies for all chromosomes except Y, corrects errors in the prior references, and introduces nearly 200 million base pairs of sequence containing 1956 gene predictions, 99 of which are predicted to be protein coding. The completed regions include all centromeric satellite arrays, recent segmental duplications, and the short arms of all five acrocentric chromosomes, unlocking these complex regions of the genome to variational and functional studies.},
  number={6588},
  journal={Science},
  publisher={American Association for the Advancement of Science},
  author={Nurk, Sergey and Koren, Sergey and Rhie, Arang and Rautiainen, Mikko and Bzikadze, Andrey V. and Mikheenko, Alla and Vollger, Mitchell R. and Altemose, Nicolas and Uralsky, Lev and Gershman, Ariel and Aganezov, Sergey and Hoyt, Savannah J. and Diekhans, Mark and Logsdon, Glennis A. and Alonge, Michael and Antonarakis, Stylianos E. and Borchers, Matthew and Bouffard, Gerard G. and Brooks, Shelise Y. and Caldas, Gina V. and Chen, Nae-Chyun and Cheng, Haoyu and Chin, Chen-Shan and Chow, William and de Lima, Leonardo G. and Dishuck, Philip C. and Durbin, Richard and Dvorkina, Tatiana and Fiddes, Ian T. and Formenti, Giulio and Fulton, Robert S. and Fungtammasan, Arkarachai and Garrison, Erik and Grady, Patrick G. S. and Graves-Lindsay, Tina A. and Hall, Ira M. and Hansen, Nancy F. and Hartley, Gabrielle A. and Haukness, Marina and Howe, Kerstin and Hunkapiller, Michael W. and Jain, Chirag and Jain, Miten and Jarvis, Erich D. and Kerpedjiev, Peter and Kirsche, Melanie and Kolmogorov, Mikhail and Korlach, Jonas and Kremitzki, Milinn and Li, Heng and Maduro, Valerie V. and Marschall, Tobias and McCartney, Ann M. and McDaniel, Jennifer and Miller, Danny E. and Mullikin, James C. and Myers, Eugene W. and Olson, Nathan D. and Paten, Benedict and Peluso, Paul and Pevzner, Pavel A. and Porubsky, David and Potapova, Tamara and Rogaev, Evgeny I. and Rosenfeld, Jeffrey A. and Salzberg, Steven L. and Schneider, Valerie A. and Sedlazeck, Fritz J. and Shafin, Kishwar and Shew, Colin J. and Shumate, Alaina and Sims, Ying and Smit, Arian F. A. and Soto, Daniela C. and Sović, Ivan and Storer, Jessica M. and Streets, Aaron and Sullivan, Beth A. and Thibaud-Nissen, Françoise and Torrance, James and Wagner, Justin and Walenz, Brian P. and Wenger, Aaron and Wood, Jonathan M. D. and Xiao, Chunlin and Yan, Stephanie M. and Young, Alice C. and Zarate, Samantha and Surti, Urvashi and McCoy, Rajiv C. and Dennis, Megan Y. and Alexandrov, Ivan A. and Gerton, Jennifer L. and O’Neill, Rachel J. and Timp, Winston and Zook, Justin M. and Schatz, Michael C. and Eichler, Evan E. and Miga, Karen H. and Phillippy, Adam M.},
  year={2022},
  month=apr,
  pages={44–53}
}

@article{Pearson2013,
  title={An Introduction to Sequence Similarity (“Homology”) Searching},
  volume={42},
  rights={http://onlinelibrary.wiley.com/termsAndConditions#vor},
  ISSN={1934-3396, 1934-340X},
  url={https://currentprotocols.onlinelibrary.wiley.com/doi/10.1002/0471250953.bi0301s42},
  DOI={10.1002/0471250953.bi0301s42},
  abstractNote={Sequence similarity searching, typically with BLAST (units 3.3, 3.4), is the most widely used, and most reliable, strategy for characterizing newly determined sequences. Sequence similarity searches can identify ”homologous” proteins or genes by detecting excess similarity – statistically significant similarity that reflects common ancestry. This unit provides an overview of the inference of homology from significant similarity, and introduces other units in this chapter that provide more details on effective strategies for identifying homologs.},
  number={1},
  journal={Current Protocols in Bioinformatics},
  author={Pearson, William R.},
  year={2013},
  month=jun,
  language={en}
}

@article{Pepke2009,
  title={Computation for ChIP-seq and RNA-seq studies},
  volume={6},
  ISSN={1548-7091},
  url={https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4121056/},
  DOI={10.1038/nmeth.1371},
  abstractNote={Genome-wide measurements of protein-DNA interactions and transcriptomes are increasingly done by deep DNA sequencing methods (ChIP-seq and RNA-seq). The power and richness of these counting-based measurements comes at the cost of routinely handling tens to hundreds of millions of reads. While early-adopters necessarily developed their own custom computer code to analyze the first ChIP-seq and RNA-seq datasets, a new generation of more sophisticated algorithms and software tools are emerging to assist in the analysis phase of these projects. This review describes the multilayered analyses of ChIP-seq and RNA-seq datasets, discusses the software packages currently available to perform tasks at each layer, and describes some upcoming challenges and features for future analysis tools. We also discuss how software choices and uses are affected by specific aspects of the underlying biology and data structure, including genome size, positional clustering of transcription factor binding sites, transcript discovery, and expression quantification.},
  number={11 0},
  journal={Nature methods},
  author={Pepke, Shirley and Wold, Barbara and Mortazavi, Ali},
  year={2009},
  month=nov,
  pages={S22–S32}
}


@article{Rao2019,
  doi = {10.3389/fgene.2018.00636},
  url = {https://doi.org/10.3389/fgene.2018.00636},
  year = {2019},
  month = jan,
  publisher = {Frontiers Media {SA}},
  volume = {9},
  author = {Mohan S. Rao and Terry R. Van Vleet and Rita Ciurlionis and Wayne R. Buck and Scott W. Mittelstadt and Eric A. G. Blomme and Michael J. Liguori},
  title = {Comparison of {RNA}-Seq and Microarray Gene Expression Platforms for the Toxicogenomic Evaluation of Liver From Short-Term Rat Toxicity Studies},
  journal = {Frontiers in Genetics}
}

@website{refinebioexamples2019,
  year = {2019},
  title = {Introduction to Microarray Data},
  url = {https://alexslemonade.github.io/refinebio-examples/02-microarray/00-intro-to-microarray.html},
  author = {CCDL for ALSF},
}

@article{Rhie2023,
  title={The complete sequence of a human Y chromosome},
  volume={621},
  rights={2023 This is a U.S. Government work and not under copyright protection in the US; foreign copyright protection may apply},
  ISSN={1476-4687},
  url={https://www.nature.com/articles/s41586-023-06457-y},
  DOI={10.1038/s41586-023-06457-y},
  abstractNote={The human Y chromosome has been notoriously difficult to sequence and assemble because of its complex repeat structure that includes long palindromes, tandem repeats and segmental duplications1–3. As a result, more than half of the Y chromosome is missing from the GRCh38 reference sequence and it remains the last human chromosome to be finished4,5. Here, the Telomere-to-Telomere (T2T) consortium presents the complete 62,460,029-base-pair sequence of a human Y chromosome from the HG002 genome (T2T-Y) that corrects multiple errors in GRCh38-Y and adds over 30 million base pairs of sequence to the reference, showing the complete ampliconic structures of gene families TSPY, DAZ and RBMY; 41 additional protein-coding genes, mostly from the TSPY family; and an alternating pattern of human satellite 1 and 3 blocks in the heterochromatic Yq12 region. We have combined T2T-Y with a previous assembly of the CHM13 genome4 and mapped available population variation, clinical variants and functional genomics data to produce a complete and comprehensive reference sequence for all 24 human chromosomes.},
  number={7978},
  journal={Nature},
  publisher={Nature Publishing Group},
  author={Rhie, Arang and Nurk, Sergey and Cechova, Monika and Hoyt, Savannah J. and Taylor, Dylan J. and Altemose, Nicolas and Hook, Paul W. and Koren, Sergey and Rautiainen, Mikko and Alexandrov, Ivan A. and Allen, Jamie and Asri, Mobin and Bzikadze, Andrey V. and Chen, Nae-Chyun and Chin, Chen-Shan and Diekhans, Mark and Flicek, Paul and Formenti, Giulio and Fungtammasan, Arkarachai and Garcia Giron, Carlos and Garrison, Erik and Gershman, Ariel and Gerton, Jennifer L. and Grady, Patrick G. S. and Guarracino, Andrea and Haggerty, Leanne and Halabian, Reza and Hansen, Nancy F. and Harris, Robert and Hartley, Gabrielle A. and Harvey, William T. and Haukness, Marina and Heinz, Jakob and Hourlier, Thibaut and Hubley, Robert M. and Hunt, Sarah E. and Hwang, Stephen and Jain, Miten and Kesharwani, Rupesh K. and Lewis, Alexandra P. and Li, Heng and Logsdon, Glennis A. and Lucas, Julian K. and Makalowski, Wojciech and Markovic, Christopher and Martin, Fergal J. and Mc Cartney, Ann M. and McCoy, Rajiv C. and McDaniel, Jennifer and McNulty, Brandy M. and Medvedev, Paul and Mikheenko, Alla and Munson, Katherine M. and Murphy, Terence D. and Olsen, Hugh E. and Olson, Nathan D. and Paulin, Luis F. and Porubsky, David and Potapova, Tamara and Ryabov, Fedor and Salzberg, Steven L. and Sauria, Michael E. G. and Sedlazeck, Fritz J. and Shafin, Kishwar and Shepelev, Valery A. and Shumate, Alaina and Storer, Jessica M. and Surapaneni, Likhitha and Taravella Oill, Angela M. and Thibaud-Nissen, Françoise and Timp, Winston and Tomaszkiewicz, Marta and Vollger, Mitchell R. and Walenz, Brian P. and Watwood, Allison C. and Weissensteiner, Matthias H. and Wenger, Aaron M. and Wilson, Melissa A. and Zarate, Samantha and Zhu, Yiming and Zook, Justin M. and Eichler, Evan E. and O’Neill, Rachel J. and Schatz, Michael C. and Miga, Karen H. and Makova, Kateryna D. and Phillippy, Adam M.},
  year={2023},
  month=sep,
  pages={344–354},
  language={en}
}


@Manual{rmarkdown2021,
  title = {rmarkdown: Dynamic Documents for R},
  author = {JJ Allaire and Yihui Xie 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 = {2021},
  note = {R package version 2.10},
  url = {https://github.com/rstudio/rmarkdown},
}

@article{Schatz2010,
  title={Assembly of large genomes using second-generation sequencing},
  volume={20},
  ISSN={1088-9051, 1549-5469},
  url={https://genome.cshlp.org/content/20/9/1165},
  DOI={10.1101/gr.101360.109},
  abstractNote={Second-generation sequencing technology can now be used to sequence an entire human genome in a matter of days and at low cost. Sequence read lengths, initially very short, have rapidly increased since the technology first appeared, and we now are seeing a growing number of efforts to sequence large genomes de novo from these short reads. In this Perspective, we describe the issues associated with short-read assembly, the different types of data produced by second-gen sequencers, and the latest assembly algorithms designed for these data. We also review the genomes that have been assembled recently from short reads and make recommendations for sequencing strategies that will yield a high-quality assembly.},
  note={Company: Cold Spring Harbor Laboratory Press
        Distributor: Cold Spring Harbor Laboratory Press
        Institution: Cold Spring Harbor Laboratory Press
        Label: Cold Spring Harbor Laboratory Press
        publisher: Cold Spring Harbor Lab
        PMID: 20508146},
  number={9},
  journal={Genome Research},
  author={Schatz, Michael C. and Delcher, Arthur L. and Salzberg, Steven L.},
  year={2010},
  month=sep,
  pages={1165–1173},
  language={en}
}

@article{Sistrom2016,
  title={De Novo Genome Assembly Shows Genome Wide Similarity between Trypanosoma brucei brucei and Trypanosoma brucei rhodesiense},
  volume={11},
  ISSN={1932-6203},
  url={https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0147660},
  DOI={10.1371/journal.pone.0147660},
  abstractNote={Background Trypanosoma brucei is a eukaryotic pathogen which causes African trypanosomiasis. It is notable for its variant surface glycoprotein (VSG) coat, which undergoes antigenic variation enabled by a large suite of VSG pseudogenes, allowing for persistent evasion of host adaptive immunity. While Trypanosoma brucei rhodesiense (Tbr) and T. b gambiense (Tbg) are human infective, related T. b. brucei (Tbb) is cleared by human sera. A single gene, the Serum Resistance Associated (SRA) gene, confers Tbr its human infectivity phenotype. Potential genetic recombination of this gene between Tbr and non-human infective Tbb strains has significant epidemiological consequences for Human African Trypanosomiasis outbreaks. Results Using long and short read whole genome sequencing, we generated a hybrid de novo assembly of a Tbr strain, producing 4,210 scaffolds totaling approximately 38.8 megabases, which comprise a significant proportion of the Tbr genome, and thus represents a valuable tool for a comparative genomics analyses among human and non-human infective T. brucei and future complete genome assembly. We detected 5,970 putative genes, of which two, an alcohol oxidoreductase and a pentatricopeptide repeat-containing protein, were members of gene families common to all T. brucei subspecies, but variants specific to the Tbr strain sequenced in this study. Our findings confirmed the extremely high level of genomic similarity between the two parasite subspecies found in other studies. Conclusions We confirm at the whole genome level high similarity between the two Tbb and Tbr strains studied. The discovery of extremely minor genomic differentiation between Tbb and Tbr suggests that the transference of the SRA gene via genetic recombination could potentially result in novel human infective strains, thus all genetic backgrounds of T. brucei should be considered potentially human infective in regions where Tbr is prevalent.}, number={2},
  journal={PLOS ONE},
  publisher={Public Library of Science},
  author={Sistrom, Mark and Evans, Benjamin and Benoit, Joshua and Balmer, Oliver and Aksoy, Serap and Caccone, Adalgisa},
  year={2016},
  month=feb,
  pages={e0147660},
  language={en}
}

@article{Slonim_Yanai_2009,
  title={Getting Started in Gene Expression Microarray Analysis},
  volume={5},
  ISSN={1553-7358},
  url={https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1000543},
  DOI={10.1371/journal.pcbi.1000543},
  number={10},
  journal={PLOS Computational Biology},
  publisher={Public Library of Science},
  author={Slonim, Donna K. and Yanai, Itai},
  year={2009},
  month=oct,
  pages={e1000543},
  language={en}
}


@article{Svensson2017,
  doi = {10.1038/nmeth.4220},
  url = {https://doi.org/10.1038/nmeth.4220},
  year = {2017},
  month = mar,
  publisher = {Springer Science and Business Media {LLC}},
  volume = {14},
  number = {4},
  pages = {381--387},
  author = {Valentine Svensson and Kedar Nath Natarajan and Lam-Ha Ly and Ricardo J Miragaia and Charlotte Labalette and Iain C Macaulay and Ana Cvejic and Sarah A Teichmann},
  title = {Power analysis of single-cell {RNA}-sequencing experiments},
  journal = {Nature Methods}
}

@website{Smith2015,
  url = {https://cgatoxford.wordpress.com/2015/08/14/unique-molecular-identifiers-the-problem-the-solution-and-the-proof/},
  author = {Tom Smith},
  year = {2015},
  month = {August},
  title = {Unique Molecular Identifiers – the problem, the solution and the proof},
  journal = {CGAT},
}

@website{Starmer2017-rnaseq,
  url={https://www.youtube.com/watch?v=tlf6wYJrwKY},
  year={2017},
  month=aug,
  author = {Josh Starmer}
  }


@article{Tarca2006,
  author  = {Tarca, A. L.  and Romero, R.  and Draghici, S. },
  title   = {Analysis of microarray experiments of gene expression profiling},
  journal = {American Journal of Obstetrics and Gynecology},
  year    = {2006},
  volume  = {195},
  number  = {2},
  pages   = {373--388},
  month   = {Aug},
  doi     = {10.1016/j.ajog.2006.07.001},
  url     = {https://www.ncbi.nlm.nih.gov/pmc/articles/PMC2435252/}
}

@ARTICLE{Tignat-Perrier2022,
  title     = "Microorganisms floating through the air",
  author    = "Tignat-Perrier, Romie and T{\'e}cher, Nathalie and Vogel,
               Timothy M and Larose, Catherine and Dommergue, Aur{\'e}lien",
  journal   = "Front. Young Minds",
  publisher = "Frontiers Media SA",
  volume    =  10,
  month     =  mar,
  year      =  2022,
  copyright = "https://creativecommons.org/licenses/by/4.0/"
}


@article{Taylor2006,
  title={ESPERR: Learning strong and weak signals in genomic sequence alignments to identify functional elements},
  volume={16},
  ISSN={1088-9051},
  url={https://www.ncbi.nlm.nih.gov/pmc/articles/PMC1665643/},
  DOI={10.1101/gr.4537706},
  abstractNote={Genomic sequence signals—such as base composition, presence of particular motifs, or evolutionary constraint—have been used effectively to identify functional elements. However, approaches based only on specific signals known to correlate with function can be quite limiting. When training data are available, application of computational learning algorithms to multispecies alignments has the potential to capture broader and more informative sequence and evolutionary patterns that better characterize a class of elements. However, effective exploitation of patterns in multispecies alignments is impeded by the vast number of possible alignment columns and by a limited understanding of which particular strings of columns may characterize a given class. We have developed a computational method, called ESPERR (evolutionary and sequence pattern extraction through reduced representations), which uses training examples to learn encodings of multispecies alignments into reduced forms tailored for the prediction of chosen classes of functional elements. ESPERR produces a greatly improved Regulatory Potential score, which can discriminate regulatory regions from neutral sites with excellent accuracy (∼94%). This score captures strong signals (GC content and conservation), as well as subtler signals (with small contributions from many different alignment patterns) that characterize the regulatory elements in our training set. ESPERR is also effective for predicting other classes of functional elements, as we show for DNaseI hypersensitive sites and highly conserved regions with developmental enhancer activity. Our software, training data, and genome-wide predictions are available from our Web site (http://www.bx.psu.edu/projects/esperr).},
  number={12},
  journal={Genome Research},
  author={Taylor, James and Tyekucheva, Svitlana and King, David C. and Hardison, Ross C. and Miller, Webb and Chiaromonte, Francesca},
  year={2006},
  month=dec,
  pages={1596–1604}
}

@article{Taylor_2024,
  title={Beyond the Human Genome Project: The Age of Complete Human Genome Sequences and Pangenome References},
  ISSN={1527-8204, 1545-293X},
  url={https://www.annualreviews.org/content/journals/10.1146/annurev-genom-021623-081639},
  DOI={10.1146/annurev-genom-021623-081639},
  abstractNote={The Human Genome Project was an enormous accomplishment, providing a foundation for countless explorations into the genetics and genomics of the human species. Yet for many years, the human genome reference sequence remained incomplete and lacked representation of human genetic diversity. Recently, two major advances have emerged to address these shortcomings: complete gap-free human genome sequences, such as the one developed by the Telomere-to-Telomere Consortium, and high-quality pangenomes, such as the one developed by the Human Pangenome Reference Consortium. Facilitated by advances in long-read DNA sequencing and genome assembly algorithms, complete human genome sequences resolve regions that have been historically difficult to sequence, including centromeres, telomeres, and segmental duplications. In parallel, pangenomes capture the extensive genetic diversity across populations worldwide. Together, these advances usher in a new era of genomics research, enhancing the accuracy of genomic analysis, paving the path for precision medicine, and contributing to deeper insights into human biology.},
  journal={Annual Review of Genomics and Human Genetics},
  author={Taylor, Dylan J. and Eizenga, Jordan M. and Li, Qiuhui and Das, Arun and Jenike, Katharine M. and Kenny, Eimear E. and Miga, Karen H. and Monlong, Jean and McCoy, Rajiv C. and Paten, Benedict and Schatz, Michael C.},
  year={2024},
  month=apr,
  language={en}
}

@article{Turner2009,
  doi = {10.1146/annurev-genom-082908-150112},
  url = {https://doi.org/10.1146/annurev-genom-082908-150112},
  year = {2009},
  month = sep,
  publisher = {Annual Reviews},
  volume = {10},
  number = {1},
  pages = {263--284},
  author = {Emily H. Turner and Sarah B. Ng and Deborah A. Nickerson and Jay Shendure},
  title = {Methods for Genomic Partitioning},
  journal = {Annual Review of Genomics and Human Genetics}
}

@article{Wong2011,
  title={Unraveling the Genetics of Cancer: Genome Sequencing and Beyond},
  volume={12},
  ISSN={1527-8204, 1545-293X},
  url={https://www.annualreviews.org/doi/10.1146/annurev-genom-082509-141532},
  DOI={10.1146/annurev-genom-082509-141532},
  abstractNote={Advances in next-generation sequencing technology are enabling the systematic analyses of whole cancer genomes, providing insights into the landscape of somatic mutations and the great genetic heterogeneity that defines the unique signature of an individual tumor. Moreover, integrated studies of the genome, epigenome, and transcriptome reveal mechanisms of tumorigenesis at multiple levels. Progress in sequencing technologies and bioinformatics will improve the costs, sensitivity, and accuracy of detecting somatic mutations, while large-scale projects are underway to coordinate cancer genome sequencing at the global level to facilitate the generation and dissemination of high-quality uniform genetic data. These developments will create opportunities for deeper studies of cancer genetics and the clinical application of genome sequencing, and will motivate further research in cancer pathogenesis.},
  number={1},
  journal={Annual Review of Genomics and Human Genetics},
  author={Wong, Kit Man and Hudson, Thomas J. and McPherson, John D.},
  year={2011},
  month=sep,
  pages={407–430},
  language={en}
}

@Book{Xie2018,
  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},
  note = {ISBN 9781138359338},
  url = {https://bookdown.org/yihui/rmarkdown},
}

@article{Xiao2022,
  title={Personalized genome assembly for accurate cancer somatic mutation discovery using tumor-normal paired reference samples},
  volume={23},
  ISSN={1474-760X},
  url={https://doi.org/10.1186/s13059-022-02803-x},
  DOI={10.1186/s13059-022-02803-x},
  abstractNote={The use of a personalized haplotype-specific genome assembly, rather than an unrelated, mosaic genome like GRCh38, as a reference for detecting the full spectrum of somatic events from cancers has long been advocated but has never been explored in tumor-normal paired samples. Here, we provide the first demonstrated use of de novo assembled personalized genome as a reference for cancer mutation detection and quantifying the effects of the reference genomes on the accuracy of somatic mutation detection.},
  number={1},
  journal={Genome Biology},
  author={Xiao, Chunlin and Chen, Zhong and Chen, Wanqiu and Padilla, Cory and Colgan, Michael and Wu, Wenjun and Fang, Li-Tai and Liu, Tiantian and Yang, Yibin and Schneider, Valerie and Wang, Charles and Xiao, Wenming},
  year={2022},
  month=nov,
  pages={237}
}

@Book{Xie2020,
  title = {R Markdown Cookbook},
  author = {Yihui Xie and Christophe Dervieux and Emily Riederer},
  publisher = {Chapman and Hall/CRC},
  address = {Boca Raton, Florida},
  year = {2020},
  note = {ISBN 9780367563837},
  url = {https://bookdown.org/yihui/rmarkdown-cookbook},
}

@article{Yu2012,
  doi = {10.1038/nprot.2012.137},
  url = {https://doi.org/10.1038/nprot.2012.137},
  year = {2012},
  month = nov,
  publisher = {Springer Science and Business Media {LLC}},
  volume = {7},
  number = {12},
  pages = {2159--2170},
  author = {Miao Yu and Gary C Hon and Keith E Szulwach and Chun-Xiao Song and Peng Jin and Bing Ren and Chuan He},
  title = {Tet-assisted bisulfite sequencing of 5-hydroxymethylcytosine},
  journal = {Nature Protocols}
}

@article{Zhang2015,
  doi = {10.1186/s13059-015-0694-1},
  url = {https://doi.org/10.1186/s13059-015-0694-1},
  year = {2015},
  month = jun,
  publisher = {Springer Science and Business Media {LLC}},
  volume = {16},
  number = {1},
  author = {Wenqian Zhang and Ying Yu and Falk Hertwig and Jean Thierry-Mieg and Wenwei Zhang and Danielle Thierry-Mieg and Jian Wang and Cesare Furlanello and Viswanath Devanarayan and Jie Cheng and Youping Deng and Barbara Hero and Huixiao Hong and Meiwen Jia and Li Li and Simon M Lin and Yuri Nikolsky and Andr{\'{e}} Oberthuer and Tao Qing and Zhenqiang Su and Ruth Volland and Charles Wang and May D. Wang and Junmei Ai and Davide Albanese and Shahab Asgharzadeh and Smadar Avigad and Wenjun Bao and Marina Bessarabova and Murray H. Brilliant and Benedikt Brors and Marco Chierici and Tzu-Ming Chu and Jibin Zhang and Richard G. Grundy and Min Max He and Scott Hebbring and Howard L. Kaufman and Samir Lababidi and Lee J. Lancashire and Yan Li and Xin X. Lu and Heng Luo and Xiwen Ma and Baitang Ning and Rosa Noguera and Martin Peifer and John H. Phan and Frederik Roels and Carolina Rosswog and Susan Shao and Jie Shen and Jessica Theissen and Gian Paolo Tonini and Jo Vandesompele and Po-Yen Wu and Wenzhong Xiao and Joshua Xu and Weihong Xu and Jiekun Xuan and Yong Yang and Zhan Ye and Zirui Dong and Ke K. Zhang and Ye Yin and Chen Zhao and Yuanting Zheng and Russell D. Wolfinger and Tieliu Shi and Linda H. Malkas and Frank Berthold and Jun Wang and Weida Tong and Leming Shi and Zhiyu Peng and Matthias Fischer},
  title = {Comparison of {RNA}-seq and microarray-based models for clinical endpoint prediction},
  journal = {Genome Biology}
}

@article{Zhang2022,
  title={Cancer Genomic Rearrangements and Copy Number Alterations from Errors in Cell Division},
  volume={6},
  rights={http://creativecommons.org/licenses/by/4.0/},
  ISSN={2472-3428, 2472-3428},
  url={https://www.annualreviews.org/doi/10.1146/annurev-cancerbio-070620-094029},
  DOI={10.1146/annurev-cancerbio-070620-094029},
  abstractNote={Analysis of cancer genomes has shown that a large fraction of chromosomal changes originate from catastrophic events including whole-genome duplication, chromothripsis, breakage-fusion-bridge cycles, and chromoplexy. Through sophisticated computational analysis of cancer genomes and experimental recapitulation of these catastrophic alterations, we have gained significant insights into the origin, mechanism, and evolutionary dynamics of cancer genome complexity. In this review, we summarize this progress and survey the major unresolved questions, with particular emphasis on the relative contributions of chromosome fragmentation and DNA replication errors to complex chromosomal alterations.},
  number={1},
  journal={Annual Review of Cancer Biology},
  author={Zhang, Cheng-Zhong and Pellman, David},
  year={2022},
  month=apr,
  pages={245–268},
  language={en}
}

@article{Ziemann2016,
  doi = {10.1186/s13059-016-1044-7},
  url = {https://doi.org/10.1186/s13059-016-1044-7},
  year = {2016},
  month = aug,
  publisher = {Springer Science and Business Media {LLC}},
  volume = {17},
  number = {1},
  author = {Mark Ziemann and Yotam Eren and Assam El-Osta},
  title = {Gene name errors are widespread in the scientific literature},
  journal = {Genome Biology}
}

@article{Ziegenhain2017,
	title = {Comparative {Analysis} of {Single}-{Cell} {RNA} {Sequencing} {Methods}},
	volume = {65},
	issn = {10972765},
	url = {https://linkinghub.elsevier.com/retrieve/pii/S1097276517300497},
	doi = {10.1016/j.molcel.2017.01.023},
	language = {en},
	number = {4},
	urldate = {2022-10-05},
	journal = {Molecular Cell},
	author = {Ziegenhain, Christoph and Vieth, Beate and Parekh, Swati and Reinius, Björn and Guillaumet-Adkins, Amy and Smets, Martha and Leonhardt, Heinrich and Heyn, Holger and Hellmann, Ines and Enard, Wolfgang},
	month = feb,
	year = {2017},
	pages = {631--643.e4},
}

@article{Zhang2019,
	title = {Comparative {Analysis} of {Droplet}-{Based} {Ultra}-{High}-{Throughput} {Single}-{Cell} {RNA}-{Seq} {Systems}},
	volume = {73},
	issn = {10972765},
	url = {https://linkinghub.elsevier.com/retrieve/pii/S1097276518308803},
	doi = {10.1016/j.molcel.2018.10.020},
	language = {en},
	number = {1},
	urldate = {2022-10-05},
	journal = {Molecular Cell},
	author = {Zhang, Xiannian and Li, Tianqi and Liu, Feng and Chen, Yaqi and Yao, Jiacheng and Li, Zeyao and Huang, Yanyi and Wang, Jianbin},
	month = jan,
	year = {2019},
	pages = {130--142.e5},
}

@article{Singh2022,
  doi = {10.3390/diagnostics12071539},
  url = {https://doi.org/10.3390/diagnostics12071539},
  year = {2022},
  month = jun,
  publisher = {{MDPI} {AG}},
  volume = {12},
  number = {7},
  pages = {1539},
  author = {Rajesh R. Singh},
  title = {Target Enrichment Approaches for Next-Generation Sequencing Applications in Oncology},
  journal = {Diagnostics}
}

@article{Sims2014,
  doi = {10.1038/nrg3642},
  url = {https://doi.org/10.1038/nrg3642},
  year = {2014},
  month = jan,
  publisher = {Springer Science and Business Media {LLC}},
  volume = {15},
  number = {2},
  pages = {121--132},
  author = {David Sims and Ian Sudbery and Nicholas E. Ilott and Andreas Heger and Chris P. Ponting},
  title = {Sequencing depth and coverage: key considerations in genomic analyses},
  journal = {Nature Reviews Genetics}
}

@article{Bentley2008,
  doi = {10.1038/nature07517},
  url = {https://doi.org/10.1038/nature07517},
  year = {2008},
  month = nov,
  publisher = {Springer Science and Business Media {LLC}},
  volume = {456},
  number = {7218},
  pages = {53--59},
  author = {David R. Bentley and Shankar Balasubramanian and Harold P. Swerdlow and Geoffrey P. Smith and John Milton and Clive G. Brown and Kevin P. Hall and Dirk J. Evers and Colin L. Barnes and Helen R. Bignell and Jonathan M. Boutell and Jason Bryant and Richard J. Carter and R. Keira Cheetham and Anthony J. Cox and Darren J. Ellis and Michael R. Flatbush and Niall A. Gormley and Sean J. Humphray and Leslie J. Irving and Mirian S. Karbelashvili and Scott M. Kirk and Heng Li and Xiaohai Liu and Klaus S. Maisinger and Lisa J. Murray and Bojan Obradovic and Tobias Ost and Michael L. Parkinson and Mark R. Pratt and Isabelle M. J. Rasolonjatovo and Mark T. Reed and Roberto Rigatti and Chiara Rodighiero and Mark T. Ross and Andrea Sabot and Subramanian V. Sankar and Aylwyn Scally and Gary P. Schroth and Mark E. Smith and Vincent P. Smith and Anastassia Spiridou and Peta E. Torrance and Svilen S. Tzonev and Eric H. Vermaas and Klaudia Walter and Xiaolin Wu and Lu Zhang and Mohammed D. Alam and Carole Anastasi and Ify C. Aniebo and David M. D. Bailey and Iain R. Bancarz and Saibal Banerjee and Selena G. Barbour and Primo A. Baybayan and Vincent A. Benoit and Kevin F. Benson and Claire Bevis and Phillip J. Black and Asha Boodhun and Joe S. Brennan and John A. Bridgham and Rob C. Brown and Andrew A. Brown and Dale H. Buermann and Abass A. Bundu and James C. Burrows and Nigel P. Carter and Nestor Castillo and Maria Chiara E. Catenazzi and Simon Chang and R. Neil Cooley and Natasha R. Crake and Olubunmi O. Dada and Konstantinos D. Diakoumakos and Belen Dominguez-Fernandez and David J. Earnshaw and Ugonna C. Egbujor and David W. Elmore and Sergey S. Etchin and Mark R. Ewan and Milan Fedurco and Louise J. Fraser and Karin V. Fuentes Fajardo and W. Scott Furey and David George and Kimberley J. Gietzen and Colin P. Goddard and George S. Golda and Philip A. Granieri and David E. Green and David L. Gustafson and Nancy F. Hansen and Kevin Harnish and Christian D. Haudenschild and Narinder I. Heyer and Matthew M. Hims and Johnny T. Ho and Adrian M. Horgan and Katya Hoschler and Steve Hurwitz and Denis V. Ivanov and Maria Q. Johnson and Terena James and T. A. Huw Jones and Gyoung-Dong Kang and Tzvetana H. Kerelska and Alan D. Kersey and Irina Khrebtukova and Alex P. Kindwall and Zoya Kingsbury and Paula I. Kokko-Gonzales and Anil Kumar and Marc A. Laurent and Cynthia T. Lawley and Sarah E. Lee and Xavier Lee and Arnold K. Liao and Jennifer A. Loch and Mitch Lok and Shujun Luo and Radhika M. Mammen and John W. Martin and Patrick G. McCauley and Paul McNitt and Parul Mehta and Keith W. Moon and Joe W. Mullens and Taksina Newington and Zemin Ning and Bee Ling Ng and Sonia M. Novo and Michael J. O'Neill and Mark A. Osborne and Andrew Osnowski and Omead Ostadan and Lambros L. Paraschos and Lea Pickering and Andrew C. Pike and Alger C. Pike and D. Chris Pinkard and Daniel P. Pliskin and Joe Podhasky and Victor J. Quijano and Come Raczy and Vicki H. Rae and Stephen R. Rawlings and Ana Chiva Rodriguez and Phyllida M. Roe and John Rogers and Maria C. Rogert Bacigalupo and Nikolai Romanov and Anthony Romieu and Rithy K. Roth and Natalie J. Rourke and Silke T. Ruediger and Eli Rusman and Raquel M. Sanches-Kuiper and Martin R. Schenker and Josefina M. Seoane and Richard J. Shaw and Mitch K. Shiver and Steven W. Short and Ning L. Sizto and Johannes P. Sluis and Melanie A. Smith and Jean Ernest Sohna Sohna and Eric J. Spence and Kim Stevens and Neil Sutton and Lukasz Szajkowski and Carolyn L. Tregidgo and Gerardo Turcatti and Stephanie vandeVondele and Yuli Verhovsky and Selene M. Virk and Suzanne Wakelin and Gregory C. Walcott and Jingwen Wang and Graham J. Worsley and Juying Yan and Ling Yau and Mike Zuerlein and Jane Rogers and James C. Mullikin and Matthew E. Hurles and Nick J. McCooke and John S. West and Frank L. Oaks and Peter L. Lundberg and David Klenerman and Richard Durbin and Anthony J. Smith},
  title = {Accurate whole human genome sequencing using reversible terminator chemistry},
  journal = {Nature}
}

@article{Clark2011,
  doi = {10.1038/nbt.1975},
  url = {https://doi.org/10.1038/nbt.1975},
  year = {2011},
  month = sep,
  publisher = {Springer Science and Business Media {LLC}},
  volume = {29},
  number = {10},
  pages = {908--914},
  author = {Michael J Clark and Rui Chen and Hugo Y K Lam and Konrad J Karczewski and Rong Chen and Ghia Euskirchen and Atul J Butte and Michael Snyder},
  title = {Performance comparison of exome {DNA} sequencing technologies},
  journal = {Nature Biotechnology}
}

@article{BewickeCopley2019,
  doi = {10.1016/j.csbj.2019.10.004},
  url = {https://doi.org/10.1016/j.csbj.2019.10.004},
  year = {2019},
  publisher = {Elsevier {BV}},
  volume = {17},
  pages = {1348--1359},
  author = {Findlay Bewicke-Copley and Emil Arjun Kumar and Giuseppe Palladino and Koorosh Korfi and Jun Wang},
  title = {Applications and analysis of targeted genomic sequencing in cancer studies},
  journal = {Computational and Structural Biotechnology Journal}
}

@article{Hwang2019,
  doi = {10.1038/s41598-019-39108-2},
  url = {https://doi.org/10.1038/s41598-019-39108-2},
  year = {2019},
  month = mar,
  publisher = {Springer Science and Business Media {LLC}},
  volume = {9},
  number = {1},
  author = {Kyu-Baek Hwang and In-Hee Lee and Honglan Li and Dhong-Geon Won and Carles Hernandez-Ferrer and Jose Alberto Negron and Sek Won Kong},
  title = {Comparative analysis of whole-genome sequencing pipelines to minimize false negative findings},
  journal = {Scientific Reports}
}

@article{Naj2019,
  doi = {10.1016/j.ygeno.2018.05.004},
  url = {https://doi.org/10.1016/j.ygeno.2018.05.004},
  year = {2019},
  month = jul,
  publisher = {Elsevier {BV}},
  volume = {111},
  number = {4},
  pages = {808--818},
  author = {Adam C. Naj and Honghuang Lin and Badri N. Vardarajan and Simon White and Daniel Lancour and Yiyi Ma and Michael Schmidt and Fangui Sun and Mariusz Butkiewicz and William S. Bush and Brian W. Kunkle and John Malamon and Najaf Amin and Seung Hoan Choi and Kara L. Hamilton-Nelson and Sven J. van der Lee and Namrata Gupta and Daniel C. Koboldt and Mohamad Saad and Bowen Wang and Alejandro Q. Nato and Harkirat K. Sohi and Amanda Kuzma and Li-San Wang and L. Adrienne Cupples and Cornelia van Duijn and Sudha Seshadri and Gerard D. Schellenberg and Eric Boerwinkle and Joshua C. Bis and Jos{\'{e}}e Dupuis and William J. Salerno and Ellen M. Wijsman and Eden R. Martin and Anita L. DeStefano},
  title = {Quality control and integration of genotypes from two calling pipelines for whole genome sequence data in the Alzheimer{\textquotesingle}s disease sequencing project},
  journal = {Genomics}
}

@article{He2020,
  doi = {10.1093/bib/bbaa083},
  url = {https://doi.org/10.1093/bib/bbaa083},
  year = {2020},
  month = jun,
  publisher = {Oxford University Press ({OUP})},
  volume = {22},
  number = {3},
  author = {Xiaoyu He and Shanyu Chen and Ruilin Li and Xinyin Han and Zhipeng He and Danyang Yuan and Shuying Zhang and Xiaohong Duan and Beifang Niu},
  title = {Comprehensive fundamental somatic variant calling and quality management strategies for human cancer genomes},
  journal = {Briefings in Bioinformatics}
}

@article{ghavi2019highly,
  title={Highly rearranged chromosomes reveal uncoupling between genome topology and gene expression},
  author={Ghavi-Helm, Yad and Jankowski, Aleksander and Meiers, Sascha and Viales, Rebecca R and Korbel, Jan O and Furlong, Eileen EM},
  journal={Nature genetics},
  volume={51},
  number={8},
  pages={1272--1282},
  year={2019},
  publisher={Nature Publishing Group}
}

@article{ramirez2016deeptools2,
  title={deepTools2: a next generation web server for deep-sequencing data analysis},
  author={Ram{\'\i}rez, Fidel and Ryan, Devon P and Gr{\"u}ning, Bj{\o}rn and Bhardwaj, Vivek and Kilpert, Fabian and Richter, Andreas S and Heyne, Steffen and D{\textquoteright}hertog, Wannes and Lassmann, Timo and Monaco, Giulio and others},
  journal={Nucleic acids research},
  volume={44},
  number={W1},
  pages={W160--W165},
  year={2016},
  publisher={Oxford University Press}
}

@article{schep2017chromvar,
  title={chromVAR: inferring transcription-factor-associated accessibility from single-cell epigenomic data},
  author={Schep, Alicia N and Wu, Bin and Buenrostro, Jason D and Greenleaf, William J},
  journal={Nature methods},
  volume={14},
  number={10},
  pages={975--978},
  year={2017},
  publisher={Nature Publishing Group},
  url = {https://www.nature.com/articles/nmeth.4401}
}

@article{heinz2010simple,
  title={Simple combinations of lineage-determining transcription factors prime cis-regulatory elements required for macrophage and B cell identities},
  author={Heinz, S and Benner, Christopher and Spann, Nathanael and Bertolino, Eric and Lin, Yen Ching and Laslo, Petra and Cheng, Jia and Murre, Cornelis and Singh, Harinder and Glass, Christopher K and others},
  journal={Molecular cell},
  volume={38},
  number={4},
  pages={576--589},
  year={2010},
  publisher={Elsevier},
  url = {https://pubmed.ncbi.nlm.nih.gov/20513432/}
}

@article{zhang2008model,
  title={Model-based analysis of ChIP-Seq (MACS)},
  author={Zhang, Yong and Liu, Tao and Meyer, Clifford A and Eeckhoute, Jie and Johnson, David S and Bernstein, Bradley E and Nusbaum, Chad and Myers, Richard M and Brown, Myles and Li, Wei and others},
  journal={Genome biology},
  volume={9},
  number={9},
  pages={R137},
  year={2008},
  publisher={BioMed Central},
  url = {https://genomebiology.biomedcentral.com/articles/10.1186/gb-2008-9-9-r137}
}

@article{dobin2013star,
  title={STAR: ultrafast universal RNA-seq aligner},
  author={Dobin, Alexander and Davis, Carrie A and Schlesinger, Felix and Drenkow, Jorg and Zaleski, Chris and Jha, Sonali and Batut, Philippe and Chaisson, Mark and Gingeras, Thomas R},
  journal={Bioinformatics},
  volume={29},
  number={1},
  pages={15--21},
  year={2013},
  publisher={Oxford University Press},
  url = {https://academic.oup.com/bioinformatics/article/29/1/15/272537}
}

@article{kim2015hisat,
  title={HISAT: a fast spliced aligner with low memory requirements},
  author={Kim, Daehwan and Langmead, Ben and Salzberg, Steven L},
  journal={Nature methods},
  volume={12},
  number={4},
  pages={357--360},
  year={2015},
  publisher={Nature Publishing Group},
  url = {https://www.nature.com/articles/nmeth.3317}
}

@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},
  url = {https://www.nature.com/articles/nbt.3519}
}

@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},
  url = {https://pubmed.ncbi.nlm.nih.gov/28263959/}
}

@article{zheng2017massively,
  title={Massively parallel digital transcriptional profiling of single cells},
  author={Zheng, Grace XY and Terry, Jessica M and Belgrader, Phillip and Ryvkin, Paul and Bent, Zachary W and Wilson, Ryan and Ziraldo, Solongo B and Wheeler, Tobias D and McDermott, Geoff P and Zhu, Junjie and others},
  journal={Nature communications},
  volume={8},
  number={1},
  pages={1--12},
  year={2017},
  publisher={Nature Publishing Group},
  url = {https://www.nature.com/articles/ncomms14049}
}

@article{andrews2010fastqc,
  title={FastQC: a quality control tool for high throughput sequence data},
  author={Andrews, Simon},
  url = {https://www.bioinformatics.babraham.ac.uk/projects/fastqc/},
  publisher = {Babraham Bioinformatics}
}

@article{krueger2015trim,
  title={Trim Galore!: a wrapper tool around Cutadapt and FastQC to consistently apply quality and adapter trimming to FastQ files},
  author={Krueger, Felix and Andrews, Simon R},
  url = {https://www.bioinformatics.babraham.ac.uk/projects/trim_galore/}
}

@article{liu2019bismark,
  title={Bismark: a flexible aligner and methylation caller for Bisulfite-Seq applications},
  author={Liu, Yi and Siegmund, Kimberly D and Laird, Peter W and Berman, Benjamin P},
  journal={Bioinformatics},
  volume={36},
  number={22-23},
  pages={5280--5282},
  year={2019},
  publisher={Oxford University Press},
  url = {https://academic.oup.com/bioinformatics/article/27/11/1571/216956}
}

@article{langmead2012fast,
  title={Fast gapped-read alignment with Bowtie 2},
  author={Langmead, Ben and Salzberg, Steven L},
  journal={Nature methods},
  volume={9},
  number={4},
  pages={357--359},
  year={2012},
  publisher={Nature Publishing Group},
  url = {https://www.nature.com/articles/nmeth.1923}
}

@article{akalin2012methylome,
  title={methylKit: a comprehensive R package for the analysis of genome-wide DNA methylation profiles},
  author={Akalin, Altuna and Kormaksson, Matthias and Li, Sheng and Garrett-Bakelman, Francine E and Figueroa, Maria E and Melnick, Ari and Mason, Christopher E},
  journal={Genome biology},
  volume={13},
  number={10},
  pages={R87},
  year={2012},
  publisher={BioMed Central},
  url = {https://genomebiology.biomedcentral.com/articles/10.1186/gb-2012-13-10-r87}
}

@article{feng2014dss,
  title={Differential methylation analysis for BS-seq data under general experimental design},
  author={Feng, Hui and Conneely, Karen N},
  journal={Bioinformatics},
  volume={32},
  number={2},
  pages={289--291},
  year={2016},
  publisher={Oxford University Press},
  url = {https://pubmed.ncbi.nlm.nih.gov/26819470/}
}

@article{mcginnis2020doubletfinder,
  title={DoubletFinder: doublet detection in single-cell RNA sequencing data using artificial nearest neighbors},
  author={McGinnis, Christopher S and Murrow, Lillian M and Gartner, Zev J},
  journal={Cell systems},
  volume={8},
  number={4},
  pages={329--337. e4},
  year={2020},
  publisher={Elsevier},
  url = {https://pubmed.ncbi.nlm.nih.gov/30954475/}
}

@article{wolock2019scrublet,
  title={scrublet: Computational Identification of Cell Doublets in Single-Cell Transcriptomic Data},
  author={Wolock, Samuel L and Krishnaswamy, Smita and Huang, B Jesse},
  journal={Cell systems},
  volume={8},
  number={4},
  pages={281--291. e9},
  year={2019},
  publisher={Elsevier},
  url = {https://pubmed.ncbi.nlm.nih.gov/30954476/}
}

@article{de2019doubletdecon,
  title={DoubletDecon: Deconvoluting Doublets from Single-Cell RNA-Sequencing Data},
  author={De Pasquale, Elisa and Dudoit, Sandrine},
  journal={Cell reports},
  volume={29},
  number={6},
  pages={1718--1727. e8},
  year={2019},
  publisher={Elsevier},
  url = {https://www.sciencedirect.com/science/article/pii/S2211124719312860}
}


@article{kang2018demuxlet,
  title={Multiplexed droplet single-cell RNA-sequencing using natural genetic variation},
  author={Kang, Hyun Min and Subramaniam, Murali and Targ, Sheryl and Nguyen, Cuong Q and Maliskova, Lenka and McCarthy, Eavan and Wan, Yishai and Wong, Shannon and Byrnes, Lindsay and Lanata, Christine M and others},
  journal={Genome biology},
  volume={19},
  number={1},
  pages={1--12},
  year={2018},
  publisher={BioMed Central}
}
@article{Kornberg1999,
  title={Chromatin structure and transcription},
  author={Kornberg, Roger D and Lorch, Yahli},
  journal={Annual review of cell and developmental biology},
  volume={15},
  pages={49--84},
  year={1999},
  publisher={Annual Reviews 4139 El Camino Way, PO Box 10139, Palo Alto, CA 94303-0139, USA}
}

@article{Kimura2013,
  title={Histone modifications for human epigenome analysis},
  author={Kimura, Hiroshi},
  journal={Journal of human genetics},
  volume={58},
  number={7},
  pages={439--445},
  year={2013},
  publisher={Nature Publishing Group}
}

@article{Zentner2013,
  title={Regulation of nucleosome dynamics by histone modifications},
  author={Zentner, Gabriel E and Henikoff, Steven},
  journal={Nature structural & molecular biology},
  volume={20},
  number={3},
  pages={259--266},
  year={2013},
  publisher={Nature Publishing Group}
}

@article{Bernstein2007,
  title={The mammalian epigenome},
  author={Bernstein, Bradley E and Meissner, Alexander and Lander, Eric S},
  journal={Cell},
  volume={128},
  number={4},
  pages={669--681},
  year={2007},
  publisher={Elsevier}
}

@article{Chen2014,
  title={Chromatin modifiers and remodellers: regulators of cellular differentiation},
  author={Chen, Ting and Dent, Sharon YR},
  journal={Nature reviews genetics},
  volume={15},
  number={2},
  pages={93--106},
  year={2014},
  publisher={Nature Publishing Group}
}

@article{Zaret2011,
  title={Pioneer transcription factors: establishing competence for gene expression},
  author={Zaret, Kenneth S and Carroll, Jason S},
  journal={Genes & development},
  volume={25},
  number={21},
  pages={2227--2241},
  year={2011},
  publisher={Cold Spring Harbor Laboratory Press}
}

@article{Kouzarides2007,
  title={Chromatin modifications and their function},
  author={Kouzarides, Tony},
  journal={Cell},
  volume={128},
  number={4},
  pages={693--705},
  year={2007},
  publisher={Elsevier}
}

@article{Dawson2012,
  title={Cancer epigenetics: from mechanism to therapy},
  author={Dawson, Mark A and Kouzarides, Tony},
  journal={Cell},
  volume={150},
  number={1},
  pages={12--27},
  year={2012},
  publisher={Elsevier}
}

@article{Goldberg2007,
  title={Epigenetics: a landscape takes shape},
  author={Goldberg, AD and Allis, CD and Bernstein, E},
  journal={Cell},
  volume={128},
  number={4},
  pages={635--638},
  year={2007},
  publisher={Elsevier}
}

@article{core2008nascent,
  title={Nascent RNA sequencing reveals widespread pausing and divergent initiation at human promoters},
  author={Core, Leighton J and Waterfall, Joshua J and Lis, John T},
  journal={Science},
  volume={322},
  number={5909},
  pages={1845--1848},
  year={2008},
  publisher={American Association for the Advancement of Science}
}

@article{park2018gene,
  title={Gene Expression Profiling by GRO-Seq in Single Cells},
  author={Park, Daeun and Won, Kyoung-Jae},
  journal={Methods in Molecular Biology (Clifton, N.J.)},
  volume={1722},
  pages={1--15},
  year={2018},
  publisher={Springer}
}

@article{kaya2019cut,
  title={CUT\&Tag for efficient epigenomic profiling of small samples and single cells},
  author={Kaya-Okur, Hicran S and Wu, Suzanna J and Codomo, Catherine A and Pledger, Emily S and Bryson, Timothy D and Henikoff, Jorja G},
  journal={Nature communications},
  volume={10},
  number={1},
  pages={1930},
  year={2019},
  publisher={Nature Publishing Group}
}

@article{skene2017efficient,
  title={An efficient targeted nuclease strategy for high-resolution mapping of DNA binding sites},
  author={Skene, Peter J and Henikoff, Steven},
  journal={eLife},
  volume={6},
  pages={e21856},
  year={2017},
  publisher={eLife Sciences Publications Limited}
}

@article{skene2018targeted,
  title={Targeted DamID (TaDa): A Toolbox for Selective Genome-wide Profiling of DNA- and Chromatin-binding Proteins},
  author={Skene, Peter J and Henikoff, Steven},
  journal={Current Protocols in Molecular Biology},
  volume={122},
  number={1},
  pages={e82},
  year={2018},
  publisher={Wiley Online Library}
}

@article{Qiu2017,
	title = {Reversed graph embedding resolves complex single-cell trajectories},
	volume = {14},
	issn = {1548-7105},
	doi = {10.1038/nmeth.4402},
	abstract = {Single-cell trajectories can unveil how gene regulation governs cell fate decisions. However, learning the structure of complex trajectories with multiple branches remains a challenging computational problem. We present Monocle 2, an algorithm that uses reversed graph embedding to describe multiple fate decisions in a fully unsupervised manner. We applied Monocle 2 to two studies of blood development and found that mutations in the genes encoding key lineage transcription factors divert cells to alternative fates.},
	language = {eng},
	number = {10},
	journal = {Nature Methods},
	author = {Qiu, Xiaojie and Mao, Qi and Tang, Ying and Wang, Li and Chawla, Raghav and Pliner, Hannah A. and Trapnell, Cole},
	month = oct,
	year = {2017},
	pmid = {28825705},
	pmcid = {PMC5764547},
	keywords = {Algorithms, Animals, Cell Differentiation, Computer Simulation, Gene Expression Regulation, Developmental, Models, Biological, Mutation, Transcription Factors, Transcriptome},
	pages = {979--982},
}

@article{Street2018,
	title = {Slingshot: cell lineage and pseudotime inference for single-cell transcriptomics},
	volume = {19},
	issn = {1471-2164},
	shorttitle = {Slingshot},
	doi = {10.1186/s12864-018-4772-0},
	abstract = {BACKGROUND: Single-cell transcriptomics allows researchers to investigate complex communities of heterogeneous cells. It can be applied to stem cells and their descendants in order to chart the progression from multipotent progenitors to fully differentiated cells. While a variety of statistical and computational methods have been proposed for inferring cell lineages, the problem of accurately characterizing multiple branching lineages remains difficult to solve.
RESULTS: We introduce Slingshot, a novel method for inferring cell lineages and pseudotimes from single-cell gene expression data. In previously published datasets, Slingshot correctly identifies the biological signal for one to three branching trajectories. Additionally, our simulation study shows that Slingshot infers more accurate pseudotimes than other leading methods.
CONCLUSIONS: Slingshot is a uniquely robust and flexible tool which combines the highly stable techniques necessary for noisy single-cell data with the ability to identify multiple trajectories. Accurate lineage inference is a critical step in the identification of dynamic temporal gene expression.},
	language = {eng},
	number = {1},
	journal = {BMC genomics},
	author = {Street, Kelly and Risso, Davide and Fletcher, Russell B. and Das, Diya and Ngai, John and Yosef, Nir and Purdom, Elizabeth and Dudoit, Sandrine},
	month = jun,
	year = {2018},
	pmid = {29914354},
	pmcid = {PMC6007078},
	keywords = {Cell Lineage, Cluster Analysis, Gene Expression Profiling, Humans, Myoblasts, Skeletal, Single-Cell Analysis, Software, Lineage inference, Pseudotime inference, RNA-Seq, Single cell},
	pages = {477},
}

@article{Wolf2019,
	title = {{PAGA}: graph abstraction reconciles clustering with trajectory inference through a topology preserving map of single cells},
	volume = {20},
	issn = {1474-760X},
	shorttitle = {{PAGA}},
	url = {https://doi.org/10.1186/s13059-019-1663-x},
	doi = {10.1186/s13059-019-1663-x},
	abstract = {Single-cell RNA-seq quantifies biological heterogeneity across both discrete cell types and continuous cell transitions. Partition-based graph abstraction (PAGA) provides an interpretable graph-like map of the arising data manifold, based on estimating connectivity of manifold partitions (https://github.com/theislab/paga). PAGA maps preserve the global topology of data, allow analyzing data at different resolutions, and result in much higher computational efficiency of the typical exploratory data analysis workflow. We demonstrate the method by inferring structure-rich cell maps with consistent topology across four hematopoietic datasets, adult planaria and the zebrafish embryo and benchmark computational performance on one million neurons.},
	number = {1},
	urldate = {2023-07-11},
	journal = {Genome Biology},
	author = {Wolf, F. Alexander and Hamey, Fiona K. and Plass, Mireya and Solana, Jordi and Dahlin, Joakim S. and Göttgens, Berthold and Rajewsky, Nikolaus and Simon, Lukas and Theis, Fabian J.},
	month = mar,
	year = {2019},
	pages = {59},
}

@article{Setty2019,
	title = {Characterization of cell fate probabilities in single-cell data with {Palantir}},
	volume = {37},
	copyright = {2019 The Author(s), under exclusive licence to Springer Nature America, Inc.},
	issn = {1546-1696},
	url = {https://www.nature.com/articles/s41587-019-0068-4},
	doi = {10.1038/s41587-019-0068-4},
	abstract = {Single-cell RNA sequencing studies of differentiating systems have raised fundamental questions regarding the discrete versus continuous nature of both differentiation and cell fate. Here we present Palantir, an algorithm that models trajectories of differentiating cells by treating cell fate as a probabilistic process and leverages entropy to measure cell plasticity along the trajectory. Palantir generates a high-resolution pseudo-time ordering of cells and, for each cell state, assigns a probability of differentiating into each terminal state. We apply our algorithm to human bone marrow single-cell RNA sequencing data and detect important landmarks of hematopoietic differentiation. Palantir’s resolution enables the identification of key transcription factors that drive lineage fate choice and closely track when cells lose plasticity. We show that Palantir outperforms existing algorithms in identifying cell lineages and recapitulating gene expression trends during differentiation, is generalizable to diverse tissue types, and is well-suited to resolving less-studied differentiating systems.},
	language = {en},
	number = {4},
	urldate = {2023-07-11},
	journal = {Nature Biotechnology},
	author = {Setty, Manu and Kiseliovas, Vaidotas and Levine, Jacob and Gayoso, Adam and Mazutis, Linas and Pe’er, Dana},
	month = apr,
	year = {2019},
	keywords = {Computational models, Gene regulation, Gene regulatory networks, Haematopoiesis, Machine learning},
	pages = {451--460},
}

@article{Fang2021,
	title = {Comprehensive analysis of single cell {ATAC}-seq data with {SnapATAC}},
	volume = {12},
	copyright = {2021 The Author(s)},
	issn = {2041-1723},
	url = {https://www.nature.com/articles/s41467-021-21583-9},
	doi = {10.1038/s41467-021-21583-9},
	abstract = {Identification of the cis-regulatory elements controlling cell-type specific gene expression patterns is essential for understanding the origin of cellular diversity. Conventional assays to map regulatory elements via open chromatin analysis of primary tissues is hindered by sample heterogeneity. Single cell analysis of accessible chromatin (scATAC-seq) can overcome this limitation. However, the high-level noise of each single cell profile and the large volume of data pose unique computational challenges. Here, we introduce SnapATAC, a software package for analyzing scATAC-seq datasets. SnapATAC dissects cellular heterogeneity in an unbiased manner and map the trajectories of cellular states. Using the Nyström method, SnapATAC can process data from up to a million cells. Furthermore, SnapATAC incorporates existing tools into a comprehensive package for analyzing single cell ATAC-seq dataset. As demonstration of its utility, SnapATAC is applied to 55,592 single-nucleus ATAC-seq profiles from the mouse secondary motor cortex. The analysis reveals {\textasciitilde}370,000 candidate regulatory elements in 31 distinct cell populations in this brain region and inferred candidate cell-type specific transcriptional regulators.},
	language = {en},
	number = {1},
	urldate = {2023-07-11},
	journal = {Nature Communications},
	author = {Fang, Rongxin and Preissl, Sebastian and Li, Yang and Hou, Xiaomeng and Lucero, Jacinta and Wang, Xinxin and Motamedi, Amir and Shiau, Andrew K. and Zhou, Xinzhu and Xie, Fangming and Mukamel, Eran A. and Zhang, Kai and Zhang, Yanxiao and Behrens, M. Margarita and Ecker, Joseph R. and Ren, Bing},
	month = feb,
	year = {2021},
	keywords = {Bioinformatics, Computational biology and bioinformatics, Epigenomics, Sequencing},
	pages = {1337},
}

@misc{stuartlab2023,
	title = {Analyzing {PBMC} {scATAC}-seq},
	url = {https://stuartlab.org/signac/articles/pbmc_vignette.html},
	abstract = {Signac},
	language = {en},
  year = {2023},
  month = {May},
	urldate = {2023-07-11},
}

@misc{stat115,
	title = {{STAT115} {Chapter} 21.1 {Single}-{Cell} {ATAC}-seq {Technique}},
	url = {https://www.youtube.com/watch?v=ufUVMHLDa00},
	language = {en},
  year = {2021},
	urldate = {2023-07-11},
}

@incollection{ospina2023primer,
  title={A Primer on preprocessing, visualization, clustering, and phenotyping of barcode-based spatial transcriptomics data},
  author={Ospina, Oscar and Soupir, Alex and Fridley, Brooke L},
  booktitle={Statistical Genomics},
  pages={115--140},
  year={2023},
  publisher={Springer}
}

@article{rao2021exploring,
  title={Exploring tissue architecture using spatial transcriptomics},
  author={Rao, Anjali and Barkley, Dalia and Fran{\c{c}}a, Gustavo S and Yanai, Itai},
  journal={Nature},
  volume={596},
  number={7871},
  pages={211--220},
  year={2021},
  publisher={Nature Publishing Group UK London}
}

@article{williams2022introduction,
  title={An introduction to spatial transcriptomics for biomedical research},
  author={Williams, Cameron G and Lee, Hyun Jae and Asatsuma, Takahiro and Vento-Tormo, Roser and Haque, Ashraful},
  journal={Genome Medicine},
  volume={14},
  number={1},
  pages={1--18},
  year={2022},
  publisher={BioMed Central}
}

@article{dries2021advances,
  title={Advances in spatial transcriptomic data analysis},
  author={Dries, Ruben and Chen, Jiaji and Del Rossi, Natalie and Khan, Mohammed Muzamil and Sistig, Adriana and Yuan, Guo-Cheng},
  journal={Genome research},
  volume={31},
  number={10},
  pages={1706--1718},
  year={2021},
  publisher={Cold Spring Harbor Lab}
}

@article{longo2021integrating,
  title={Integrating single-cell and spatial transcriptomics to elucidate intercellular tissue dynamics},
  author={Longo, Sophia K and Guo, Margaret G and Ji, Andrew L and Khavari, Paul A},
  journal={Nature Reviews Genetics},
  volume={22},
  number={10},
  pages={627--644},
  year={2021},
  publisher={Nature Publishing Group UK London}
}

@article{hunter2021spatially,
  title={Spatially resolved transcriptomics reveals the architecture of the tumor-microenvironment interface},
  author={Hunter, Miranda V and Moncada, Reuben and Weiss, Joshua M and Yanai, Itai and White, Richard M},
  journal={Nature communications},
  volume={12},
  number={1},
  pages={6278},
  year={2021},
  publisher={Nature Publishing Group UK London}
}

@article{ravi2022spatially,
  title={Spatially resolved multi-omics deciphers bidirectional tumor-host interdependence in glioblastoma},
  author={Ravi, Vidhya M and Will, Paulina and Kueckelhaus, Jan and Sun, Na and Joseph, Kevin and Sali{\'e}, Henrike and Vollmer, Lea and Kuliesiute, Ugne and von Ehr, Jasmin and Benotmane, Jasim K and others},
  journal={Cancer Cell},
  volume={40},
  number={6},
  pages={639--655},
  year={2022},
  publisher={Elsevier}
}

@article{hu2021spagcn,
  title={SpaGCN: Integrating gene expression, spatial location and histology to identify spatial domains and spatially variable genes by graph convolutional network},
  author={Hu, Jian and Li, Xiangjie and Coleman, Kyle and Schroeder, Amelia and Ma, Nan and Irwin, David J and Lee, Edward B and Shinohara, Russell T and Li, Mingyao},
  journal={Nature methods},
  volume={18},
  number={11},
  pages={1342--1351},
  year={2021},
  publisher={Nature Publishing Group US New York}
}

@article{xu2022deepst,
  title={DeepST: identifying spatial domains in spatial transcriptomics by deep learning},
  author={Xu, Chang and Jin, Xiyun and Wei, Songren and Wang, Pingping and Luo, Meng and Xu, Zhaochun and Yang, Wenyi and Cai, Yideng and Xiao, Lixing and Lin, Xiaoyu and others},
  journal={Nucleic Acids Research},
  volume={50},
  number={22},
  pages={e131--e131},
  year={2022},
  publisher={Oxford University Press}
}

@article{tan2020spacell,
  title={SpaCell: integrating tissue morphology and spatial gene expression to predict disease cells},
  author={Tan, Xiao and Su, Andrew and Tran, Minh and Nguyen, Quan},
  journal={Bioinformatics},
  volume={36},
  number={7},
  pages={2293--2294},
  year={2020},
  publisher={Oxford University Press}
}

@article{guilliams2022spatial,
  title={Spatial proteogenomics reveals distinct and evolutionarily conserved hepatic macrophage niches},
  author={Guilliams, Martin and Bonnardel, Johnny and Haest, Birthe and Vanderborght, Bart and Wagner, Camille and Remmerie, Anneleen and Bujko, Anna and Martens, Liesbet and Thon{\'e}, Tinne and Browaeys, Robin and others},
  journal={Cell},
  volume={185},
  number={2},
  pages={379--396},
  year={2022},
  publisher={Elsevier}
}

@article{wu2021single,
  title={A single-cell and spatially resolved atlas of human breast cancers},
  author={Wu, Sunny Z and Al-Eryani, Ghamdan and Roden, Daniel Lee and Junankar, Simon and Harvey, Kate and Andersson, Alma and Thennavan, Aatish and Wang, Chenfei and Torpy, James R and Bartonicek, Nenad and others},
  journal={Nature genetics},
  volume={53},
  number={9},
  pages={1334--1347},
  year={2021},
  publisher={Nature Publishing Group US New York}
}

@article{lyubetskaya2022assessment,
  title={Assessment of spatial transcriptomics for oncology discovery},
  author={Lyubetskaya, Anna and Rabe, Brian and Fisher, Andrew and Lewin, Anne and Neuhaus, Isaac and Brett, Constance and Brett, Todd and Pereira, Ethel and Golhar, Ryan and Kebede, Sami and others},
  journal={Cell Reports Methods},
  volume={2},
  number={11},
  year={2022},
  publisher={Elsevier}
}

@article{zhang2022clinical,
  title={Clinical and translational values of spatial transcriptomics},
  author={Zhang, Linlin and Chen, Dongsheng and Song, Dongli and Liu, Xiaoxia and Zhang, Yanan and Xu, Xun and Wang, Xiangdong},
  journal={Signal Transduction and Targeted Therapy},
  volume={7},
  number={1},
  pages={111},
  year={2022},
  publisher={Nature Publishing Group UK London}
}

@article{raredon2023comprehensive,
  title={Comprehensive visualization of cell--cell interactions in single-cell and spatial transcriptomics with NICHES},
  author={Raredon, Micha Sam Brickman and Yang, Junchen and Kothapalli, Neeharika and Lewis, Wesley and Kaminski, Naftali and Niklason, Laura E and Kluger, Yuval},
  journal={Bioinformatics},
  volume={39},
  number={1},
  pages={btac775},
  year={2023}
}

@article{wang2023promising,
  title={The Promising Application of Cell-cell Interaction Analysis in Cancer From Single-cell and Spatial Transcriptomics},
  author={Wang, Xinyi and Almet, Axel A and Nie, Qing},
  booktitle={Seminars in Cancer Biology},
  year={2023}
}

@article{bergholtz2021best,
  title={Best practices for spatial profiling for breast cancer research with the GeoMx{\textregistered} digital spatial profiler},
  author={Bergholtz, Helga and Carter, Jodi M and Cesano, Alessandra and Cheang, Maggie Chon U and Church, Sarah E and Divakar, Prajan and Fuhrman, Christopher A and Goel, Shom and Gong, Jingjing and Guerriero, Jennifer L and others},
  journal={Cancers},
  volume={13},
  number={17},
  pages={4456},
  year={2021}
}

@article{yue2023guidebook,
  title={A guidebook of spatial transcriptomic technologies, data resources and analysis approaches},
  author={Yue, Liangchen and Liu, Feng and Hu, Jiongsong and Yang, Pin and Wang, Yuxiang and Dong, Junguo and Shu, Wenjie and Huang, Xingxu and Wang, Shengqi},
  journal={Computational and Structural Biotechnology Journal},
  year={2023},
  publisher={Elsevier}
}

@article{wang2021spatial,
  title={Spatial transcriptomics and proteomics technologies for deconvoluting the tumor microenvironment},
  author={Wang, Nan and Li, Xia and Wang, Rongshui and Ding, Zhiyong},
  journal={Biotechnology journal},
  volume={16},
  number={9},
  pages={2100041},
  year={2021},
  publisher={Wiley Online Library}
}

@article{he2022high,
  title={High-plex imaging of RNA and proteins at subcellular resolution in fixed tissue by spatial molecular imaging},
  author={He, Shanshan and Bhatt, Ruchir and Brown, Carl and Brown, Emily A and Buhr, Derek L and Chantranuvatana, Kan and Danaher, Patrick and Dunaway, Dwayne and Garrison, Ryan G and Geiss, Gary and others},
  journal={Nature Biotechnology},
  volume={40},
  number={12},
  pages={1794--1806},
  year={2022},
  publisher={Nature Publishing Group US New York}
}

@article{zhang2021spatially,
  title={Spatially resolved cell atlas of the mouse primary motor cortex by MERFISH},
  author={Zhang, Meng and Eichhorn, Stephen W and Zingg, Brian and Yao, Zizhen and Cotter, Kaelan and Zeng, Hongkui and Dong, Hongwei and Zhuang, Xiaowei},
  journal={Nature},
  volume={598},
  number={7879},
  pages={137--143},
  year={2021},
  publisher={Nature Publishing Group UK London}
}

@article{staahl2016visualization,
  title={Visualization and analysis of gene expression in tissue sections by spatial transcriptomics},
  author={St{\aa}hl, Patrik L and Salm{\'e}n, Fredrik and Vickovic, Sanja and Lundmark, Anna and Navarro, Jos{\'e} Fern{\'a}ndez and Magnusson, Jens and Giacomello, Stefania and Asp, Michaela and Westholm, Jakub O and Huss, Mikael and others},
  journal={Science},
  volume={353},
  number={6294},
  pages={78--82},
  year={2016},
  publisher={American Association for the Advancement of Science}
}

@article{zhao2022modeling,
  title={Modeling zero inflation is not necessary for spatial transcriptomics},
  author={Zhao, Peiyao and Zhu, Jiaqiang and Ma, Ying and Zhou, Xiang},
  journal={Genome Biology},
  volume={23},
  number={1},
  pages={118},
  year={2022},
  publisher={Springer}
}

@article{hafemeister2019normalization,
  title={Normalization and variance stabilization of single-cell RNA-seq data using regularized negative binomial regression},
  author={Hafemeister, Christoph and Satija, Rahul},
  journal={Genome biology},
  volume={20},
  number={1},
  pages={296},
  year={2019},
  publisher={Springer}
}