% todo sort alphabetically % seperate online sources @Article{alok17, author = {A. Al-Okaily and B. Almarri and S. Yami and C. Huang}, date = {2017-04-01}, journaltitle = {Journal of Computational Biology}, title = {Toward a Better Compression for {DNA} Sequences Using Huffman Encoding}, doi = {10.1089/cmb.2016.0151}, number = {4}, pages = {280--288}, volume = {24}, publisher = {Mary Ann Liebert Inc.}, } @Article{Cock_2009, author = {P. Cock and C. Fields and N. Goto and M. Heuer and P. Rice}, date = {2009-12}, journaltitle = {Nucleic Acids Research}, title = {The Sanger {FASTQ} file format for sequences with quality scores, and the Solexa/Illumina {FASTQ} variants}, doi = {10.1093/nar/gkp1137}, number = {6}, pages = {1767--1771}, volume = {38}, publisher = {Oxford University Press ({OUP})}, } @Article{cells, author = {E. Bianconi and A. Piovesan and F. Facchin and A. Beraudi and R. Casadei and F. Frabetti and L. Vitale and M. Pelleri and S. Tassani and F. Piva and S. Perez-Amodio and P. Strippoli and S. Canaider}, date = {2013-07}, journaltitle = {Annals of Human Biology}, title = {An estimation of the number of cells in the human body}, doi = {10.3109/03014460.2013.807878}, number = {6}, pages = {463--471}, volume = {40}, publisher = {Informa {UK} Limited}, } @Article{dna_structure, author = {J. Watson and F. Crick}, date = {1953-04}, journaltitle = {Nature}, title = {Molecular Structure of Nucleic Acids: A Structure for Deoxyribose Nucleic Acid}, doi = {10.1038/171737a0}, number = {4356}, pages = {737--738}, volume = {171}, publisher = {Springer Science and Business Media {LLC}}, } @Article{iupac, author = {A. Johnson}, date = {2010-03}, journaltitle = {Bioinformatics}, title = {An extended {IUPAC} nomenclature code for polymorphic nucleic acids}, doi = {10.1093/bioinformatics/btq098}, number = {10}, pages = {1386--1389}, volume = {26}, publisher = {Oxford University Press ({OUP})}, } @TechReport{rfc1951, author = {P. Deutsch}, date = {1996-05}, title = {{DEFLATE} Compressed Data Format Specification version 1.3}, doi = {10.17487/rfc1951}, url = {https://www.rfc-editor.org/rfc/rfc1951}, publisher = {{RFC} Editor}, } @Article{Shannon_1948, author = {C. E. Shannon}, date = {1948-07}, journaltitle = {Bell System Technical Journal}, title = {A Mathematical Theory of Communication}, doi = {10.1002/j.1538-7305.1948.tb01338.x}, number = {3}, pages = {379--423}, volume = {27}, publisher = {Institute of Electrical and Electronics Engineers ({IEEE})}, } @InProceedings{compr-visual, author = {S. Khuri and H. Hsu}, booktitle = {Proceedings of the 2000 {ACM} symposium on Applied computing - {SAC} {\textquotesingle}00}, date = {2000}, title = {Tools for visualizing text compression algorithms}, doi = {10.1145/335603.335716}, publisher = {{ACM} Press}, } @Article{lcqs, author = {J. Fu and B. Ke and S. Dong}, date = {2020-03}, journaltitle = {{BMC} Bioinformatics}, title = {{LCQS}: an efficient lossless compression tool of quality scores with random access functionality}, doi = {10.1186/s12859-020-3428-7}, number = {1}, volume = {21}, publisher = {Springer Science and Business Media {LLC}}, } @Book{delfs_knebl, author = {H. Delfs and H. Knebl}, date = {2007}, title = {Introduction to Cryptography}, isbn = {9783540492436}, pages = {368}, publisher = {Springer}, subtitle = {Principles and Applications (Information Security and Cryptography)}, } @Article{cc14, author = {K. Sailunaz and M. Kotwal and M. Huda}, date = {2014-03}, journaltitle = {International Journal of Computer Applications}, title = {Data Compression Considering Text Files}, doi = {10.5120/15765-4456}, number = {11}, pages = {27--32}, volume = {90}, publisher = {Foundation of Computer Science}, } @Article{cnet13, author = {M. RajShivare and Y. Maravi and S. Sharma}, date = {2013-10}, journaltitle = {International Journal of Computer Applications}, title = {Analysis of Header Compression Techniques for Networks: A Review}, doi = {10.5120/13856-1701}, number = {5}, pages = {13--20}, volume = {80}, publisher = {Foundation of Computer Science}, } @TechReport{rfcgzip, author = {P. Deutsch and J. Gailly and M. Adler and P. Deutsch and G. Randers-Pehrson}, date = {1996-05}, title = {GZIP file format specification version 4.3}, number = {1952}, type = {RFC}, howpublished = {Internet Requests for Comments}, issn = {2070-1721}, month = {May}, publisher = {RFC}, year = {1996}, } @Article{huf52, author = {D. A. Huffman}, title = {A Method for the Construction of Minimum-Redundancy Codes}, number = {9}, pages = {1098-1101}, volume = {40}, added-at = {2009-01-14T00:43:43.000+0100}, description = {dret'd bibliography}, interhash = {d00a180c1c2e7851560c2d51e0fd8f92}, intrahash = {585b817b85d7278b868329672ddded96}, journal = {Proceedings of the Institute of Radio Engineers}, keywords = {imported}, month = {September}, timestamp = {2009-01-14T00:43:44.000+0100}, uri = {http://compression.graphicon.ru/download/articles/huff/huffman_1952_minimum-redundancy-codes.pdf}, year = {1952}, } @Article{moffat20, author = {A. Moffat}, date = {2020-07}, journaltitle = {{ACM} Computing Surveys}, title = {Huffman Coding}, doi = {10.1145/3342555}, number = {4}, pages = {1--35}, volume = {52}, publisher = {Association for Computing Machinery ({ACM})}, } @Article{moffat_arith, author = {A. Moffat and R. Neal and I. Witten}, date = {1998-07}, journaltitle = {{ACM} Transactions on Information Systems}, title = {Arithmetic coding revisited}, doi = {10.1145/290159.290162}, number = {3}, pages = {256--294}, volume = {16}, publisher = {Association for Computing Machinery ({ACM})}, } @Article{ris76, author = {J. Rissanen}, date = {1976-05}, journaltitle = {{IBM} Journal of Research and Development}, title = {Generalized Kraft Inequality and Arithmetic Coding}, doi = {10.1147/rd.203.0198}, number = {3}, pages = {198--203}, volume = {20}, publisher = {{IBM}}, } @Article{ieee-float, title = {IEEE Standard for Floating-Point Arithmetic}, doi = {10.1109/IEEESTD.2019.8766229}, pages = {1-84}, journal = {IEEE Std 754-2019 (Revision of IEEE 754-2008)}, year = {2019}, } @Article{big-o, author = {M. Firdous and A. Rouf}, title = {The Big-O of Mathematics and Computer Science}, doi = {10.26855/jamc.2022.03.001}, pages = {1-3}, volume = {6}, month = {01}, year = {2022}, } @Article{sam12, author = {P. Danecek and J. Bonfield and J. Liddle and J. Marshall and V. Ohan and M. Pollard and A. Whitwham and T. Keane and S. McCarthy and R. Davies and H. Li}, date = {2021-01}, journaltitle = {{GigaScience}}, title = {Twelve years of {SAMtools} and {BCFtools}}, doi = {10.1093/gigascience/giab008}, number = {2}, volume = {10}, publisher = {Oxford University Press ({OUP})}, } @Article{cram-origin, author = {M. Fritz and R. Leinonen and G. Cochrane and E. Birney}, date = {2011-01}, journaltitle = {Genome Research}, title = {Efficient storage of high throughput {DNA} sequencing data using reference-based compression}, doi = {10.1101/gr.114819.110}, number = {5}, pages = {734--740}, volume = {21}, publisher = {Cold Spring Harbor Laboratory}, } @TechReport{rfcansi, author = {K. Simonsen}, series = {Request for Comments}, number = {1345}, howpublished = {RFC 1345}, publisher = {RFC Editor}, doi = {10.17487/RFC1345}, url = {https://www.rfc-editor.org/info/rfc1345}, title = {{Character Mnemonics and Character Sets}}, pagetotal = {103}, year = {1992}, month = {jun}, } @Article{witten87, author = {I. Witten and R. Neal and J. Cleary}, date = {1987-06}, journaltitle = {Communications of the {ACM}}, title = {Arithmetic coding for data compression}, doi = {10.1145/214762.214771}, issn = {0001-0782}, number = {6}, pages = {520–540}, url = {https://doi.org/10.1145/214762.214771}, volume = {30}, abstract = {The state of the art in data compression is arithmetic coding, not the better-known Huffman method. Arithmetic coding gives greater compression, is faster for adaptive models, and clearly separates the model from the channel encoding.}, address = {New York, NY, USA}, issue_date = {June 1987}, journal = {Commun. ACM}, month = {jun}, numpages = {21}, publisher = {Association for Computing Machinery ({ACM})}, year = {1987}, } @InProceedings{geco, author = {D. Pratas and A. Pinho and P. Ferreira}, booktitle = {2016 Data Compression Conference ({DCC})}, date = {2016-03}, title = {Efficient Compression of Genomic Sequences}, doi = {10.1109/DCC.2016.60}, publisher = {{IEEE}}, } @Article{survey, author = {M. Hosseini and D. Pratas and A. Pinho}, date = {2016-10}, journaltitle = {Information}, title = {A Survey on Data Compression Methods for Biological Sequences}, doi = {10.3390/info7040056}, number = {4}, pages = {56}, volume = {7}, publisher = {{MDPI} {AG}}, } @Article{vertical, author = {K. Kredens and J. Martins and O. Dordal and M. Ferrandin and R. Herai and E. Scalabrin and B. {\'{A}}vila}, date = {2020-05}, journaltitle = {{PLOS} {ONE}}, title = {Vertical lossless genomic data compression tools for assembled genomes: A systematic literature review}, doi = {10.1371/journal.pone.0232942}, editor = {Rashid Mehmood}, number = {5}, pages = {e0232942}, volume = {15}, publisher = {Public Library of Science ({PLoS})}, } @TechReport{isompeg, author = {{ISO Central Secretary}}, date = {2020-10}, institution = {International Organization for Standardization}, title = {MPGE-G}, language = {en}, number = {ISO/IEC 23092-1:2020}, type = {Standard}, url = {https://www.iso.org/standard/23092.html}, year = {2019}, } @ARTICLE{9455132, author={J. Voges and M. Hernaez and M. Mattavelli and J. Ostermann}, journal={Proceedings of the IEEE}, title={An Introduction to MPEG-G: The First Open ISO/IEC Standard for the Compression and Exchange of Genomic Sequencing Data}, year={2021}, volume={109}, number={9}, pages={1607-1622}, doi={10.1109/JPROC.2021.3082027} } @Article{haplo, author = {W. Low and R. Tearle and R. Liu and S. Koren and A. Rhie and D. Bickhart and B. Rosen and Z. Kronenberg and S. Kingan and E. Tseng and F. Thibaud-Nissen and F. Martin and K. Billis and J. Ghurye and A. Hastie and J. Lee and A. Pang and M. Heaton and A. Phillippy and S. Hiendleder and T. Smith and J. Williams}, date = {2020-04}, journaltitle = {Nature Communications}, title = {Haplotype-resolved genomes provide insights into structural variation and gene content in Angus and Brahman cattle}, doi = {10.1038/s41467-020-15848-y}, number = {1}, volume = {11}, publisher = {Springer Science and Business Media {LLC}}, } @Article{pet21, author = {S. Petoukhov}, date = {2021-10}, title = {Tensor Rules in the Stochastic Organization of Genomes and Genetic Stochastic Resonance in Algebraic Biology}, doi = {10.20944/preprints202110.0093.v1}, publisher = {{MDPI} {AG}}, } @TechReport{iso-ascii, author = {ISO/IEC JTC 1/SC 2 Coded character sets}, date = {1998-04}, institution = {International Organization for Standardization}, title = {Information technology — 8-bit single-byte coded graphic character sets — Part 1: Latin alphabet No. 1}, type = {Standard}, address = {Geneva, CH}, key = {ISO8859-1:1998}, volume = {1998}, year = {1998}, } @Book{dict, author = {C. McIntosh}, date = {2013}, title = {Cambridge International Dictionary of English}, isbn = {9781107035157}, pages = {1856}, publisher = {Cambridge University Press}, } @TechReport{rfc-udp, author = {J. Postel}, date = {1980-08-28}, institution = {RFC Editor}, title = {User Datagram Protocol}, doi = {10.17487/RFC0768}, number = {768}, pagetotal = {3}, url = {https://www.rfc-editor.org/info/rfc768}, howpublished = {RFC 768}, month = {aug}, publisher = {RFC Editor}, series = {Request for Comments}, year = {1980}, } @TechReport{isoutf, author = {ISO/IEC JTC 1/SC 2 Coded character sets}, title = {ISO/IEC 10646:2020 UTF}, date = {2020-12}, institution = {International Organization for Standardization}, title = {Information technology — Universal coded character set (UCS)}, type = {Standard}, address = {Geneva, CH}, key = {ISO10646:2020}, } @Article{lz77, author = {Ziv, J. and Lempel, A.}, title = {A universal algorithm for sequential data compression}, doi = {10.1109/TIT.1977.1055714}, number = {3}, pages = {337-343}, volume = {23}, journal = {IEEE Transactions on Information Theory}, year = {1977}, } @Article{wang_22, author = {S. Wang and C. Gao and Y. Zheng and L. Yi and J. Lu and X. Huang and J. Cai and P. Zhang and Y. Cui and A. Ke}, date = {2022-02}, journaltitle = {Molecular Cancer}, title = {Current applications and future perspective of {CRISPR}/Cas9 gene editing in cancer}, doi = {10.1186/s12943-022-01518-8}, number = {1}, volume = {21}, publisher = {Springer Science and Business Media {LLC}}, } @Article{ju_21, author = {Philomin, J. and R. Singh and J. Poland and S. Shrestha and J. Huerta-Espino and V. Govindan and S. Mondal and L. Crespo-Herrera and U. Kumar and A. Joshi and T. Payne and P. Bhati and V. Tomar and F. Consolacion and J. Serna}, date = {2021-03}, journaltitle = {Scientific Reports}, title = {Elucidating the genetics of grain yield and stress-resilience in bread wheat using a large-scale genome-wide association mapping study with 55,568 lines}, doi = {10.1038/s41598-021-84308-4}, number = {1}, volume = {11}, publisher = {Springer Science and Business Media {LLC}}, } @Article{mo_83, author = {A. Motulsky}, date = {1983-01}, journaltitle = {Science}, title = {Impact of Genetic Manipulation on Society and Medicine}, doi = {10.1126/science.6336852}, number = {4581}, pages = {135--140}, volume = {219}, publisher = {American Association for the Advancement of Science ({AAAS})}, } @Online{ftp-igsr, date = {2022-11-10}, title = {IGSR: The International Genome Sample Resource}, url = {https://ftp.1000genomes.ebi.ac.uk}, } @Online{ftp-ncbi, date = {2022-11-01}, title = {NCBI National Center for Biotechnology Information}, url = {https://ftp.ncbi.nlm.nih.gov/genomes/}, } @Online{ftp-ensembl, date = {2022-10-15}, title = {ENSEMBL Rapid Release}, url = {https://ftp.ensembl.org}, } @Book{cthreading, author = {Quinn, Michael J.}, title = {Parallel Programming in C with MPI and OpenMP}, isbn = {0071232656}, publisher = {McGraw-Hill Education Group}, year = {2003}, } @Online{geco-repo, author = {Cobilab}, date = {2022-11-19}, title = {Repositories for the three versions of GeCo}, url = {https://github.com/cobilab}, } @Online{code-analysis, author = {Ryan Dewhurst}, date = {2022-11-20}, editor = {Kirsten S and Nick Bloor and Sarah Baso and James Bowie and Evgeniy Ryzhkov and Iberiam and Ann Campbell and Jonathan Marcil and Christina Schelin and Jie Wang and Fabian and Achim and Dirk Wetter}, title = {Static Code Analysis}, url = {https://owasp.org/www-community/controls/Static_Code_Analysis}, } @Online{gpl, title = {GNU Public License}, url = {http://www.gnu.org/licenses/gpl-3.0.html}, } @Online{mitlic, title = {MIT License}, url = {https://spdx.org/licenses/MIT.html}, } @Online{bam, author = {The SAM/BAM Format Specification Working Group}, date = {2022-08-22}, title = {Sequence Alignment/Map Format Specification}, url = {https://github.com/samtools/hts-specs}, urldate = {2022-09-12}, version = {44b4167}, } @Online{ucsc, author = {UCSC - University of California, Santa Cruz}, date = {2022-10-28}, title = {UCSC Genome Browser}, url = {https://genome.ucsc.edu/}, urldate = {2022-10-28}, } @Online{ensembl, author = {P. Flicek}, date = {2022-10-24}, title = {ENSEMBL Project}, url = {http://www.ensembl.org/}, } @Online{ga4gh, date = {2022-10-10}, title = {Global Alliance for Genomics and Health}, url = {https://github.com/samtools/hts-specs.}, } @Online{bed, author = {Sanger Institute, Genome Research Limited}, date = {2022-10-20}, title = {BED Browser Extensible Data}, url = {https://samtools.github.io/hts-specs/BEDv1.pdf}, } @Online{illufastq, author = {Illumina}, date = {2022-11-17}, title = {Illumina FASTq file structure explained}, url = {https://support.illumina.com/bulletins/2016/04/fastq-files-explained.html}, } @Online{twobit, date = {2022-09-22}, editor = {UCSC University of California Sata Cruz}, title = {TwoBit File Format}, url = {https://genome-source.gi.ucsc.edu/gitlist/kent.git/raw/master/src/inc/twoBit.h}, } @Comment{jabref-meta: databaseType:biblatex;}