{"id":"https://openalex.org/W6944039822","doi":"https://doi.org/10.15488/12422","title":"Compression of DNA sequencing data","display_name":"Compression of DNA sequencing data","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W6944039822","doi":"https://doi.org/10.15488/12422"},"language":"en","primary_location":{"id":"pmh:oai:www.repo.uni-hannover.de:123456789/12521","is_oa":false,"landing_page_url":"https://www.repo.uni-hannover.de/handle/123456789/12521","pdf_url":null,"source":{"id":"https://openalex.org/S4306401575","display_name":"Institutional Repository of Leibniz Universit\u00e4t Hannover (Leibniz Universit\u00e4t Hannover)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114112103","host_organization_name":"Leibniz University Hannover","host_organization_lineage":["https://openalex.org/I114112103"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/DoctoralThesis"},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.15488/12422","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Voges, Jan","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Voges, Jan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.30593229,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9363999962806702,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9363999962806702,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10741","display_name":"Video Coding and Compression Technologies","score":0.007899999618530273,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10901","display_name":"Advanced Data Compression Techniques","score":0.0052999998442828655,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.6808000206947327},{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.5062000155448914},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.4950000047683716},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.45680001378059387},{"id":"https://openalex.org/keywords/dna-sequencing","display_name":"DNA sequencing","score":0.4471000134944916},{"id":"https://openalex.org/keywords/data-compression-ratio","display_name":"Data compression ratio","score":0.40450000762939453},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.39469999074935913},{"id":"https://openalex.org/keywords/rate\u2013distortion-theory","display_name":"Rate\u2013distortion theory","score":0.3855000138282776},{"id":"https://openalex.org/keywords/reference-genome","display_name":"Reference genome","score":0.3587999939918518},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.32749998569488525},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.3206999897956848}],"concepts":[{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.6808000206947327},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6496000289916992},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5667999982833862},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.5062000155448914},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4950000047683716},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.45680001378059387},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.4471000134944916},{"id":"https://openalex.org/C94835093","wikidata":"https://www.wikidata.org/wiki/Q3113333","display_name":"Data compression ratio","level":5,"score":0.40450000762939453},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.39469999074935913},{"id":"https://openalex.org/C64185310","wikidata":"https://www.wikidata.org/wiki/Q843483","display_name":"Rate\u2013distortion theory","level":3,"score":0.3855000138282776},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3734000027179718},{"id":"https://openalex.org/C192953774","wikidata":"https://www.wikidata.org/wiki/Q7307127","display_name":"Reference genome","level":4,"score":0.3587999939918518},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.32749998569488525},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3206999897956848},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.31200000643730164},{"id":"https://openalex.org/C81081738","wikidata":"https://www.wikidata.org/wiki/Q55542","display_name":"Lossless compression","level":3,"score":0.296999990940094},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.29409998655319214},{"id":"https://openalex.org/C25797200","wikidata":"https://www.wikidata.org/wiki/Q828137","display_name":"Compression ratio","level":3,"score":0.2928999960422516},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.28630000352859497},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27630001306533813},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.2750999927520752},{"id":"https://openalex.org/C165021410","wikidata":"https://www.wikidata.org/wiki/Q55564","display_name":"Lossy compression","level":2,"score":0.27379998564720154},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.2727999985218048},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.2703999876976013},{"id":"https://openalex.org/C132917006","wikidata":"https://www.wikidata.org/wiki/Q5250436","display_name":"Deep sequencing","level":4,"score":0.2703999876976013},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.2687999904155731},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.2671000063419342},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.26080000400543213},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.2578999996185303},{"id":"https://openalex.org/C53533937","wikidata":"https://www.wikidata.org/wiki/Q185020","display_name":"Histogram","level":3,"score":0.2549999952316284},{"id":"https://openalex.org/C50056821","wikidata":"https://www.wikidata.org/wiki/Q774502","display_name":"Rate\u2013distortion optimization","level":5,"score":0.2498999983072281},{"id":"https://openalex.org/C18949551","wikidata":"https://www.wikidata.org/wiki/Q740578","display_name":"Sequence assembly","level":5,"score":0.24969999492168427},{"id":"https://openalex.org/C1769480","wikidata":"https://www.wikidata.org/wiki/Q1345239","display_name":"Entropy encoding","level":3,"score":0.24860000610351562},{"id":"https://openalex.org/C20556612","wikidata":"https://www.wikidata.org/wiki/Q4469374","display_name":"Volume (thermodynamics)","level":2,"score":0.24570000171661377},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.23759999871253967},{"id":"https://openalex.org/C175732694","wikidata":"https://www.wikidata.org/wiki/Q1128713","display_name":"Context-adaptive binary arithmetic coding","level":3,"score":0.2296999990940094},{"id":"https://openalex.org/C202887219","wikidata":"https://www.wikidata.org/wiki/Q3895221","display_name":"Parametrization (atmospheric modeling)","level":3,"score":0.2289000004529953},{"id":"https://openalex.org/C2778192920","wikidata":"https://www.wikidata.org/wiki/Q16874989","display_name":"Signal compression","level":4,"score":0.22859999537467957},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.22840000689029694},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.2282000035047531}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:www.repo.uni-hannover.de:123456789/12521","is_oa":false,"landing_page_url":"https://www.repo.uni-hannover.de/handle/123456789/12521","pdf_url":null,"source":{"id":"https://openalex.org/S4306401575","display_name":"Institutional Repository of Leibniz Universit\u00e4t Hannover (Leibniz Universit\u00e4t Hannover)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114112103","host_organization_name":"Leibniz University Hannover","host_organization_lineage":["https://openalex.org/I114112103"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/DoctoralThesis"},{"id":"doi:10.15488/12422","is_oa":true,"landing_page_url":"https://doi.org/10.15488/12422","pdf_url":null,"source":{"id":"https://openalex.org/S7407052956","display_name":"Leibniz Universit\u00e4t Hannover","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"doi:10.15488/12422","is_oa":true,"landing_page_url":"https://doi.org/10.15488/12422","pdf_url":null,"source":{"id":"https://openalex.org/S7407052956","display_name":"Leibniz Universit\u00e4t Hannover","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"With":[0,175],"the":[1,4,10,32,35,44,65,87,114,119,122,127,143,154,173,183,208,220,239,254,257,262,292],"release":[2],"of":[3,7,12,37,46,49,67,73,89,113,121,147,157,201,229,242,256,281,291,298],"latest":[5],"generations":[6],"sequencing":[8,13,39,75],"machines,":[9],"cost":[11],"a":[14,84,101,140,196,211],"whole":[15],"human":[16],"genome":[17],"has":[18],"dropped":[19],"to":[20,31,100,118,170,181,186,216,247,253,273],"less":[21],"than":[22],"US$1,000.":[23],"The":[24,77,104,235],"potential":[25],"applications":[26],"in":[27,80,219,279,296,300],"several":[28],"fields":[29],"lead":[30,215],"forecast":[33],"that":[34,96,152,167,269],"amount":[36],"DNA":[38,74],"data":[40,61,184,209],"will":[41],"soon":[42],"surpass":[43],"volume":[45],"other":[47],"types":[48],"data,":[50],"such":[51],"as":[52,210],"video":[53],"data.":[54,76],"In":[55],"this":[56,81],"dissertation,":[57],"we":[58,162,193,287],"present":[59],"novel":[60],"compression":[62,88,107,146,264,283],"technologies":[63],"with":[64],"aim":[66],"enhancing":[68],"storage,":[69],"transmission,":[70],"and":[71,133,145,268,284,295],"processing":[72],"first":[78,240],"contribution":[79,138,237],"dissertation":[82],"is":[83,139,179,238],"method":[85,105,125,141,177,260,272],"for":[86,142,199],"aligned":[90,99],"reads,":[91],"i.e.,":[92,150],"read-out":[93,159],"sequence":[94],"fragments":[95],"have":[97,304],"been":[98,305],"reference":[102],"sequence.":[103],"improves":[106],"by":[108],"implicitly":[109],"assembling":[110],"local":[111],"parts":[112],"underlying":[115],"sequences.":[116],"Compared":[117],"state":[120,255],"art,":[123,258],"our":[124,176,202,259,271,302],"achieves":[126,225,261],"best":[128,263],"trade-off":[129],"between":[130],"memory":[131],"usage":[132],"compressed":[134],"size.":[135],"Our":[136],"second":[137],"quantization":[144],"quality":[148,190,233],"scores,":[149],"values":[151],"quantify":[153],"error":[155],"probability":[156],"each":[158],"base.":[160],"Specifically,":[161],"propose":[163],"two":[164],"Bayesian":[165],"models":[166,203],"are":[168],"used":[169],"precisely":[171],"control":[172],"quantization.":[174],"it":[178],"possible":[180],"compress":[182],"down":[185],"0.15":[187],"bit":[188,231],"per":[189,232],"score.":[191,234],"Notably,":[192],"can":[194],"recommend":[195],"particular":[197,297],"parametrization":[198,224],"one":[200],"which\u2014by":[204],"removing":[205],"noise":[206],"from":[207],"side":[212],"effect\u2014does":[213],"not":[214],"any":[217],"degradation":[218],"distortion":[221],"metric.":[222],"This":[223],"an":[226,243,289],"average":[227],"rate":[228],"0.45":[230],"third":[236],"implementation":[241],"entropy":[244],"codec":[245],"compliant":[246],"MPEG-G.":[248],"We":[249],"show":[250],"that,":[251],"compared":[252],"ranks":[265],"on":[266],"average,":[267],"adding":[270],"CRAM":[274],"would":[275],"be":[276],"beneficial":[277],"both":[278],"terms":[280],"achievable":[282],"speed.":[285],"Finally,":[286],"provide":[288],"overview":[290],"standardization":[293],"landscape,":[294],"MPEG-G,":[299],"which":[301],"contributions":[303],"integrated.":[306]},"counts_by_year":[],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}