{"id":"https://openalex.org/W57114836","doi":null,"title":"Algorithms for Next-Generation High-Throughput Sequencing Technologies","display_name":"Algorithms for Next-Generation High-Throughput Sequencing Technologies","publication_year":2011,"publication_date":"2011-01-01","ids":{"openalex":"https://openalex.org/W57114836","mag":"57114836"},"language":"en","primary_location":{"id":"pmh:oai:escholarship.org/ark:/13030/qt86b9c87d","doi":null,"is_oa":true,"landing_page_url":"https://escholarship.org/uc/item/86b9c87d","pdf_url":"https://escholarship.org/uc/item/86b9c87d","source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"etd"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://escholarship.org/uc/item/86b9c87d","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Wei\u2010Chun Kao","orcid":"https://orcid.org/0000-0001-8687-6334","observed_orcids":["https://orcid.org/0000-0001-8687-6334"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Wei\u2010Chun Kao","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-8687-6334","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.000699999975040555,"subfield":{"id":"https://openalex.org/subfields/2614","display_name":"Theoretical Computer Science"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12946","display_name":"Fractal and DNA sequence analysis","score":0.00019999999494757503,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/base-calling","display_name":"base calling","score":0.718999981880188},{"id":"https://openalex.org/keywords/sequencing-error-correction","display_name":"sequencing error correction","score":0.6940000057220459},{"id":"https://openalex.org/keywords/next-generation-sequencing","display_name":"next-generation sequencing","score":0.703000009059906},{"id":"https://openalex.org/keywords/echo","display_name":"echo","score":0.5669999718666077},{"id":"https://openalex.org/keywords/single-nucleotide-polymorphism-detection","display_name":"single nucleotide polymorphism detection","score":0.8349999785423279},{"id":"https://openalex.org/keywords/genome-assembly","display_name":"genome assembly","score":0.7279999852180481},{"id":"https://openalex.org/keywords/de-novo-sequencing","display_name":"de novo sequencing","score":0.7730000019073486},{"id":"https://openalex.org/keywords/parameter-optimization","display_name":"parameter optimization","score":0.6050000190734863},{"id":"https://openalex.org/keywords/statistical-models","display_name":"statistical models","score":0.6000000238418579}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7060983777046204},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.6102964878082275},{"id":"https://openalex.org/C113425843","wikidata":"https://www.wikidata.org/wiki/Q5953213","display_name":"Hybrid genome assembly","level":5,"score":0.477098286151886},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4749836325645447},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.4566132724285126},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.428110808134079},{"id":"https://openalex.org/C18949551","wikidata":"https://www.wikidata.org/wiki/Q740578","display_name":"Sequence assembly","level":5,"score":0.4240038990974426},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.42245718836784363},{"id":"https://openalex.org/C192953774","wikidata":"https://www.wikidata.org/wiki/Q7307127","display_name":"Reference genome","level":4,"score":0.37209758162498474},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.1296989917755127},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"score":0.0},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.0},{"id":"https://openalex.org/C162317418","wikidata":"https://www.wikidata.org/wiki/Q252857","display_name":"Transcriptome","level":4,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"pmh:oai:escholarship.org/ark:/13030/qt86b9c87d","doi":null,"is_oa":true,"landing_page_url":"https://escholarship.org/uc/item/86b9c87d","pdf_url":"https://escholarship.org/uc/item/86b9c87d","source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"etd"},{"id":"pmh:qt86b9c87d","doi":null,"is_oa":true,"landing_page_url":"http://www.escholarship.org/uc/item/86b9c87d","pdf_url":"http://www.escholarship.org/uc/item/86b9c87d","source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Kao, Wei-Chun. (2011). Algorithms for Next-Generation High-Throughput Sequencing Technologies. UC Berkeley: Electrical Engineering & Computer Sciences. Retrieved from: http://www.escholarship.org/uc/item/86b9c87d","raw_type":"dissertation"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.406.173","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.406.173","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.eecs.berkeley.edu/Pubs/TechRpts/2011/EECS-2011-99.pdf","raw_type":"text"},{"id":"pmh:oai:berkeley.edu:28722-bk0009t0f1t","doi":null,"is_oa":false,"landing_page_url":"http://techreports.lib.berkeley.edu/accessPages/EECS-2011-99.html","pdf_url":null,"source":{"id":"https://openalex.org/S7407050879","display_name":"UC Berkeley","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I95457486","host_organization_name":"University of California, Berkeley","host_organization_lineage":["https://openalex.org/I95457486"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"technical reports"},{"id":"mag:57114836","doi":null,"is_oa":false,"landing_page_url":"https://escholarship.org/content/qt86b9c87d/qt86b9c87d.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:escholarship.org/ark:/13030/qt86b9c87d","doi":null,"is_oa":true,"landing_page_url":"https://escholarship.org/uc/item/86b9c87d","pdf_url":"https://escholarship.org/uc/item/86b9c87d","source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"etd"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W57114836.pdf","grobid_xml":"https://content.openalex.org/works/W57114836.grobid-xml"},"referenced_works_count":49,"referenced_works":["https://openalex.org/W1498892184","https://openalex.org/W1598134722","https://openalex.org/W1966822396","https://openalex.org/W1969454651","https://openalex.org/W1971356995","https://openalex.org/W1987940356","https://openalex.org/W1988037647","https://openalex.org/W1991133427","https://openalex.org/W2024060531","https://openalex.org/W2059670608","https://openalex.org/W2059676477","https://openalex.org/W2059776850","https://openalex.org/W2085060961","https://openalex.org/W2087064593","https://openalex.org/W2098131178","https://openalex.org/W2107233609","https://openalex.org/W2112113834","https://openalex.org/W2113312463","https://openalex.org/W2117945751","https://openalex.org/W2119745866","https://openalex.org/W2124985265","https://openalex.org/W2125109709","https://openalex.org/W2131088968","https://openalex.org/W2131776122","https://openalex.org/W2136651963","https://openalex.org/W2138270253","https://openalex.org/W2139760555","https://openalex.org/W2140897574","https://openalex.org/W2142403957","https://openalex.org/W2142702487","https://openalex.org/W2142749416","https://openalex.org/W2144662851","https://openalex.org/W2151732271","https://openalex.org/W2152246890","https://openalex.org/W2154537630","https://openalex.org/W2155845142","https://openalex.org/W2156434996","https://openalex.org/W2158869408","https://openalex.org/W2160199621","https://openalex.org/W2160969485","https://openalex.org/W2162289196","https://openalex.org/W2167435540","https://openalex.org/W2170568588","https://openalex.org/W2171777347","https://openalex.org/W2172266558","https://openalex.org/W7096157630","https://openalex.org/W7097369121","https://openalex.org/W7098838276","https://openalex.org/W7099585975"],"related_works":["https://openalex.org/W2307431445","https://openalex.org/W7096157630","https://openalex.org/W1987940356","https://openalex.org/W2025362134","https://openalex.org/W2059776850","https://openalex.org/W1980667059","https://openalex.org/W1966582186","https://openalex.org/W2163251627","https://openalex.org/W2416975758","https://openalex.org/W2108999555"],"abstract_inverted_index":{"Recent":[0],"advances":[1],"of":[2,11,99,119,188,267,319],"DNA":[3],"sequencing":[4,52,58,147,212,309],"technologies":[5,74],"are":[6,34,252,312],"allowingresearchers":[7],"to":[8,68,83,138,232,242,259,306],"generateimmense":[9],"amounts":[10],"data":[12,129,139,321],"in":[13,86,314],"a":[14,31,70,97,141],"fast":[15],"and":[16,23,115,133,185,214,255,292,323],"cost":[17],"effective":[18],"fashion,":[19],"enablinggenome-wide":[20],"association":[21],"study":[22],"populationgenetic":[24],"research":[25],"which":[26],"could":[27],"not":[28,223],"be":[29,84,203,230,257,272,304],"done":[30],"decade":[32],"ago.There":[33],"quite":[35],"numerous":[36],"computational":[37],"challenges":[38],"arising":[39],"from":[40,64,308],"thisadvancement,":[41],"however.":[42],"Examples":[43],"include":[44],"efficient":[45],"algorithms":[46,54,60,80,109,239,311],"for":[47,55,61,110,198,249],"processing":[48],"rawdata":[49],"generated":[50],"by":[51,156],"instruments,":[53],"detecting":[56,62],"andcorrecting":[57],"errors,":[59],"genomevariations":[63],"sequence":[65,176,320],"data,":[66],"just":[67],"name":[69],"few.":[71],"Because":[72],"differentsequencing":[73],"can":[75,170,228,256,287,303],"have":[76,171],"drastically":[77],"differentcharacteristics,":[78],"these":[79,250,280],"often":[81],"need":[82],"adapted":[85],"orderto":[87],"produce":[88],"most":[89],"accurate":[90],"results.In":[91],"this":[92],"thesis,":[93],"I":[94],"will":[95,164,202,283],"address":[96],"few":[98],"the":[100,111,158,174,180,186,191,246,265],"aforementioned":[101],"problems.":[102],"First,":[103],"Iwill":[104],"describe":[105],"two":[106],"model-based":[107],"basecalling":[108],"Illuminasequencing":[112],"platforms:":[113],"BayesCall":[114,120,150],"naiveBayesCall.":[116],"The":[117,205],"novelty":[118],"algorithmis":[121],"that":[122,167,285,301],"it":[123,135,221],"is":[124,136,298],"fully":[125],"unsupervised,":[126],"requiring":[127],"notraining":[128],"with":[130],"known":[131],"labels,":[132],"therefore":[134],"applicable":[137],"without":[140,161],"reference":[142],"sequence.It":[143],"also":[144,165,229,293,299],"dramatically":[145,153,273],"improves":[146,154],"accuracies.Built":[148],"upon":[149],"algorithm,":[151,195],"naiveBayesCall":[152],"computationalefficiency":[155],"approximating":[157],"original":[159],"model":[160],"sacrificingaccuracy.":[162],"We":[163,282],"show":[166,284],"improved":[168],"basecall":[169],"positiveeffects":[172],"on":[173,225,275],"downstream":[175,295,317],"analysis,":[177],"such":[178],"as":[179],"detection":[181],"ofsingle":[182],"nucleotide":[183],"polymorphism":[184],"assembly":[187],"novel":[189],"genomes.In":[190],"third":[192],"chapter,":[193],"an":[194],"called":[196],"ECHO,":[197],"correcting":[199],"short-readsequencing":[200],"errors":[201],"described.":[204],"correction":[206,238,269],"algorithm":[207,270],"efficiently":[208],"computesall":[209],"overlaps":[210],"between":[211],"reads":[213],"corrects":[215],"errorsby":[216],"using":[217],"statistical":[218,276],"models.":[219],"Since":[220],"does":[222],"rely":[224],"referencegenomes,":[226],"ECHO":[227,278,286,302],"applied":[231],"de":[233],"novo":[234],"sequencing.Most":[235],"other":[236],"error":[237,268,290],"require":[240],"users":[241],"specifykey":[243],"parameters,":[244],"but":[245],"optimal":[247],"values":[248],"parameters":[251,263],"unknown":[253],"tousers":[254],"hard":[258],"specify.":[260],"Without":[261],"key":[262],"beingoptimized,":[264],"effectiveness":[266],"couldsometimes":[271],"reduced.Based":[274],"models,":[277],"optimizes":[279],"parametersaccordingly.":[281],"significantly":[288],"reducesequence":[289],"rates":[291],"facilitate":[294],"sequenceanalysis.":[296],"It":[297],"demonstrated":[300],"extended":[305],"detectheterozygousity":[307],"data.These":[310],"developed":[313],"hopes":[315],"tomake":[316],"analysis":[318],"easier":[322],"ultimatelyfacilitate":[324],"genome":[325],"researches.":[326]},"counts_by_year":[{"year":2020,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}