{"id":"https://openalex.org/W2466892528","doi":"https://doi.org/10.1093/bioinformatics/btw385","title":"GeneCodeq: quality score compression and improved genotyping using a Bayesian framework","display_name":"GeneCodeq: quality score compression and improved genotyping using a Bayesian framework","publication_year":2016,"publication_date":"2016-06-26","ids":{"openalex":"https://openalex.org/W2466892528","doi":"https://doi.org/10.1093/bioinformatics/btw385","mag":"2466892528","pmid":"https://pubmed.ncbi.nlm.nih.gov/27354700"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btw385","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btw385","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/32/20/3124/25040466/btw385.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/32/20/3124/25040466/btw385.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027135098","display_name":"Daniel L. Greenfield","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Daniel L. Greenfield","raw_affiliation_strings":["1 PetaGene, Ideaspace, 3 Charles Babbage Rd, Cambridge CB3 0GT, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1 PetaGene, Ideaspace, 3 Charles Babbage Rd, Cambridge CB3 0GT, UK","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091002491","display_name":"Oliver Stegle","orcid":"https://orcid.org/0000-0002-8818-7193"},"institutions":[{"id":"https://openalex.org/I1303153112","display_name":"European Bioinformatics Institute","ror":"https://ror.org/02catss52","country_code":"GB","type":"facility","lineage":["https://openalex.org/I1303153112","https://openalex.org/I4210138560"]},{"id":"https://openalex.org/I87048295","display_name":"Wellcome Trust","ror":"https://ror.org/029chgv08","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I87048295"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Oliver Stegle","raw_affiliation_strings":["2 European Molecular Biology Laboratory, European Bioinformatics Institute, Wellcome Trust Genome Campus, Hinxton, Cambridge CB10 1SQ, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"2 European Molecular Biology Laboratory, European Bioinformatics Institute, Wellcome Trust Genome Campus, Hinxton, Cambridge CB10 1SQ, UK","institution_ids":["https://openalex.org/I1303153112","https://openalex.org/I87048295"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075897525","display_name":"Alban Rrustemi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alban Rrustemi","raw_affiliation_strings":["1 PetaGene, Ideaspace, 3 Charles Babbage Rd, Cambridge CB3 0GT, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1 PetaGene, Ideaspace, 3 Charles Babbage Rd, Cambridge CB3 0GT, UK","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5027135098"],"corresponding_institution_ids":[],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":6.0634,"has_fulltext":true,"cited_by_count":25,"citation_normalized_percentile":{"value":0.96378312,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"32","issue":"20","first_page":"3124","last_page":"3132"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.7206000089645386,"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":0.7206000089645386,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.0828000009059906,"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/T10261","display_name":"Genetic Associations and Epidemiology","score":0.01899999938905239,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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/computer-science","display_name":"Computer science","score":0.7782524824142456},{"id":"https://openalex.org/keywords/lossy-compression","display_name":"Lossy compression","score":0.7398115992546082},{"id":"https://openalex.org/keywords/lossless-compression","display_name":"Lossless compression","score":0.6912472248077393},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.5567891001701355},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5357726216316223},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.5131148099899292},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.4437383711338043},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.29634472727775574},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24035972356796265}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7782524824142456},{"id":"https://openalex.org/C165021410","wikidata":"https://www.wikidata.org/wiki/Q55564","display_name":"Lossy compression","level":2,"score":0.7398115992546082},{"id":"https://openalex.org/C81081738","wikidata":"https://www.wikidata.org/wiki/Q55542","display_name":"Lossless compression","level":3,"score":0.6912472248077393},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5567891001701355},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5357726216316223},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.5131148099899292},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.4437383711338043},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.29634472727775574},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24035972356796265},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D001499","descriptor_name":"Bayes Theorem","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001499","descriptor_name":"Bayes Theorem","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001499","descriptor_name":"Bayes Theorem","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005838","descriptor_name":"Genotype","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005838","descriptor_name":"Genotype","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005838","descriptor_name":"Genotype","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D044962","descriptor_name":"Data Compression","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D044962","descriptor_name":"Data Compression","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D044962","descriptor_name":"Data Compression","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btw385","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btw385","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/32/20/3124/25040466/btw385.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:27354700","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/27354700","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics (Oxford, England)","raw_type":null},{"id":"pmh:oai:open-archive.highwire.org:bioinfo:32/20/3124","is_oa":false,"landing_page_url":"http://bioinformatics.oxfordjournals.org/cgi/content/short/32/20/3124","pdf_url":null,"source":{"id":"https://openalex.org/S4406923041","display_name":"HighWire Press Open Archive","issn_l":null,"issn":null,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"TEXT"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btw385","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btw385","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/32/20/3124/25040466/btw385.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2466892528.pdf","grobid_xml":"https://content.openalex.org/works/W2466892528.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W109642580","https://openalex.org/W1931027898","https://openalex.org/W2020255088","https://openalex.org/W2069066547","https://openalex.org/W2074490119","https://openalex.org/W2092373383","https://openalex.org/W2092880969","https://openalex.org/W2096791516","https://openalex.org/W2098513839","https://openalex.org/W2104846587","https://openalex.org/W2105821863","https://openalex.org/W2109153336","https://openalex.org/W2119923823","https://openalex.org/W2125557405","https://openalex.org/W2131106408","https://openalex.org/W2150131459","https://openalex.org/W2153707226","https://openalex.org/W2156690988","https://openalex.org/W2159084616","https://openalex.org/W2163251627","https://openalex.org/W2168133698"],"related_works":["https://openalex.org/W2385628723","https://openalex.org/W2547124190","https://openalex.org/W3180760233","https://openalex.org/W1970394887","https://openalex.org/W3035703949","https://openalex.org/W4247601675","https://openalex.org/W755971114","https://openalex.org/W4210455546","https://openalex.org/W1982468865","https://openalex.org/W2377574787"],"abstract_inverted_index":{"MOTIVATION:":[0],"The":[1],"exponential":[2],"reduction":[3],"in":[4,11,28,36,136,204],"cost":[5],"of":[6,15,19,22,31,73,100,113,119,127,143,170,198,215],"genome":[7],"sequencing":[8],"has":[9,45],"resulted":[10],"a":[12,63,85,111,167,211],"rapid":[13],"growth":[14],"genomic":[16],"data.":[17],"Most":[18],"the":[20,29,71,98,117,120,125,163,176,193,217],"entropy":[21,118,160],"short":[23],"read":[24,32],"data":[25,75,129,237],"lies":[26],"not":[27],"sequence":[30,172],"bases":[33],"themselves":[34],"but":[35],"their":[37,56],"Quality":[38],"Scores-the":[39],"confidence":[40],"measurement":[41],"that":[42,68,139,191,209],"each":[43],"base":[44],"been":[46],"sequenced":[47],"correctly.":[48],"Lossless":[49],"compression":[50,137,155,202],"methods":[51,67],"are":[52,238],"now":[53],"close":[54],"to":[55,96,115,157,165,174,181,221],"theoretical":[57,189],"limits":[58],"and":[59,123,161,196],"hence":[60],"there":[61],"is":[62,229],"need":[64],"for":[65,92],"lossy":[66,154],"further":[69,158],"reduce":[70,116,159],"complexity":[72],"these":[74,128],"without":[76,103],"impacting":[77,105],"downstream":[78],"analyses.":[79],"RESULTS:":[80],"We":[81],"here":[82],"propose":[83],"GeneCodeq,":[84],"Bayesian":[86],"method":[87],"inspired":[88],"by":[89],"coding":[90],"theory":[91],"adjusting":[93],"quality":[94,101,121,200],"scores":[95,102,122],"improve":[97,175],"compressibility":[99,126],"adversely":[104],"genotyping":[106,223],"accuracy.":[107,178,224],"Our":[108,146],"model":[109,177,218],"leverages":[110],"corpus":[112],"k-mers":[114],"thereby":[124],"(in":[130],"FASTQ":[131],"or":[132],"SAM/BAM/CRAM":[133],"files),":[134],"resulting":[135],"ratios":[138],"significantly":[140],"exceeds":[141],"those":[142],"other":[144],"methods.":[145],"approach":[147],"can":[148,219],"also":[149,186],"be":[150],"combined":[151],"with":[152],"existing":[153],"schemes":[156,203],"allows":[162],"user":[164],"specify":[166],"reference":[168],"panel":[169],"expected":[171],"variations":[173],"In":[179],"addition":[180],"extensive":[182],"empirical":[183,194],"evaluation,":[184],"we":[185,207],"derive":[187],"novel":[188],"insights":[190],"explain":[192],"performance":[195],"pitfalls":[197],"corpus-based":[199],"score":[201],"general.":[205],"Finally,":[206],"show":[208],"as":[210],"positive":[212],"side":[213],"effect":[214],"compression,":[216],"lead":[220],"improved":[222],"AVAILABILITY":[225],"AND":[226],"IMPLEMENTATION:":[227],"GeneCodeq":[228],"available":[230,239],"at:":[231],"github.com/genecodeq/eval":[232],"CONTACT:":[233],"dan@petagene.comSupplementary":[234],"information:":[235],"Supplementary":[236],"at":[240],"Bioinformatics":[241],"online.":[242]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}