{"id":"https://openalex.org/W7142289632","doi":"https://doi.org/10.1177/15578666261436820","title":"Assessment of PHRED Score Characteristics in Illumina MiSeq Amplicon Sequencing","display_name":"Assessment of PHRED Score Characteristics in Illumina MiSeq Amplicon Sequencing","publication_year":2026,"publication_date":"2026-03-28","ids":{"openalex":"https://openalex.org/W7142289632","doi":"https://doi.org/10.1177/15578666261436820","pmid":"https://pubmed.ncbi.nlm.nih.gov/41902738"},"language":"en","primary_location":{"id":"doi:10.1177/15578666261436820","is_oa":false,"landing_page_url":"https://doi.org/10.1177/15578666261436820","pdf_url":null,"source":{"id":"https://openalex.org/S78571599","display_name":"Journal of Computational Biology","issn_l":"1066-5277","issn":["1066-5277","1557-8666"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320443","host_organization_name":"Mary Ann Liebert, Inc.","host_organization_lineage":["https://openalex.org/P4310320443"],"host_organization_lineage_names":["Mary Ann Liebert, Inc."],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Computational Biology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13051658/","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062028212","display_name":"Seth Sims","orcid":"https://orcid.org/0000-0003-2126-0197"},"institutions":[{"id":"https://openalex.org/I1289490764","display_name":"Centers for Disease Control and Prevention","ror":"https://ror.org/042twtr12","country_code":"US","type":"funder","lineage":["https://openalex.org/I1289490764","https://openalex.org/I1299022934"]},{"id":"https://openalex.org/I181565077","display_name":"Georgia State University","ror":"https://ror.org/03qt6ba18","country_code":"US","type":"education","lineage":["https://openalex.org/I181565077"]},{"id":"https://openalex.org/I4210124306","display_name":"The Centers","ror":"https://ror.org/033tgbx59","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210124306"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"SETH SIMS","raw_affiliation_strings":["Department of Computer Science, College of Arts and Sciences, Georgia State University, Atlanta, Georgia, USA","Molecular Epidemiology and Bioinformatics Laboratory, Division of Viral Hepatitis, Centers for Disease Control and Prevention, Atlanta, Georgia, USA"],"raw_orcid":"https://orcid.org/0000-0003-2126-0197","affiliations":[{"raw_affiliation_string":"Department of Computer Science, College of Arts and Sciences, Georgia State University, Atlanta, Georgia, USA","institution_ids":["https://openalex.org/I181565077"]},{"raw_affiliation_string":"Molecular Epidemiology and Bioinformatics Laboratory, Division of Viral Hepatitis, Centers for Disease Control and Prevention, Atlanta, Georgia, USA","institution_ids":["https://openalex.org/I1289490764","https://openalex.org/I4210124306"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085435304","display_name":"Yury Khudyakov","orcid":null},"institutions":[{"id":"https://openalex.org/I1289490764","display_name":"Centers for Disease Control and Prevention","ror":"https://ror.org/042twtr12","country_code":"US","type":"funder","lineage":["https://openalex.org/I1289490764","https://openalex.org/I1299022934"]},{"id":"https://openalex.org/I4210124306","display_name":"The Centers","ror":"https://ror.org/033tgbx59","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210124306"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"YURY KHUDYAKOV","raw_affiliation_strings":["Molecular Epidemiology and Bioinformatics Laboratory, Division of Viral Hepatitis, Centers for Disease Control and Prevention, Atlanta, Georgia, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Molecular Epidemiology and Bioinformatics Laboratory, Division of Viral Hepatitis, Centers for Disease Control and Prevention, Atlanta, Georgia, USA","institution_ids":["https://openalex.org/I1289490764","https://openalex.org/I4210124306"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5123947396","display_name":"Alexander Zelikovsky","orcid":null},"institutions":[{"id":"https://openalex.org/I17877952","display_name":"Sechenov University","ror":"https://ror.org/02yqqv993","country_code":"RU","type":"education","lineage":["https://openalex.org/I17877952"]},{"id":"https://openalex.org/I181565077","display_name":"Georgia State University","ror":"https://ror.org/03qt6ba18","country_code":"US","type":"education","lineage":["https://openalex.org/I181565077"]}],"countries":["RU","US"],"is_corresponding":false,"raw_author_name":"ALEXANDER ZELIKOVSKY","raw_affiliation_strings":["Department of Computer Science, College of Arts and Sciences, Georgia State University, Atlanta, Georgia, USA","The Laboratory of Bioinformatics, I.M. Sechenov First Moscow State Medical University, Moscow, Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, College of Arts and Sciences, Georgia State University, Atlanta, Georgia, USA","institution_ids":["https://openalex.org/I181565077"]},{"raw_affiliation_string":"The Laboratory of Bioinformatics, I.M. Sechenov First Moscow State Medical University, Moscow, Russia","institution_ids":["https://openalex.org/I17877952"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5062028212"],"corresponding_institution_ids":["https://openalex.org/I1289490764","https://openalex.org/I181565077","https://openalex.org/I4210124306"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.4218805,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"33","issue":"5-6","first_page":"705","last_page":"715"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10151","display_name":"Hepatitis C virus research","score":0.25459998846054077,"subfield":{"id":"https://openalex.org/subfields/2721","display_name":"Hepatology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T10151","display_name":"Hepatitis C virus research","score":0.25459998846054077,"subfield":{"id":"https://openalex.org/subfields/2721","display_name":"Hepatology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11819","display_name":"Data-Driven Disease Surveillance","score":0.16769999265670776,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10866","display_name":"Nutritional Studies and Diet","score":0.019099999219179153,"subfield":{"id":"https://openalex.org/subfields/2739","display_name":"Public Health, Environmental and Occupational Health"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/calibration","display_name":"Calibration","score":0.6258000135421753},{"id":"https://openalex.org/keywords/amplicon","display_name":"Amplicon","score":0.5547000169754028},{"id":"https://openalex.org/keywords/brier-score","display_name":"Brier score","score":0.5177000164985657},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.43959999084472656},{"id":"https://openalex.org/keywords/protocol","display_name":"Protocol (science)","score":0.392300009727478},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.3919999897480011},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.3517000079154968}],"concepts":[{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.6258000135421753},{"id":"https://openalex.org/C8185291","wikidata":"https://www.wikidata.org/wiki/Q2844457","display_name":"Amplicon","level":4,"score":0.5547000169754028},{"id":"https://openalex.org/C35405484","wikidata":"https://www.wikidata.org/wiki/Q4967066","display_name":"Brier score","level":2,"score":0.5177000164985657},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.4909999966621399},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4611999988555908},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.43959999084472656},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.4122999906539917},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.392300009727478},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.3919999897480011},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3562000095844269},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.3517000079154968},{"id":"https://openalex.org/C22679943","wikidata":"https://www.wikidata.org/wiki/Q159375","display_name":"Standard deviation","level":2,"score":0.33719998598098755},{"id":"https://openalex.org/C2779346075","wikidata":"https://www.wikidata.org/wiki/Q7268763","display_name":"Quality Score","level":3,"score":0.33059999346733093},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.31459999084472656},{"id":"https://openalex.org/C2776836416","wikidata":"https://www.wikidata.org/wiki/Q1364844","display_name":"False alarm","level":2,"score":0.30720001459121704},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29899999499320984},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2915000021457672},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.28780001401901245},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.2818000018596649},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.26969999074935913},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2623000144958496},{"id":"https://openalex.org/C132917006","wikidata":"https://www.wikidata.org/wiki/Q5250436","display_name":"Deep sequencing","level":4,"score":0.2572000026702881}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D002138","descriptor_name":"Calibration","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016013","descriptor_name":"Likelihood Functions","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000592","qualifier_name":"standards","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":"Q000592","qualifier_name":"standards","is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1177/15578666261436820","is_oa":false,"landing_page_url":"https://doi.org/10.1177/15578666261436820","pdf_url":null,"source":{"id":"https://openalex.org/S78571599","display_name":"Journal of Computational Biology","issn_l":"1066-5277","issn":["1066-5277","1557-8666"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320443","host_organization_name":"Mary Ann Liebert, Inc.","host_organization_lineage":["https://openalex.org/P4310320443"],"host_organization_lineage_names":["Mary Ann Liebert, Inc."],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Computational Biology","raw_type":"journal-article"},{"id":"pmid:41902738","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41902738","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":"Journal of computational biology : a journal of computational molecular cell biology","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:13051658","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13051658/","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"J Comput Biol","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:pubmedcentral.nih.gov:13051658","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13051658/","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"J Comput Biol","raw_type":"Text"},"sustainable_development_goals":[{"score":0.4811384379863739,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"},{"score":0.41094857454299927,"id":"https://metadata.un.org/sdg/3","display_name":"Good health and well-being"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320332162","display_name":"Centers for Disease Control and Prevention","ror":"https://ror.org/042twtr12"},{"id":"https://openalex.org/F4320337422","display_name":"National Center for HIV/AIDS, Viral Hepatitis, STD, and TB Prevention","ror":"https://ror.org/01wjn2x92"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1975553990","https://openalex.org/W2011301426","https://openalex.org/W2023943903","https://openalex.org/W2026777696","https://openalex.org/W2047634553","https://openalex.org/W2073241381","https://openalex.org/W2084396669","https://openalex.org/W2105368763","https://openalex.org/W2119923823","https://openalex.org/W2121016876","https://openalex.org/W2162667876","https://openalex.org/W2168408208","https://openalex.org/W2342249984","https://openalex.org/W2602843592","https://openalex.org/W2734616888","https://openalex.org/W2772837219","https://openalex.org/W2895871329","https://openalex.org/W3003257820","https://openalex.org/W3021737082","https://openalex.org/W3081064828"],"related_works":[],"abstract_inverted_index":{"PHRED":[0,31,54,69,129,132,215],"scores":[1,32,70,133,173,184,188,216,234,243],"are":[2,145,235,245],"confidence":[3],"values":[4],"associated":[5],"with":[6],"each":[7,104,119],"basecall":[8,25],"generated":[9],"by":[10,37,77,192,248,263],"sequencers.":[11],"The":[12,28,86,131,169,241],"score":[13],"is":[14,26],"defined":[15],"as":[16],"a":[17,59,90],"monotonic":[18],"function":[19],"of":[20,30,49,105,113,127,171,197,229,238,253,266],"the":[21,24,47,50,68,78,106,128,172,177,190,249,254,258,264,267],"probability":[22],"that":[23,117,185],"incorrect.":[27],"calibration":[29,48,65,212],"has":[33],"previously":[34],"been":[35],"examined":[36],"evaluating":[38],"errors":[39],"made":[40],"in":[41,71,94,220,257],"reading":[42],"known":[43],"sequences.":[44],"We":[45,62],"investigated":[46],"Illumina":[51],"MiSeq":[52,178],"instrument":[53,179],"model":[55,112],"using":[56],"data":[57],"from":[58,103,139,166],"large":[60],"dataset.":[61],"also":[63],"derive":[64],"methods":[66],"for":[67,189,214],"datasets":[72],"similar":[73],"to":[74,123,210],"those":[75],"produced":[76,182],"Global":[79],"Hepatitis":[80],"Outbreak":[81],"and":[82],"Surveillance":[83],"Technology":[84],"(GHOST).":[85],"GHOST":[87],"protocol":[88],"uses":[89],"short":[91],"amplicon,":[92],"resulting":[93],"many":[95],"positions":[96],"having":[97],"two":[98],"base":[99,115,269],"calls,":[100],"one":[101],"coming":[102],"paired":[107],"reads.":[108],"A":[109],"maximum":[110],"likelihood":[111],"redundant":[114,226],"calls":[116],"match":[118],"other":[120],"was":[121],"used":[122],"estimate":[124],"corrected":[125],"probabilities":[126],"scores.":[130],"showed":[134],"only":[135],"small":[136],"absolute":[137],"deviations":[138,148],"their":[140],"target":[141],"values.":[142],"These":[143],"differences":[144],"statistically":[146],"significant":[147],"(":[149],"<mml:math":[150,198],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[151,199],"display=\"inline\"":[152,200],"overflow=\"scroll\">":[153,201],"<mml:mrow>":[154,202],"<mml:mi":[155],"mathvariant=\"bold-italic\">p</mml:mi>":[156],"<mml:mo>":[157,160],"</mml:mo>":[158,161],"<mml:mo>&lt;</mml:mo>":[159],"<mml:mn>0.0001</mml:mn>":[162],"</mml:mrow>":[163,205],"</mml:math>":[164,206],")":[165],"being":[167],"calibrated.":[168],"accuracy":[170],"varied":[174],"significantly":[175],"between":[176],"runs.":[180],"Recalibration":[181],"quality":[183,233,242],"improved":[186],"Brier":[187],"dataset":[191],"an":[193],"average":[194],"relative":[195],"improvement":[196],"<mml:mn>2.83</mml:mn>":[203],"<mml:mi>%</mml:mi>":[204],".":[207],"Methods":[208],"developed":[209],"create":[211],"curves":[213],"will":[217],"be":[218],"useful":[219],"improving":[221],"error-correction":[222],"pipelines":[223],"based":[224],"on":[225],"deep":[227],"sequencing":[228,255],"amplicon":[230],"data.":[231],"However,":[232],"relatively":[236],"uninformative":[237],"substitution":[239],"errors.":[240],"assigned":[244],"determined":[246],"more":[247],"global":[250],"error":[251],"rate":[252],"run":[256],"current":[259],"machine":[260],"cycle":[261],"than":[262],"characteristics":[265],"specific":[268],"call.":[270]},"counts_by_year":[],"updated_date":"2026-05-27T06:14:07.914337","created_date":"2026-03-29T00:00:00"}