{"id":"https://openalex.org/W2621273083","doi":"https://doi.org/10.1145/3019612.3019614","title":"A profile-based probabilistic approach for the detection of anomalies in the cytochrome C oxidase I amplicon sequences","display_name":"A profile-based probabilistic approach for the detection of anomalies in the cytochrome C oxidase I amplicon sequences","publication_year":2017,"publication_date":"2017-04-03","ids":{"openalex":"https://openalex.org/W2621273083","doi":"https://doi.org/10.1145/3019612.3019614","mag":"2621273083"},"language":"en","primary_location":{"id":"doi:10.1145/3019612.3019614","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3019612.3019614","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Symposium on Applied Computing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035080938","display_name":"Mahdi Belcaid","orcid":"https://orcid.org/0009-0004-5185-0643"},"institutions":[{"id":"https://openalex.org/I117965899","display_name":"University of Hawai\u02bbi at M\u0101noa","ror":"https://ror.org/01wspgy28","country_code":"US","type":"education","lineage":["https://openalex.org/I117965899"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mahdi Belcaid","raw_affiliation_strings":["University of Hawaii at Manoa, Honolulu, Hawaii"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Hawaii at Manoa, Honolulu, Hawaii","institution_ids":["https://openalex.org/I117965899"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049084621","display_name":"Guylaine Poisson","orcid":null},"institutions":[{"id":"https://openalex.org/I117965899","display_name":"University of Hawai\u02bbi at M\u0101noa","ror":"https://ror.org/01wspgy28","country_code":"US","type":"education","lineage":["https://openalex.org/I117965899"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Guylaine Poisson","raw_affiliation_strings":["University of Hawaii at Manoa, Honolulu, Hawaii"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Hawaii at Manoa, Honolulu, Hawaii","institution_ids":["https://openalex.org/I117965899"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":0.04851832,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"11","last_page":"17"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9995999932289124,"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":0.9995999932289124,"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/T10895","display_name":"Species Distribution and Climate Change","score":0.9972000122070312,"subfield":{"id":"https://openalex.org/subfields/2302","display_name":"Ecological Modeling"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10487","display_name":"Plant and animal studies","score":0.9904000163078308,"subfield":{"id":"https://openalex.org/subfields/1105","display_name":"Ecology, Evolution, Behavior and Systematics"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.6680128574371338},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6159150004386902},{"id":"https://openalex.org/keywords/indel","display_name":"Indel","score":0.613278865814209},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.576979398727417},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.49779510498046875},{"id":"https://openalex.org/keywords/amplicon","display_name":"Amplicon","score":0.4918661117553711},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.4844120144844055},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44365692138671875},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.43938860297203064},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.3669390380382538},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.22742310166358948},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.19075873494148254},{"id":"https://openalex.org/keywords/polymerase-chain-reaction","display_name":"Polymerase chain reaction","score":0.07766193151473999},{"id":"https://openalex.org/keywords/ecology","display_name":"Ecology","score":0.0771312415599823}],"concepts":[{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6680128574371338},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6159150004386902},{"id":"https://openalex.org/C119054055","wikidata":"https://www.wikidata.org/wiki/Q1576681","display_name":"Indel","level":5,"score":0.613278865814209},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.576979398727417},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.49779510498046875},{"id":"https://openalex.org/C8185291","wikidata":"https://www.wikidata.org/wiki/Q2844457","display_name":"Amplicon","level":4,"score":0.4918661117553711},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.4844120144844055},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44365692138671875},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.43938860297203064},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.3669390380382538},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.22742310166358948},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.19075873494148254},{"id":"https://openalex.org/C49105822","wikidata":"https://www.wikidata.org/wiki/Q176996","display_name":"Polymerase chain reaction","level":3,"score":0.07766193151473999},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0771312415599823},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C153209595","wikidata":"https://www.wikidata.org/wiki/Q501128","display_name":"Single-nucleotide polymorphism","level":4,"score":0.0},{"id":"https://openalex.org/C135763542","wikidata":"https://www.wikidata.org/wiki/Q106016","display_name":"Genotype","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3019612.3019614","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3019612.3019614","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Symposium on Applied Computing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/15","display_name":"Life in Land","score":0.7400000095367432}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1870798554","https://openalex.org/W1952156077","https://openalex.org/W1994562145","https://openalex.org/W2009570821","https://openalex.org/W2053565808","https://openalex.org/W2101120467","https://openalex.org/W2103041471","https://openalex.org/W2105368763","https://openalex.org/W2116647628","https://openalex.org/W2118020555","https://openalex.org/W2121011688","https://openalex.org/W2127774996","https://openalex.org/W2136879569","https://openalex.org/W2160378127","https://openalex.org/W2170747616","https://openalex.org/W2170885088","https://openalex.org/W2171894968","https://openalex.org/W2218504836","https://openalex.org/W2336324290","https://openalex.org/W2336485197","https://openalex.org/W3121953277","https://openalex.org/W4245668478","https://openalex.org/W4253630494","https://openalex.org/W6628944751","https://openalex.org/W7073602151"],"related_works":["https://openalex.org/W2033001683","https://openalex.org/W2167094946","https://openalex.org/W2894284492","https://openalex.org/W4387460329","https://openalex.org/W2046457574","https://openalex.org/W1949458596","https://openalex.org/W3144677376","https://openalex.org/W32785519","https://openalex.org/W4382398022","https://openalex.org/W2160515792"],"abstract_inverted_index":{"The":[0,126],"cytochrome":[1],"c":[2],"oxidase":[3],"1":[4],"(COI)":[5],"gene":[6],"is":[7,129],"among":[8],"the":[9,39,52,84,124,141,145,155,167],"most":[10],"popular":[11],"markers":[12],"for":[13,21,46,94,166],"molecular":[14],"biodiversity":[15],"estimation.":[16],"In":[17],"essence,":[18],"COI-based":[19,47],"approaches":[20],"taxonomic":[22],"identification":[23,40],"rely":[24],"on":[25],"comprehensive":[26],"reference":[27,57,118,152],"databases":[28,58],"to":[29,33,37,49,69,101,108,120,132,140,172],"assign":[30],"unknown":[31],"sequences":[32,136,153],"known":[34],"species":[35],"and/or":[36],"enhance":[38],"of":[41,56,144,148,157,169],"new":[42,90,170],"species.":[43],"As":[44],"such,":[45],"methods":[48],"be":[50],"effective,":[51],"accuracy":[53],"and":[54,72,105,112,134],"integrity":[55],"are":[59,98],"critical.":[60],"However,":[61],"as":[62],"COI":[63,117,151,176],"repositories":[64],"grow,":[65],"it":[66],"becomes":[67],"difficult":[68],"manually":[70],"curate":[71],"validate":[73],"user-contributed":[74],"data.":[75],"This,":[76],"in":[77],"turn,":[78],"propagates":[79],"prediction":[80],"errors,":[81],"therefore":[82],"reinforcing":[83],"cycle.":[85],"Here,":[86],"we":[87],"propose":[88],"a":[89,163],"computationally":[91],"efficient":[92],"approach":[93,115],"identifying":[95],"anomalies":[96],"which":[97,161],"either":[99],"due":[100],"systematic":[102],"biases":[103],"(indels":[104],"chimeras)":[106],"or":[107],"user":[109],"error":[110],"(mistranslation":[111],"misclassification).":[113],"Our":[114],"uses":[116],"alignments":[119],"model":[121,128],"substitutions":[122],"across":[123],"marker.":[125],"resulting":[127],"subsequently":[130],"used":[131],"screen":[133,173],"identify":[135,154],"with":[137],"incongruous":[138],"fit":[139],"model.":[142],"Analysis":[143],"complete":[146],"set":[147],"curated":[149],"Insecta":[150],"presence":[156],"numerous":[158],"anomalous":[159],"sequences,":[160],"makes":[162],"strong":[164],"case":[165],"importance":[168],"strategies":[171],"publicly":[174],"available":[175],"references.":[177]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
