{"id":"https://openalex.org/W2055314899","doi":"https://doi.org/10.1109/dexa.2012.45","title":"Enhancing Protein Domain Detection Using Domain Co-occurrence and Domain Exclusion","display_name":"Enhancing Protein Domain Detection Using Domain Co-occurrence and Domain Exclusion","publication_year":2012,"publication_date":"2012-09-01","ids":{"openalex":"https://openalex.org/W2055314899","doi":"https://doi.org/10.1109/dexa.2012.45","mag":"2055314899"},"language":"en","primary_location":{"id":"doi:10.1109/dexa.2012.45","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dexa.2012.45","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 23rd International Workshop on Database and Expert Systems Applications","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/A5010022863","display_name":"Amel Ghouila","orcid":"https://orcid.org/0000-0002-1597-1841"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I108714496","display_name":"Tunis University","ror":"https://ror.org/02q1spa57","country_code":"TN","type":"education","lineage":["https://openalex.org/I108714496"]},{"id":"https://openalex.org/I4210101743","display_name":"Laboratoire d'Informatique, de Robotique et de Micro\u00e9lectronique de Montpellier","ror":"https://ror.org/013yean28","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I151295451","https://openalex.org/I19894307","https://openalex.org/I4210101743","https://openalex.org/I4210159245","https://openalex.org/I4412460525"]}],"countries":["FR","TN"],"is_corresponding":true,"raw_author_name":"Amel Ghouila","raw_affiliation_strings":["Computer Sciences Department, Faculty of Sciences, URPAH, Tunis, Tunisia","Methods and algorithms for Bioinformatics LIRMM, Faculty of Sciences Tunis, Tunisia","Methods and algorithms for Bioinformatics, LIRMM, CNRS, University Montpellier 2, Montpellier, France"],"affiliations":[{"raw_affiliation_string":"Computer Sciences Department, Faculty of Sciences, URPAH, Tunis, Tunisia","institution_ids":[]},{"raw_affiliation_string":"Methods and algorithms for Bioinformatics LIRMM, Faculty of Sciences Tunis, Tunisia","institution_ids":["https://openalex.org/I108714496"]},{"raw_affiliation_string":"Methods and algorithms for Bioinformatics, LIRMM, CNRS, University Montpellier 2, Montpellier, France","institution_ids":["https://openalex.org/I4210101743","https://openalex.org/I1294671590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078068308","display_name":"Olivier Gascuel","orcid":"https://orcid.org/0000-0002-9412-9723"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210101743","display_name":"Laboratoire d'Informatique, de Robotique et de Micro\u00e9lectronique de Montpellier","ror":"https://ror.org/013yean28","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I151295451","https://openalex.org/I19894307","https://openalex.org/I4210101743","https://openalex.org/I4210159245","https://openalex.org/I4412460525"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Olivier Gascuel","raw_affiliation_strings":["Methods and algorithms for Bioinformatics, LIRMM, CNRS, University Montpellier 2, Montpellier, France","URPAH, Faculty of Sciences Tunis, Tunisia"],"affiliations":[{"raw_affiliation_string":"Methods and algorithms for Bioinformatics, LIRMM, CNRS, University Montpellier 2, Montpellier, France","institution_ids":["https://openalex.org/I4210101743","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"URPAH, Faculty of Sciences Tunis, Tunisia","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070511935","display_name":"Sadok Ben Yahia","orcid":"https://orcid.org/0000-0001-8939-8948"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I19894307","display_name":"Universit\u00e9 de Montpellier","ror":"https://ror.org/051escj72","country_code":"FR","type":"education","lineage":["https://openalex.org/I19894307"]},{"id":"https://openalex.org/I4210101743","display_name":"Laboratoire d'Informatique, de Robotique et de Micro\u00e9lectronique de Montpellier","ror":"https://ror.org/013yean28","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I151295451","https://openalex.org/I19894307","https://openalex.org/I4210101743","https://openalex.org/I4210159245","https://openalex.org/I4412460525"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Sadok Ben Yahia","raw_affiliation_strings":["Methods and algorithms for Bioinformatics LIRMM, CNRS, Univ. Montpellier 2, Montpellier, France"],"affiliations":[{"raw_affiliation_string":"Methods and algorithms for Bioinformatics LIRMM, CNRS, Univ. Montpellier 2, Montpellier, France","institution_ids":["https://openalex.org/I19894307","https://openalex.org/I1294671590","https://openalex.org/I4210101743"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049393621","display_name":"Laurent Br\u00e9h\u00e9lin","orcid":"https://orcid.org/0000-0002-2582-2831"},"institutions":[{"id":"https://openalex.org/I4210101743","display_name":"Laboratoire d'Informatique, de Robotique et de Micro\u00e9lectronique de Montpellier","ror":"https://ror.org/013yean28","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I151295451","https://openalex.org/I19894307","https://openalex.org/I4210101743","https://openalex.org/I4210159245","https://openalex.org/I4412460525"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I19894307","display_name":"Universit\u00e9 de Montpellier","ror":"https://ror.org/051escj72","country_code":"FR","type":"education","lineage":["https://openalex.org/I19894307"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Laurent Brehelin","raw_affiliation_strings":["Methods and algorithms for Bioinformatics LIRMM, CNRS, Univ. Montpellier 2, Montpellier, France"],"affiliations":[{"raw_affiliation_string":"Methods and algorithms for Bioinformatics LIRMM, CNRS, Univ. Montpellier 2, Montpellier, France","institution_ids":["https://openalex.org/I19894307","https://openalex.org/I1294671590","https://openalex.org/I4210101743"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5010022863"],"corresponding_institution_ids":["https://openalex.org/I108714496","https://openalex.org/I1294671590","https://openalex.org/I4210101743"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.08825122,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"36","issue":null,"first_page":"223","last_page":"228"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.9943000078201294,"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/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.9943000078201294,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9926999807357788,"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/T10044","display_name":"Protein Structure and Dynamics","score":0.9873999953269958,"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/domain","display_name":"Domain (mathematical analysis)","score":0.7015477418899536},{"id":"https://openalex.org/keywords/false-positive-paradox","display_name":"False positive paradox","score":0.6853397488594055},{"id":"https://openalex.org/keywords/protein-domain","display_name":"Protein domain","score":0.6330569982528687},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.621240496635437},{"id":"https://openalex.org/keywords/protein-sequencing","display_name":"Protein sequencing","score":0.5105575323104858},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.5036179423332214},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.49247679114341736},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.48144739866256714},{"id":"https://openalex.org/keywords/structural-classification-of-proteins-database","display_name":"Structural Classification of Proteins database","score":0.4706301689147949},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4608798027038574},{"id":"https://openalex.org/keywords/protein-function-prediction","display_name":"Protein function prediction","score":0.4429442882537842},{"id":"https://openalex.org/keywords/structural-alignment","display_name":"Structural alignment","score":0.4402283728122711},{"id":"https://openalex.org/keywords/sequence-alignment","display_name":"Sequence alignment","score":0.43598055839538574},{"id":"https://openalex.org/keywords/protein-family","display_name":"Protein family","score":0.4267060160636902},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4000808000564575},{"id":"https://openalex.org/keywords/protein-structure","display_name":"Protein structure","score":0.3779253363609314},{"id":"https://openalex.org/keywords/protein-function","display_name":"Protein function","score":0.27148211002349854},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.26934683322906494},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.26206445693969727},{"id":"https://openalex.org/keywords/peptide-sequence","display_name":"Peptide sequence","score":0.24134984612464905},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.22267159819602966},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.15096473693847656},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13536235690116882}],"concepts":[{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.7015477418899536},{"id":"https://openalex.org/C64869954","wikidata":"https://www.wikidata.org/wiki/Q1859747","display_name":"False positive paradox","level":2,"score":0.6853397488594055},{"id":"https://openalex.org/C144292202","wikidata":"https://www.wikidata.org/wiki/Q898273","display_name":"Protein domain","level":3,"score":0.6330569982528687},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.621240496635437},{"id":"https://openalex.org/C10010492","wikidata":"https://www.wikidata.org/wiki/Q3142557","display_name":"Protein sequencing","level":4,"score":0.5105575323104858},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5036179423332214},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.49247679114341736},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.48144739866256714},{"id":"https://openalex.org/C58773245","wikidata":"https://www.wikidata.org/wiki/Q4832556","display_name":"Structural Classification of Proteins database","level":3,"score":0.4706301689147949},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4608798027038574},{"id":"https://openalex.org/C207060522","wikidata":"https://www.wikidata.org/wiki/Q7251473","display_name":"Protein function prediction","level":4,"score":0.4429442882537842},{"id":"https://openalex.org/C4668613","wikidata":"https://www.wikidata.org/wiki/Q4116110","display_name":"Structural alignment","level":5,"score":0.4402283728122711},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.43598055839538574},{"id":"https://openalex.org/C171897839","wikidata":"https://www.wikidata.org/wiki/Q417841","display_name":"Protein family","level":3,"score":0.4267060160636902},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4000808000564575},{"id":"https://openalex.org/C47701112","wikidata":"https://www.wikidata.org/wiki/Q735188","display_name":"Protein structure","level":2,"score":0.3779253363609314},{"id":"https://openalex.org/C2986374874","wikidata":"https://www.wikidata.org/wiki/Q8054","display_name":"Protein function","level":3,"score":0.27148211002349854},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26934683322906494},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.26206445693969727},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.24134984612464905},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.22267159819602966},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.15096473693847656},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13536235690116882},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/dexa.2012.45","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dexa.2012.45","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 23rd International Workshop on Database and Expert Systems Applications","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.800000011920929,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1930237957","https://openalex.org/W2011983053","https://openalex.org/W2040184829","https://openalex.org/W2106013076","https://openalex.org/W2112792893","https://openalex.org/W2113403117","https://openalex.org/W2141885858","https://openalex.org/W2147614887","https://openalex.org/W2148950394","https://openalex.org/W2168799765","https://openalex.org/W4210623056","https://openalex.org/W4245668478","https://openalex.org/W4251569098","https://openalex.org/W6681765588"],"related_works":["https://openalex.org/W2075451741","https://openalex.org/W2070693796","https://openalex.org/W2130393164","https://openalex.org/W2318097870","https://openalex.org/W2155238244","https://openalex.org/W2164753093","https://openalex.org/W2821108685","https://openalex.org/W1496233740","https://openalex.org/W2041862730","https://openalex.org/W2019177511"],"abstract_inverted_index":{"Among":[0],"the":[1,36,43,87,90,93,96,106,109,115,143,151,159,196,215,221,233,236],"relevant":[2],"annotations":[3],"that":[4,23,149,188,208],"can":[5,111],"be":[6,112],"at-tributed":[7],"to":[8,82,120,163,178,183,199,212],"a":[9,13,48,62,67,73,84,100,141,167,173],"protein,":[10],"domains":[11,17,162,171,187,194,223],"occupy":[12],"key":[14],"position.":[15],"Protein":[16],"are":[18,24,189],"sequential":[19],"and":[20,30,53,66,92,202],"structural":[21],"motifs":[22],"found":[25],"independently":[26],"in":[27,31,57,114,172,190],"different":[28,32],"proteins":[29,121],"combinations.":[33],"One":[34],"of":[35,50,108,122,153,161,195,217,235],"most":[37],"widely":[38],"used":[39,81],"domain":[40,52,110,155,180],"scheme":[41],"is":[42,47,59,80,98],"Pfam":[44,58,78,154],"database":[45],"which":[46],"collection":[49],"protein":[51,75],"families.":[54],"Each":[55],"family":[56],"represented":[60],"by":[61,104,157,225],"multiple":[63],"sequence":[64,91],"alignment":[65],"Hidden":[68],"Markov":[69],"Model":[70],"(HMM).When":[71],"analyzing":[72],"new":[74,222],"sequence,":[76],"each":[77],"HMM":[79],"compute":[83],"score":[85,97],"measuring":[86],"similarity":[88],"between":[89],"domain.":[94],"If":[95],"above":[99],"given":[101],"threshold":[102],"provided":[103],"Pfam,":[105],"presence":[107],"asserted":[113],"protein.":[116,174,197],"However,":[117],"when":[118],"applied":[119],"organisms":[123],"with":[124,166,192],"high":[125],"evolutionary":[126],"distance":[127],"from":[128],"classical":[129],"model":[130],"organisms,":[131],"this":[132,209],"strategy":[133,210],"may":[134],"miss":[135],"several":[136],"domains.":[137],"We":[138],"recently":[139],"proposed":[140],"method,":[142],"Co-Occurrence":[144],"Domain":[145],"Detection":[146],"approach":[147],"(CODD),":[148],"improves":[150],"sensitivity":[152,234],"detection":[156],"exploiting":[158],"tendency":[160],"appear":[164],"preferentially":[165],"few":[168],"other":[169,193],"favorite":[170],"Here,":[175],"we":[176,206],"propose":[177],"integrate":[179],"exclusion":[181],"information":[182],"prune":[184],"false":[185,218],"positive":[186],"conflict":[191],"Applied":[198],"P.":[200],"falciparum":[201],"L.":[203],"major":[204],"proteins,":[205],"show":[207],"allows":[211],"substantially":[213],"reduce":[214],"proportion":[216],"positives":[219],"among":[220],"predicted":[224],"CODD,":[226],"while":[227],"preserving":[228],"as":[229,231],"much":[230],"possible":[232],"approach.":[237]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}