{"id":"https://openalex.org/W2798996574","doi":"https://doi.org/10.1371/journal.pcbi.1005889","title":"Improving pairwise comparison of protein sequences with domain co-occurrence","display_name":"Improving pairwise comparison of protein sequences with domain co-occurrence","publication_year":2018,"publication_date":"2018-01-02","ids":{"openalex":"https://openalex.org/W2798996574","doi":"https://doi.org/10.1371/journal.pcbi.1005889","mag":"2798996574","pmid":"https://pubmed.ncbi.nlm.nih.gov/29293498"},"language":"en","primary_location":{"id":"doi:10.1371/journal.pcbi.1005889","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1005889","pdf_url":"https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1005889&type=printable","source":{"id":"https://openalex.org/S86033158","display_name":"PLoS Computational Biology","issn_l":"1553-734X","issn":["1553-734X","1553-7358"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLOS Computational Biology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1005889&type=printable","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005552606","display_name":"Christophe Menichelli","orcid":"https://orcid.org/0000-0001-9161-3715"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","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/I4405261681"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Christophe Menichelli","raw_affiliation_strings":["IBC, LIRMM, Univ. Montpellier, CNRS, Montpellier, France"],"affiliations":[{"raw_affiliation_string":"IBC, LIRMM, Univ. Montpellier, CNRS, Montpellier, France","institution_ids":["https://openalex.org/I4210101743","https://openalex.org/I19894307","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":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I157536573","display_name":"Institut Pasteur","ror":"https://ror.org/0495fxg12","country_code":"FR","type":"nonprofit","lineage":["https://openalex.org/I157536573"]},{"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/I4405261681"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Olivier Gascuel","raw_affiliation_strings":["IBC, LIRMM, Univ. Montpellier, CNRS, Montpellier, France","Unit\u00e9 de Bioinformatique Evolutive, C3BI - USR 3756, Institut Pasteur et CNRS, Paris, France"],"affiliations":[{"raw_affiliation_string":"IBC, LIRMM, Univ. Montpellier, CNRS, Montpellier, France","institution_ids":["https://openalex.org/I4210101743","https://openalex.org/I19894307","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"Unit\u00e9 de Bioinformatique Evolutive, C3BI - USR 3756, Institut Pasteur et CNRS, Paris, France","institution_ids":["https://openalex.org/I157536573","https://openalex.org/I1294671590"]}]},{"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/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","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/I4405261681"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Laurent Br\u00e9h\u00e9lin","raw_affiliation_strings":["IBC, LIRMM, Univ. Montpellier, CNRS, Montpellier, France"],"affiliations":[{"raw_affiliation_string":"IBC, LIRMM, Univ. Montpellier, CNRS, Montpellier, France","institution_ids":["https://openalex.org/I4210101743","https://openalex.org/I19894307","https://openalex.org/I1294671590"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5049393621"],"corresponding_institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I19894307","https://openalex.org/I4210101743"],"apc_list":{"value":2655,"currency":"USD","value_usd":2655},"apc_paid":{"value":1882,"currency":"EUR","value_usd":2029},"fwci":0.3723,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.59885245,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"14","issue":"1","first_page":"e1005889","last_page":"e1005889"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9998999834060669,"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":0.9998999834060669,"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/T10519","display_name":"Advanced Proteomics Techniques and Applications","score":0.9954000115394592,"subfield":{"id":"https://openalex.org/subfields/1607","display_name":"Spectroscopy"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10602","display_name":"Glycosylation and Glycoproteins Research","score":0.9948999881744385,"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/false-positive-paradox","display_name":"False positive paradox","score":0.7421258091926575},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.6890792846679688},{"id":"https://openalex.org/keywords/protein-domain","display_name":"Protein domain","score":0.6445034742355347},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.5659323334693909},{"id":"https://openalex.org/keywords/sequence-alignment","display_name":"Sequence alignment","score":0.5548049807548523},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5500631332397461},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5411256551742554},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5052183270454407},{"id":"https://openalex.org/keywords/multiple-sequence-alignment","display_name":"Multiple sequence alignment","score":0.49088746309280396},{"id":"https://openalex.org/keywords/protein-function-prediction","display_name":"Protein function prediction","score":0.47251802682876587},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4598032534122467},{"id":"https://openalex.org/keywords/protein-sequencing","display_name":"Protein sequencing","score":0.4529399871826172},{"id":"https://openalex.org/keywords/smith\u2013waterman-algorithm","display_name":"Smith\u2013Waterman algorithm","score":0.4521805942058563},{"id":"https://openalex.org/keywords/proteome","display_name":"Proteome","score":0.4504103660583496},{"id":"https://openalex.org/keywords/structural-classification-of-proteins-database","display_name":"Structural Classification of Proteins database","score":0.4454249441623688},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4171295762062073},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.36077073216438293},{"id":"https://openalex.org/keywords/protein-structure","display_name":"Protein structure","score":0.35714614391326904},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.3268945813179016},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.23543167114257812},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2352558970451355},{"id":"https://openalex.org/keywords/peptide-sequence","display_name":"Peptide sequence","score":0.2045840322971344},{"id":"https://openalex.org/keywords/protein-function","display_name":"Protein function","score":0.1610686480998993},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13283908367156982}],"concepts":[{"id":"https://openalex.org/C64869954","wikidata":"https://www.wikidata.org/wiki/Q1859747","display_name":"False positive paradox","level":2,"score":0.7421258091926575},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.6890792846679688},{"id":"https://openalex.org/C144292202","wikidata":"https://www.wikidata.org/wiki/Q898273","display_name":"Protein domain","level":3,"score":0.6445034742355347},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5659323334693909},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.5548049807548523},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5500631332397461},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5411256551742554},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5052183270454407},{"id":"https://openalex.org/C88031987","wikidata":"https://www.wikidata.org/wiki/Q1377767","display_name":"Multiple sequence alignment","level":5,"score":0.49088746309280396},{"id":"https://openalex.org/C207060522","wikidata":"https://www.wikidata.org/wiki/Q7251473","display_name":"Protein function prediction","level":4,"score":0.47251802682876587},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4598032534122467},{"id":"https://openalex.org/C10010492","wikidata":"https://www.wikidata.org/wiki/Q3142557","display_name":"Protein sequencing","level":4,"score":0.4529399871826172},{"id":"https://openalex.org/C72802188","wikidata":"https://www.wikidata.org/wiki/Q1683352","display_name":"Smith\u2013Waterman algorithm","level":5,"score":0.4521805942058563},{"id":"https://openalex.org/C104397665","wikidata":"https://www.wikidata.org/wiki/Q860947","display_name":"Proteome","level":2,"score":0.4504103660583496},{"id":"https://openalex.org/C58773245","wikidata":"https://www.wikidata.org/wiki/Q4832556","display_name":"Structural Classification of Proteins database","level":3,"score":0.4454249441623688},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4171295762062073},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.36077073216438293},{"id":"https://openalex.org/C47701112","wikidata":"https://www.wikidata.org/wiki/Q735188","display_name":"Protein structure","level":2,"score":0.35714614391326904},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.3268945813179016},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.23543167114257812},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2352558970451355},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.2045840322971344},{"id":"https://openalex.org/C2986374874","wikidata":"https://www.wikidata.org/wiki/Q8054","display_name":"Protein function","level":3,"score":0.1610686480998993},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13283908367156982},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[{"descriptor_ui":"D000072417","descriptor_name":"Protein Domains","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000072417","descriptor_name":"Protein Domains","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000072417","descriptor_name":"Protein Domains","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010963","descriptor_name":"Plasmodium falciparum","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D010963","descriptor_name":"Plasmodium falciparum","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D010963","descriptor_name":"Plasmodium falciparum","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D010963","descriptor_name":"Plasmodium falciparum","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D010963","descriptor_name":"Plasmodium falciparum","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D010963","descriptor_name":"Plasmodium falciparum","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D015800","descriptor_name":"Protozoan Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D015800","descriptor_name":"Protozoan Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D015800","descriptor_name":"Protozoan Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D015800","descriptor_name":"Protozoan Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D015800","descriptor_name":"Protozoan Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D015800","descriptor_name":"Protozoan Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":6,"locations":[{"id":"doi:10.1371/journal.pcbi.1005889","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1005889","pdf_url":"https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1005889&type=printable","source":{"id":"https://openalex.org/S86033158","display_name":"PLoS Computational Biology","issn_l":"1553-734X","issn":["1553-734X","1553-7358"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLOS Computational Biology","raw_type":"journal-article"},{"id":"pmid:29293498","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/29293498","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":"PLoS computational biology","raw_type":null},{"id":"pmh:oai:HAL:lirmm-01744475v1","is_oa":true,"landing_page_url":"https://hal-lirmm.ccsd.cnrs.fr/lirmm-01744475","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"PLoS Computational Biology, 2018, 14 (1), pp.e1005889. &#x27E8;10.1371/journal.pcbi.1005889&#x27E9;","raw_type":"Journal articles"},{"id":"pmh:oai:RePEc:plo:pcbi00:1005889","is_oa":false,"landing_page_url":"https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1005889","pdf_url":null,"source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},{"id":"pmh:oai:doaj.org/article:ea0053acea6e4d349465a49d6da1f440","is_oa":true,"landing_page_url":"https://doaj.org/article/ea0053acea6e4d349465a49d6da1f440","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"PLoS Computational Biology, Vol 14, Iss 1, p e1005889 (2018)","raw_type":"article"},{"id":"pmh:oai:europepmc.org:4689621","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/5766236","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1371/journal.pcbi.1005889","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1005889","pdf_url":"https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1005889&type=printable","source":{"id":"https://openalex.org/S86033158","display_name":"PLoS Computational Biology","issn_l":"1553-734X","issn":["1553-734X","1553-7358"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLOS Computational Biology","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Life in Land","score":0.6700000166893005,"id":"https://metadata.un.org/sdg/15"}],"awards":[{"id":"https://openalex.org/G3335229504","display_name":null,"funder_award_id":"Avenir","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G6178185026","display_name":null,"funder_award_id":"ANR-JCJC","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G7445899374","display_name":null,"funder_award_id":"ANR-JCJC-2010","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2798996574.pdf","grobid_xml":"https://content.openalex.org/works/W2798996574.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W1977516605","https://openalex.org/W1995260859","https://openalex.org/W2007745123","https://openalex.org/W2009570821","https://openalex.org/W2010830967","https://openalex.org/W2011983053","https://openalex.org/W2015292449","https://openalex.org/W2016682035","https://openalex.org/W2021064499","https://openalex.org/W2040184829","https://openalex.org/W2051119339","https://openalex.org/W2055043387","https://openalex.org/W2076502650","https://openalex.org/W2080382112","https://openalex.org/W2082667898","https://openalex.org/W2087885007","https://openalex.org/W2102461176","https://openalex.org/W2103017472","https://openalex.org/W2118340207","https://openalex.org/W2122879306","https://openalex.org/W2125596158","https://openalex.org/W2132495279","https://openalex.org/W2132926880","https://openalex.org/W2147442130","https://openalex.org/W2149531726","https://openalex.org/W2151831732","https://openalex.org/W2158714788","https://openalex.org/W2160458088","https://openalex.org/W2163910672","https://openalex.org/W2179402585","https://openalex.org/W2224056471","https://openalex.org/W2490955734","https://openalex.org/W2739999456","https://openalex.org/W2951608279"],"related_works":["https://openalex.org/W2948014085","https://openalex.org/W2103737249","https://openalex.org/W2004215917","https://openalex.org/W2143450062","https://openalex.org/W2318097870","https://openalex.org/W3186624150","https://openalex.org/W2106931463","https://openalex.org/W1496233740","https://openalex.org/W1490120815","https://openalex.org/W2019177511"],"abstract_inverted_index":{"Comparing":[0],"and":[1,51,138,177,227,247],"aligning":[2],"protein":[3,24,30,107],"sequences":[4],"is":[5,72,99],"an":[6,166,178],"essential":[7],"task":[8],"in":[9,133,201,223],"bioinformatics.":[10],"More":[11],"specifically,":[12],"local":[13],"alignment":[14,226],"tools":[15,44],"like":[16],"BLAST":[17,136,175],"are":[18,45,61,233,250],"widely":[19],"used":[20,46,151],"for":[21,58,199],"identifying":[22],"conserved":[23],"sub-sequences,":[25],"which":[26],"likely":[27],"correspond":[28],"to":[29,36,69,74,79,85,89,110,127,139,158,235],"domains":[31,108,118,198,222],"or":[32],"functional":[33],"motifs.":[34],"However,":[35],"limit":[37],"the":[38,80,91,120,145,171,183,207,217,220,244],"number":[39,115,172],"of":[40,93,103,116,147,168,170,173,180,182,206,216,219,225,237,243],"false":[41],"positives,":[42],"these":[43,148],"with":[47,112,190],"stringent":[48],"sequence-similarity":[49],"thresholds":[50],"hence":[52],"can":[53,187],"miss":[54],"several":[55],"hits,":[56],"especially":[57],"species":[59],"that":[60,186,231,236],"phylogenetically":[62],"distant":[63],"from":[64],"reference":[65],"organisms.":[66],"A":[67],"solution":[68],"this":[70,129],"problem":[71],"then":[73],"integrate":[75],"additional":[76],"contextual":[77],"information":[78,130],"procedure.":[81],"Here,":[82],"we":[83],"propose":[84,124],"use":[86],"domain":[87,142],"co-occurrence":[88,98],"increase":[90,167,179],"sensitivity":[92],"pairwise":[94],"sequence":[95],"comparisons.":[96],"Domain":[97],"a":[100,113,125,134,155,191],"strong":[101],"feature":[102],"proteins,":[104],"since":[105],"most":[106,202],"tend":[109],"appear":[111],"limited":[114],"other":[117],"on":[119,144],"same":[121],"protein.":[122],"We":[123,150],"method":[126,194],"take":[128],"into":[131],"account":[132],"typical":[135],"analysis":[137],"construct":[140],"new":[141,197,221],"families":[143],"basis":[146],"results.":[149],"Plasmodium":[152],"falciparum":[153],"as":[154],"case":[156],"study":[157,215],"evaluate":[159],"our":[160,214],"method.":[161],"The":[162],"experimental":[163],"findings":[164],"showed":[165],"14%":[169],"significant":[174],"hits":[176],"25%":[181],"proteome":[184],"area":[185],"be":[188,211],"covered":[189],"domain.":[192],"Our":[193],"identified":[195],"2240":[196],"which,":[200],"cases,":[203],"no":[204],"model":[205],"Pfam":[208,239],"database":[209],"could":[210],"linked.":[212],"Moreover,":[213],"quality":[218],"terms":[224],"physicochemical":[228],"properties":[229],"show":[230],"they":[232],"close":[234],"standard":[238],"domains.":[240],"Source":[241],"code":[242],"proposed":[245],"approach":[246],"supplementary":[248],"data":[249],"available":[251],"at:":[252],"https://gite.lirmm.fr/menichelli/pairwise-comparison-with-cooccurrence.":[253]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
