{"id":"https://openalex.org/W2143738072","doi":"https://doi.org/10.1093/bioinformatics/btg089","title":"EPPS: mining the COG database by an extended phylogeneticpatterns search","display_name":"EPPS: mining the COG database by an extended phylogeneticpatterns search","publication_year":2003,"publication_date":"2003-04-11","ids":{"openalex":"https://openalex.org/W2143738072","doi":"https://doi.org/10.1093/bioinformatics/btg089","mag":"2143738072","pmid":"https://pubmed.ncbi.nlm.nih.gov/12691996"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btg089","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btg089","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/19/6/784/48903939/bioinformatics_19_6_784.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/19/6/784/48903939/bioinformatics_19_6_784.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048548226","display_name":"Klaus Reichard","orcid":null},"institutions":[{"id":"https://openalex.org/I155976169","display_name":"Witten/Herdecke University","ror":"https://ror.org/00yq55g44","country_code":"DE","type":"education","lineage":["https://openalex.org/I155976169"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Klaus Reichard","raw_affiliation_strings":["Institute of Mathematics, AG Statistics Institute of Neurobiochemistry, AG Proteinchemistry, University of Witten/Herdecke, Stockumer Str. 10, 58448 Witten, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Mathematics, AG Statistics Institute of Neurobiochemistry, AG Proteinchemistry, University of Witten/Herdecke, Stockumer Str. 10, 58448 Witten, Germany","institution_ids":["https://openalex.org/I155976169"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011299508","display_name":"Michael Kaufmann","orcid":"https://orcid.org/0000-0001-7595-1386"},"institutions":[{"id":"https://openalex.org/I155976169","display_name":"Witten/Herdecke University","ror":"https://ror.org/00yq55g44","country_code":"DE","type":"education","lineage":["https://openalex.org/I155976169"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Michael Kaufmann","raw_affiliation_strings":["Witten-Herdecke University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Witten-Herdecke University","institution_ids":["https://openalex.org/I155976169"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I155976169"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":0.7982,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.70459382,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"19","issue":"6","first_page":"784","last_page":"785"},"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/T10012","display_name":"Genetic diversity and population structure","score":0.9952999949455261,"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"}},{"id":"https://openalex.org/T10434","display_name":"Chromosomal and Genetic Variations","score":0.9731000065803528,"subfield":{"id":"https://openalex.org/subfields/1110","display_name":"Plant Science"},"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/executable","display_name":"Executable","score":0.8947141766548157},{"id":"https://openalex.org/keywords/phylogenetic-tree","display_name":"Phylogenetic tree","score":0.8073433637619019},{"id":"https://openalex.org/keywords/cog","display_name":"Cog","score":0.6805011630058289},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5723528265953064},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4669913351535797},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.4138840436935425},{"id":"https://openalex.org/keywords/microsoft-windows","display_name":"Microsoft Windows","score":0.4125169813632965},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.37814104557037354},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.3081331253051758},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.26646536588668823},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.21404463052749634},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.1581745743751526}],"concepts":[{"id":"https://openalex.org/C160145156","wikidata":"https://www.wikidata.org/wiki/Q778586","display_name":"Executable","level":2,"score":0.8947141766548157},{"id":"https://openalex.org/C193252679","wikidata":"https://www.wikidata.org/wiki/Q242125","display_name":"Phylogenetic tree","level":3,"score":0.8073433637619019},{"id":"https://openalex.org/C4661277","wikidata":"https://www.wikidata.org/wiki/Q1054157","display_name":"Cog","level":2,"score":0.6805011630058289},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5723528265953064},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4669913351535797},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.4138840436935425},{"id":"https://openalex.org/C508378895","wikidata":"https://www.wikidata.org/wiki/Q1406","display_name":"Microsoft Windows","level":3,"score":0.4125169813632965},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37814104557037354},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.3081331253051758},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26646536588668823},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.21404463052749634},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.1581745743751526},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[{"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":"D003628","descriptor_name":"Database Management Systems","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003628","descriptor_name":"Database Management Systems","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003628","descriptor_name":"Database Management Systems","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010802","descriptor_name":"Phylogeny","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D010802","descriptor_name":"Phylogeny","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D010802","descriptor_name":"Phylogeny","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000145","qualifier_name":"classification","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":"D012680","descriptor_name":"Sensitivity and Specificity","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012680","descriptor_name":"Sensitivity and Specificity","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012680","descriptor_name":"Sensitivity and Specificity","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015203","descriptor_name":"Reproducibility of Results","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015203","descriptor_name":"Reproducibility of Results","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015203","descriptor_name":"Reproducibility of Results","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","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":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017124","descriptor_name":"Conserved Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017124","descriptor_name":"Conserved Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017124","descriptor_name":"Conserved Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017386","descriptor_name":"Sequence Homology, Amino Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D017386","descriptor_name":"Sequence Homology, Amino Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D017386","descriptor_name":"Sequence Homology, Amino Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":4,"locations":[{"id":"doi:10.1093/bioinformatics/btg089","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btg089","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/19/6/784/48903939/bioinformatics_19_6_784.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:12691996","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/12691996","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:CiteSeerX.psu:10.1.1.853.399","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.853.399","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://bioinformatics.oxfordjournals.org/content/19/6/784.full.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.860.1268","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.860.1268","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.biosino.org/bioinformatics/EPPS%20mining%20the%20COG%20database%20by%20an%20extended%20phylogenetic%20patterns%20search.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btg089","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btg089","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/19/6/784/48903939/bioinformatics_19_6_784.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":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W1990453950","https://openalex.org/W1995686191","https://openalex.org/W2023218781","https://openalex.org/W2165390912","https://openalex.org/W2169929748"],"related_works":["https://openalex.org/W2370021894","https://openalex.org/W2350807346","https://openalex.org/W2143738072","https://openalex.org/W2160423863","https://openalex.org/W2150707112","https://openalex.org/W2769887238","https://openalex.org/W2061763576","https://openalex.org/W1972362308","https://openalex.org/W2139658365","https://openalex.org/W2069010617"],"abstract_inverted_index":{"Abstract":[0],"Summary:":[1],"EPPS":[2,79,108],"runs":[3],"under":[4],"Microsoft":[5],"Windows.":[6],"It":[7],"is":[8,23,51,109],"an":[9],"extended":[10],"version":[11],"of":[12,21,27,41,60,66],"the":[13,24,34,38,47,58,61,64,74,81,104],"phylogenetic":[14,31,76],"patterns":[15],"search":[16,62],"(PPS).":[17],"The":[18,54],"output":[19,105],"condition":[20],"PPS":[22],"exact":[25],"match":[26,73],"a":[28],"user":[29,55],"defined":[30,89,97],"pattern":[32,35],"with":[33],"represented":[36],"by":[37,63],"respective":[39],"cluster":[40],"orthologous":[42],"groups":[43],"(COG).":[44],"In":[45],"contrast,":[46],"software":[48],"described":[49],"here":[50],"less":[52],"restrictive.":[53],"may":[56],"define":[57],"accuracy":[59],"number":[65],"genomes":[67],"that":[68],"are":[69,93,101,118],"allowed":[70],"not":[71,94],"to":[72,83,90,98],"predefined":[75],"pattern.":[77],"Thus,":[78],"has":[80],"advantage":[82],"detect":[84],"COGs":[85],"even":[86],"if":[87],"organisms":[88,96],"be":[91,99,129],"included":[92],"or":[95],"excluded":[100],"present":[102],"in":[103],"COGs.":[106],"Availability:":[107],"free":[110],"and":[111,115],"both":[112],"windows":[113],"executable":[114],"source":[116],"code":[117],"available":[119],"at":[120],"http://www.uni-wh.de/de/nawi/institut/protein/epps.html":[121],"Contact:":[122],"mika@uni-wh.de":[123],"*":[124],"To":[125],"whom":[126],"correspondence":[127],"should":[128],"addressed.":[130]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
