{"id":"https://openalex.org/W2806747943","doi":"https://doi.org/10.1186/s12859-018-2148-8","title":"Surveying alignment-free features for Ortholog detection in related yeast proteomes by using supervised big data classifiers","display_name":"Surveying alignment-free features for Ortholog detection in related yeast proteomes by using supervised big data classifiers","publication_year":2018,"publication_date":"2018-05-03","ids":{"openalex":"https://openalex.org/W2806747943","doi":"https://doi.org/10.1186/s12859-018-2148-8","mag":"2806747943","pmid":"https://pubmed.ncbi.nlm.nih.gov/29724166"},"language":"en","primary_location":{"id":"doi:10.1186/s12859-018-2148-8","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-018-2148-8","pdf_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/s12859-018-2148-8","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/s12859-018-2148-8","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063031157","display_name":"Deborah Galpert Ca\u0144izares","orcid":"https://orcid.org/0000-0002-5222-3324"},"institutions":[{"id":"https://openalex.org/I3018837529","display_name":"Universidad Central \"Marta Abreu\" de las Villas (UCLV)","ror":"https://ror.org/01cdy6h50","country_code":"CU","type":"education","lineage":["https://openalex.org/I3018837529"]}],"countries":["CU"],"is_corresponding":true,"raw_author_name":"Deborah Galpert","raw_affiliation_strings":["Departamento de Ciencia de la Computaci\u00f3n, Universidad Central \u00a8Marta Abreu\u00a8 de Las Villas (UCLV), 54830, Santa Clara, Cuba"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Departamento de Ciencia de la Computaci\u00f3n, Universidad Central \u00a8Marta Abreu\u00a8 de Las Villas (UCLV), 54830, Santa Clara, Cuba","institution_ids":["https://openalex.org/I3018837529"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090921348","display_name":"Alberto Fern\u00e1ndez","orcid":"https://orcid.org/0000-0002-6480-8434"},"institutions":[{"id":"https://openalex.org/I173304897","display_name":"Universidad de Granada","ror":"https://ror.org/04njjy449","country_code":"ES","type":"education","lineage":["https://openalex.org/I173304897"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Alberto Fern\u00e1ndez","raw_affiliation_strings":["Department of Computer Science and Artificial Intelligence, Research Center on Information and Communications Technology (CITIC-UGR), University of Granada, 18071, Granada, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Artificial Intelligence, Research Center on Information and Communications Technology (CITIC-UGR), University of Granada, 18071, Granada, Spain","institution_ids":["https://openalex.org/I173304897"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045016749","display_name":"Francisco Herrera","orcid":"https://orcid.org/0000-0002-7283-312X"},"institutions":[{"id":"https://openalex.org/I173304897","display_name":"Universidad de Granada","ror":"https://ror.org/04njjy449","country_code":"ES","type":"education","lineage":["https://openalex.org/I173304897"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Francisco Herrera","raw_affiliation_strings":["Department of Computer Science and Artificial Intelligence, Research Center on Information and Communications Technology (CITIC-UGR), University of Granada, 18071, Granada, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Artificial Intelligence, Research Center on Information and Communications Technology (CITIC-UGR), University of Granada, 18071, Granada, Spain","institution_ids":["https://openalex.org/I173304897"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017842519","display_name":"Agostinho Antunes","orcid":"https://orcid.org/0000-0002-1328-1732"},"institutions":[{"id":"https://openalex.org/I182534213","display_name":"Universidade do Porto","ror":"https://ror.org/043pwc612","country_code":"PT","type":"education","lineage":["https://openalex.org/I182534213"]}],"countries":["PT"],"is_corresponding":true,"raw_author_name":"Agostinho Antunes","raw_affiliation_strings":["CIIMAR/CIMAR, Centro Interdisciplinar de Investiga\u00e7\u00e3o Marinha e Ambiental, Universidade do Porto, Terminal de Cruzeiros do Porto de Leix\u00f5es, Av. General Norton de Matos s/n 4450-208 Matosinhos, Porto, Portugal","Departamento de Biologia, Faculdade de Ci\u00eancias, Universidade do Porto, Rua do Campo Alegre, 4169-007, Porto, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CIIMAR/CIMAR, Centro Interdisciplinar de Investiga\u00e7\u00e3o Marinha e Ambiental, Universidade do Porto, Terminal de Cruzeiros do Porto de Leix\u00f5es, Av. General Norton de Matos s/n 4450-208 Matosinhos, Porto, Portugal","institution_ids":["https://openalex.org/I182534213"]},{"raw_affiliation_string":"Departamento de Biologia, Faculdade de Ci\u00eancias, Universidade do Porto, Rua do Campo Alegre, 4169-007, Porto, Portugal","institution_ids":["https://openalex.org/I182534213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009956308","display_name":"Reinaldo Molina","orcid":"https://orcid.org/0000-0001-5098-5432"},"institutions":[{"id":"https://openalex.org/I3018837529","display_name":"Universidad Central \"Marta Abreu\" de las Villas (UCLV)","ror":"https://ror.org/01cdy6h50","country_code":"CU","type":"education","lineage":["https://openalex.org/I3018837529"]}],"countries":["CU"],"is_corresponding":true,"raw_author_name":"Reinaldo Molina-Ruiz","raw_affiliation_strings":["Centro de Bioactivos Qu\u00edmicos (CBQ), Universidad Central \u00a8Marta Abreu\u00a8 de Las Villas (UCLV), 54830, Santa Clara, Cuba"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centro de Bioactivos Qu\u00edmicos (CBQ), Universidad Central \u00a8Marta Abreu\u00a8 de Las Villas (UCLV), 54830, Santa Clara, Cuba","institution_ids":["https://openalex.org/I3018837529"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000044766","display_name":"Guillerm\u0131\u0301n Ag\u00fcero-Chapin","orcid":"https://orcid.org/0000-0002-9908-2418"},"institutions":[{"id":"https://openalex.org/I182534213","display_name":"Universidade do Porto","ror":"https://ror.org/043pwc612","country_code":"PT","type":"education","lineage":["https://openalex.org/I182534213"]},{"id":"https://openalex.org/I3018837529","display_name":"Universidad Central \"Marta Abreu\" de las Villas (UCLV)","ror":"https://ror.org/01cdy6h50","country_code":"CU","type":"education","lineage":["https://openalex.org/I3018837529"]},{"id":"https://openalex.org/I4210108197","display_name":"Universidad Central","ror":"https://ror.org/01kyyzm82","country_code":"BO","type":"education","lineage":["https://openalex.org/I4210108197"]},{"id":"https://openalex.org/I4210111418","display_name":"Universidad Central","ror":"https://ror.org/01wnb0b83","country_code":"CR","type":"education","lineage":["https://openalex.org/I4210111418"]}],"countries":["BO","CR","CU","PT"],"is_corresponding":true,"raw_author_name":"Guillermin Ag\u00fcero-Chapin","raw_affiliation_strings":["CIIMAR/CIMAR, Centro Interdisciplinar de Investiga\u00e7\u00e3o Marinha e Ambiental, Universidade do Porto, Terminal de Cruzeiros do Porto de Leix\u00f5es, Av. General Norton de Matos s/n 4450-208 Matosinhos, Porto, Portugal. gchapin@ciimar.up.pt","Centro de Bioactivos Qu\u00edmicos (CBQ), Universidad Central \u00a8Marta Abreu\u00a8 de Las Villas (UCLV), 54830, Santa Clara, Cuba. gchapin@ciimar.up.pt","Departamento de Biologia, Faculdade de Ci\u00eancias, Universidade do Porto, Rua do Campo Alegre, 4169-007, Porto, Portugal. gchapin@ciimar.up.pt","CIIMAR/CIMAR, Centro Interdisciplinar de Investiga\u00e7\u00e3o Marinha e Ambiental, Universidade do Porto, Terminal de Cruzeiros do Porto de Leix\u00f5es, Av. General Norton de Matos s/n 4450-208 Matosinhos, Porto, Portugal"],"raw_orcid":"https://orcid.org/0000-0002-9908-2418","affiliations":[{"raw_affiliation_string":"CIIMAR/CIMAR, Centro Interdisciplinar de Investiga\u00e7\u00e3o Marinha e Ambiental, Universidade do Porto, Terminal de Cruzeiros do Porto de Leix\u00f5es, Av. General Norton de Matos s/n 4450-208 Matosinhos, Porto, Portugal. gchapin@ciimar.up.pt","institution_ids":["https://openalex.org/I182534213"]},{"raw_affiliation_string":"Centro de Bioactivos Qu\u00edmicos (CBQ), Universidad Central \u00a8Marta Abreu\u00a8 de Las Villas (UCLV), 54830, Santa Clara, Cuba. gchapin@ciimar.up.pt","institution_ids":["https://openalex.org/I3018837529","https://openalex.org/I4210111418","https://openalex.org/I4210108197"]},{"raw_affiliation_string":"Departamento de Biologia, Faculdade de Ci\u00eancias, Universidade do Porto, Rua do Campo Alegre, 4169-007, Porto, Portugal. gchapin@ciimar.up.pt","institution_ids":["https://openalex.org/I182534213"]},{"raw_affiliation_string":"CIIMAR/CIMAR, Centro Interdisciplinar de Investiga\u00e7\u00e3o Marinha e Ambiental, Universidade do Porto, Terminal de Cruzeiros do Porto de Leix\u00f5es, Av. General Norton de Matos s/n 4450-208 Matosinhos, Porto, Portugal","institution_ids":["https://openalex.org/I182534213"]}]}],"institutions":[],"countries_distinct_count":5,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5000044766","https://openalex.org/A5009956308","https://openalex.org/A5017842519","https://openalex.org/A5045016749","https://openalex.org/A5063031157","https://openalex.org/A5090921348"],"corresponding_institution_ids":["https://openalex.org/I173304897","https://openalex.org/I182534213","https://openalex.org/I3018837529","https://openalex.org/I4210108197","https://openalex.org/I4210111418"],"apc_list":{"value":1690,"currency":"GBP","value_usd":2072},"apc_paid":{"value":1690,"currency":"GBP","value_usd":2072},"fwci":0.2784,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.56932304,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"19","issue":"1","first_page":"166","last_page":"166"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.6173999905586243,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.6173999905586243,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.20749999582767487,"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/T12576","display_name":"vaccines and immunoinformatics approaches","score":0.10199999809265137,"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/pairwise-comparison","display_name":"Pairwise comparison","score":0.6802613735198975},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6140150427818298},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5863345861434937},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.5665155649185181},{"id":"https://openalex.org/keywords/proteome","display_name":"Proteome","score":0.5606508851051331},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4882214367389679},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.4743034839630127},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4685462713241577},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.4616730213165283},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.44049137830734253},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.36212795972824097},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.3608998656272888},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.2725899815559387}],"concepts":[{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.6802613735198975},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6140150427818298},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5863345861434937},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.5665155649185181},{"id":"https://openalex.org/C104397665","wikidata":"https://www.wikidata.org/wiki/Q860947","display_name":"Proteome","level":2,"score":0.5606508851051331},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4882214367389679},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.4743034839630127},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4685462713241577},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.4616730213165283},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44049137830734253},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.36212795972824097},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.3608998656272888},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.2725899815559387},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003663","descriptor_name":"Decision Trees","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003663","descriptor_name":"Decision Trees","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003663","descriptor_name":"Decision Trees","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012441","descriptor_name":"Saccharomyces cerevisiae","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D012441","descriptor_name":"Saccharomyces cerevisiae","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D012441","descriptor_name":"Saccharomyces cerevisiae","qualifier_ui":"Q000378","qualifier_name":"metabolism","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":"D020543","descriptor_name":"Proteome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D020543","descriptor_name":"Proteome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D020543","descriptor_name":"Proteome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D029701","descriptor_name":"Saccharomyces cerevisiae Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D029701","descriptor_name":"Saccharomyces cerevisiae Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D029701","descriptor_name":"Saccharomyces cerevisiae Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"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":7,"locations":[{"id":"doi:10.1186/s12859-018-2148-8","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-018-2148-8","pdf_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/s12859-018-2148-8","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},{"id":"pmid:29724166","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/29724166","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":"BMC bioinformatics","raw_type":null},{"id":"pmh:oai:digibug.ugr.es:10481/55857","is_oa":true,"landing_page_url":"http://hdl.handle.net/10481/55857","pdf_url":null,"source":{"id":"https://openalex.org/S4306400567","display_name":"Institutional Repository of the University of Granada (University of Granada)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I173304897","host_organization_name":"Universidad de Granada","host_organization_lineage":["https://openalex.org/I173304897"],"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":"","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:doaj.org/article:08f0f24c51e6428893bc41563875fc20","is_oa":true,"landing_page_url":"https://doaj.org/article/08f0f24c51e6428893bc41563875fc20","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics, Vol 19, Iss 1, Pp 1-17 (2018)","raw_type":"article"},{"id":"pmh:oai:europepmc.org:4860626","is_oa":true,"landing_page_url":"http://europepmc.org/pmc/articles/PMC5934817","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:5934817","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/5934817","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics","raw_type":"Text"},{"id":"pmh:oai:repositorio-aberto.up.pt:10216/120462","is_oa":true,"landing_page_url":"https://hdl.handle.net/10216/120462","pdf_url":null,"source":{"id":"https://openalex.org/S4306402433","display_name":"Portuguese National Funding Agency for Science, Research and Technology (RCAAP Project by FCT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"journal article"}],"best_oa_location":{"id":"doi:10.1186/s12859-018-2148-8","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-018-2148-8","pdf_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/s12859-018-2148-8","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/15","score":0.5600000023841858,"display_name":"Life in Land"}],"awards":[{"id":"https://openalex.org/G1516346500","display_name":null,"funder_award_id":"01-0145","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"},{"id":"https://openalex.org/G3511642293","display_name":null,"funder_award_id":"NORTE-01-0145-FEDER-000031","funder_id":"https://openalex.org/F4320335322","funder_display_name":"European Regional Development Fund"},{"id":"https://openalex.org/G3550249319","display_name":null,"funder_award_id":"NORTE 2020","funder_id":"https://openalex.org/F4320335322","funder_display_name":"European Regional Development Fund"},{"id":"https://openalex.org/G4724859719","display_name":null,"funder_award_id":"01-0145","funder_id":"https://openalex.org/F4320335322","funder_display_name":"European Regional Development Fund"},{"id":"https://openalex.org/G6603360721","display_name":null,"funder_award_id":"PORTUGAL 2020","funder_id":"https://openalex.org/F4320335322","funder_display_name":"European Regional Development Fund"},{"id":"https://openalex.org/G7584003722","display_name":null,"funder_award_id":"NORTE-01-0145","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"},{"id":"https://openalex.org/G7623127295","display_name":null,"funder_award_id":"SFRH/BPD/92978/2013","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"},{"id":"https://openalex.org/G8073781356","display_name":null,"funder_award_id":"NORTE-01-0145-FEDER-000031","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"},{"id":"https://openalex.org/G8274051256","display_name":null,"funder_award_id":"NORTE 2020","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"},{"id":"https://openalex.org/G843627452","display_name":null,"funder_award_id":"SFRH/BPD/92978/2013","funder_id":"https://openalex.org/F4320335322","funder_display_name":"European Regional Development Fund"}],"funders":[{"id":"https://openalex.org/F4320334779","display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia","ror":"https://ror.org/00snfqn58"},{"id":"https://openalex.org/F4320335322","display_name":"European Regional Development Fund","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2806747943.pdf","grobid_xml":"https://content.openalex.org/works/W2806747943.grobid-xml"},"referenced_works_count":63,"referenced_works":["https://openalex.org/W184299416","https://openalex.org/W1485408073","https://openalex.org/W1530303756","https://openalex.org/W1547142901","https://openalex.org/W1617947194","https://openalex.org/W1865899696","https://openalex.org/W1964612763","https://openalex.org/W1970613018","https://openalex.org/W1990453950","https://openalex.org/W1992221283","https://openalex.org/W1992311227","https://openalex.org/W1993711987","https://openalex.org/W2008856488","https://openalex.org/W2009234149","https://openalex.org/W2010473599","https://openalex.org/W2014682834","https://openalex.org/W2019488416","https://openalex.org/W2025089689","https://openalex.org/W2034070267","https://openalex.org/W2037883697","https://openalex.org/W2038968181","https://openalex.org/W2042084565","https://openalex.org/W2045911289","https://openalex.org/W2047672715","https://openalex.org/W2048448217","https://openalex.org/W2075006095","https://openalex.org/W2075171145","https://openalex.org/W2099321785","https://openalex.org/W2101347991","https://openalex.org/W2110506769","https://openalex.org/W2112072385","https://openalex.org/W2112884978","https://openalex.org/W2114358087","https://openalex.org/W2114606763","https://openalex.org/W2117602634","https://openalex.org/W2121479060","https://openalex.org/W2127660113","https://openalex.org/W2131975293","https://openalex.org/W2138486754","https://openalex.org/W2142096960","https://openalex.org/W2143592941","https://openalex.org/W2145100181","https://openalex.org/W2145957695","https://openalex.org/W2152800101","https://openalex.org/W2154044807","https://openalex.org/W2158714788","https://openalex.org/W2159266221","https://openalex.org/W2160257187","https://openalex.org/W2161472339","https://openalex.org/W2161550872","https://openalex.org/W2167188257","https://openalex.org/W2168048337","https://openalex.org/W2171963266","https://openalex.org/W2173213060","https://openalex.org/W2180806933","https://openalex.org/W2184648260","https://openalex.org/W2279172997","https://openalex.org/W2593875029","https://openalex.org/W2754472824","https://openalex.org/W2764005395","https://openalex.org/W2954364924","https://openalex.org/W2963288913","https://openalex.org/W4238585340"],"related_works":["https://openalex.org/W2487162673","https://openalex.org/W2378211422","https://openalex.org/W2942366970","https://openalex.org/W2793211469","https://openalex.org/W2949152769","https://openalex.org/W4372354731","https://openalex.org/W1482441085","https://openalex.org/W2966858528","https://openalex.org/W2894446834","https://openalex.org/W2151687600"],"abstract_inverted_index":{"BACKGROUND:":[0],"The":[1,63,147,260,286],"development":[2],"of":[3,11,15,121,127,203,218,288,318,324,332],"new":[4],"ortholog":[5,29,47,139,180,300,326],"detection":[6,140,181,301,327],"algorithms":[7,106],"and":[8,44,68,79,103,151,156,159,207,225],"the":[9,45,104,119,125,132,175,200,215,219,243,271,275,306,316,330],"improvement":[10],"existing":[12],"ones":[13],"are":[14],"major":[16],"importance":[17],"in":[18,33,89,131,141,182,230,291,302,338],"functional":[19],"genomics.":[20],"We":[21],"have":[22],"previously":[23],"introduced":[24],"a":[25,34,71,90,110,237,250,256],"successful":[26],"supervised":[27,64,91,128,189,292],"pairwise":[28,41,84,138,171],"classification":[30,177,307,320],"approach":[31],"implemented":[32,130],"big":[35,92,134,293],"data":[36,93,135,294],"platform":[37,136],"that":[38,254,265,323],"considered":[39],"several":[40,83,142,169],"protein":[42,85,172,335],"features":[43,86,102,123,173,227,267,279,290],"low":[46],"pair":[48,253,336],"ratios":[49],"found":[50],"between":[51,199],"two":[52],"annotated":[53],"proteomes":[54,304],"(Galpert,":[55],"D":[56],"et":[57],"al.,":[58],"BioMed":[59],"Research":[60],"International,":[61],"2015).":[62],"models":[65,129,295],"were":[66,100,107,195,228,268,277],"built":[67,160],"tested":[69],"using":[70],"Saccharomycete":[72],"yeast":[73,144,184,251,303],"benchmark":[74],"dataset":[75],"proposed":[76,105],"by":[77],"Salichos":[78],"Rokas":[80],"(2011).":[81],"Despite":[82],"being":[87],"combined":[88,167,229],"approach;":[94],"they":[95],"all,":[96],"to":[97,117,281,322],"some":[98],"extent":[99],"alignment-based":[101,163,204,224,266,312],"evaluated":[108],"on":[109,124],"unique":[111],"test":[112],"set.":[113],"Here,":[114],"we":[115],"aim":[116],"evaluate":[118],"impact":[120],"alignment-free":[122,170,211,226,278,289,334],"performance":[126,178,321],"Spark":[133,148,231],"for":[137,179,249,270],"related":[143,280],"proteomes.":[145,221],"RESULTS:":[146],"Random":[149],"Forest":[150],"Decision":[152,232],"Trees":[153,233],"with":[154,161,168,210,234,310],"oversampling":[155],"undersampling":[157],"techniques,":[158],"only":[162],"similarity":[164,205,313,317],"measures":[165,206],"or":[166],"showed":[174,264],"highest":[176],"three":[183],"proteome":[185,252],"pairs.":[186],"Although":[187],"such":[188],"approaches":[190],"outperformed":[191],"traditional":[192,325],"methods,":[193],"there":[194],"no":[196],"significant":[197],"differences":[198],"exclusive":[201],"use":[202],"their":[208,319],"combination":[209],"features,":[212],"even":[213],"within":[214,242],"twilight":[216,244],"zone":[217,245],"studied":[220],"Just":[222],"when":[223],"imbalance":[235],"management,":[236],"higher":[238],"success":[239],"rate":[240],"(98.71%)":[241],"could":[246],"be":[247],"achieved":[248,309],"underwent":[255],"whole":[257],"genome":[258],"duplication.":[259],"feature":[261],"selection":[262],"study":[263],"top-ranked":[269],"best":[272],"classifiers":[273],"while":[274],"runners-up":[276],"amino":[282],"acid":[283],"composition.":[284],"CONCLUSIONS:":[285],"incorporation":[287],"did":[296],"not":[297],"significantly":[298],"improve":[299],"regarding":[305],"qualities":[308],"just":[311],"measures.":[314],"However,":[315],"methods":[328],"encourages":[329],"evaluation":[331],"other":[333],"descriptors":[337],"future":[339],"research.":[340]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2}],"updated_date":"2026-06-19T17:40:00.097472","created_date":"2025-10-10T00:00:00"}
