{"id":"https://openalex.org/W2737578470","doi":"https://doi.org/10.1186/s12859-017-1758-x","title":"Exploring general-purpose protein features for distinguishing enzymes and non-enzymes within the twilight zone","display_name":"Exploring general-purpose protein features for distinguishing enzymes and non-enzymes within the twilight zone","publication_year":2017,"publication_date":"2017-07-21","ids":{"openalex":"https://openalex.org/W2737578470","doi":"https://doi.org/10.1186/s12859-017-1758-x","mag":"2737578470","pmid":"https://pubmed.ncbi.nlm.nih.gov/28732462"},"language":"en","primary_location":{"id":"doi:10.1186/s12859-017-1758-x","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-017-1758-x","pdf_url":"https://link.springer.com/content/pdf/10.1186/s12859-017-1758-x.pdf","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://link.springer.com/content/pdf/10.1186/s12859-017-1758-x.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054389046","display_name":"Yasser B. Ruiz\u2010Blanco","orcid":"https://orcid.org/0000-0001-5400-4427"},"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"]},{"id":"https://openalex.org/I4210090782","display_name":"Max-Planck-Institut f\u00fcr Kohlenforschung","ror":"https://ror.org/00a7vgh58","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210090782"]}],"countries":["CU","DE"],"is_corresponding":false,"raw_author_name":"Yasser B. Ruiz-Blanco","raw_affiliation_strings":["Facultad de Qu\u00edmica y Farmacia, Universidad Central \"Marta Abreu\" de Las Villas, 54830, Santa Clara, Cuba","Theoretical Chemistry, Max Planck Institute f\u00fcr Kohlenforschung, 45470, Mulheim an der Ruhr, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facultad de Qu\u00edmica y Farmacia, Universidad Central \"Marta Abreu\" de Las Villas, 54830, Santa Clara, Cuba","institution_ids":["https://openalex.org/I3018837529"]},{"raw_affiliation_string":"Theoretical Chemistry, Max Planck Institute f\u00fcr Kohlenforschung, 45470, Mulheim an der Ruhr, Germany","institution_ids":["https://openalex.org/I4210090782"]}]},{"author_position":"middle","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":["CIMAR/CIIMAR, 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, 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","CIMAR/CIIMAR, 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, Porto, Portugal"],"raw_orcid":"https://orcid.org/0000-0002-9908-2418","affiliations":[{"raw_affiliation_string":"CIMAR/CIIMAR, 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, 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/I4210108197","https://openalex.org/I4210111418"]},{"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":"CIMAR/CIIMAR, 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, Porto, Portugal","institution_ids":["https://openalex.org/I182534213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000961076","display_name":"Enrique Garc\u00eda\u2010Hern\u00e1ndez","orcid":"https://orcid.org/0000-0003-4561-4973"},"institutions":[{"id":"https://openalex.org/I8961855","display_name":"Universidad Nacional Aut\u00f3noma de M\u00e9xico","ror":"https://ror.org/01tmp8f25","country_code":"MX","type":"education","lineage":["https://openalex.org/I8961855"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Enrique Garc\u00eda-Hern\u00e1ndez","raw_affiliation_strings":["Instituto de Qu\u00edmica, Universidad Nacional Aut\u00f3noma de M\u00e9xico (UNAM), 04360, D.F, M\u00e9xico, Mexico"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Instituto de Qu\u00edmica, Universidad Nacional Aut\u00f3noma de M\u00e9xico (UNAM), 04360, D.F, M\u00e9xico, Mexico","institution_ids":["https://openalex.org/I8961855"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035402210","display_name":"Orlando \u00c1lvarez","orcid":"https://orcid.org/0000-0002-4335-2255"},"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":false,"raw_author_name":"Orlando \u00c1lvarez","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":"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":false,"raw_author_name":"Agostinho Antunes","raw_affiliation_strings":["CIMAR/CIIMAR, 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, 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":"CIMAR/CIIMAR, 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, 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":"last","author":{"id":"https://openalex.org/A5078223816","display_name":"James R. Green","orcid":"https://orcid.org/0000-0002-6039-2355"},"institutions":[{"id":"https://openalex.org/I67031392","display_name":"Carleton University","ror":"https://ror.org/02qtvee93","country_code":"CA","type":"education","lineage":["https://openalex.org/I67031392"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"James Green","raw_affiliation_strings":["Department of Systems and Computer Engineering, Carleton University, Ottawa, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Systems and Computer Engineering, Carleton University, Ottawa, Canada","institution_ids":["https://openalex.org/I67031392"]}]}],"institutions":[],"countries_distinct_count":7,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5000044766"],"corresponding_institution_ids":["https://openalex.org/I182534213","https://openalex.org/I3018837529","https://openalex.org/I4210108197","https://openalex.org/I4210111418"],"apc_list":{"value":2790,"currency":"USD","value_usd":2790},"apc_paid":{"value":2790,"currency":"USD","value_usd":2790},"fwci":0.8108,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":{"value":0.70760186,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"18","issue":"1","first_page":"349","last_page":"349"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9984999895095825,"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/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.9958000183105469,"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/benchmark","display_name":"Benchmark (surveying)","score":0.6876267194747925},{"id":"https://openalex.org/keywords/proteome","display_name":"Proteome","score":0.6179206967353821},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.6095077991485596},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5806167721748352},{"id":"https://openalex.org/keywords/protein-function-prediction","display_name":"Protein function prediction","score":0.5740734338760376},{"id":"https://openalex.org/keywords/structural-bioinformatics","display_name":"Structural bioinformatics","score":0.5732433199882507},{"id":"https://openalex.org/keywords/protein-structure-database","display_name":"Protein structure database","score":0.5670176148414612},{"id":"https://openalex.org/keywords/sequence-alignment","display_name":"Sequence alignment","score":0.535744845867157},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5343244671821594},{"id":"https://openalex.org/keywords/structural-alignment","display_name":"Structural alignment","score":0.5109645128250122},{"id":"https://openalex.org/keywords/protein-methods","display_name":"Protein methods","score":0.5010390281677246},{"id":"https://openalex.org/keywords/protein-sequencing","display_name":"Protein sequencing","score":0.4903585910797119},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.4786578416824341},{"id":"https://openalex.org/keywords/protein-family","display_name":"Protein family","score":0.4750090539455414},{"id":"https://openalex.org/keywords/protein-function","display_name":"Protein function","score":0.45295250415802},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4523315727710724},{"id":"https://openalex.org/keywords/structural-similarity","display_name":"Structural similarity","score":0.45001286268234253},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.445730984210968},{"id":"https://openalex.org/keywords/protein-structure","display_name":"Protein structure","score":0.43637269735336304},{"id":"https://openalex.org/keywords/multiple-sequence-alignment","display_name":"Multiple sequence alignment","score":0.4273764193058014},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38379737734794617},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.34660351276397705},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.32531580328941345},{"id":"https://openalex.org/keywords/peptide-sequence","display_name":"Peptide sequence","score":0.28978902101516724},{"id":"https://openalex.org/keywords/sequence-database","display_name":"Sequence database","score":0.20219358801841736},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.1920894980430603},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.13891828060150146},{"id":"https://openalex.org/keywords/biochemistry","display_name":"Biochemistry","score":0.08054384589195251}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6876267194747925},{"id":"https://openalex.org/C104397665","wikidata":"https://www.wikidata.org/wiki/Q860947","display_name":"Proteome","level":2,"score":0.6179206967353821},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.6095077991485596},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5806167721748352},{"id":"https://openalex.org/C207060522","wikidata":"https://www.wikidata.org/wiki/Q7251473","display_name":"Protein function prediction","level":4,"score":0.5740734338760376},{"id":"https://openalex.org/C69131567","wikidata":"https://www.wikidata.org/wiki/Q2068215","display_name":"Structural bioinformatics","level":3,"score":0.5732433199882507},{"id":"https://openalex.org/C136475424","wikidata":"https://www.wikidata.org/wiki/Q7251500","display_name":"Protein structure database","level":4,"score":0.5670176148414612},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.535744845867157},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5343244671821594},{"id":"https://openalex.org/C4668613","wikidata":"https://www.wikidata.org/wiki/Q4116110","display_name":"Structural alignment","level":5,"score":0.5109645128250122},{"id":"https://openalex.org/C111364199","wikidata":"https://www.wikidata.org/wiki/Q2915896","display_name":"Protein methods","level":4,"score":0.5010390281677246},{"id":"https://openalex.org/C10010492","wikidata":"https://www.wikidata.org/wiki/Q3142557","display_name":"Protein sequencing","level":4,"score":0.4903585910797119},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.4786578416824341},{"id":"https://openalex.org/C171897839","wikidata":"https://www.wikidata.org/wiki/Q417841","display_name":"Protein family","level":3,"score":0.4750090539455414},{"id":"https://openalex.org/C2986374874","wikidata":"https://www.wikidata.org/wiki/Q8054","display_name":"Protein function","level":3,"score":0.45295250415802},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4523315727710724},{"id":"https://openalex.org/C139489369","wikidata":"https://www.wikidata.org/wiki/Q770846","display_name":"Structural similarity","level":2,"score":0.45001286268234253},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.445730984210968},{"id":"https://openalex.org/C47701112","wikidata":"https://www.wikidata.org/wiki/Q735188","display_name":"Protein structure","level":2,"score":0.43637269735336304},{"id":"https://openalex.org/C88031987","wikidata":"https://www.wikidata.org/wiki/Q1377767","display_name":"Multiple sequence alignment","level":5,"score":0.4273764193058014},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38379737734794617},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.34660351276397705},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.32531580328941345},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.28978902101516724},{"id":"https://openalex.org/C41584329","wikidata":"https://www.wikidata.org/wiki/Q175902","display_name":"Sequence database","level":3,"score":0.20219358801841736},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.1920894980430603},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.13891828060150146},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.08054384589195251},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"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":"D001426","descriptor_name":"Bacterial Proteins","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001426","descriptor_name":"Bacterial Proteins","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001426","descriptor_name":"Bacterial Proteins","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D004798","descriptor_name":"Enzymes","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D004798","descriptor_name":"Enzymes","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D004798","descriptor_name":"Enzymes","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":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020543","descriptor_name":"Proteome","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D020543","descriptor_name":"Proteome","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D020543","descriptor_name":"Proteome","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D020592","descriptor_name":"Shewanella","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D020592","descriptor_name":"Shewanella","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D020592","descriptor_name":"Shewanella","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D060388","descriptor_name":"Support Vector Machine","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D060388","descriptor_name":"Support Vector Machine","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D060388","descriptor_name":"Support Vector Machine","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":7,"locations":[{"id":"doi:10.1186/s12859-017-1758-x","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-017-1758-x","pdf_url":"https://link.springer.com/content/pdf/10.1186/s12859-017-1758-x.pdf","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:28732462","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/28732462","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:carleton.ca:14455","is_oa":true,"landing_page_url":"https://ir.library.carleton.ca/pub/14455","pdf_url":null,"source":{"id":"https://openalex.org/S4306402514","display_name":"Carleton University's Institutional Repository (MacOdrum Library, Carleton University)","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":"BMC Bioinformatics vol. 18 no. 1","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:doaj.org/article:ff0a29516e424b4d854ec40d0e209808","is_oa":true,"landing_page_url":"https://doaj.org/article/ff0a29516e424b4d854ec40d0e209808","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 18, Iss 1, Pp 1-14 (2017)","raw_type":"article"},{"id":"pmh:oai:europepmc.org:4363020","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/5521120","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"},{"id":"pmh:oai:pure.mpg.de:item_2564516","is_oa":false,"landing_page_url":"http://hdl.handle.net/21.11116/0000-0000-FFC7-1","pdf_url":null,"source":{"id":"https://openalex.org/S4306400654","display_name":"MPG.PuRe (Max Planck Society)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I149899117","host_organization_name":"Max Planck Society","host_organization_lineage":["https://openalex.org/I149899117"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:repositorio-aberto.up.pt:10216/120519","is_oa":true,"landing_page_url":"https://hdl.handle.net/10216/120519","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/s12859-017-1758-x","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-017-1758-x","pdf_url":"https://link.springer.com/content/pdf/10.1186/s12859-017-1758-x.pdf","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/16","display_name":"Peace, Justice and strong institutions","score":0.5899999737739563}],"awards":[{"id":"https://openalex.org/G1167214205","display_name":null,"funder_award_id":"COMPETE","funder_id":"https://openalex.org/F4320335322","funder_display_name":"European Regional Development Fund"},{"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/G1578237752","display_name":null,"funder_award_id":"COMPETE","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"},{"id":"https://openalex.org/G2673245850","display_name":null,"funder_award_id":"PT2020","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"},{"id":"https://openalex.org/G274581676","display_name":null,"funder_award_id":"POCI-01","funder_id":"https://openalex.org/F4320335322","funder_display_name":"European Regional Development Fund"},{"id":"https://openalex.org/G2977163839","display_name":null,"funder_award_id":"PAPIIT-IN200115","funder_id":"https://openalex.org/F4320335100","funder_display_name":"Direcci\u00f3n General de Asuntos del Personal Acad\u00e9mico, Universidad Nacional Aut\u00f3noma de M\u00e9xico"},{"id":"https://openalex.org/G4176497637","display_name":null,"funder_award_id":"COMPETE 2020","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"},{"id":"https://openalex.org/G4316116677","display_name":null,"funder_award_id":"NORTE2020","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"},{"id":"https://openalex.org/G4455079242","display_name":null,"funder_award_id":"POCI-01-","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/G5224927334","display_name":null,"funder_award_id":"POCI-01-","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"},{"id":"https://openalex.org/G5321319778","display_name":null,"funder_award_id":"NORTE-01-0145-FEDER-000035","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"},{"id":"https://openalex.org/G540664130","display_name":null,"funder_award_id":"IN200115","funder_id":"https://openalex.org/F4320335100","funder_display_name":"Direcci\u00f3n General de Asuntos del Personal Acad\u00e9mico, Universidad Nacional Aut\u00f3noma de M\u00e9xico"},{"id":"https://openalex.org/G547185811","display_name":null,"funder_award_id":"PT2020","funder_id":"https://openalex.org/F4320335322","funder_display_name":"European Regional Development Fund"},{"id":"https://openalex.org/G5722953299","display_name":null,"funder_award_id":"NORTE2020","funder_id":"https://openalex.org/F4320335322","funder_display_name":"European Regional Development Fund"},{"id":"https://openalex.org/G6033153441","display_name":"Diversidade sensorial animal: solu\u00e7\u00f5es gen\u00f3micas inovadoras para melhorar a percep\u00e7\u00e3o de est\u00edmulos ambientais","funder_award_id":"PTDC/AAG-GLO/6887/2014","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"},{"id":"https://openalex.org/G7302880105","display_name":null,"funder_award_id":"NORTE-01-0145-FEDER-000035","funder_id":"https://openalex.org/F4320335322","funder_display_name":"European Regional Development Fund"},{"id":"https://openalex.org/G7464844668","display_name":null,"funder_award_id":"POCI-01-0124-FEDER-016845","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"},{"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/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/F4320321974","display_name":"Universitat de Val\u00e8ncia","ror":"https://ror.org/043nxc105"},{"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/F4320335100","display_name":"Direcci\u00f3n General de Asuntos del Personal Acad\u00e9mico, Universidad Nacional Aut\u00f3noma de M\u00e9xico","ror":"https://ror.org/01tmp8f25"},{"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/W2737578470.pdf","grobid_xml":"https://content.openalex.org/works/W2737578470.grobid-xml"},"referenced_works_count":83,"referenced_works":["https://openalex.org/W112873001","https://openalex.org/W140618018","https://openalex.org/W421463624","https://openalex.org/W1179283095","https://openalex.org/W1496257230","https://openalex.org/W1543932334","https://openalex.org/W1639032689","https://openalex.org/W1661871015","https://openalex.org/W1737800760","https://openalex.org/W1970613018","https://openalex.org/W1971896762","https://openalex.org/W1972863608","https://openalex.org/W1975304761","https://openalex.org/W1976159745","https://openalex.org/W1976656799","https://openalex.org/W1978914444","https://openalex.org/W1980397590","https://openalex.org/W1980497258","https://openalex.org/W1982910530","https://openalex.org/W1985718949","https://openalex.org/W1992311227","https://openalex.org/W1995808589","https://openalex.org/W1995875735","https://openalex.org/W1998490996","https://openalex.org/W2014731953","https://openalex.org/W2023306209","https://openalex.org/W2026666393","https://openalex.org/W2041404167","https://openalex.org/W2043886357","https://openalex.org/W2043906184","https://openalex.org/W2049012227","https://openalex.org/W2050160299","https://openalex.org/W2053423550","https://openalex.org/W2054068479","https://openalex.org/W2054453488","https://openalex.org/W2055043387","https://openalex.org/W2056053405","https://openalex.org/W2063088204","https://openalex.org/W2064664178","https://openalex.org/W2066759237","https://openalex.org/W2076022581","https://openalex.org/W2079105106","https://openalex.org/W2079193139","https://openalex.org/W2087064593","https://openalex.org/W2087866582","https://openalex.org/W2092750499","https://openalex.org/W2101220662","https://openalex.org/W2101940264","https://openalex.org/W2107749303","https://openalex.org/W2111973517","https://openalex.org/W2115595474","https://openalex.org/W2117077088","https://openalex.org/W2119421613","https://openalex.org/W2124610693","https://openalex.org/W2126819771","https://openalex.org/W2128653811","https://openalex.org/W2131421334","https://openalex.org/W2132292391","https://openalex.org/W2133990480","https://openalex.org/W2141885858","https://openalex.org/W2142498761","https://openalex.org/W2145957695","https://openalex.org/W2151831732","https://openalex.org/W2152800101","https://openalex.org/W2155161278","https://openalex.org/W2155524195","https://openalex.org/W2161550872","https://openalex.org/W2166637863","https://openalex.org/W2176982668","https://openalex.org/W2190044768","https://openalex.org/W2203756811","https://openalex.org/W2280799770","https://openalex.org/W2296592747","https://openalex.org/W2489559155","https://openalex.org/W2557395024","https://openalex.org/W2584459311","https://openalex.org/W2978725006","https://openalex.org/W3194139813","https://openalex.org/W4210531204","https://openalex.org/W4213345021","https://openalex.org/W4235848672","https://openalex.org/W6680741628","https://openalex.org/W6681029592"],"related_works":["https://openalex.org/W4383473004","https://openalex.org/W1989756167","https://openalex.org/W2064459092","https://openalex.org/W76317090","https://openalex.org/W2097311600","https://openalex.org/W2084743099","https://openalex.org/W2470147982","https://openalex.org/W2398461637","https://openalex.org/W4322579338","https://openalex.org/W2737578470"],"abstract_inverted_index":{"Computational":[0],"prediction":[1],"of":[2,7,15,18,62,103,124,128,149,155,171,179,189,227,282,313,318,329],"protein":[3,89,106,152,201,287,298,335],"function":[4,336],"constitutes":[5],"one":[6,162],"the":[8,16,59,101,114,119,122,134,147,168,217,225,258,276,293,305,311,326],"more":[9],"complex":[10],"problems":[11],"in":[12,22,26,110,254],"Bioinformatics,":[13],"because":[14,154],"diversity":[17,159],"functions":[19],"and":[20,77,93,210,232,239,310,333],"mechanisms":[21],"that":[23,35,160,223],"proteins":[24,34,192,317],"exert":[25],"nature.":[27],"This":[28],"issue":[29],"is":[30,131,144,290],"reinforced":[31],"especially":[32],"for":[33,113,133,146,237],"share":[36],"very":[37],"low":[38],"primary":[39],"or":[40],"tertiary":[41],"structure":[42],"similarity":[43],"to":[44,57,66,86,99,163,331],"existing":[45],"annotated":[46],"proteomes.":[47],"In":[48],"this":[49,67,255],"sense,":[50],"new":[51],"alignment-free":[52,338],"(AF)":[53],"tools":[54],"are":[55],"needed":[56],"overcome":[58],"inherent":[60],"limitations":[61],"classic":[63],"alignment-based":[64,172],"approaches":[65],"issue.":[68],"We":[69,221],"have":[70,82],"recently":[71],"introduced":[72,132],"AF":[73,105,151],"protein-numerical-encoding":[74],"programs":[75],"(TI2BioP":[76],"ProtDCal),":[78],"whose":[79],"sequence-based":[80,181],"features":[81,212],"been":[83],"successfully":[84],"applied":[85],"detect":[87],"remote":[88],"homologs,":[90],"post-translational":[91],"modifications":[92],"antibacterial":[94],"peptides.":[95],"Here":[96],"we":[97],"aim":[98],"demonstrate":[100],"applicability":[102,281],"4":[104],"descriptor":[107,202],"families,":[108],"implemented":[109],"our":[111,125,150,180,323],"programs,":[112],"identification":[115],"enzyme-like":[116],"proteins.":[117],"At":[118],"same":[120],"time,":[121],"use":[123],"novel":[126],"family":[127],"3D\u2013structure-based":[129,244],"descriptors":[130,229],"first":[135,247],"time.":[136],"The":[137,177,242,280,301],"Dobson":[138],"&":[139],"Doig":[140],"(D&D)":[141],"benchmark":[142,197,219,272],"dataset":[143,274],"used":[145],"evaluation":[148],"descriptors,":[153,262],"its":[156],"proven":[157],"structural":[158],"permits":[161],"emulate":[164],"an":[165],"experiment":[166],"within":[167],"twilight":[169],"zone":[170],"methods":[173,252,330],"(pair-wise":[174],"identity":[175],"<30%).":[176],"performance":[178],"predictor":[182],"was":[183],"further":[184],"assessed":[185,215,253],"using":[186,216,304,337],"a":[187,196,264,271,285],"subset":[188],"formerly":[190,314],"uncharacterized":[191,315],"which":[193],"currently":[194],"represent":[195],"annotation":[198,273],"dataset.":[199,220,256],"Four":[200],"families":[203,226],"(sequence-composition-based":[204],"(0D),":[205],"linear-topology-based":[206],"(1D),":[207],"pseudo-fold-topology-based":[208],"(2D)":[209],"3D\u2013structure":[211],"(3D),":[213],"were":[214],"D&D":[218,308],"show":[222],"only":[224],"ProtDCal\u2019s":[228],"(0D,":[230],"1D":[231,261],"3D)":[233],"encode":[234],"significant":[235],"information":[236],"enzymes":[238],"non-enzymes":[240],"discrimination.":[241],"obtained":[243],"classifier":[245],"ranked":[246],"among":[248],"several":[249],"other":[250],"SVM-based":[251],"Furthermore,":[257],"model":[259,332],"leveraging":[260],"showed":[263],"higher":[265],"success":[266],"rate":[267],"than":[268],"EzyPred":[269],"on":[270,325],"from":[275],"Shewanella":[277,319],"oneidensis":[278,320],"proteome.":[279],"ProtDCal":[283],"as":[284],"general-purpose-AF":[286],"modelling":[288],"method":[289],"illustrated":[291],"through":[292],"discrimination":[294],"between":[295],"two":[296],"comprehensive":[297],"functional":[299],"classes.":[300],"observed":[302],"performances":[303],"highly":[306],"diverse":[307],"dataset,":[309],"set":[312],"(hard-to-annotate)":[316],",":[321],"places":[322],"methodology":[324],"top":[327],"range":[328],"predict":[334],"approaches.":[339]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}
