{"id":"https://openalex.org/W2097413543","doi":"https://doi.org/10.1093/bioinformatics/bti806","title":"Application of compression-based distance measures to protein sequence classification: a methodological study","display_name":"Application of compression-based distance measures to protein sequence classification: a methodological study","publication_year":2005,"publication_date":"2005-11-29","ids":{"openalex":"https://openalex.org/W2097413543","doi":"https://doi.org/10.1093/bioinformatics/bti806","mag":"2097413543","pmid":"https://pubmed.ncbi.nlm.nih.gov/16317070"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/bti806","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bti806","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/22/4/407/446420/bti806.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/22/4/407/446420/bti806.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020008023","display_name":"Andr\u00e1s Kocsor","orcid":null},"institutions":[{"id":"https://openalex.org/I4210152167","display_name":"MTA-SZTE Research Group on Artificial Intelligence","ror":"https://ror.org/0507fk326","country_code":"HU","type":"facility","lineage":["https://openalex.org/I227486990","https://openalex.org/I4210152167","https://openalex.org/I7597260"]},{"id":"https://openalex.org/I7597260","display_name":"Hungarian Academy of Sciences","ror":"https://ror.org/02ks8qq67","country_code":"HU","type":"funder","lineage":["https://openalex.org/I7597260"]},{"id":"https://openalex.org/I227486990","display_name":"University of Szeged","ror":"https://ror.org/01pnej532","country_code":"HU","type":"education","lineage":["https://openalex.org/I227486990"]}],"countries":["HU"],"is_corresponding":true,"raw_author_name":"Andr\u00e1s Kocsor","raw_affiliation_strings":["Research Group on Artificial Intelligence of the Hungarian Academy of Sciences and University of Szeged 1 \u00a0 1 \u00a0 \u00a0 Aradi v\u00e9rtan\u00fak tere 1., H-6720 Szeged, Hungary"],"affiliations":[{"raw_affiliation_string":"Research Group on Artificial Intelligence of the Hungarian Academy of Sciences and University of Szeged 1 \u00a0 1 \u00a0 \u00a0 Aradi v\u00e9rtan\u00fak tere 1., H-6720 Szeged, Hungary","institution_ids":["https://openalex.org/I4210152167","https://openalex.org/I227486990","https://openalex.org/I7597260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037717293","display_name":"Attila Kert\u00e9sz\u2010Farkas","orcid":"https://orcid.org/0000-0001-8110-7253"},"institutions":[{"id":"https://openalex.org/I4210152167","display_name":"MTA-SZTE Research Group on Artificial Intelligence","ror":"https://ror.org/0507fk326","country_code":"HU","type":"facility","lineage":["https://openalex.org/I227486990","https://openalex.org/I4210152167","https://openalex.org/I7597260"]},{"id":"https://openalex.org/I7597260","display_name":"Hungarian Academy of Sciences","ror":"https://ror.org/02ks8qq67","country_code":"HU","type":"funder","lineage":["https://openalex.org/I7597260"]},{"id":"https://openalex.org/I227486990","display_name":"University of Szeged","ror":"https://ror.org/01pnej532","country_code":"HU","type":"education","lineage":["https://openalex.org/I227486990"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Attila Kert\u00e9sz-Farkas","raw_affiliation_strings":["Research Group on Artificial Intelligence of the Hungarian Academy of Sciences and University of Szeged 1 \u00a0 1 \u00a0 \u00a0 Aradi v\u00e9rtan\u00fak tere 1., H-6720 Szeged, Hungary"],"affiliations":[{"raw_affiliation_string":"Research Group on Artificial Intelligence of the Hungarian Academy of Sciences and University of Szeged 1 \u00a0 1 \u00a0 \u00a0 Aradi v\u00e9rtan\u00fak tere 1., H-6720 Szeged, Hungary","institution_ids":["https://openalex.org/I4210152167","https://openalex.org/I227486990","https://openalex.org/I7597260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048342687","display_name":"L\u00e1szl\u00f3 Kaj\u00e1n","orcid":"https://orcid.org/0000-0001-8624-5970"},"institutions":[{"id":"https://openalex.org/I91080651","display_name":"International Centre for Genetic Engineering and Biotechnology","ror":"https://ror.org/043bgf219","country_code":"IT","type":"nonprofit","lineage":["https://openalex.org/I91080651"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"L\u00e1szl\u00f3 Kaj\u00e1n","raw_affiliation_strings":["Bioinformatics Group, International Centre for Genetic Engineering and Biotechnology 2 \u00a0 2 \u00a0 \u00a0 Padriciano 99, I-34012 Trieste, Italy"],"affiliations":[{"raw_affiliation_string":"Bioinformatics Group, International Centre for Genetic Engineering and Biotechnology 2 \u00a0 2 \u00a0 \u00a0 Padriciano 99, I-34012 Trieste, Italy","institution_ids":["https://openalex.org/I91080651"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111912750","display_name":"S\u00e1ndor Pongor","orcid":null},"institutions":[{"id":"https://openalex.org/I91080651","display_name":"International Centre for Genetic Engineering and Biotechnology","ror":"https://ror.org/043bgf219","country_code":"IT","type":"nonprofit","lineage":["https://openalex.org/I91080651"]},{"id":"https://openalex.org/I2800351701","display_name":"HUN-REN Szegedi Biol\u00f3giai Kutat\u00f3k\u00f6zpont","ror":"https://ror.org/016gb1631","country_code":"HU","type":"facility","lineage":["https://openalex.org/I2800351701","https://openalex.org/I7597260"]},{"id":"https://openalex.org/I7597260","display_name":"Hungarian Academy of Sciences","ror":"https://ror.org/02ks8qq67","country_code":"HU","type":"funder","lineage":["https://openalex.org/I7597260"]}],"countries":["HU","IT"],"is_corresponding":false,"raw_author_name":"S\u00e1ndor Pongor","raw_affiliation_strings":["Bioinformatics Group, Biological Research Centre, Hungarian Academy of Sciences 3 \u00a0 3 \u00a0 \u00a0 Temesv\u00e1ri krt. 62, H-6701 Szeged, Hungary","Bioinformatics Group, International Centre for Genetic Engineering and Biotechnology 2 \u00a0 2 \u00a0 \u00a0 Padriciano 99, I-34012 Trieste, Italy"],"affiliations":[{"raw_affiliation_string":"Bioinformatics Group, Biological Research Centre, Hungarian Academy of Sciences 3 \u00a0 3 \u00a0 \u00a0 Temesv\u00e1ri krt. 62, H-6701 Szeged, Hungary","institution_ids":["https://openalex.org/I2800351701","https://openalex.org/I7597260"]},{"raw_affiliation_string":"Bioinformatics Group, International Centre for Genetic Engineering and Biotechnology 2 \u00a0 2 \u00a0 \u00a0 Padriciano 99, I-34012 Trieste, Italy","institution_ids":["https://openalex.org/I91080651"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5020008023"],"corresponding_institution_ids":["https://openalex.org/I227486990","https://openalex.org/I4210152167","https://openalex.org/I7597260"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":3.671,"has_fulltext":true,"cited_by_count":75,"citation_normalized_percentile":{"value":0.93587089,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"22","issue":"4","first_page":"407","last_page":"412"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9987000226974487,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6204702258110046},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5450875759124756},{"id":"https://openalex.org/keywords/protein-sequencing","display_name":"Protein sequencing","score":0.5063060522079468},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.49889278411865234},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4696608781814575},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.4680563807487488},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.46160808205604553},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.43608421087265015},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.42825233936309814},{"id":"https://openalex.org/keywords/sequence-alignment","display_name":"Sequence alignment","score":0.42629244923591614},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42254793643951416},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3823542594909668},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.3250437378883362},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.22782886028289795},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.15513479709625244},{"id":"https://openalex.org/keywords/peptide-sequence","display_name":"Peptide sequence","score":0.14405816793441772},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.12111935019493103}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6204702258110046},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5450875759124756},{"id":"https://openalex.org/C10010492","wikidata":"https://www.wikidata.org/wiki/Q3142557","display_name":"Protein sequencing","level":4,"score":0.5063060522079468},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.49889278411865234},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4696608781814575},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.4680563807487488},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.46160808205604553},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.43608421087265015},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.42825233936309814},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.42629244923591614},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42254793643951416},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3823542594909668},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3250437378883362},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.22782886028289795},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.15513479709625244},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.14405816793441772},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.12111935019493103},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"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":"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":"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":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000032","qualifier_name":"analysis","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000032","qualifier_name":"analysis","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000032","qualifier_name":"analysis","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":"Q000145","qualifier_name":"classification","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":"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":"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":"D044962","descriptor_name":"Data Compression","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D044962","descriptor_name":"Data Compression","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D044962","descriptor_name":"Data Compression","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/bti806","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bti806","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/22/4/407/446420/bti806.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:16317070","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/16317070","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:zenodo.org:100637","is_oa":true,"landing_page_url":"https://www.openaccessrepository.it/record/100637","pdf_url":null,"source":{"id":"https://openalex.org/S4306402478","display_name":"INFM-OAR (INFN Catania)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210116497","host_organization_name":"Istituto Nazionale di Fisica Nucleare, Sezione di Catania","host_organization_lineage":["https://openalex.org/I4210116497"],"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":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/bti806","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bti806","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/22/4/407/446420/bti806.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":[{"id":"https://openalex.org/G7541558665","display_name":null,"funder_award_id":"Bolyai","funder_id":"https://openalex.org/F4320322192","funder_display_name":"Magyar Tudom\u00e1nyos Akad\u00e9mia"}],"funders":[{"id":"https://openalex.org/F4320322192","display_name":"Magyar Tudom\u00e1nyos Akad\u00e9mia","ror":"https://ror.org/02ks8qq67"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2097413543.pdf","grobid_xml":"https://content.openalex.org/works/W2097413543.grobid-xml"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W854322902","https://openalex.org/W1542652324","https://openalex.org/W1576520375","https://openalex.org/W1592091759","https://openalex.org/W1601740268","https://openalex.org/W1638203394","https://openalex.org/W1973714307","https://openalex.org/W1996423252","https://openalex.org/W2002832354","https://openalex.org/W2008386840","https://openalex.org/W2009570821","https://openalex.org/W2015696044","https://openalex.org/W2051119339","https://openalex.org/W2053186076","https://openalex.org/W2055043387","https://openalex.org/W2074231493","https://openalex.org/W2077770566","https://openalex.org/W2083060511","https://openalex.org/W2084787613","https://openalex.org/W2087064593","https://openalex.org/W2124145810","https://openalex.org/W2124158580","https://openalex.org/W2125598538","https://openalex.org/W2125725297","https://openalex.org/W2128859735","https://openalex.org/W2135346934","https://openalex.org/W2140244239","https://openalex.org/W2144221002","https://openalex.org/W2145876138","https://openalex.org/W2150839989","https://openalex.org/W2151554142","https://openalex.org/W2158714788","https://openalex.org/W2158957948","https://openalex.org/W2171963266","https://openalex.org/W2283504545","https://openalex.org/W2544883878","https://openalex.org/W2799061466","https://openalex.org/W4230946174","https://openalex.org/W4230960895","https://openalex.org/W6634442568","https://openalex.org/W6678649364","https://openalex.org/W6729899252"],"related_works":["https://openalex.org/W1967080779","https://openalex.org/W2612632602","https://openalex.org/W2321805087","https://openalex.org/W1936662467","https://openalex.org/W2804480386","https://openalex.org/W2121560377","https://openalex.org/W2140187548","https://openalex.org/W2053803793","https://openalex.org/W3186624150","https://openalex.org/W2008335091"],"abstract_inverted_index":{"We":[0],"constructed":[1,106],"compression-based":[2],"distance":[3],"measures":[4],"(CBMs)":[5],"using":[6,26],"the":[7,10,21,41,70,79,82,85,100,121],"Lempel-Zlv":[8],"and":[9,14,24,58,65,81,110,124],"PPMZ":[11],"compression":[12],"algorithms":[13],"compared":[15],"their":[16],"performance":[17,101],"with":[18],"that":[19,119],"of":[20,40,69,84,102,120],"Smith-Waterman":[22,122],"algorithm":[23,123],"BLAST,":[25],"nearest":[27],"neighbour":[28],"or":[29,115],"support":[30],"vector":[31],"machine":[32],"classification":[33,89],"schemes.":[34],"The":[35],"datasets":[36],"included":[37],"a":[38,51,76,103,108,111],"subset":[39],"SCOP":[42],"protein":[43,49],"structure":[44],"database":[45],"to":[46],"test":[47],"distant":[48],"similarities,":[50],"3-phosphoglycerate-kinase":[52],"sequences":[53,86],"selected":[54],"from":[55,107],"archaean,":[56],"bacterial":[57],"eukaryotic":[59],"species":[60],"as":[61,63],"well":[62,94],"low":[64],"high-complexity":[66],"sequence":[67],"segments":[68],"human":[71],"proteome,":[72],"CBMs":[73,91],"values":[74],"show":[75],"dependence":[77],"on":[78,95],"length":[80],"complexity":[83],"compared.":[87],"In":[88],"tasks":[90],"performed":[92],"especially":[93],"distantly":[96],"related":[97],"proteins":[98],"where":[99],"combined":[104],"measure,":[105],"CBM":[109],"BLAST":[112],"score,":[113],"approached":[114],"even":[116],"slightly":[117],"exceeded":[118],"two":[125],"hidden":[126],"Markov":[127],"model-based":[128],"algorithms.":[129]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":5}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
