{"id":"https://openalex.org/W2144041189","doi":"https://doi.org/10.1109/hicss.1994.323570","title":"A protein family classification method for analysis of large DNA sequences","display_name":"A protein family classification method for analysis of large DNA sequences","publication_year":1994,"publication_date":"1994-01-01","ids":{"openalex":"https://openalex.org/W2144041189","doi":"https://doi.org/10.1109/hicss.1994.323570","mag":"2144041189"},"language":"en","primary_location":{"id":"doi:10.1109/hicss.1994.323570","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hicss.1994.323570","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Seventh Hawaii International Conference on System Sciences HICSS-94","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5098198231","display_name":"Henikoff","orcid":null},"institutions":[{"id":"https://openalex.org/I1344073410","display_name":"Howard Hughes Medical Institute","ror":"https://ror.org/006w34k90","country_code":"US","type":"facility","lineage":["https://openalex.org/I1344073410"]},{"id":"https://openalex.org/I4210089486","display_name":"Fred Hutch Cancer Center","ror":"https://ror.org/007ps6h72","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210089486"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Henikoff","raw_affiliation_strings":["Fred Hutchinson Cancer Res. Center, Howard Hughes Med. Inst., Seattle, WA, USA"],"affiliations":[{"raw_affiliation_string":"Fred Hutchinson Cancer Res. Center, Howard Hughes Med. Inst., Seattle, WA, USA","institution_ids":["https://openalex.org/I1344073410","https://openalex.org/I4210089486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5098198231","display_name":"Henikoff","orcid":null},"institutions":[{"id":"https://openalex.org/I1344073410","display_name":"Howard Hughes Medical Institute","ror":"https://ror.org/006w34k90","country_code":"US","type":"facility","lineage":["https://openalex.org/I1344073410"]},{"id":"https://openalex.org/I4210089486","display_name":"Fred Hutch Cancer Center","ror":"https://ror.org/007ps6h72","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210089486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Henikoff","raw_affiliation_strings":["Fred Hutchinson Cancer Res. Center, Howard Hughes Med. Inst., Seattle, WA, USA"],"affiliations":[{"raw_affiliation_string":"Fred Hutchinson Cancer Res. Center, Howard Hughes Med. Inst., Seattle, WA, USA","institution_ids":["https://openalex.org/I1344073410","https://openalex.org/I4210089486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5098198231"],"corresponding_institution_ids":["https://openalex.org/I1344073410","https://openalex.org/I4210089486"],"apc_list":null,"apc_paid":null,"fwci":0.1346,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.44049992,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"183","issue":null,"first_page":"265","last_page":"274"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10521","display_name":"RNA and protein synthesis mechanisms","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/T10521","display_name":"RNA and protein synthesis mechanisms","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":0.9994000196456909,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9975000023841858,"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/homology","display_name":"Homology (biology)","score":0.5719363689422607},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.5628287196159363},{"id":"https://openalex.org/keywords/dna","display_name":"DNA","score":0.5567368268966675},{"id":"https://openalex.org/keywords/sequence-database","display_name":"Sequence database","score":0.5177244544029236},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5154483914375305},{"id":"https://openalex.org/keywords/dna-sequencing","display_name":"DNA sequencing","score":0.47462666034698486},{"id":"https://openalex.org/keywords/protein-sequencing","display_name":"Protein sequencing","score":0.4656814932823181},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.4605163335800171},{"id":"https://openalex.org/keywords/sequence-analysis","display_name":"Sequence analysis","score":0.4579412639141083},{"id":"https://openalex.org/keywords/sequence-logo","display_name":"Sequence logo","score":0.4572874903678894},{"id":"https://openalex.org/keywords/protein-family","display_name":"Protein family","score":0.4435679316520691},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.4211728274822235},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3825063109397888},{"id":"https://openalex.org/keywords/peptide-sequence","display_name":"Peptide sequence","score":0.3248264193534851},{"id":"https://openalex.org/keywords/consensus-sequence","display_name":"Consensus sequence","score":0.2770008146762848},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.25814664363861084},{"id":"https://openalex.org/keywords/base-sequence","display_name":"Base sequence","score":0.20921429991722107}],"concepts":[{"id":"https://openalex.org/C165525559","wikidata":"https://www.wikidata.org/wiki/Q224180","display_name":"Homology (biology)","level":3,"score":0.5719363689422607},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5628287196159363},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.5567368268966675},{"id":"https://openalex.org/C41584329","wikidata":"https://www.wikidata.org/wiki/Q175902","display_name":"Sequence database","level":3,"score":0.5177244544029236},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5154483914375305},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.47462666034698486},{"id":"https://openalex.org/C10010492","wikidata":"https://www.wikidata.org/wiki/Q3142557","display_name":"Protein sequencing","level":4,"score":0.4656814932823181},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.4605163335800171},{"id":"https://openalex.org/C61053724","wikidata":"https://www.wikidata.org/wiki/Q1154615","display_name":"Sequence analysis","level":3,"score":0.4579412639141083},{"id":"https://openalex.org/C105082737","wikidata":"https://www.wikidata.org/wiki/Q7452470","display_name":"Sequence logo","level":5,"score":0.4572874903678894},{"id":"https://openalex.org/C171897839","wikidata":"https://www.wikidata.org/wiki/Q417841","display_name":"Protein family","level":3,"score":0.4435679316520691},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.4211728274822235},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3825063109397888},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.3248264193534851},{"id":"https://openalex.org/C54985914","wikidata":"https://www.wikidata.org/wiki/Q1295754","display_name":"Consensus sequence","level":4,"score":0.2770008146762848},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.25814664363861084},{"id":"https://openalex.org/C3017666073","wikidata":"https://www.wikidata.org/wiki/Q1764062","display_name":"Base sequence","level":3,"score":0.20921429991722107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hicss.1994.323570","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hicss.1994.323570","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Seventh Hawaii International Conference on System Sciences HICSS-94","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320310042","display_name":"Aspen Center for Physics","ror":"https://ror.org/05gqcbq50"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W7046360","https://openalex.org/W1422803820","https://openalex.org/W1525091092","https://openalex.org/W1558365920","https://openalex.org/W1589115128","https://openalex.org/W1971143006","https://openalex.org/W1982496832","https://openalex.org/W1982996449","https://openalex.org/W1983609607","https://openalex.org/W1992648037","https://openalex.org/W2019019284","https://openalex.org/W2040703580","https://openalex.org/W2045825097","https://openalex.org/W2051916497","https://openalex.org/W2055043387","https://openalex.org/W2056486650","https://openalex.org/W2087064593","https://openalex.org/W2089431713","https://openalex.org/W2110969161","https://openalex.org/W2156899368","https://openalex.org/W2471648340","https://openalex.org/W4236236547","https://openalex.org/W4240777919","https://openalex.org/W6600294125","https://openalex.org/W6720341360"],"related_works":["https://openalex.org/W2036521446","https://openalex.org/W2103210188","https://openalex.org/W2610344215","https://openalex.org/W2011602722","https://openalex.org/W2410245591","https://openalex.org/W2054124141","https://openalex.org/W2001848433","https://openalex.org/W150090254","https://openalex.org/W2027345511","https://openalex.org/W2356901565"],"abstract_inverted_index":{"A":[0],"method":[1],"is":[2,103],"described":[3],"for":[4,21,65],"identification":[5],"and":[6,77,110],"classification":[7],"of":[8,25,40,53,57,68,74,108,118],"proteins":[9],"encoded":[10,95],"in":[11,96,113],"large":[12,98],"DNA":[13,99],"sequences.":[14,100],"Previously,":[15],"an":[16],"automated":[17],"system":[18,35],"was":[19],"introduced":[20],"the":[22,48,72,106,114],"general":[23],"detection":[24,67,73,107],"amino":[26],"acid":[27],"sequence":[28,42,117],"motifs":[29],"within":[30],"diverse":[31],"protein":[32,63],"families.":[33],"The":[34,101],"generated":[36],"a":[37],"database":[38,56,84],"consisting":[39],"aligned":[41],"segments":[43],"(blocks)":[44],"that":[45,82],"correspond":[46],"to":[47,91],"most":[49],"highly":[50],"conserved":[51],"regions":[52],"proteins.":[54],"This":[55],"blocks":[58],"can":[59,87],"be":[60,89],"searched":[61],"using":[62],"queries":[64],"sensitive":[66],"homology":[69],"based":[70],"on":[71],"both":[75],"local":[76],"global":[78],"similarities.":[79],"We":[80],"show":[81],"this":[83],"searching":[85],"approach":[86,102],"also":[88],"used":[90],"detect":[92],"distant":[93],"relatives":[94],"very":[97],"illustrated":[104],"by":[105],"known":[109],"new":[111],"relationships":[112],"315":[115],"kilobase":[116],"yeast":[119],"chromosome":[120],"III.<":[121],"<ETX":[122],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[123],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">&gt;</ETX>":[124]},"counts_by_year":[{"year":2012,"cited_by_count":1}],"updated_date":"2026-02-25T21:11:00.739837","created_date":"2025-10-10T00:00:00"}