{"id":"https://openalex.org/W3114310315","doi":"https://doi.org/10.1093/bioinformatics/btaa1054","title":"Minimally overlapping words for sequence similarity search","display_name":"Minimally overlapping words for sequence similarity search","publication_year":2020,"publication_date":"2020-12-01","ids":{"openalex":"https://openalex.org/W3114310315","doi":"https://doi.org/10.1093/bioinformatics/btaa1054","mag":"3114310315","pmid":"https://pubmed.ncbi.nlm.nih.gov/33346833"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btaa1054","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btaa1054","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/36/22-23/5344/36855836/btaa1054.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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":"hybrid","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/36/22-23/5344/36855836/btaa1054.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055829507","display_name":"Martin C. Frith","orcid":"https://orcid.org/0000-0003-0998-2859"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]},{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Martin C Frith","raw_affiliation_strings":["AIST-Waseda University CBBD-OIL , AIST, Tokyo, Japan","Artificial Intelligence Research Center , AIST, Tokyo, Japan","Graduate School of Frontier Sciences, University of Tokyo , Chiba, Japan"],"affiliations":[{"raw_affiliation_string":"AIST-Waseda University CBBD-OIL , AIST, Tokyo, Japan","institution_ids":["https://openalex.org/I150744194"]},{"raw_affiliation_string":"Artificial Intelligence Research Center , AIST, Tokyo, Japan","institution_ids":[]},{"raw_affiliation_string":"Graduate School of Frontier Sciences, University of Tokyo , Chiba, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055679303","display_name":"Laurent No\u00e9","orcid":"https://orcid.org/0000-0002-1170-8376"},"institutions":[{"id":"https://openalex.org/I2279609970","display_name":"Universit\u00e9 de Lille","ror":"https://ror.org/02kzqn938","country_code":"FR","type":"education","lineage":["https://openalex.org/I2279609970"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Laurent No\u00e9","raw_affiliation_strings":["CRIStAL UMR9189, Universit\u00e9 de Lille, Villeneuve d\u2019Ascq , France"],"affiliations":[{"raw_affiliation_string":"CRIStAL UMR9189, Universit\u00e9 de Lille, Villeneuve d\u2019Ascq , France","institution_ids":["https://openalex.org/I2279609970"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012626407","display_name":"Gr\u00e9gory Kucherov","orcid":"https://orcid.org/0000-0001-5899-5424"},"institutions":[{"id":"https://openalex.org/I4210154111","display_name":"Universit\u00e9 Gustave Eiffel","ror":"https://ror.org/03x42jk29","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210154111"]},{"id":"https://openalex.org/I4210152518","display_name":"Laboratoire d'Informatique Gaspard-Monge","ror":"https://ror.org/04t50yk91","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I142631665","https://openalex.org/I4210145102","https://openalex.org/I4210152518","https://openalex.org/I4210154111","https://openalex.org/I4210159245"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I125989756","display_name":"Skolkovo Institute of Science and Technology","ror":"https://ror.org/03f9nc143","country_code":"RU","type":"education","lineage":["https://openalex.org/I125989756"]}],"countries":["FR","RU"],"is_corresponding":false,"raw_author_name":"Gregory Kucherov","raw_affiliation_strings":["LIGM, CNRS, Universit\u00e9 Gustave Eiffel, Marne-la-Valle\u00e9 , France","Skolkovo Institute of Science and Technology , Moscow, Russia"],"affiliations":[{"raw_affiliation_string":"LIGM, CNRS, Universit\u00e9 Gustave Eiffel, Marne-la-Valle\u00e9 , France","institution_ids":["https://openalex.org/I4210152518","https://openalex.org/I1294671590","https://openalex.org/I4210154111"]},{"raw_affiliation_string":"Skolkovo Institute of Science and Technology , Moscow, Russia","institution_ids":["https://openalex.org/I125989756"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5055829507"],"corresponding_institution_ids":["https://openalex.org/I150744194","https://openalex.org/I74801974"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":3.5629,"has_fulltext":true,"cited_by_count":36,"citation_normalized_percentile":{"value":0.94137217,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"36","issue":"22-23","first_page":"5344","last_page":"5350"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9994999766349792,"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"}},{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9993000030517578,"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":0.996999979019165,"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/computer-science","display_name":"Computer science","score":0.699297308921814},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5985434055328369},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.590995192527771},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5831959247589111},{"id":"https://openalex.org/keywords/seeding","display_name":"Seeding","score":0.5395829081535339},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5161274671554565},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4625064730644226},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.44198933243751526},{"id":"https://openalex.org/keywords/sensitivity","display_name":"Sensitivity (control systems)","score":0.44116532802581787},{"id":"https://openalex.org/keywords/nearest-neighbor-search","display_name":"Nearest neighbor search","score":0.4376629590988159},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4263519048690796},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.42229267954826355},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.1394573450088501},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.09774661064147949},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.0798141360282898}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.699297308921814},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5985434055328369},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.590995192527771},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5831959247589111},{"id":"https://openalex.org/C36248471","wikidata":"https://www.wikidata.org/wiki/Q7445669","display_name":"Seeding","level":2,"score":0.5395829081535339},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5161274671554565},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4625064730644226},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.44198933243751526},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.44116532802581787},{"id":"https://openalex.org/C116738811","wikidata":"https://www.wikidata.org/wiki/Q608751","display_name":"Nearest neighbor search","level":2,"score":0.4376629590988159},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4263519048690796},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.42229267954826355},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.1394573450088501},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.09774661064147949},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0798141360282898},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1093/bioinformatics/btaa1054","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btaa1054","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/36/22-23/5344/36855836/btaa1054.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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:33346833","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33346833","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:HAL:hal-03087470v1","is_oa":true,"landing_page_url":"https://hal.science/hal-03087470","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"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":"Bioinformatics, 2020, &#x27E8;10.1093/bioinformatics/btaa1054&#x27E9;","raw_type":"Journal articles"},{"id":"pmh:oai:pubmedcentral.nih.gov:8016470","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8016470","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btaa1054","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btaa1054","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/36/22-23/5344/36855836/btaa1054.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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2726982149","display_name":null,"funder_award_id":"20-51-50007","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"},{"id":"https://openalex.org/F4320321079","display_name":"Russian Foundation for Basic Research","ror":"https://ror.org/02mh1ke95"},{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3114310315.pdf","grobid_xml":"https://content.openalex.org/works/W3114310315.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W1759861793","https://openalex.org/W1825683889","https://openalex.org/W1928030931","https://openalex.org/W2056176729","https://openalex.org/W2106532429","https://openalex.org/W2109616780","https://openalex.org/W2111071896","https://openalex.org/W2125266506","https://openalex.org/W2128591967","https://openalex.org/W2139371638","https://openalex.org/W2141445158","https://openalex.org/W2144560237","https://openalex.org/W2159954944","https://openalex.org/W2160464048","https://openalex.org/W2162758337","https://openalex.org/W2183091601","https://openalex.org/W2763390627","https://openalex.org/W2789843538","https://openalex.org/W2792368734","https://openalex.org/W2892689606","https://openalex.org/W2950572599","https://openalex.org/W2951822379","https://openalex.org/W3027570368","https://openalex.org/W3028050938","https://openalex.org/W3098719287","https://openalex.org/W3100437611","https://openalex.org/W6640326986","https://openalex.org/W6685863130"],"related_works":["https://openalex.org/W2352942191","https://openalex.org/W2390371481","https://openalex.org/W2373196487","https://openalex.org/W1987103269","https://openalex.org/W2515349569","https://openalex.org/W2315981300","https://openalex.org/W2389665570","https://openalex.org/W2366106936","https://openalex.org/W2332619769","https://openalex.org/W4387185219"],"abstract_inverted_index":{"Supplementary":[0],"data":[1],"are":[2],"available":[3],"at":[4],"Bioinformatics":[5],"online.":[6]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":6}],"updated_date":"2026-03-04T09:10:02.777135","created_date":"2025-10-10T00:00:00"}
