{"id":"https://openalex.org/W2040975520","doi":"https://doi.org/10.1109/bibm.2012.6392695","title":"Efficient filtration for similarity search with spaced k-mer neighbors","display_name":"Efficient filtration for similarity search with spaced k-mer neighbors","publication_year":2012,"publication_date":"2012-10-01","ids":{"openalex":"https://openalex.org/W2040975520","doi":"https://doi.org/10.1109/bibm.2012.6392695","mag":"2040975520"},"language":"en","primary_location":{"id":"doi:10.1109/bibm.2012.6392695","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm.2012.6392695","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Bioinformatics and Biomedicine","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100695260","display_name":"Weiming Li","orcid":"https://orcid.org/0000-0002-7443-7067"},"institutions":[{"id":"https://openalex.org/I125749732","display_name":"Western University","ror":"https://ror.org/02grkyz14","country_code":"CA","type":"education","lineage":["https://openalex.org/I125749732"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Weiming Li","raw_affiliation_strings":["Department of Computer Science, University of Western Ontario, London, ONT, Canada","Department of Computer Science, University of Western Ontario, London, ON, Canada N6A 5B7"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Western Ontario, London, ONT, Canada","institution_ids":["https://openalex.org/I125749732"]},{"raw_affiliation_string":"Department of Computer Science, University of Western Ontario, London, ON, Canada N6A 5B7","institution_ids":["https://openalex.org/I125749732"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100749727","display_name":"Bin Ma","orcid":"https://orcid.org/0000-0001-6254-4087"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Bin Ma","raw_affiliation_strings":["School of Computer Science, University of Waterloo, Waterloo, ONT, Canada","School of Computer Science, University of Waterloo, Waterloo, ON, Canada N2L 3G1"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Waterloo, Waterloo, ONT, Canada","institution_ids":["https://openalex.org/I151746483"]},{"raw_affiliation_string":"School of Computer Science, University of Waterloo, Waterloo, ON, Canada N2L 3G1","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081729547","display_name":"Kaizhong Zhang","orcid":"https://orcid.org/0000-0003-1734-5921"},"institutions":[{"id":"https://openalex.org/I125749732","display_name":"Western University","ror":"https://ror.org/02grkyz14","country_code":"CA","type":"education","lineage":["https://openalex.org/I125749732"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Kaizhong Zhang","raw_affiliation_strings":["Department of Computer Science, University of Western Ontario, London, ONT, Canada","Department of Computer Science, University of Western Ontario, London, ON, Canada N6A 5B7"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Western Ontario, London, ONT, Canada","institution_ids":["https://openalex.org/I125749732"]},{"raw_affiliation_string":"Department of Computer Science, University of Western Ontario, London, ON, Canada N6A 5B7","institution_ids":["https://openalex.org/I125749732"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9976000189781189,"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/T11106","display_name":"Data Management and Algorithms","score":0.964900016784668,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/nearest-neighbor-search","display_name":"Nearest neighbor search","score":0.8127530813217163},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.724612295627594},{"id":"https://openalex.org/keywords/seeding","display_name":"Seeding","score":0.6969883441925049},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.624853253364563},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5584937334060669},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.5128369927406311},{"id":"https://openalex.org/keywords/sensitivity","display_name":"Sensitivity (control systems)","score":0.5063489675521851},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5039255023002625},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46260130405426025},{"id":"https://openalex.org/keywords/filtration","display_name":"Filtration (mathematics)","score":0.46056538820266724},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.45844388008117676},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4471549689769745},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.44000983238220215},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4184316396713257},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37034258246421814},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.27798548340797424},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.13853484392166138},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.09372073411941528},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08069723844528198}],"concepts":[{"id":"https://openalex.org/C116738811","wikidata":"https://www.wikidata.org/wiki/Q608751","display_name":"Nearest neighbor search","level":2,"score":0.8127530813217163},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.724612295627594},{"id":"https://openalex.org/C36248471","wikidata":"https://www.wikidata.org/wiki/Q7445669","display_name":"Seeding","level":2,"score":0.6969883441925049},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.624853253364563},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5584937334060669},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.5128369927406311},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.5063489675521851},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5039255023002625},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46260130405426025},{"id":"https://openalex.org/C128489963","wikidata":"https://www.wikidata.org/wiki/Q1187724","display_name":"Filtration (mathematics)","level":2,"score":0.46056538820266724},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.45844388008117676},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4471549689769745},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.44000983238220215},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4184316396713257},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37034258246421814},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.27798548340797424},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.13853484392166138},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.09372073411941528},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08069723844528198},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bibm.2012.6392695","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm.2012.6392695","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Bioinformatics and Biomedicine","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1574999200","https://openalex.org/W1644094983","https://openalex.org/W1823228142","https://openalex.org/W1955121107","https://openalex.org/W1975442866","https://openalex.org/W2055043387","https://openalex.org/W2084252156","https://openalex.org/W2106811687","https://openalex.org/W2107903949","https://openalex.org/W2116398954","https://openalex.org/W2121272213","https://openalex.org/W2128591967","https://openalex.org/W2131989567","https://openalex.org/W2143124024","https://openalex.org/W2143210482","https://openalex.org/W2241580500","https://openalex.org/W4233334497","https://openalex.org/W4236236547"],"related_works":["https://openalex.org/W2352942191","https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W2390371481","https://openalex.org/W2373196487","https://openalex.org/W98480971","https://openalex.org/W2150291671","https://openalex.org/W1987103269","https://openalex.org/W2027972911","https://openalex.org/W2146343568"],"abstract_inverted_index":{"In":[0,21],"DNA":[1],"and":[2,43,60,70],"protein":[3,46],"sequence":[4],"similarity":[5,47],"search,":[6],"seeding":[7,26,95],"(or":[8],"filtration)":[9],"has":[10],"been":[11],"widely":[12],"used":[13],"to":[14,34,64],"trade":[15],"search":[16,19],"sensitivity":[17,44],"with":[18],"speed.":[20],"this":[22],"paper,":[23],"a":[24,36,53],"new":[25,50],"method,":[27],"called":[28],"spaced":[29,56],"k-mer":[30],"neighbors,":[31,59],"is":[32,77],"introduced":[33],"provide":[35],"more":[37],"efficient":[38,74],"tradeoff":[39,91],"between":[40,67],"the":[41,62,68,80,86,90],"speed":[42],"in":[45],"search.":[48],"The":[49],"method":[51,87],"pre-selects":[52],"set":[54],"of":[55],"k-mers":[57],"as":[58],"uses":[61],"neighbors":[63],"detect":[65],"hits":[66],"query":[69],"database":[71],"sequences.":[72],"An":[73],"heuristic":[75],"algorithm":[76],"proposed":[78],"for":[79],"neighbor":[81],"selection.":[82],"We":[83],"demonstrate":[84],"that":[85],"can":[88],"improve":[89],"efficiency":[92],"over":[93],"existing":[94],"methods.":[96]},"counts_by_year":[{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}