{"id":"https://openalex.org/W2022653138","doi":"https://doi.org/10.1109/tcbb.2014.2306831","title":"Optimizing Spaced &lt;formula formulatype=\"inline\"&gt;&lt;tex Notation=\"TeX\"&gt;$k$&lt;/tex&gt;&lt;/formula&gt;-mer Neighbors for Efficient Filtration in Protein Similarity Search","display_name":"Optimizing Spaced &lt;formula formulatype=\"inline\"&gt;&lt;tex Notation=\"TeX\"&gt;$k$&lt;/tex&gt;&lt;/formula&gt;-mer Neighbors for Efficient Filtration in Protein Similarity Search","publication_year":2014,"publication_date":"2014-02-19","ids":{"openalex":"https://openalex.org/W2022653138","doi":"https://doi.org/10.1109/tcbb.2014.2306831","mag":"2022653138","pmid":"https://pubmed.ncbi.nlm.nih.gov/26355786"},"language":"en","primary_location":{"id":"doi:10.1109/tcbb.2014.2306831","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcbb.2014.2306831","pdf_url":null,"source":{"id":"https://openalex.org/S36029991","display_name":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","issn_l":"1545-5963","issn":["1545-5963","1557-9964","2374-0043"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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, ON, Canada","Department of Computer Science, University of Western, Ontario, London, ON, Canada#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Western Ontario, London, ON, Canada","institution_ids":["https://openalex.org/I125749732"]},{"raw_affiliation_string":"Department of Computer Science, University of Western, Ontario, London, ON, Canada#TAB#","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, Canada","School of Computer Science,, University of Waterloo, Waterloo, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Waterloo, Waterloo, Canada","institution_ids":["https://openalex.org/I151746483"]},{"raw_affiliation_string":"School of Computer Science,, University of Waterloo, Waterloo, Canada","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, ON, Canada","Department of Computer Science, University of Western, Ontario, London, ON, Canada#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Western Ontario, London, ON, Canada","institution_ids":["https://openalex.org/I125749732"]},{"raw_affiliation_string":"Department of Computer Science, University of Western, Ontario, London, ON, Canada#TAB#","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":0.8284,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.80591221,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"11","issue":"2","first_page":"398","last_page":"406"},"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9983000159263611,"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":0.9976000189781189,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/nearest-neighbor-search","display_name":"Nearest neighbor search","score":0.7477717399597168},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6715216636657715},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5917893648147583},{"id":"https://openalex.org/keywords/seeding","display_name":"Seeding","score":0.5653012990951538},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5543474555015564},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.531726598739624},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5179049372673035},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.5123001337051392},{"id":"https://openalex.org/keywords/k-mer","display_name":"k-mer","score":0.5108006000518799},{"id":"https://openalex.org/keywords/notation","display_name":"Notation","score":0.42432254552841187},{"id":"https://openalex.org/keywords/sensitivity","display_name":"Sensitivity (control systems)","score":0.4138835668563843},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3963189125061035},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.37106117606163025},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.32786017656326294},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2896689176559448},{"id":"https://openalex.org/keywords/dna-sequencing","display_name":"DNA sequencing","score":0.26971447467803955},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.20101648569107056},{"id":"https://openalex.org/keywords/dna","display_name":"DNA","score":0.18768629431724548},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.1312936544418335},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.11357671022415161},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.08077099919319153}],"concepts":[{"id":"https://openalex.org/C116738811","wikidata":"https://www.wikidata.org/wiki/Q608751","display_name":"Nearest neighbor search","level":2,"score":0.7477717399597168},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6715216636657715},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5917893648147583},{"id":"https://openalex.org/C36248471","wikidata":"https://www.wikidata.org/wiki/Q7445669","display_name":"Seeding","level":2,"score":0.5653012990951538},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5543474555015564},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.531726598739624},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5179049372673035},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.5123001337051392},{"id":"https://openalex.org/C2279292","wikidata":"https://www.wikidata.org/wiki/Q6322851","display_name":"k-mer","level":4,"score":0.5108006000518799},{"id":"https://openalex.org/C45357846","wikidata":"https://www.wikidata.org/wiki/Q2001982","display_name":"Notation","level":2,"score":0.42432254552841187},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.4138835668563843},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3963189125061035},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.37106117606163025},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32786017656326294},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2896689176559448},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.26971447467803955},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.20101648569107056},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.18768629431724548},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.1312936544418335},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.11357671022415161},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.08077099919319153},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","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/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":[{"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":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D004330","descriptor_name":"Drosophila","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D004330","descriptor_name":"Drosophila","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D004330","descriptor_name":"Drosophila","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","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":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017386","descriptor_name":"Sequence Homology, Amino Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D017386","descriptor_name":"Sequence Homology, Amino Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D017386","descriptor_name":"Sequence Homology, Amino Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","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":"D051379","descriptor_name":"Mice","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D051379","descriptor_name":"Mice","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D051379","descriptor_name":"Mice","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1109/tcbb.2014.2306831","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcbb.2014.2306831","pdf_url":null,"source":{"id":"https://openalex.org/S36029991","display_name":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","issn_l":"1545-5963","issn":["1545-5963","1557-9964","2374-0043"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","raw_type":"journal-article"},{"id":"pmid:26355786","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/26355786","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":"IEEE/ACM transactions on computational biology and bioinformatics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"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/W2017608260","https://openalex.org/W2035482939","https://openalex.org/W2040975520","https://openalex.org/W2055043387","https://openalex.org/W2084252156","https://openalex.org/W2106811687","https://openalex.org/W2107903949","https://openalex.org/W2109692166","https://openalex.org/W2115872073","https://openalex.org/W2116398954","https://openalex.org/W2121272213","https://openalex.org/W2128591967","https://openalex.org/W2131989567","https://openalex.org/W2140154634","https://openalex.org/W2143124024","https://openalex.org/W2143210482","https://openalex.org/W2158714788","https://openalex.org/W2241580500","https://openalex.org/W4230194953","https://openalex.org/W4233334497","https://openalex.org/W4236236547","https://openalex.org/W6690132952"],"related_works":["https://openalex.org/W1966359094","https://openalex.org/W2616508114","https://openalex.org/W2337746918","https://openalex.org/W2476683972","https://openalex.org/W2075688075","https://openalex.org/W2094615112","https://openalex.org/W2564509174","https://openalex.org/W73805934","https://openalex.org/W30767601","https://openalex.org/W2022653138"],"abstract_inverted_index":{"Large-scale":[0],"comparison":[1],"or":[2,43],"similarity":[3,25,85],"search":[4,26,54,57],"of":[5,12,90,100,144],"genomic":[6],"DNA":[7,21],"and":[8,22,80,122],"protein":[9,23,83],"sequence":[10,24,84,121],"is":[11,103],"fundamental":[13],"importance":[14],"in":[15,82],"modern":[16],"molecular":[17],"biology.":[18],"To":[19],"perform":[20],"efficiently,":[27],"seeding":[28,66,156],"(or":[29],"filtration)":[30],"method":[31,89,143],"has":[32],"been":[33],"widely":[34],"used":[35,115],"where":[36],"only":[37],"sequences":[38],"sharing":[39],"a":[40,64,74,98],"common":[41],"pattern":[42],"\"seed\"":[44],"are":[45,113],"subject":[46],"to":[47,116],"detailed":[48],"comparison.":[49],"Therefore":[50],"these":[51],"methods":[52],"trade":[53],"sensitivity":[55,79],"with":[56],"speed.":[58],"In":[59],"this":[60],"paper,":[61],"we":[62],"introduce":[63],"new":[65],"method,":[67],"called":[68],"spaced":[69,91,96,101,110,133,145],"k-mer":[70,92,111,146],"neighbors,":[71,93],"which":[72],"provides":[73],"better":[75],"tradeoff":[76,152],"between":[77,119],"the":[78,88,132,142,150],"speed":[81],"search.":[86],"With":[87],"for":[94,131],"each":[95],"k-mer,":[97],"set":[99],"k-mers":[102],"selected":[104],"as":[105],"its":[106],"neighbors.":[107],"These":[108],"pre-selected":[109],"neighbors":[112,147],"then":[114],"detect":[117],"hits":[118],"query":[120],"database":[123],"sequences.":[124],"We":[125],"propose":[126],"an":[127],"efficient":[128],"heuristic":[129],"algorithm":[130],"neighbor":[134],"selection.":[135],"Our":[136],"computational":[137],"experimental":[138],"results":[139],"demonstrate":[140],"that":[141],"can":[148],"improve":[149],"overall":[151],"efficiency":[153],"over":[154],"existing":[155],"methods.":[157]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2016-06-24T00:00:00"}
