{"id":"https://openalex.org/W2094476817","doi":"https://doi.org/10.1145/2339530.2339649","title":"Efficient evaluation of large sequence kernels","display_name":"Efficient evaluation of large sequence kernels","publication_year":2012,"publication_date":"2012-08-12","ids":{"openalex":"https://openalex.org/W2094476817","doi":"https://doi.org/10.1145/2339530.2339649","mag":"2094476817"},"language":"en","primary_location":{"id":"doi:10.1145/2339530.2339649","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2339530.2339649","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th ACM SIGKDD international conference on Knowledge discovery and data mining","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/A5028780139","display_name":"Pavel P. Kuksa","orcid":"https://orcid.org/0000-0003-2248-6403"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pavel P. Kuksa","raw_affiliation_strings":["NEC Laboratories America, Princeton, NJ, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NEC Laboratories America, Princeton, NJ, USA","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020368096","display_name":"Vladimir Pavlovi\u0107","orcid":"https://orcid.org/0000-0003-3979-1236"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vladimir Pavlovic","raw_affiliation_strings":["Rutgers University, New Brunswick, NJ, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rutgers University, New Brunswick, NJ, USA","institution_ids":["https://openalex.org/I102322142"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.20762829,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"759","last_page":"767"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9991000294685364,"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"}},{"id":"https://openalex.org/T10901","display_name":"Advanced Data Compression Techniques","score":0.9965999722480774,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/sequence","display_name":"Sequence (biology)","score":0.6538971662521362},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5845933556556702},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.1753332018852234}],"concepts":[{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6538971662521362},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5845933556556702},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.1753332018852234},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2339530.2339649","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2339530.2339649","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7400000095367432}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1480643256","https://openalex.org/W1510073064","https://openalex.org/W1716169354","https://openalex.org/W1857358525","https://openalex.org/W1969051510","https://openalex.org/W2016202965","https://openalex.org/W2020816856","https://openalex.org/W2058119134","https://openalex.org/W2059999539","https://openalex.org/W2063389953","https://openalex.org/W2099760476","https://openalex.org/W2105099387","https://openalex.org/W2106296076","https://openalex.org/W2106575335","https://openalex.org/W2107725114","https://openalex.org/W2108837639","https://openalex.org/W2109109045","https://openalex.org/W2111125131","https://openalex.org/W2117866949","https://openalex.org/W2124225821","https://openalex.org/W2136490963","https://openalex.org/W2148603752","https://openalex.org/W2149298154","https://openalex.org/W2156455118","https://openalex.org/W2170960297","https://openalex.org/W2283504545","https://openalex.org/W4285719527","https://openalex.org/W6678167290"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W2350741829","https://openalex.org/W2530322880","https://openalex.org/W1596801655"],"abstract_inverted_index":{"Classification":[0],"of":[1,11,30,106,117,123,136,144],"sequences":[2],"drawn":[3],"from":[4],"a":[5,9,35,61,102,114,120,127],"finite":[6],"alphabet":[7,77,100],"using":[8,101],"family":[10],"string":[12,138,147],"kernels":[13,33,46,70,118],"with":[14,51,119,172],"inexact":[15],"matching":[16],"(e.g.,":[17],"spectrum":[18],"or":[19],"mismatch)":[20],"has":[21],"shown":[22],"great":[23],"success":[24],"in":[25],"machine":[26],"learning.":[27],"However,":[28],"selection":[29,132],"optimal":[31],"mismatch":[32],"for":[34,47,71,91],"particular":[36],"task":[37,80],"is":[38],"severely":[39],"limited":[40],"by":[41,84],"inability":[42],"to":[43,67,98,112,129],"compute":[44],"such":[45],"long":[48],"substrings":[49],"(k-mers)":[50],"potentially":[52],"many":[53],"mismatches":[54],"(m).":[55],"In":[56],"this":[57],"work":[58],"we":[59,149],"introduce":[60],"new":[62],"method":[63],"that":[64,168],"allows":[65],"us":[66],"exactly":[68],"evaluate":[69],"large":[72,145],"k,":[73],"m":[74],"and":[75,94,133,162],"arbitrary":[76],"size.":[78],"The":[79],"can":[81,175],"be":[82],"accomplished":[83],"first":[85],"solving":[86],"the":[87,137,142],"more":[88],"tractable":[89],"problem":[90],"small":[92,103],"alphabets,":[93],"then":[95],"trivially":[96],"generalizing":[97],"any":[99],"linear":[104],"system":[105],"equations.":[107],"This":[108],"makes":[109],"it":[110],"possible":[111],"explore":[113],"larger":[115,173],"set":[116],"wide":[121],"range":[122],"kernel":[124],"parameters,":[125],"opening":[126],"possibility":[128],"better":[130],"model":[131],"improved":[134],"performance":[135],"kernels.":[139],"To":[140],"investigate":[141],"utility":[143],"(k,m)":[146],"kernels,":[148],"consider":[150],"several":[151],"sequence":[152],"classification":[153,177],"problems,":[154],"including":[155],"protein":[156],"remote":[157],"homology":[158],"detection,":[159],"fold":[160],"prediction,":[161],"music":[163],"classification.":[164],"Our":[165],"results":[166],"show":[167],"increased":[169],"k-mer":[170],"lengths":[171],"substitutions":[174],"improve":[176],"performance.":[178]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}