{"id":"https://openalex.org/W1994400985","doi":"https://doi.org/10.1145/2350176.2350179","title":"2D similarity kernels for biological sequence classification","display_name":"2D similarity kernels for biological sequence classification","publication_year":2012,"publication_date":"2012-08-12","ids":{"openalex":"https://openalex.org/W1994400985","doi":"https://doi.org/10.1145/2350176.2350179","mag":"1994400985"},"language":"en","primary_location":{"id":"doi:10.1145/2350176.2350179","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2350176.2350179","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 11th International Workshop on Data Mining in Bioinformatics","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/A5028780139","display_name":"Pavel P. Kuksa","orcid":"https://orcid.org/0000-0003-2248-6403"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Pavel P. Kuksa","raw_affiliation_strings":["NEC Laboratories America, Inc, Princeton, NJ"],"affiliations":[{"raw_affiliation_string":"NEC Laboratories America, Inc, Princeton, NJ","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5028780139"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5253,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.63819024,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"15","last_page":"20"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9998000264167786,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9998000264167786,"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":0.9987999796867371,"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/T10885","display_name":"Gene expression and cancer classification","score":0.989799976348877,"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/string-kernel","display_name":"String kernel","score":0.8216149806976318},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.7633795738220215},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6649570465087891},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.651930034160614},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6212891936302185},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5462749004364014},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5450282096862793},{"id":"https://openalex.org/keywords/biological-data","display_name":"Biological data","score":0.5409227013587952},{"id":"https://openalex.org/keywords/kernel-method","display_name":"Kernel method","score":0.5379008054733276},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5376312732696533},{"id":"https://openalex.org/keywords/protein-sequencing","display_name":"Protein sequencing","score":0.4687614142894745},{"id":"https://openalex.org/keywords/sequence-alignment","display_name":"Sequence alignment","score":0.45608752965927124},{"id":"https://openalex.org/keywords/sequence-analysis","display_name":"Sequence analysis","score":0.43693289160728455},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.3670961260795593},{"id":"https://openalex.org/keywords/peptide-sequence","display_name":"Peptide sequence","score":0.3530612885951996},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.34886088967323303},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.29465973377227783},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2187102735042572},{"id":"https://openalex.org/keywords/polynomial-kernel","display_name":"Polynomial kernel","score":0.21794357895851135},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.1757686734199524},{"id":"https://openalex.org/keywords/dna","display_name":"DNA","score":0.15189003944396973},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.10642498731613159}],"concepts":[{"id":"https://openalex.org/C55851704","wikidata":"https://www.wikidata.org/wiki/Q7623983","display_name":"String kernel","level":5,"score":0.8216149806976318},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.7633795738220215},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6649570465087891},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.651930034160614},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6212891936302185},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5462749004364014},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5450282096862793},{"id":"https://openalex.org/C201797286","wikidata":"https://www.wikidata.org/wiki/Q4914986","display_name":"Biological data","level":2,"score":0.5409227013587952},{"id":"https://openalex.org/C122280245","wikidata":"https://www.wikidata.org/wiki/Q620622","display_name":"Kernel method","level":3,"score":0.5379008054733276},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5376312732696533},{"id":"https://openalex.org/C10010492","wikidata":"https://www.wikidata.org/wiki/Q3142557","display_name":"Protein sequencing","level":4,"score":0.4687614142894745},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.45608752965927124},{"id":"https://openalex.org/C61053724","wikidata":"https://www.wikidata.org/wiki/Q1154615","display_name":"Sequence analysis","level":3,"score":0.43693289160728455},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3670961260795593},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.3530612885951996},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.34886088967323303},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.29465973377227783},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2187102735042572},{"id":"https://openalex.org/C160446489","wikidata":"https://www.wikidata.org/wiki/Q7226642","display_name":"Polynomial kernel","level":4,"score":0.21794357895851135},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.1757686734199524},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.15189003944396973},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.10642498731613159},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2350176.2350179","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2350176.2350179","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 11th International Workshop on Data Mining in Bioinformatics","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":29,"referenced_works":["https://openalex.org/W1510073064","https://openalex.org/W1969051510","https://openalex.org/W1986532736","https://openalex.org/W1995918845","https://openalex.org/W2016202965","https://openalex.org/W2020816856","https://openalex.org/W2031324152","https://openalex.org/W2037263319","https://openalex.org/W2059999539","https://openalex.org/W2105099387","https://openalex.org/W2107725114","https://openalex.org/W2108837639","https://openalex.org/W2109109045","https://openalex.org/W2111125131","https://openalex.org/W2117077088","https://openalex.org/W2117806412","https://openalex.org/W2119290215","https://openalex.org/W2124225821","https://openalex.org/W2125493259","https://openalex.org/W2136490963","https://openalex.org/W2148603752","https://openalex.org/W2151531457","https://openalex.org/W2161195767","https://openalex.org/W2293597654","https://openalex.org/W2597289420","https://openalex.org/W3007254004","https://openalex.org/W3008624235","https://openalex.org/W4235848672","https://openalex.org/W4405648826"],"related_works":["https://openalex.org/W2163203700","https://openalex.org/W4206904133","https://openalex.org/W1975708617","https://openalex.org/W2148753920","https://openalex.org/W3013206934","https://openalex.org/W2020816856","https://openalex.org/W1835000624","https://openalex.org/W1984421104","https://openalex.org/W2535206775","https://openalex.org/W4401177601"],"abstract_inverted_index":{"String":[0],"kernel-based":[1],"machine":[2],"learning":[3],"methods":[4,41,62],"have":[5],"yielded":[6],"great":[7],"success":[8],"in":[9,66,75],"practical":[10],"tasks":[11,22,92],"of":[12,45,69,71,81],"structured/sequential":[13],"data":[14,49,65],"analysis.":[15],"They":[16],"often":[17],"exhibit":[18],"state-of-the-art":[19,102],"performance":[20],"on":[21,43],"such":[23],"as":[24],"document":[25],"topic":[26],"elucidation,":[27],"biological":[28,76],"sequence":[29,64,77,90,103],"classification,":[30],"or":[31,52,79],"protein":[32,89],"superfamily":[33],"and":[34],"fold":[35],"prediction.":[36],"However,":[37],"typical":[38],"string":[39,48],"kernel":[40,61],"rely":[42],"analysis":[44],"discrete":[46],"1D":[47],"(e.g.,":[50],"DNA":[51],"amino":[53,83],"acid":[54,84],"sequences).":[55],"This":[56],"work":[57],"introduces":[58],"new":[59],"2D":[60,94],"for":[63],"the":[67],"form":[68],"sequences":[70,80],"feature":[72],"vectors":[73],"(as":[74],"profiles,":[78],"individual":[82],"physico-chemical":[85],"descriptors).":[86],"On":[87],"three":[88],"classification":[91,104],"proposed":[93],"kernels":[95],"show":[96],"significant":[97],"15-20%":[98],"improvements":[99],"compared":[100],"to":[101],"methods.":[105]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}