{"id":"https://openalex.org/W2121950477","doi":"https://doi.org/10.1093/bioinformatics/bth141","title":"Protein homology detection using string alignment kernels","display_name":"Protein homology detection using string alignment kernels","publication_year":2004,"publication_date":"2004-02-26","ids":{"openalex":"https://openalex.org/W2121950477","doi":"https://doi.org/10.1093/bioinformatics/bth141","mag":"2121950477"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/bth141","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bth141","pdf_url":null,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"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/A5040675658","display_name":"Hiroto Saigo","orcid":"https://orcid.org/0000-0001-5314-5367"},"institutions":[{"id":"https://openalex.org/I4399598384","display_name":"Kyoto University Institute for Chemical Research","ror":"https://ror.org/0349bbg69","country_code":null,"type":"facility","lineage":["https://openalex.org/I22299242","https://openalex.org/I4399598384"]},{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Hiroto Saigo","raw_affiliation_strings":["Bioinformatics Center, Institute for Chemical Research, Kyoto University, Uji 611-0011, Japan"],"affiliations":[{"raw_affiliation_string":"Bioinformatics Center, Institute for Chemical Research, Kyoto University, Uji 611-0011, Japan","institution_ids":["https://openalex.org/I22299242","https://openalex.org/I4399598384"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064770739","display_name":"Jean\u2010Philippe Vert","orcid":"https://orcid.org/0000-0001-9510-8441"},"institutions":[{"id":"https://openalex.org/I70768539","display_name":"\u00c9cole Nationale Sup\u00e9rieure des Mines de Paris","ror":"https://ror.org/04y8cs423","country_code":"FR","type":"education","lineage":["https://openalex.org/I190752583","https://openalex.org/I2746051580","https://openalex.org/I70768539"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Jean-Philippe Vert","raw_affiliation_strings":["Centre de G\u00e9ostatistique, Ecole des Mines de Paris, 35 rue Saint-Honor\u00e9, Fontainebleau, 77300, France"],"affiliations":[{"raw_affiliation_string":"Centre de G\u00e9ostatistique, Ecole des Mines de Paris, 35 rue Saint-Honor\u00e9, Fontainebleau, 77300, France","institution_ids":["https://openalex.org/I70768539"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109202903","display_name":"Nobuhisa Ueda","orcid":null},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]},{"id":"https://openalex.org/I4399598384","display_name":"Kyoto University Institute for Chemical Research","ror":"https://ror.org/0349bbg69","country_code":null,"type":"facility","lineage":["https://openalex.org/I22299242","https://openalex.org/I4399598384"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Nobuhisa Ueda","raw_affiliation_strings":["Bioinformatics Center, Institute for Chemical Research, Kyoto University, Uji 611-0011, Japan"],"affiliations":[{"raw_affiliation_string":"Bioinformatics Center, Institute for Chemical Research, Kyoto University, Uji 611-0011, Japan","institution_ids":["https://openalex.org/I22299242","https://openalex.org/I4399598384"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016330265","display_name":"Tatsuya Akutsu","orcid":"https://orcid.org/0000-0001-9763-797X"},"institutions":[{"id":"https://openalex.org/I4399598384","display_name":"Kyoto University Institute for Chemical Research","ror":"https://ror.org/0349bbg69","country_code":null,"type":"facility","lineage":["https://openalex.org/I22299242","https://openalex.org/I4399598384"]},{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tatsuya Akutsu","raw_affiliation_strings":["Bioinformatics Center, Institute for Chemical Research, Kyoto University, Uji 611-0011, Japan"],"affiliations":[{"raw_affiliation_string":"Bioinformatics Center, Institute for Chemical Research, Kyoto University, Uji 611-0011, Japan","institution_ids":["https://openalex.org/I22299242","https://openalex.org/I4399598384"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5040675658"],"corresponding_institution_ids":["https://openalex.org/I22299242","https://openalex.org/I4399598384"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":8.9232,"has_fulltext":false,"cited_by_count":379,"citation_normalized_percentile":{"value":0.98709505,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":"20","issue":"11","first_page":"1682","last_page":"1689"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9988999962806702,"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/T10044","display_name":"Protein Structure and Dynamics","score":0.9987000226974487,"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/discriminative-model","display_name":"Discriminative model","score":0.8012924790382385},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.7583589553833008},{"id":"https://openalex.org/keywords/smith\u2013waterman-algorithm","display_name":"Smith\u2013Waterman algorithm","score":0.6430066823959351},{"id":"https://openalex.org/keywords/homology","display_name":"Homology (biology)","score":0.6377661228179932},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6290287375450134},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.6150243878364563},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5707587003707886},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5626463890075684},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5501289963722229},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4814126491546631},{"id":"https://openalex.org/keywords/string-kernel","display_name":"String kernel","score":0.4740588068962097},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.4666222333908081},{"id":"https://openalex.org/keywords/sequence-alignment","display_name":"Sequence alignment","score":0.4618614614009857},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.43491289019584656},{"id":"https://openalex.org/keywords/similarity-measure","display_name":"Similarity measure","score":0.41308218240737915},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.352253794670105},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.33974653482437134},{"id":"https://openalex.org/keywords/kernel-method","display_name":"Kernel method","score":0.3303402066230774},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22521305084228516},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.21080690622329712},{"id":"https://openalex.org/keywords/peptide-sequence","display_name":"Peptide sequence","score":0.14342564344406128},{"id":"https://openalex.org/keywords/radial-basis-function-kernel","display_name":"Radial basis function kernel","score":0.13362255692481995},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.12535899877548218},{"id":"https://openalex.org/keywords/amino-acid","display_name":"Amino acid","score":0.08533364534378052}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8012924790382385},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.7583589553833008},{"id":"https://openalex.org/C72802188","wikidata":"https://www.wikidata.org/wiki/Q1683352","display_name":"Smith\u2013Waterman algorithm","level":5,"score":0.6430066823959351},{"id":"https://openalex.org/C165525559","wikidata":"https://www.wikidata.org/wiki/Q224180","display_name":"Homology (biology)","level":3,"score":0.6377661228179932},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6290287375450134},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.6150243878364563},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5707587003707886},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5626463890075684},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5501289963722229},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4814126491546631},{"id":"https://openalex.org/C55851704","wikidata":"https://www.wikidata.org/wiki/Q7623983","display_name":"String kernel","level":5,"score":0.4740588068962097},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.4666222333908081},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.4618614614009857},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.43491289019584656},{"id":"https://openalex.org/C2776517306","wikidata":"https://www.wikidata.org/wiki/Q29017317","display_name":"Similarity measure","level":2,"score":0.41308218240737915},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.352253794670105},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.33974653482437134},{"id":"https://openalex.org/C122280245","wikidata":"https://www.wikidata.org/wiki/Q620622","display_name":"Kernel method","level":3,"score":0.3303402066230774},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22521305084228516},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.21080690622329712},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.14342564344406128},{"id":"https://openalex.org/C75866337","wikidata":"https://www.wikidata.org/wiki/Q7280263","display_name":"Radial basis function kernel","level":4,"score":0.13362255692481995},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.12535899877548218},{"id":"https://openalex.org/C515207424","wikidata":"https://www.wikidata.org/wiki/Q8066","display_name":"Amino acid","level":2,"score":0.08533364534378052},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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/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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/bth141","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bth141","pdf_url":null,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmh:oai:HAL:hal-00433587v1","is_oa":false,"landing_page_url":"https://hal.science/hal-00433587","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bioinformatics, 2004, 20 (11), pp.1682-9. ⟨10.1093/bioinformatics/bth141⟩","raw_type":"Journal articles"},{"id":"pmh:oai:pure.mpg.de:item_1792114","is_oa":false,"landing_page_url":"http://hdl.handle.net/11858/00-001M-0000-0013-F3D1-3","pdf_url":null,"source":{"id":"https://openalex.org/S4306400654","display_name":"MPG.PuRe (Max Planck Society)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I149899117","host_organization_name":"Max Planck Society","host_organization_lineage":["https://openalex.org/I149899117"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bioinformatics","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7599999904632568}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W179694669","https://openalex.org/W1422803820","https://openalex.org/W1528620860","https://openalex.org/W1542652324","https://openalex.org/W1549656520","https://openalex.org/W1558365920","https://openalex.org/W1560724230","https://openalex.org/W1563088657","https://openalex.org/W1576213419","https://openalex.org/W1675272512","https://openalex.org/W2009570821","https://openalex.org/W2013570924","https://openalex.org/W2020816856","https://openalex.org/W2055043387","https://openalex.org/W2084787613","https://openalex.org/W2085277871","https://openalex.org/W2087064593","https://openalex.org/W2087347434","https://openalex.org/W2102122585","https://openalex.org/W2107725114","https://openalex.org/W2140000393","https://openalex.org/W2140244239","https://openalex.org/W2148603752","https://openalex.org/W2156455118","https://openalex.org/W2158714788","https://openalex.org/W2283504545","https://openalex.org/W2554813760","https://openalex.org/W2798909945","https://openalex.org/W3144619878","https://openalex.org/W4236236547","https://openalex.org/W4250029775","https://openalex.org/W4376453320"],"related_works":["https://openalex.org/W2948014085","https://openalex.org/W2004215917","https://openalex.org/W2103737249","https://openalex.org/W1974956921","https://openalex.org/W2139695554","https://openalex.org/W1972247471","https://openalex.org/W1486249959","https://openalex.org/W2166325055","https://openalex.org/W2163203700","https://openalex.org/W2746873660"],"abstract_inverted_index":{"Abstract":[0],"Motivation:":[1],"Remote":[2],"homology":[3,122],"detection":[4],"between":[5,57,81],"protein":[6],"sequences":[7,83],"is":[8],"a":[9,111],"central":[10],"problem":[11,30],"in":[12,34,99],"computational":[13],"biology.":[14],"Discriminative":[15],"methods":[16,27,119],"involving":[17],"support":[18],"vector":[19],"machines":[20],"(SVMs)":[21],"are":[22],"currently":[23],"the":[24,29,35,49,55,79,95,114],"most":[25],"effective":[26],"for":[28,64,120],"of":[31,44,94],"superfamily":[32],"recognition":[33],"Structural":[36],"Classification":[37],"Of":[38],"Proteins":[39],"(SCOP)":[40],"database.":[41],"The":[42],"performance":[43],"SVMs":[45],"depends":[46],"critically":[47],"on":[48,103,110],"kernel":[50],"function":[51],"used":[52],"to":[53,67,106],"quantify":[54],"similarity":[56,80],"sequences.":[58,96],"Results:":[59],"We":[60],"propose":[61],"new":[62,115],"kernels":[63,77,116],"strings":[65],"adapted":[66],"biological":[68],"sequences,":[69],"which":[70],"we":[71],"call":[72],"local":[73,90],"alignment":[74],"kernels.":[75],"These":[76],"measure":[78],"two":[82],"by":[84],"summing":[85],"up":[86],"scores":[87],"obtained":[88],"from":[89],"alignments":[91],"with":[92,101],"gaps":[93],"When":[97],"tested":[98],"combination":[100],"SVM":[102],"their":[104],"ability":[105],"recognize":[107],"SCOP":[108],"superfamilies":[109],"benchmark":[112],"dataset,":[113],"outperform":[117],"state-of-the-art":[118],"remote":[121],"detection.":[123],"Availability:":[124],"Software":[125],"and":[126],"data":[127],"available":[128],"upon":[129],"request.":[130]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":20},{"year":2018,"cited_by_count":17},{"year":2017,"cited_by_count":22},{"year":2016,"cited_by_count":17},{"year":2015,"cited_by_count":23},{"year":2014,"cited_by_count":15},{"year":2013,"cited_by_count":24},{"year":2012,"cited_by_count":21}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2016-06-24T00:00:00"}