{"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","pmid":"https://pubmed.ncbi.nlm.nih.gov/14988126"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/bth141","doi":"https://doi.org/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,"listed_in":["abdc-a","anvur-class-a","anvur-scientific","ccf-a","cwts-core","doaj","dongbi-b","doyens","jufo-3","ki-jl-2","medline","norway-2","oarl","poland-200","russia-white-list-1","vabb-shw"],"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"},"parent_works":[],"lineage":["https://openalex.org/W2121950477"],"child_works_count":0,"type":"article","is_traditional":true,"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/A5040675658","display_name":"Hiroto Saigo","orcid":"https://orcid.org/0000-0001-5314-5367","observed_orcids":["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":"JP","type":"facility","lineage":["https://openalex.org/I22299242","https://openalex.org/I4399598384"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroto Saigo","raw_affiliation_strings":["Bioinformatics Center, Institute for Chemical Research, Kyoto University, Uji, 611-0011, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bioinformatics Center, Institute for Chemical Research, Kyoto University, Uji, 611-0011, Japan","institution_ids":["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","observed_orcids":["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"],"raw_orcid":null,"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":null,"display_name":"Nobuhisa Ueda","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4399598384","display_name":"Kyoto University Institute for Chemical Research","ror":"https://ror.org/0349bbg69","country_code":"JP","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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bioinformatics Center, Institute for Chemical Research, Kyoto University, Uji 611-0011, Japan","institution_ids":["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","observed_orcids":["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":"JP","type":"facility","lineage":["https://openalex.org/I22299242","https://openalex.org/I4399598384"]}],"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bioinformatics Center, Institute for Chemical Research, Kyoto University, Uji 611-0011, Japan","institution_ids":["https://openalex.org/I4399598384"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":3989,"currency":"USD","value_usd":3989},"apc_paid":null,"fwci":7.1211,"has_fulltext":false,"cited_by_count":380,"citation_normalized_percentile":{"value":0.98568507,"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":0.88919997215271,"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":0.88919997215271,"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":0.0494999997317791,"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":0.046300001442432404,"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/remote-homology-detection","display_name":"remote homology detection","score":0.8600000143051147},{"id":"https://openalex.org/keywords/protein-sequence-alignment","display_name":"protein sequence alignment","score":0.6359999775886536},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"support vector machine","score":0.9089999794960022},{"id":"https://openalex.org/keywords/sequence-similarity-measures","display_name":"sequence similarity measures","score":0.5090000033378601}],"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":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003205","descriptor_name":"Computing Methodologies","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D017386","descriptor_name":"Sequence Homology, Amino Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017434","descriptor_name":"Protein Structure, Tertiary","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":4,"locations":[{"id":"doi:10.1093/bioinformatics/bth141","doi":"https://doi.org/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,"listed_in":["abdc-a","anvur-class-a","anvur-scientific","ccf-a","cwts-core","doaj","dongbi-b","doyens","jufo-3","ki-jl-2","medline","norway-2","oarl","poland-200","russia-white-list-1","vabb-shw"],"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":"pmid:14988126","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/14988126","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,"listed_in":[],"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":"Bioinformatics (Oxford, England)","raw_type":"Comparative Study"},{"id":"pmh:oai:HAL:hal-00433587v1","doi":null,"is_oa":false,"landing_page_url":"https://hal.science/hal-00433587","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"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":"info:eu-repo/semantics/article"},{"id":"pmh:oai:pure.mpg.de:item_1792114","doi":null,"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,"listed_in":[],"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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"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/W2066715908","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/W4250029775"],"related_works":["https://openalex.org/W2106575335","https://openalex.org/W2170960297","https://openalex.org/W2142013909","https://openalex.org/W7099238557","https://openalex.org/W7096392514","https://openalex.org/W2020816856","https://openalex.org/W2283504545","https://openalex.org/W2047429137"],"abstract_inverted_index":{"MOTIVATION:":[0],"Remote":[1],"homology":[2,121],"detection":[3],"between":[4,56,80],"protein":[5],"sequences":[6,82],"is":[7],"a":[8,110],"central":[9],"problem":[10,29],"in":[11,33,98],"computational":[12],"biology.":[13],"Discriminative":[14],"methods":[15,26,118],"involving":[16],"support":[17],"vector":[18],"machines":[19],"(SVMs)":[20],"are":[21],"currently":[22],"the":[23,28,34,48,54,78,94,113],"most":[24],"effective":[25],"for":[27,63,119],"of":[30,43,93],"superfamily":[31],"recognition":[32],"Structural":[35],"Classification":[36],"Of":[37],"Proteins":[38],"(SCOP)":[39],"database.":[40],"The":[41],"performance":[42],"SVMs":[44],"depends":[45],"critically":[46],"on":[47,102,109],"kernel":[49],"function":[50],"used":[51],"to":[52,66,105],"quantify":[53],"similarity":[55,79],"sequences.":[57,95],"RESULTS:":[58],"We":[59],"propose":[60],"new":[61,114],"kernels":[62,76,115],"strings":[64],"adapted":[65],"biological":[67],"sequences,":[68],"which":[69],"we":[70],"call":[71],"local":[72,89],"alignment":[73],"kernels.":[74],"These":[75],"measure":[77],"two":[81],"by":[83],"summing":[84],"up":[85],"scores":[86],"obtained":[87],"from":[88],"alignments":[90],"with":[91,100],"gaps":[92],"When":[96],"tested":[97],"combination":[99],"SVM":[101],"their":[103],"ability":[104],"recognize":[106],"SCOP":[107],"superfamilies":[108],"benchmark":[111],"dataset,":[112],"outperform":[116],"state-of-the-art":[117],"remote":[120],"detection.":[122],"AVAILABILITY:":[123],"Software":[124],"and":[125],"data":[126],"available":[127],"upon":[128],"request.":[129]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":21},{"year":2018,"cited_by_count":16},{"year":2017,"cited_by_count":22},{"year":2016,"cited_by_count":17},{"year":2015,"cited_by_count":22},{"year":2014,"cited_by_count":12},{"year":2013,"cited_by_count":24},{"year":2012,"cited_by_count":23}],"updated_date":"2026-11-14T11:04:58.165337","created_date":"2016-06-24T00:00:00"}