{"id":"https://openalex.org/W2170960297","doi":"https://doi.org/10.1093/bioinformatics/btg431","title":"Mismatch string kernels for discriminative protein classification","display_name":"Mismatch string kernels for discriminative protein classification","publication_year":2004,"publication_date":"2004-01-22","ids":{"openalex":"https://openalex.org/W2170960297","doi":"https://doi.org/10.1093/bioinformatics/btg431","mag":"2170960297","pmid":"https://pubmed.ncbi.nlm.nih.gov/14990442"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btg431","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btg431","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/20/4/467/48905245/bioinformatics_20_4_467.pdf","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","pubmed"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/20/4/467/48905245/bioinformatics_20_4_467.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5085231879","display_name":"Christina S. Leslie","orcid":"https://orcid.org/0000-0002-4571-5910"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Christina S. Leslie","raw_affiliation_strings":["Department of Computer Science, Columbia University, 1214 Amsterdam Avenue, Mail Code 0401, New York, NY 10027, USA. cleslie@cs.columbia.edu","Department of Computer Science, Columbia University, 1214 Amsterdam Avenue, Mail Code 0401, New York, NY 10027, USA,"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Columbia University, 1214 Amsterdam Avenue, Mail Code 0401, New York, NY 10027, USA. cleslie@cs.columbia.edu","institution_ids":["https://openalex.org/I78577930"]},{"raw_affiliation_string":"Department of Computer Science, Columbia University, 1214 Amsterdam Avenue, Mail Code 0401, New York, NY 10027, USA,","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009368988","display_name":"Eleazar Eskin","orcid":"https://orcid.org/0000-0003-1149-4758"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eleazar Eskin","raw_affiliation_strings":["Department of Computer Science, Columbia University, 1214 Amsterdam Avenue, Mail Code 0401, New York, NY 10027, USA,"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Columbia University, 1214 Amsterdam Avenue, Mail Code 0401, New York, NY 10027, USA,","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111601441","display_name":"Adiel Cohen","orcid":null},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Adiel Cohen","raw_affiliation_strings":["Department of Computer Science, Columbia University, 1214 Amsterdam Avenue, Mail Code 0401, New York, NY 10027, USA,"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Columbia University, 1214 Amsterdam Avenue, Mail Code 0401, New York, NY 10027, USA,","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076635608","display_name":"Jason Weston","orcid":null},"institutions":[{"id":"https://openalex.org/I4210112925","display_name":"Max Planck Institute for Biological Cybernetics","ror":"https://ror.org/026nmvv73","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210112925"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jason Weston","raw_affiliation_strings":["Max-Planck Institute for Biological Cybernetics, Spemannstrasse 38, 72076 Tbingen, Germany and","Max-Planck Institute for Biological Cybernetics, Spemannstrasse 38, 72076 T\u00fcbingen, Germany and"],"affiliations":[{"raw_affiliation_string":"Max-Planck Institute for Biological Cybernetics, Spemannstrasse 38, 72076 Tbingen, Germany and","institution_ids":["https://openalex.org/I4210112925"]},{"raw_affiliation_string":"Max-Planck Institute for Biological Cybernetics, Spemannstrasse 38, 72076 T\u00fcbingen, Germany and","institution_ids":["https://openalex.org/I4210112925"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057375933","display_name":"William Stafford Noble","orcid":"https://orcid.org/0000-0001-7283-4715"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"William Stafford Noble","raw_affiliation_strings":["Department of Genome Sciences, University of Washington, 1705 NE Pacific Street, Seattle, WA 98195, USA"],"affiliations":[{"raw_affiliation_string":"Department of Genome Sciences, University of Washington, 1705 NE Pacific Street, Seattle, WA 98195, USA","institution_ids":["https://openalex.org/I201448701"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5085231879"],"corresponding_institution_ids":["https://openalex.org/I78577930"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":14.3498,"has_fulltext":true,"cited_by_count":571,"citation_normalized_percentile":{"value":0.99513197,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"20","issue":"4","first_page":"467","last_page":"476"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9995999932289124,"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/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.9959999918937683,"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":0.8194120526313782},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6752269268035889},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.6640741229057312},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6540778279304504},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.642890214920044},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6391485333442688},{"id":"https://openalex.org/keywords/string-kernel","display_name":"String kernel","score":0.5484800934791565},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4870779812335968},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.47838273644447327},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.47291144728660583},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4207104444503784},{"id":"https://openalex.org/keywords/kernel-method","display_name":"Kernel method","score":0.38029003143310547},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.2757692337036133},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.25213974714279175},{"id":"https://openalex.org/keywords/radial-basis-function-kernel","display_name":"Radial basis function kernel","score":0.16974902153015137}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8194120526313782},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6752269268035889},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.6640741229057312},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6540778279304504},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.642890214920044},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6391485333442688},{"id":"https://openalex.org/C55851704","wikidata":"https://www.wikidata.org/wiki/Q7623983","display_name":"String kernel","level":5,"score":0.5484800934791565},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4870779812335968},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47838273644447327},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.47291144728660583},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4207104444503784},{"id":"https://openalex.org/C122280245","wikidata":"https://www.wikidata.org/wiki/Q620622","display_name":"Kernel method","level":3,"score":0.38029003143310547},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.2757692337036133},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25213974714279175},{"id":"https://openalex.org/C75866337","wikidata":"https://www.wikidata.org/wiki/Q7280263","display_name":"Radial basis function kernel","level":4,"score":0.16974902153015137},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"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":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","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":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009687","descriptor_name":"Nuclear Proteins","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D009687","descriptor_name":"Nuclear Proteins","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D009687","descriptor_name":"Nuclear Proteins","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D009687","descriptor_name":"Nuclear Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D009687","descriptor_name":"Nuclear Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D009687","descriptor_name":"Nuclear Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","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":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010749","descriptor_name":"Phosphoprotein Phosphatases","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010749","descriptor_name":"Phosphoprotein Phosphatases","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010749","descriptor_name":"Phosphoprotein Phosphatases","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":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000145","qualifier_name":"classification","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":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017386","descriptor_name":"Sequence Homology, Amino Acid","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":false},{"descriptor_ui":"D017386","descriptor_name":"Sequence Homology, Amino Acid","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":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}],"locations_count":5,"locations":[{"id":"doi:10.1093/bioinformatics/btg431","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btg431","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/20/4/467/48905245/bioinformatics_20_4_467.pdf","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":"pmid:14990442","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/14990442","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":"Bioinformatics (Oxford, England)","raw_type":null},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.407.3340","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.407.3340","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://noble.gs.washington.edu/papers/leslie_mismatch2.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.86.7384","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.86.7384","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ccls.columbia.edu/compbio/mismatch/longer-mismatch.pdf","raw_type":"text"},{"id":"pmh:oai:pure.mpg.de:item_3180590","is_oa":false,"landing_page_url":"http://hdl.handle.net/21.11116/0000-0005-4F63-4","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":{"id":"doi:10.1093/bioinformatics/btg431","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btg431","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/20/4/467/48905245/bioinformatics_20_4_467.pdf","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"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7599999904632568}],"awards":[{"id":"https://openalex.org/G101112439","display_name":null,"funder_award_id":"Fellow","funder_id":"https://openalex.org/F4320306151","funder_display_name":"Alfred P. Sloan Foundation"},{"id":"https://openalex.org/G5041625248","display_name":null,"funder_award_id":"007852","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G593386812","display_name":null,"funder_award_id":"Fellowship","funder_id":"https://openalex.org/F4320306799","funder_display_name":"Pharmaceutical Research and Manufacturers of America Foundation"},{"id":"https://openalex.org/G6894402473","display_name":null,"funder_award_id":"Fellowship","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306151","display_name":"Alfred P. Sloan Foundation","ror":"https://ror.org/052csg198"},{"id":"https://openalex.org/F4320306799","display_name":"Pharmaceutical Research and Manufacturers of America Foundation","ror":"https://ror.org/01z88k350"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2170960297.pdf","grobid_xml":"https://content.openalex.org/works/W2170960297.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W1500328508","https://openalex.org/W1541794469","https://openalex.org/W1576213419","https://openalex.org/W1582476847","https://openalex.org/W1601740268","https://openalex.org/W1969051510","https://openalex.org/W1973714307","https://openalex.org/W1990061958","https://openalex.org/W2007735554","https://openalex.org/W2008922668","https://openalex.org/W2013570924","https://openalex.org/W2018010122","https://openalex.org/W2020816856","https://openalex.org/W2055043387","https://openalex.org/W2068080810","https://openalex.org/W2085277871","https://openalex.org/W2087347434","https://openalex.org/W2102122585","https://openalex.org/W2106868411","https://openalex.org/W2107425660","https://openalex.org/W2107725114","https://openalex.org/W2112865076","https://openalex.org/W2117019496","https://openalex.org/W2117619142","https://openalex.org/W2122369731","https://openalex.org/W2122674287","https://openalex.org/W2124225821","https://openalex.org/W2145358391","https://openalex.org/W2148014281","https://openalex.org/W2148603752","https://openalex.org/W2156455118","https://openalex.org/W2158714788","https://openalex.org/W2283504545","https://openalex.org/W2320748401","https://openalex.org/W2554813760","https://openalex.org/W2610179052","https://openalex.org/W2915190566","https://openalex.org/W3150945973","https://openalex.org/W4236236547","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2167155152","https://openalex.org/W2093104230","https://openalex.org/W4390874210","https://openalex.org/W4384918963","https://openalex.org/W2128027845","https://openalex.org/W4386184937","https://openalex.org/W1493875009","https://openalex.org/W4388844349","https://openalex.org/W2105231718","https://openalex.org/W2153939756"],"abstract_inverted_index":{"We":[0,74,118],"introduce":[1],"a":[2,18,55,80],"class":[3],"of":[4,24,40,91,155],"string":[5],"kernels,":[6,9],"called":[7],"mismatch":[8,81,131],"for":[10,47,143],"use":[11],"with":[12,107,134,140],"support":[13],"vector":[14],"machines":[15],"(SVMs)":[16],"in":[17,43,95,98,168],"discriminative":[19],"approach":[20],"to":[21,59,87],"the":[22,44,52,76,89,96,103,110,130,156,161],"problem":[23],"protein":[25,61,169],"classification":[26],"and":[27,171],"remote":[28],"homology":[29,144],"detection.":[30],"These":[31],"kernels":[32,53,77,111],"measure":[33],"sequence":[34],"similarity":[35],"based":[36],"on":[37,65,115,121],"shared":[38],"occurrences":[39],"fixed-length":[41],"patterns":[42,93,158],"data,":[45],"allowing":[46,85],"mutations":[48],"between":[49],"patterns.":[50],"Thus,":[51],"provide":[54],"biologically":[56,165],"well-motivated":[57],"way":[58],"compare":[60],"sequences":[62],"without":[63],"relying":[64],"family-based":[66],"generative":[67],"models":[68],"such":[69],"as":[70],"hidden":[71],"Markov":[72],"models.":[73],"compute":[75],"efficiently":[78],"using":[79],"tree":[82],"data":[83,97],"structure,":[84],"us":[86],"calculate":[88],"contributions":[90],"all":[92],"occurring":[94],"one":[99],"pass":[100],"while":[101],"traversing":[102],"tree.":[104],"When":[105],"used":[106,133],"an":[108,135],"SVM,":[109],"enable":[112],"fast":[113],"prediction":[114],"test":[116],"sequences.":[117],"report":[119],"experiments":[120],"two":[122],"benchmark":[123],"SCOP":[124],"datasets,":[125],"where":[126],"we":[127],"show":[128],"that":[129],"kernel":[132],"SVM":[136,162],"classifier":[137,163],"performs":[138],"competitively":[139],"state-of-the-art":[141],"methods":[142],"detection,":[145],"particularly":[146],"when":[147],"very":[148],"few":[149],"training":[150],"examples":[151],"are":[152],"available.":[153],"Examination":[154],"highest-weighted":[157],"learned":[159],"by":[160],"recovers":[164],"important":[166],"motifs":[167],"families":[170],"superfamilies.":[172]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":15},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":13},{"year":2019,"cited_by_count":31},{"year":2018,"cited_by_count":32},{"year":2017,"cited_by_count":26},{"year":2016,"cited_by_count":31},{"year":2015,"cited_by_count":31},{"year":2014,"cited_by_count":26},{"year":2013,"cited_by_count":35},{"year":2012,"cited_by_count":29}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}