{"id":"https://openalex.org/W2081118143","doi":"https://doi.org/10.1145/1008992.1009109","title":"Context sensitive vocabulary and its application in protein secondary structure prediction","display_name":"Context sensitive vocabulary and its application in protein secondary structure prediction","publication_year":2004,"publication_date":"2004-07-25","ids":{"openalex":"https://openalex.org/W2081118143","doi":"https://doi.org/10.1145/1008992.1009109","mag":"2081118143"},"language":"en","primary_location":{"id":"doi:10.1145/1008992.1009109","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1008992.1009109","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th annual international ACM SIGIR conference on Research and development in information retrieval","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/A5100351175","display_name":"Yan Liu","orcid":"https://orcid.org/0000-0003-4242-4840"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yan Liu","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA","Carnegie-Mellon University, Pittsburgh, PA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie-Mellon University, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110349922","display_name":"Jaime Carbonell","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jaime Carbonell","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA","Carnegie-Mellon University, Pittsburgh, PA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie-Mellon University, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065265042","display_name":"Judith Klein\u2010Seetharaman","orcid":"https://orcid.org/0000-0002-4892-6828"},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]},{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Judith Klein-Seetharaman","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA and University of Pittsburgh, Pittsburgh, PA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA and University of Pittsburgh, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139","https://openalex.org/I170201317"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069347895","display_name":"Vanathi Gopalakrishnan","orcid":"https://orcid.org/0000-0002-7813-4055"},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vanathi Gopalakrishnan","raw_affiliation_strings":["University of Pittsburgh, Pittsburgh, PA","[University of Pittsburgh, Pittsburgh, PA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pittsburgh, Pittsburgh, PA","institution_ids":["https://openalex.org/I170201317"]},{"raw_affiliation_string":"[University of Pittsburgh, Pittsburgh, PA]","institution_ids":["https://openalex.org/I170201317"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100351175"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.2412,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.54742734,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"538","last_page":"539"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9993000030517578,"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":0.9993000030517578,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9944000244140625,"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":0.9901000261306763,"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/computer-science","display_name":"Computer science","score":0.7651801109313965},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6981781721115112},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6734799146652222},{"id":"https://openalex.org/keywords/protein-secondary-structure","display_name":"Protein secondary structure","score":0.5375170111656189},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5314162373542786},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.49628716707229614},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.4487539529800415},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40740731358528137},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.394191175699234},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.28707343339920044},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.07565754652023315},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.06604540348052979}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7651801109313965},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6981781721115112},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6734799146652222},{"id":"https://openalex.org/C62614982","wikidata":"https://www.wikidata.org/wiki/Q904984","display_name":"Protein secondary structure","level":2,"score":0.5375170111656189},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5314162373542786},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.49628716707229614},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.4487539529800415},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40740731358528137},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.394191175699234},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.28707343339920044},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.07565754652023315},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.06604540348052979},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/1008992.1009109","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1008992.1009109","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th annual international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.cmu.edu:compsci-1301","is_oa":false,"landing_page_url":"http://repository.cmu.edu/compsci/302","pdf_url":null,"source":{"id":"https://openalex.org/S4306400668","display_name":"Research Showcase @ Carnegie Mellon University (Carnegie Mellon University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I74973139","host_organization_name":"Carnegie Mellon University","host_organization_lineage":["https://openalex.org/I74973139"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computer Science Department","raw_type":"text"},{"id":"pmh:doi:10.1184/r1/6604448","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Journal contribution"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.182.9764","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.182.9764","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.cmu.edu/%7Ejgc/publication/Context_Sensitive_Vocabulary_Application_SIGIR_2004.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8500000238418579,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1985818354","https://openalex.org/W2005422315","https://openalex.org/W2049695588","https://openalex.org/W2092067718","https://openalex.org/W2104972430","https://openalex.org/W2122945697","https://openalex.org/W2147152072","https://openalex.org/W2157046483","https://openalex.org/W2260133193"],"related_works":["https://openalex.org/W4234874385","https://openalex.org/W2323648130","https://openalex.org/W2157140558","https://openalex.org/W2378782423","https://openalex.org/W2388988621","https://openalex.org/W2357797405","https://openalex.org/W2078778136","https://openalex.org/W2366623913","https://openalex.org/W2374905595","https://openalex.org/W2349784553"],"abstract_inverted_index":{"Protein":[0],"secondary":[1,63],"structure":[2],"prediction":[3,20],"is":[4],"an":[5],"important":[6],"step":[7],"towards":[8],"understanding":[9],"the":[10,44,74,78],"relation":[11],"between":[12],"protein":[13,53,62,95],"sequence":[14],"and":[15,55],"structure.":[16,64],"However,":[17],"most":[18],"current":[19],"methods":[21,59],"use":[22],"features":[23],"difficult":[24],"for":[25,52,94],"biologists":[26],"to":[27,42,60,73,88],"interpret.":[28],"In":[29],"this":[30],"paper,":[31],"we":[32],"present":[33],"a":[34,47,85],"new":[35],"method":[36,70],"that":[37,68],"applies":[38],"information":[39],"retrieval":[40],"techniques":[41],"solve":[43],"problem:we":[45],"extract":[46],"context":[48,79],"sensitive":[49,80],"biological":[50],"vocabulary":[51],"sequences":[54],"apply":[56],"text":[57],"classification":[58],"predict":[61],"Experimental":[65],"results":[66],"show":[67],"our":[69],"performs":[71],"comparably":[72],"state-of-art":[75],"methods.":[76],"Furthermore,":[77],"vocabularies":[81],"can":[82],"serve":[83],"as":[84],"useful":[86],"tool":[87],"discover":[89],"meaningful":[90],"regular":[91],"expression":[92],"patterns":[93],"structures.":[96]},"counts_by_year":[{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":3}],"updated_date":"2026-04-28T14:05:53.105641","created_date":"2025-10-10T00:00:00"}