{"id":"https://openalex.org/W2126259921","doi":"https://doi.org/10.1093/bioinformatics/btk044","title":"LSAT: learning about alternative transcripts in MEDLINE","display_name":"LSAT: learning about alternative transcripts in MEDLINE","publication_year":2006,"publication_date":"2006-01-12","ids":{"openalex":"https://openalex.org/W2126259921","doi":"https://doi.org/10.1093/bioinformatics/btk044","mag":"2126259921","pmid":"https://pubmed.ncbi.nlm.nih.gov/16410322"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btk044","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btk044","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/22/7/857/48840464/bioinformatics_22_7_857.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/22/7/857/48840464/bioinformatics_22_7_857.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012908005","display_name":"Parantu K. Shah","orcid":"https://orcid.org/0000-0003-3014-215X"},"institutions":[{"id":"https://openalex.org/I205582932","display_name":"Max Delbr\u00fcck Center","ror":"https://ror.org/04p5ggc03","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I205582932"]},{"id":"https://openalex.org/I4210138560","display_name":"European Molecular Biology Laboratory","ror":"https://ror.org/03mstc592","country_code":"DE","type":"government","lineage":["https://openalex.org/I4210138560"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Parantu K. Shah","raw_affiliation_strings":["European Molecular Biology Laboratory 1 \u00a0 1 \u00a0 \u00a0 Heidelberg, Germany","Max Delbr\u00fcck Centre for Molecular Medicine 2 \u00a0 2 \u00a0 \u00a0 Berlin-Buch, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"European Molecular Biology Laboratory 1 \u00a0 1 \u00a0 \u00a0 Heidelberg, Germany","institution_ids":["https://openalex.org/I4210138560"]},{"raw_affiliation_string":"Max Delbr\u00fcck Centre for Molecular Medicine 2 \u00a0 2 \u00a0 \u00a0 Berlin-Buch, Germany","institution_ids":["https://openalex.org/I205582932"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074309419","display_name":"Peer Bork","orcid":"https://orcid.org/0000-0002-2627-833X"},"institutions":[{"id":"https://openalex.org/I205582932","display_name":"Max Delbr\u00fcck Center","ror":"https://ror.org/04p5ggc03","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I205582932"]},{"id":"https://openalex.org/I4210138560","display_name":"European Molecular Biology Laboratory","ror":"https://ror.org/03mstc592","country_code":"DE","type":"government","lineage":["https://openalex.org/I4210138560"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Peer Bork","raw_affiliation_strings":["European Molecular Biology Laboratory 1 \u00a0 1 \u00a0 \u00a0 Heidelberg, Germany","Max Delbr\u00fcck Centre for Molecular Medicine 2 \u00a0 2 \u00a0 \u00a0 Berlin-Buch, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"European Molecular Biology Laboratory 1 \u00a0 1 \u00a0 \u00a0 Heidelberg, Germany","institution_ids":["https://openalex.org/I4210138560"]},{"raw_affiliation_string":"Max Delbr\u00fcck Centre for Molecular Medicine 2 \u00a0 2 \u00a0 \u00a0 Berlin-Buch, Germany","institution_ids":["https://openalex.org/I205582932"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5012908005"],"corresponding_institution_ids":["https://openalex.org/I205582932","https://openalex.org/I4210138560"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":1.2267,"has_fulltext":true,"cited_by_count":19,"citation_normalized_percentile":{"value":0.7770879,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"22","issue":"7","first_page":"857","last_page":"865"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.7060999870300293,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.7060999870300293,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.16619999706745148,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.034299999475479126,"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":0.7723618745803833},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6573103070259094},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6252539753913879},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.6210570931434631},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5926815271377563},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.5916483402252197},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5774067044258118},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.48361340165138245},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.4117491841316223},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.41078099608421326},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.40401846170425415}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7723618745803833},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6573103070259094},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6252539753913879},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.6210570931434631},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5926815271377563},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.5916483402252197},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5774067044258118},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.48361340165138245},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.4117491841316223},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.41078099608421326},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.40401846170425415},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D003628","descriptor_name":"Database Management Systems","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003628","descriptor_name":"Database Management Systems","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003628","descriptor_name":"Database Management Systems","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008954","descriptor_name":"Models, Biological","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008954","descriptor_name":"Models, Biological","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008954","descriptor_name":"Models, Biological","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014584","descriptor_name":"User-Computer Interface","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014584","descriptor_name":"User-Computer Interface","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014584","descriptor_name":"User-Computer Interface","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016239","descriptor_name":"MEDLINE","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016239","descriptor_name":"MEDLINE","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016239","descriptor_name":"MEDLINE","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019985","descriptor_name":"Benchmarking","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019985","descriptor_name":"Benchmarking","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019985","descriptor_name":"Benchmarking","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1093/bioinformatics/btk044","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btk044","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/22/7/857/48840464/bioinformatics_22_7_857.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:16410322","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/16410322","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}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btk044","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btk044","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/22/7/857/48840464/bioinformatics_22_7_857.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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7699999809265137}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2126259921.pdf","grobid_xml":"https://content.openalex.org/works/W2126259921.grobid-xml"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W202303397","https://openalex.org/W1560913816","https://openalex.org/W1567787856","https://openalex.org/W1604792744","https://openalex.org/W1660390307","https://openalex.org/W1954715867","https://openalex.org/W1965843937","https://openalex.org/W1999117234","https://openalex.org/W2005422315","https://openalex.org/W2027875450","https://openalex.org/W2043099927","https://openalex.org/W2048618925","https://openalex.org/W2053154970","https://openalex.org/W2057306271","https://openalex.org/W2061327015","https://openalex.org/W2064723275","https://openalex.org/W2097106271","https://openalex.org/W2102711634","https://openalex.org/W2122305935","https://openalex.org/W2124617249","https://openalex.org/W2126276057","https://openalex.org/W2139259976","https://openalex.org/W2140601463","https://openalex.org/W2148013311","https://openalex.org/W2148853951","https://openalex.org/W2160238006","https://openalex.org/W2161299591","https://openalex.org/W2168808732","https://openalex.org/W2170654002","https://openalex.org/W2885050925","https://openalex.org/W6608351394","https://openalex.org/W6634123513","https://openalex.org/W6636095811","https://openalex.org/W6640904281","https://openalex.org/W6649991593","https://openalex.org/W6684952647","https://openalex.org/W6685079732","https://openalex.org/W6753815910"],"related_works":["https://openalex.org/W2165912799","https://openalex.org/W2735662278","https://openalex.org/W2382615723","https://openalex.org/W4311804456","https://openalex.org/W1987484445","https://openalex.org/W2623658258","https://openalex.org/W2143413548","https://openalex.org/W1969219540","https://openalex.org/W2370459448","https://openalex.org/W2105067402"],"abstract_inverted_index":{"MOTIVATION:":[0],"Generation":[1],"of":[2,31,82,118,126,139,160,180,190],"alternative":[3,191],"transcripts":[4],"from":[5,67],"the":[6,29,50,68,78,93,101,108,121,142,153,187],"same":[7],"gene":[8],"is":[9,194],"an":[10],"important":[11],"biological":[12],"event":[13],"due":[14],"to":[15,60,130],"their":[16],"contribution":[17],"in":[18,22,133,152,186],"creating":[19],"functional":[20],"diversity":[21,66],"eukaryotes.":[23],"In":[24,49,141],"this":[25,35],"work,":[26],"we":[27,53,76,145],"choose":[28],"task":[30],"extracting":[32],"information":[33,46],"around":[34],"complex":[36],"topic":[37],"using":[38],"a":[39,55,72,157],"two-step":[40,182],"procedure":[41,183],"involving":[42],"machine":[43],"learning":[44],"and":[45,113,125,155],"extraction.":[47],"RESULTS:":[48],"first":[51],"step,":[52,144],"trained":[54],"classifier":[56,96],"that":[57],"inductively":[58],"learns":[59],"identify":[61],"sentences":[62,132,154],"about":[63],"physiological":[64],"transcript":[65],"MEDLINE":[69],"abstracts.":[70],"Using":[71],"large":[73],"hand-built":[74],"corpus,":[75],"compared":[77],"sentence":[79,102],"classification":[80,103],"performance":[81],"various":[83],"text":[84],"categorization":[85],"methods.":[86],"Support":[87],"vector":[88],"machines":[89],"(SVMs)":[90],"followed":[91],"by":[92],"maximum":[94],"entropy":[95],"outperformed":[97],"other":[98],"methods":[99],"for":[100,173],"task.":[104],"The":[105,164,178],"SVM":[106],"with":[107],"radial":[109],"basis":[110],"function":[111],"kernel":[112],"optimized":[114],"parameters":[115],"achieved":[116,169],"Fbeta-measure":[117,172],"91%":[119],"during":[120],"4-fold":[122],"cross":[123],"validation":[124],"74%":[127],"when":[128],"applied":[129],"all":[131,174],"more":[134],"than":[135],"12":[136],"million":[137],"abstracts":[138],"MEDLINE.":[140],"second":[143],"identified":[146],"eight":[147,175],"frequently":[148],"present":[149],"semantic":[150,161],"categories":[151],"performed":[156],"limited":[158],"amount":[159],"role":[162,165],"labeling.":[163],"labeling":[166],"step":[167],"also":[168],"very":[170],"high":[171],"categories.":[176],"AVAILABILITY:":[177],"results":[179],"our":[181],"are":[184,204],"summarized":[185],"LSAT":[188,193],"database":[189],"transcripts.":[192],"available":[195,205],"at":[196,206],"http://www.bork.embl.de/LSAT":[197],"CONTACT:":[198],"shah@embl.de":[199],"SUPPLEMENTARY":[200],"INFORMATION:":[201],"Supplementary":[202],"data":[203],"Bioinformatics":[207],"online.":[208]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
