{"id":"https://openalex.org/W1967185392","doi":"https://doi.org/10.1093/bioinformatics/btl350","title":"Substring selection for biomedical document classification","display_name":"Substring selection for biomedical document classification","publication_year":2006,"publication_date":"2006-06-23","ids":{"openalex":"https://openalex.org/W1967185392","doi":"https://doi.org/10.1093/bioinformatics/btl350","mag":"1967185392","pmid":"https://pubmed.ncbi.nlm.nih.gov/16837530"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btl350","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btl350","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/22/17/2136/48840315/bioinformatics_22_17_2136.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":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","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":"hybrid","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/22/17/2136/48840315/bioinformatics_22_17_2136.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047240103","display_name":"Bo Han","orcid":"https://orcid.org/0000-0002-6338-0958"},"institutions":[{"id":"https://openalex.org/I84392919","display_name":"Temple University","ror":"https://ror.org/00kx1jb78","country_code":"US","type":"education","lineage":["https://openalex.org/I84392919"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bo Han","raw_affiliation_strings":["Center for Information Science and Technology, Temple University 1 \u00a0 1 \u00a0 \u00a0 Philadelphia, PA 19122, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Information Science and Technology, Temple University 1 \u00a0 1 \u00a0 \u00a0 Philadelphia, PA 19122, USA","institution_ids":["https://openalex.org/I84392919"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044038055","display_name":"Zoran Obradovi\u0107","orcid":"https://orcid.org/0000-0002-2051-0142"},"institutions":[{"id":"https://openalex.org/I84392919","display_name":"Temple University","ror":"https://ror.org/00kx1jb78","country_code":"US","type":"education","lineage":["https://openalex.org/I84392919"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zoran Obradovic","raw_affiliation_strings":["Center for Information Science and Technology, Temple University 1 \u00a0 1 \u00a0 \u00a0 Philadelphia, PA 19122, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Information Science and Technology, Temple University 1 \u00a0 1 \u00a0 \u00a0 Philadelphia, PA 19122, USA","institution_ids":["https://openalex.org/I84392919"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107639854","display_name":"Zhang-Zhi Hu","orcid":"https://orcid.org/0009-0004-7455-461X"},"institutions":[{"id":"https://openalex.org/I184565670","display_name":"Georgetown University","ror":"https://ror.org/05vzafd60","country_code":"US","type":"education","lineage":["https://openalex.org/I184565670"]},{"id":"https://openalex.org/I2799903593","display_name":"Georgetown University Medical Center","ror":"https://ror.org/00hjz7x27","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799903593"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhang-Zhi Hu","raw_affiliation_strings":["Department of Biochemistry and Molecular & Cellular Biology, Georgetown University Medical Center 2 \u00a0 2 \u00a0 \u00a0 Washington DC 20007, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biochemistry and Molecular & Cellular Biology, Georgetown University Medical Center 2 \u00a0 2 \u00a0 \u00a0 Washington DC 20007, USA","institution_ids":["https://openalex.org/I184565670","https://openalex.org/I2799903593"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053761444","display_name":"Cathy Wu","orcid":"https://orcid.org/0000-0001-6379-8601"},"institutions":[{"id":"https://openalex.org/I184565670","display_name":"Georgetown University","ror":"https://ror.org/05vzafd60","country_code":"US","type":"education","lineage":["https://openalex.org/I184565670"]},{"id":"https://openalex.org/I2799903593","display_name":"Georgetown University Medical Center","ror":"https://ror.org/00hjz7x27","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799903593"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cathy H. Wu","raw_affiliation_strings":["Department of Biochemistry and Molecular & Cellular Biology, Georgetown University Medical Center 2 \u00a0 2 \u00a0 \u00a0 Washington DC 20007, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biochemistry and Molecular & Cellular Biology, Georgetown University Medical Center 2 \u00a0 2 \u00a0 \u00a0 Washington DC 20007, USA","institution_ids":["https://openalex.org/I184565670","https://openalex.org/I2799903593"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059847153","display_name":"Slobodan Vu\u010deti\u0107","orcid":"https://orcid.org/0000-0001-5884-6293"},"institutions":[{"id":"https://openalex.org/I84392919","display_name":"Temple University","ror":"https://ror.org/00kx1jb78","country_code":"US","type":"education","lineage":["https://openalex.org/I84392919"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Slobodan Vucetic","raw_affiliation_strings":["Center for Information Science and Technology, Temple University 1 \u00a0 1 \u00a0 \u00a0 Philadelphia, PA 19122, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Information Science and Technology, Temple University 1 \u00a0 1 \u00a0 \u00a0 Philadelphia, PA 19122, USA","institution_ids":["https://openalex.org/I84392919"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5059847153"],"corresponding_institution_ids":["https://openalex.org/I84392919"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":1.5248,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.79986707,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"22","issue":"17","first_page":"2136","last_page":"2142"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.4880000054836273,"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":0.4880000054836273,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.4106000065803528,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.018699999898672104,"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/substring","display_name":"Substring","score":0.8595415353775024},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7698558568954468},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.668300211429596},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6208899021148682},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5925337672233582},{"id":"https://openalex.org/keywords/naive-bayes-classifier","display_name":"Naive Bayes classifier","score":0.559423565864563},{"id":"https://openalex.org/keywords/terminology","display_name":"Terminology","score":0.5419545769691467},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5196155905723572},{"id":"https://openalex.org/keywords/document-classification","display_name":"Document classification","score":0.4585021436214447},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.4496220052242279},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.4229607880115509},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41541197896003723},{"id":"https://openalex.org/keywords/bayes-theorem","display_name":"Bayes' theorem","score":0.41220200061798096},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3980122208595276},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3222235441207886},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.17335066199302673},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.1167597770690918}],"concepts":[{"id":"https://openalex.org/C182407805","wikidata":"https://www.wikidata.org/wiki/Q2626534","display_name":"Substring","level":3,"score":0.8595415353775024},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7698558568954468},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.668300211429596},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6208899021148682},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5925337672233582},{"id":"https://openalex.org/C52001869","wikidata":"https://www.wikidata.org/wiki/Q812530","display_name":"Naive Bayes classifier","level":3,"score":0.559423565864563},{"id":"https://openalex.org/C547195049","wikidata":"https://www.wikidata.org/wiki/Q1725664","display_name":"Terminology","level":2,"score":0.5419545769691467},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5196155905723572},{"id":"https://openalex.org/C2780479914","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Document classification","level":2,"score":0.4585021436214447},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4496220052242279},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.4229607880115509},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41541197896003723},{"id":"https://openalex.org/C207201462","wikidata":"https://www.wikidata.org/wiki/Q182505","display_name":"Bayes' theorem","level":3,"score":0.41220200061798096},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3980122208595276},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3222235441207886},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.17335066199302673},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.1167597770690918},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D000043","descriptor_name":"Abstracting and Indexing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D000043","descriptor_name":"Abstracting and Indexing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D000043","descriptor_name":"Abstracting and Indexing","qualifier_ui":"Q000379","qualifier_name":"methods","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":"D000465","descriptor_name":"Algorithms","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":false},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","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":false},{"descriptor_ui":"D003628","descriptor_name":"Database Management Systems","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003628","descriptor_name":"Database Management Systems","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003628","descriptor_name":"Database Management Systems","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D004282","descriptor_name":"Documentation","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D004282","descriptor_name":"Documentation","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D004282","descriptor_name":"Documentation","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D010506","descriptor_name":"Periodicals as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D010506","descriptor_name":"Periodicals as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D010506","descriptor_name":"Periodicals as Topic","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":"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":"D018875","descriptor_name":"Vocabulary, Controlled","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D018875","descriptor_name":"Vocabulary, Controlled","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D018875","descriptor_name":"Vocabulary, Controlled","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btl350","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btl350","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/22/17/2136/48840315/bioinformatics_22_17_2136.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":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:16837530","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/16837530","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:10.1.1.106.4489","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.106.4489","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://bioinformatics.oxfordjournals.org/cgi/reprint/22/17/2136.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btl350","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btl350","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/22/17/2136/48840315/bioinformatics_22_17_2136.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":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","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","score":0.7200000286102295,"display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G3518280821","display_name":null,"funder_award_id":"U01-HG02712","funder_id":"https://openalex.org/F4320337348","funder_display_name":"National Human Genome Research Institute"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337348","display_name":"National Human Genome Research Institute","ror":"https://ror.org/00baak391"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1477589808","https://openalex.org/W1550206324","https://openalex.org/W1576520375","https://openalex.org/W1604938182","https://openalex.org/W1987213598","https://openalex.org/W1988001261","https://openalex.org/W1991570251","https://openalex.org/W2040778567","https://openalex.org/W2053166411","https://openalex.org/W2072773380","https://openalex.org/W2098162425","https://openalex.org/W2104768328","https://openalex.org/W2131924932","https://openalex.org/W2133431243","https://openalex.org/W2133456867","https://openalex.org/W2135937947","https://openalex.org/W2146724934","https://openalex.org/W2149684865","https://openalex.org/W2154703852","https://openalex.org/W2156909104","https://openalex.org/W2161732286","https://openalex.org/W2166057395","https://openalex.org/W2284943364","https://openalex.org/W2435251607","https://openalex.org/W6632865047","https://openalex.org/W6634442568","https://openalex.org/W6682304300","https://openalex.org/W6717827561"],"related_works":["https://openalex.org/W2537862391","https://openalex.org/W2417174640","https://openalex.org/W4386023432","https://openalex.org/W2968744947","https://openalex.org/W4300816751","https://openalex.org/W2126538150","https://openalex.org/W2324052717","https://openalex.org/W2186892964","https://openalex.org/W1982078379","https://openalex.org/W2015069234"],"abstract_inverted_index":{"MOTIVATION:":[0],"Attribute":[1],"selection":[2,141],"is":[3,63,159],"a":[4,14],"critical":[5],"step":[6],"in":[7,29,133,153],"development":[8],"of":[9,35,60,94,107],"document":[10],"classification":[11],"systems.":[12],"As":[13],"standard":[15],"practice,":[16],"words":[17],"are":[18,25,41,165],"stemmed":[19],"and":[20,44,117],"the":[21,58,79,101,128,138,148],"most":[22,80],"informative":[23,48],"ones":[24],"used":[26],"as":[27,83],"attributes":[28,145],"classification.":[30],"Owing":[31],"to":[32,53],"high":[33],"complexity":[34],"biomedical":[36],"terminology,":[37],"general-purpose":[38],"stemming":[39,75],"algorithms":[40],"often":[42],"conservative":[43],"could":[45],"also":[46],"remove":[47],"stems.":[49],"This":[50],"can":[51],"lead":[52],"accuracy":[54,132],"reduction,":[55],"especially":[56],"when":[57,136,143,162],"number":[59],"labeled":[61,163],"documents":[62],"small.":[64,166],"To":[65],"address":[66],"this":[67],"issue,":[68],"we":[69],"propose":[70],"an":[71],"algorithm":[72,151],"that":[73,98,114],"omits":[74],"and,":[76],"instead,":[77],"uses":[78],"discriminative":[81],"substrings":[82],"attributes.":[84],"RESULTS:":[85],"The":[86,111,156],"approach":[87,158],"was":[88],"tested":[89],"on":[90,100],"five":[91,105],"annotated":[92],"sets":[93],"abstracts":[95],"from":[96],"iProLINK":[97],"report":[99],"experimental":[102],"evidence":[103],"about":[104],"types":[106],"protein":[108],"post-translational":[109],"modifications.":[110],"experiments":[112],"showed":[113],"Naive":[115],"Bayes":[116],"support":[118],"vector":[119],"machine":[120],"classifiers":[121],"perform":[122],"consistently":[123],"better":[124],"[with":[125],"area":[126],"under":[127],"ROC":[129],"curve":[130],"(AUC)":[131],"range":[134],"0.92-0.97]":[135],"using":[137,144],"proposed":[139,157],"attribute":[140],"than":[142],"obtained":[146],"by":[147],"Porter":[149],"stemmer":[150],"(AUC":[152],"0.86-0.93":[154],"range).":[155],"particularly":[160],"useful":[161],"datasets":[164]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2014,"cited_by_count":2}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}