{"id":"https://openalex.org/W4365150760","doi":"https://doi.org/10.1186/s12859-023-05236-w","title":"Automatic extraction of ranked SNP-phenotype associations from text using a BERT-LSTM-based method","display_name":"Automatic extraction of ranked SNP-phenotype associations from text using a BERT-LSTM-based method","publication_year":2023,"publication_date":"2023-04-12","ids":{"openalex":"https://openalex.org/W4365150760","doi":"https://doi.org/10.1186/s12859-023-05236-w","pmid":"https://pubmed.ncbi.nlm.nih.gov/37046202"},"language":"en","primary_location":{"id":"doi:10.1186/s12859-023-05236-w","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-023-05236-w","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-023-05236-w","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-023-05236-w","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052680585","display_name":"Behrouz Bokharaeian","orcid":null},"institutions":[{"id":"https://openalex.org/I4210125640","display_name":"Amol University of Special Modern Technologies","ror":"https://ror.org/02twggb97","country_code":"IR","type":"education","lineage":["https://openalex.org/I4210125640"]}],"countries":["IR"],"is_corresponding":true,"raw_author_name":"Behrouz Bokharaeian","raw_affiliation_strings":["Amol University of Special Modern Technologies, Mazandaran, Iran. bokharaeian@gmail.com","Amol University of Special Modern Technologies, Mazandaran, Iran"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amol University of Special Modern Technologies, Mazandaran, Iran. bokharaeian@gmail.com","institution_ids":["https://openalex.org/I4210125640"]},{"raw_affiliation_string":"Amol University of Special Modern Technologies, Mazandaran, Iran","institution_ids":["https://openalex.org/I4210125640"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101757187","display_name":"Mohammad Hossein Dehghani","orcid":"https://orcid.org/0000-0002-6092-821X"},"institutions":[{"id":"https://openalex.org/I23946033","display_name":"University of Tehran","ror":"https://ror.org/05vf56z40","country_code":"IR","type":"education","lineage":["https://openalex.org/I23946033"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Mohammad Dehghani","raw_affiliation_strings":["School of Electrical and Computer Engineering, University of Tehran, Tehran, Iran"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, University of Tehran, Tehran, Iran","institution_ids":["https://openalex.org/I23946033"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048725475","display_name":"Alberto D\u00edaz","orcid":"https://orcid.org/0000-0003-1966-3421"},"institutions":[{"id":"https://openalex.org/I121748325","display_name":"Universidad Complutense de Madrid","ror":"https://ror.org/02p0gd045","country_code":"ES","type":"education","lineage":["https://openalex.org/I121748325"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Alberto Diaz","raw_affiliation_strings":["Facultad Informatica, Complutense University of Madrid, Madrid, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facultad Informatica, Complutense University of Madrid, Madrid, Spain","institution_ids":["https://openalex.org/I121748325"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5052680585"],"corresponding_institution_ids":["https://openalex.org/I4210125640"],"apc_list":{"value":2790,"currency":"USD","value_usd":2790},"apc_paid":{"value":2790,"currency":"USD","value_usd":2790},"fwci":1.2171,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":{"value":0.77423599,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"24","issue":"1","first_page":"144","last_page":"144"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9987000226974487,"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":0.9987000226974487,"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":0.9650999903678894,"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":0.9610000252723694,"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/artificial-intelligence","display_name":"Artificial intelligence","score":0.7352348566055298},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7226955890655518},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6383851766586304},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.5779913663864136},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5421756505966187},{"id":"https://openalex.org/keywords/snp","display_name":"SNP","score":0.5110396146774292},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.42325547337532043},{"id":"https://openalex.org/keywords/single-nucleotide-polymorphism","display_name":"Single-nucleotide polymorphism","score":0.4056418538093567},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32763049006462097},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.14385369420051575},{"id":"https://openalex.org/keywords/genotype","display_name":"Genotype","score":0.11973902583122253},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10602578520774841},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.07986178994178772}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7352348566055298},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7226955890655518},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6383851766586304},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.5779913663864136},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5421756505966187},{"id":"https://openalex.org/C139275648","wikidata":"https://www.wikidata.org/wiki/Q17134011","display_name":"SNP","level":5,"score":0.5110396146774292},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.42325547337532043},{"id":"https://openalex.org/C153209595","wikidata":"https://www.wikidata.org/wiki/Q501128","display_name":"Single-nucleotide polymorphism","level":4,"score":0.4056418538093567},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32763049006462097},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.14385369420051575},{"id":"https://openalex.org/C135763542","wikidata":"https://www.wikidata.org/wiki/Q106016","display_name":"Genotype","level":3,"score":0.11973902583122253},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10602578520774841},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.07986178994178772},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000093743","descriptor_name":"Random Forest","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000093743","descriptor_name":"Random Forest","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000093743","descriptor_name":"Random Forest","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009154","descriptor_name":"Mutation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009154","descriptor_name":"Mutation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009154","descriptor_name":"Mutation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010641","descriptor_name":"Phenotype","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010641","descriptor_name":"Phenotype","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010641","descriptor_name":"Phenotype","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020641","descriptor_name":"Polymorphism, Single Nucleotide","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D020641","descriptor_name":"Polymorphism, Single Nucleotide","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D020641","descriptor_name":"Polymorphism, Single Nucleotide","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":4,"locations":[{"id":"doi:10.1186/s12859-023-05236-w","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-023-05236-w","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-023-05236-w","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},{"id":"pmid:37046202","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37046202","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":"BMC bioinformatics","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:10099837","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10099837","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10099837/pdf/12859_2023_Article_5236.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:344f105b71bb47fe966e15d35a08d923","is_oa":true,"landing_page_url":"https://doaj.org/article/344f105b71bb47fe966e15d35a08d923","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics, Vol 24, Iss 1, Pp 1-21 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s12859-023-05236-w","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-023-05236-w","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-023-05236-w","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309627","display_name":"Colorado State University","ror":"https://ror.org/03k1gpj17"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4365150760.pdf"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W596941263","https://openalex.org/W1185176251","https://openalex.org/W1528782506","https://openalex.org/W1950048153","https://openalex.org/W2121844933","https://openalex.org/W2123020279","https://openalex.org/W2143892076","https://openalex.org/W2163165016","https://openalex.org/W2299288883","https://openalex.org/W2338565750","https://openalex.org/W2489933339","https://openalex.org/W2528213836","https://openalex.org/W2604990811","https://openalex.org/W2785059970","https://openalex.org/W2795938834","https://openalex.org/W2809349863","https://openalex.org/W2884668708","https://openalex.org/W2963621436","https://openalex.org/W2970771982","https://openalex.org/W2986133154","https://openalex.org/W2998616814","https://openalex.org/W3005237274","https://openalex.org/W3046375318","https://openalex.org/W3047960255","https://openalex.org/W3093844547","https://openalex.org/W3163785270","https://openalex.org/W3194672979","https://openalex.org/W3209877611","https://openalex.org/W4206025858"],"related_works":["https://openalex.org/W2164855536","https://openalex.org/W1997352593","https://openalex.org/W2143489661","https://openalex.org/W2070581548","https://openalex.org/W3016573916","https://openalex.org/W4281711902","https://openalex.org/W3206555169","https://openalex.org/W3157359833","https://openalex.org/W3024317680","https://openalex.org/W1511048503"],"abstract_inverted_index":{"Extraction":[0],"of":[1,3,33,36,43,167,169,181],"associations":[2,35,58],"singular":[4],"nucleotide":[5],"polymorphism":[6],"(SNP)":[7],"and":[8,62,80,83,89,94,98,138],"phenotypes":[9],"from":[10,38,59],"biomedical":[11,60],"literature":[12],"is":[13],"a":[14,92,95,125],"vital":[15],"task":[16],"in":[17,104],"BioNLP.":[18],"Recently,":[19],"some":[20],"methods":[21,51,86,101,140,153,196],"have":[22],"been":[23],"developed":[24,53,103,152],"to":[25,54,66,107,123,163,177],"extract":[26,55,108],"mutation-diseases":[27],"affiliations.":[28],"However,":[29,145],"no":[30],"accessible":[31],"method":[32,129,192],"extracting":[34],"SNP-phenotype":[37,57],"content":[39],"considers":[40],"their":[41],"degree":[42,166],"certainty.":[44],"In":[45,69],"this":[46,105],"paper,":[47],"several":[48],"machine":[49,72],"learning":[50,73,137],"were":[52,64,102,161],"ranked":[56],"abstracts":[61],"then":[63],"compared":[65],"each":[67],"other.":[68],"addition,":[70],"shallow":[71],"methods,":[74],"including":[75],"random":[76],"forest,":[77],"logistic":[78],"regression,":[79],"decision":[81],"tree":[82],"two":[84,99],"kernel-based":[85,132],"like":[87],"subtree":[88],"local":[90],"context,":[91],"rule-based":[93],"deep":[96,136],"CNN-LSTM-based":[97],"BERT-based":[100,139],"study":[106],"associations.":[109],"Furthermore,":[110],"the":[111,116,131,134,142,146,150,155,165,170,179,182,194,198],"experiments":[112,160,186],"indicated":[113],"that":[114,188],"although":[115],"used":[117,135,147,156,176],"linguist":[118],"features":[119],"could":[120],"be":[121,175],"employed":[122],"implement":[124],"superior":[126],"association":[127],"extraction":[128],"outperforming":[130],"counterparts,":[133],"exhibited":[141],"best":[143],"performance.":[144],"PubMedBERT-LSTM":[148],"outperformed":[149,193],"other":[151],"among":[154],"methods.":[157],"Moreover,":[158],"similar":[159],"conducted":[162],"estimate":[164],"certainty":[168],"extracted":[171],"association,":[172],"which":[173],"can":[174],"assess":[178],"strength":[180],"reported":[183],"association.":[184],"The":[185],"revealed":[187],"our":[189],"proposed":[190],"PubMedBERT-CNN-LSTM":[191],"sophisticated":[195],"on":[197],"task.":[199]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}
