{"id":"https://openalex.org/W4226146505","doi":"https://doi.org/10.1093/database/baac036","title":"GeMI: interactive interface for transformer-based Genomic Metadata Integration","display_name":"GeMI: interactive interface for transformer-based Genomic Metadata Integration","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4226146505","doi":"https://doi.org/10.1093/database/baac036","pmid":"https://pubmed.ncbi.nlm.nih.gov/35657113"},"language":"en","primary_location":{"id":"doi:10.1093/database/baac036","is_oa":true,"landing_page_url":"https://doi.org/10.1093/database/baac036","pdf_url":"https://academic.oup.com/database/article-pdf/doi/10.1093/database/baac036/43944508/baac036.pdf","source":{"id":"https://openalex.org/S4210201630","display_name":"Database","issn_l":"1758-0463","issn":["1758-0463"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311647","host_organization_name":"University of Oxford","host_organization_lineage":["https://openalex.org/P4310311647"],"host_organization_lineage_names":["University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Database","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://academic.oup.com/database/article-pdf/doi/10.1093/database/baac036/43944508/baac036.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021907037","display_name":"Giuseppe Serna Garc\u00eda","orcid":"https://orcid.org/0000-0002-5465-6182"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Giuseppe Serna Garcia","raw_affiliation_strings":["Department of Electronics, Information, and Bioengineering, Politecnico di Milano , Via Ponzio 34/5, Milano 20133, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Electronics, Information, and Bioengineering, Politecnico di Milano , Via Ponzio 34/5, Milano 20133, Italy","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087844608","display_name":"Michele Leone","orcid":"https://orcid.org/0000-0002-2618-5985"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Michele Leone","raw_affiliation_strings":["Department of Electronics, Information, and Bioengineering, Politecnico di Milano , Via Ponzio 34/5, Milano 20133, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Electronics, Information, and Bioengineering, Politecnico di Milano , Via Ponzio 34/5, Milano 20133, Italy","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078800193","display_name":"Anna Bernasconi","orcid":"https://orcid.org/0000-0001-8016-5750"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Anna Bernasconi","raw_affiliation_strings":["Department of Electronics, Information, and Bioengineering, Politecnico di Milano , Via Ponzio 34/5, Milano 20133, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Electronics, Information, and Bioengineering, Politecnico di Milano , Via Ponzio 34/5, Milano 20133, Italy","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069487278","display_name":"Mark Carman","orcid":"https://orcid.org/0000-0001-6575-9737"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Mark J Carman","raw_affiliation_strings":["Department of Electronics, Information, and Bioengineering, Politecnico di Milano , Via Ponzio 34/5, Milano 20133, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Electronics, Information, and Bioengineering, Politecnico di Milano , Via Ponzio 34/5, Milano 20133, Italy","institution_ids":["https://openalex.org/I93860229"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5078800193"],"corresponding_institution_ids":["https://openalex.org/I93860229"],"apc_list":{"value":1415,"currency":"GBP","value_usd":1735},"apc_paid":{"value":1415,"currency":"GBP","value_usd":1735},"fwci":1.1266,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.76152352,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"2022","issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.998199999332428,"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":0.998199999332428,"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":0.9918000102043152,"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/T10885","display_name":"Gene expression and cancer classification","score":0.9908000230789185,"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/metadata","display_name":"Metadata","score":0.7872989773750305},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7808719277381897},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5460888743400574},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.49238312244415283},{"id":"https://openalex.org/keywords/usability","display_name":"Usability","score":0.44290944933891296},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3807864189147949},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3782792091369629},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3045627474784851},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.15788757801055908}],"concepts":[{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.7872989773750305},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7808719277381897},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5460888743400574},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.49238312244415283},{"id":"https://openalex.org/C170130773","wikidata":"https://www.wikidata.org/wiki/Q216378","display_name":"Usability","level":2,"score":0.44290944933891296},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3807864189147949},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3782792091369629},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3045627474784851},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.15788757801055908}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000071253","descriptor_name":"Metadata","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000071253","descriptor_name":"Metadata","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000071253","descriptor_name":"Metadata","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":4,"locations":[{"id":"doi:10.1093/database/baac036","is_oa":true,"landing_page_url":"https://doi.org/10.1093/database/baac036","pdf_url":"https://academic.oup.com/database/article-pdf/doi/10.1093/database/baac036/43944508/baac036.pdf","source":{"id":"https://openalex.org/S4210201630","display_name":"Database","issn_l":"1758-0463","issn":["1758-0463"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311647","host_organization_name":"University of Oxford","host_organization_lineage":["https://openalex.org/P4310311647"],"host_organization_lineage_names":["University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Database","raw_type":"journal-article"},{"id":"pmid:35657113","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35657113","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":"Database : the journal of biological databases and curation","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:9216561","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9216561","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Database (Oxford)","raw_type":"Text"},{"id":"pmh:oai:re.public.polimi.it:11311/1217217","is_oa":true,"landing_page_url":"https://academic.oup.com/database/article/doi/10.1093/database/baac036/6600540","pdf_url":null,"source":{"id":"https://openalex.org/S4306400312","display_name":"Virtual Community of Pathological Anatomy (University of Castilla La Mancha)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79189158","host_organization_name":"University of Castilla-La Mancha","host_organization_lineage":["https://openalex.org/I79189158"],"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":"","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1093/database/baac036","is_oa":true,"landing_page_url":"https://doi.org/10.1093/database/baac036","pdf_url":"https://academic.oup.com/database/article-pdf/doi/10.1093/database/baac036/43944508/baac036.pdf","source":{"id":"https://openalex.org/S4210201630","display_name":"Database","issn_l":"1758-0463","issn":["1758-0463"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311647","host_organization_name":"University of Oxford","host_organization_lineage":["https://openalex.org/P4310311647"],"host_organization_lineage_names":["University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Database","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6000000238418579,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4226146505.pdf","grobid_xml":"https://content.openalex.org/works/W4226146505.grobid-xml"},"referenced_works_count":65,"referenced_works":["https://openalex.org/W2005129098","https://openalex.org/W2018363492","https://openalex.org/W2094953050","https://openalex.org/W2101696428","https://openalex.org/W2118258530","https://openalex.org/W2133564696","https://openalex.org/W2142680014","https://openalex.org/W2165446840","https://openalex.org/W2259938310","https://openalex.org/W2346673125","https://openalex.org/W2462007197","https://openalex.org/W2516809705","https://openalex.org/W2754937980","https://openalex.org/W2765397040","https://openalex.org/W2778408434","https://openalex.org/W2781236732","https://openalex.org/W2805978167","https://openalex.org/W2810819381","https://openalex.org/W2829316984","https://openalex.org/W2887704715","https://openalex.org/W2891503716","https://openalex.org/W2899915536","https://openalex.org/W2901027836","https://openalex.org/W2907094739","https://openalex.org/W2908425807","https://openalex.org/W2914132662","https://openalex.org/W2981849325","https://openalex.org/W2984636935","https://openalex.org/W2996036406","https://openalex.org/W3000297876","https://openalex.org/W3032724472","https://openalex.org/W3033098866","https://openalex.org/W3034999214","https://openalex.org/W3070389369","https://openalex.org/W3101155149","https://openalex.org/W3120223152","https://openalex.org/W3127238141","https://openalex.org/W3129125493","https://openalex.org/W3131121088","https://openalex.org/W3133324619","https://openalex.org/W3144701084","https://openalex.org/W3151623506","https://openalex.org/W3164453494","https://openalex.org/W3176390156","https://openalex.org/W4200328078","https://openalex.org/W4200399482","https://openalex.org/W4200599415","https://openalex.org/W4220967417","https://openalex.org/W4225868104","https://openalex.org/W4230030242","https://openalex.org/W4233069070","https://openalex.org/W4385245566","https://openalex.org/W6679434410","https://openalex.org/W6685133223","https://openalex.org/W6704944446","https://openalex.org/W6726258750","https://openalex.org/W6729822694","https://openalex.org/W6739901393","https://openalex.org/W6752562507","https://openalex.org/W6757753266","https://openalex.org/W6769311223","https://openalex.org/W6769921762","https://openalex.org/W6791213495","https://openalex.org/W6793693157","https://openalex.org/W6805630506"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2059659244","https://openalex.org/W2076264610","https://openalex.org/W1636283687","https://openalex.org/W2757541005","https://openalex.org/W2910550908","https://openalex.org/W4296302578","https://openalex.org/W1589115949","https://openalex.org/W3202806639","https://openalex.org/W2082060955"],"abstract_inverted_index":{"The":[0,23,87,113,238],"Gene":[1],"Expression":[2],"Omnibus":[3],"(GEO)":[4],"is":[5,125,138,242],"a":[6,63,126,160,164,166],"public":[7],"archive":[8],"containing":[9],">4":[10],"million":[11],"digital":[12],"samples":[13],"from":[14,30,79,143],"functional":[15],"genomics":[16],"experiments":[17,28],"collected":[18],"over":[19],"almost":[20],"two":[21],"decades.":[22],"accompanying":[24],"metadata":[25,72],"describing":[26],"the":[27,37,43,74,80,120,130,144,147,157,176,184,187,193],"suffer":[29],"redundancy,":[31],"inconsistency":[32],"and":[33,42,49,97,181,191,212,220,232],"incompleteness":[34],"due":[35],"to":[36,68,140,150,178,198,216],"prevalence":[38],"of":[39,45,76,84,122,129,146,162,186,222,240],"free":[40],"text":[41,82],"lack":[44],"well-defined":[46],"data":[47,102],"formats":[48],"their":[50],"validation.":[51],"To":[52],"remedy":[53],"this":[54],"situation,":[55],"we":[56],"created":[57],"Genomic":[58],"Metadata":[59],"Integration":[60],"(GeMI;":[61],"http://gmql.eu/gemi/),":[62],"web":[64],"application":[65],"that":[66,137],"learns":[67],"automatically":[69],"extract":[70,199],"structured":[71,95],"(in":[73],"form":[75],"key-value":[77],"pairs)":[78],"plain":[81],"descriptions":[83],"GEO":[85],"experiments.":[86],"extracted":[88],"information":[89],"can":[90],"then":[91],"be":[92],"indexed":[93],"for":[94,99,156],"search":[96],"used":[98],"various":[100],"downstream":[101],"mining":[103],"activities.":[104],"GeMI":[105,241],"works":[106],"in":[107],"continuous":[108],"interaction":[109],"with":[110,234],"its":[111],"users.":[112],"natural":[114],"language":[115],"processing":[116],"transformer-based":[117],"model":[118,136,188],"at":[119],"core":[121],"our":[123],"system":[124],"fine-tuned":[127],"version":[128],"Generative":[131],"Pre-trained":[132],"Transformer":[133],"2":[134],"(GPT2)":[135],"able":[139],"learn":[141],"continuously":[142],"feedback":[145],"users":[148,177],"thanks":[149],"an":[151],"active":[152],"learning":[153,168],"framework":[154],"designed":[155],"purpose.":[158],"As":[159],"part":[161],"such":[163],"framework,":[165],"machine":[167],"interpretation":[169],"mechanism":[170],"(that":[171],"exploits":[172],"saliency":[173],"maps)":[174],"allows":[175,214],"understand":[179],"easily":[180],"quickly":[182],"whether":[183],"predictions":[185],"are":[189],"correct":[190],"improves":[192],"overall":[194],"usability.":[195],"GeMI's":[196],"ability":[197],"attributes":[200],"not":[201],"explicitly":[202],"mentioned":[203],"(such":[204],"as":[205],"sex,":[206],"tissue":[207],"type,":[208,210],"cell":[209],"ethnicity":[211],"disease)":[213],"researchers":[215],"perform":[217],"specific":[218],"queries":[219],"classification":[221],"experiments,":[223],"which":[224],"was":[225],"previously":[226],"possible":[227],"only":[228],"after":[229],"spending":[230],"time":[231],"resources":[233],"tedious":[235],"manual":[236],"annotation.":[237],"usefulness":[239],"demonstrated":[243],"on":[244],"practical":[245],"research":[246],"use":[247],"cases.":[248],"Database":[249],"URL":[250],"http://gmql.eu/gemi/.":[251]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}
