{"id":"https://openalex.org/W7133189935","doi":"https://doi.org/10.1093/bioinformatics/btag102","title":"SummArIzeR: simplifying cross-database enrichment result clustering and annotation via large language models","display_name":"SummArIzeR: simplifying cross-database enrichment result clustering and annotation via large language models","publication_year":2026,"publication_date":"2026-02-27","ids":{"openalex":"https://openalex.org/W7133189935","doi":"https://doi.org/10.1093/bioinformatics/btag102","pmid":"https://pubmed.ncbi.nlm.nih.gov/41766346"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btag102","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btag102","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"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","license_id":"https://openalex.org/licenses/cc-by","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":"gold","oa_url":"https://doi.org/10.1093/bioinformatics/btag102","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036931344","display_name":"Marie Brinkmann","orcid":null},"institutions":[{"id":"https://openalex.org/I76134821","display_name":"Medical University of Vienna","ror":"https://ror.org/05n3x4p02","country_code":"AT","type":"education","lineage":["https://openalex.org/I76134821"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Marie Brinkmann","raw_affiliation_strings":["Division of Rheumatology, Department of Internal Medicine III, Medical University of Vienna , 1090 Vienna,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Division of Rheumatology, Department of Internal Medicine III, Medical University of Vienna , 1090 Vienna,","institution_ids":["https://openalex.org/I76134821"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043829152","display_name":"Michael Bonelli","orcid":"https://orcid.org/0000-0002-6122-7482"},"institutions":[{"id":"https://openalex.org/I76134821","display_name":"Medical University of Vienna","ror":"https://ror.org/05n3x4p02","country_code":"AT","type":"education","lineage":["https://openalex.org/I76134821"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Michael Bonelli","raw_affiliation_strings":["Division of Rheumatology, Department of Internal Medicine III, Medical University of Vienna , 1090 Vienna,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Division of Rheumatology, Department of Internal Medicine III, Medical University of Vienna , 1090 Vienna,","institution_ids":["https://openalex.org/I76134821"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071161720","display_name":"Anela Tosevska","orcid":"https://orcid.org/0000-0002-0892-7068"},"institutions":[{"id":"https://openalex.org/I76134821","display_name":"Medical University of Vienna","ror":"https://ror.org/05n3x4p02","country_code":"AT","type":"education","lineage":["https://openalex.org/I76134821"]}],"countries":["AT"],"is_corresponding":true,"raw_author_name":"Anela Tosevska","raw_affiliation_strings":["Division of Rheumatology, Department of Internal Medicine III, Medical University of Vienna , 1090 Vienna,"],"raw_orcid":"https://orcid.org/0000-0002-0892-7068","affiliations":[{"raw_affiliation_string":"Division of Rheumatology, Department of Internal Medicine III, Medical University of Vienna , 1090 Vienna,","institution_ids":["https://openalex.org/I76134821"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5071161720"],"corresponding_institution_ids":["https://openalex.org/I76134821"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.21645759,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"42","issue":"3","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.4442000091075897,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.4442000091075897,"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":0.14429999887943268,"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":0.0746999979019165,"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/annotation","display_name":"Annotation","score":0.7712000012397766},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7156000137329102},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.44679999351501465},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.2728999853134155}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8270000219345093},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.7712000012397766},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7156000137329102},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48579999804496765},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.44679999351501465},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4368000030517578},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40400001406669617},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2847000062465668},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28349998593330383},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2728999853134155},{"id":"https://openalex.org/C39235581","wikidata":"https://www.wikidata.org/wiki/Q5158434","display_name":"Conceptual clustering","level":5,"score":0.25589999556541443}],"mesh":[{"descriptor_ui":"D000098342","descriptor_name":"Large Language Models","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000098342","descriptor_name":"Large Language Models","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000098342","descriptor_name":"Large Language Models","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000098342","descriptor_name":"Large Language Models","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000098342","descriptor_name":"Large Language Models","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000098430","descriptor_name":"Clustering Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000098430","descriptor_name":"Clustering 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":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011381","descriptor_name":"Programming Languages","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011381","descriptor_name":"Programming Languages","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011381","descriptor_name":"Programming Languages","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":true},{"descriptor_ui":"D012984","descriptor_name":"Software","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":true},{"descriptor_ui":"D012984","descriptor_name":"Software","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":true},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D058977","descriptor_name":"Molecular Sequence Annotation","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D058977","descriptor_name":"Molecular Sequence Annotation","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D058977","descriptor_name":"Molecular Sequence Annotation","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btag102","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btag102","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"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","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:41766346","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41766346","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:pubmedcentral.nih.gov:13005729","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13005729/","pdf_url":null,"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":"Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btag102","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btag102","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"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","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321691","display_name":"Universit\u00e4t Wien","ror":"https://ror.org/03prydq77"},{"id":"https://openalex.org/F4320323437","display_name":"Medizinische Universit\u00e4t Wien","ror":"https://ror.org/05n3x4p02"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1547212375","https://openalex.org/W1969353942","https://openalex.org/W2087187685","https://openalex.org/W2098509290","https://openalex.org/W2169589032","https://openalex.org/W2406250479","https://openalex.org/W2845591014","https://openalex.org/W2889418962","https://openalex.org/W2928665623","https://openalex.org/W2950595506","https://openalex.org/W2965763753","https://openalex.org/W2997022986","https://openalex.org/W3045153201","https://openalex.org/W3145969289","https://openalex.org/W3153790631","https://openalex.org/W4220831425","https://openalex.org/W4220999976","https://openalex.org/W4281620292","https://openalex.org/W4283799942","https://openalex.org/W4381489254","https://openalex.org/W4393153069","https://openalex.org/W4400735087","https://openalex.org/W4403118713","https://openalex.org/W4404824605","https://openalex.org/W4404860874","https://openalex.org/W6925538679"],"related_works":[],"abstract_inverted_index":{"MOTIVATION:":[0],"Enrichment":[1],"analysis":[2],"across":[3,39,48],"multiple":[4,40,49],"databases":[5],"often":[6],"results":[7,38,54],"in":[8,138],"a":[9,60,133],"high":[10],"level":[11],"of":[12,21,81],"redundancy":[13],"due":[14],"to":[15,33,86,107],"overlapping":[16],"terms,":[17],"complicating":[18],"the":[19,68,82],"interpretation":[20,45],"biological":[22],"data.":[23],"To":[24],"address":[25],"this,":[26],"we":[27],"developed":[28],"SummArIzeR,":[29],"an":[30,77,128],"R":[31,130],"package":[32,124],"cluster":[34,65,69,94],"and":[35,46,66,92],"annotate":[36],"enrichment":[37,53],"databases,":[41],"enabling":[42],"fast,":[43],"intuitive":[44],"comparison":[47],"conditions.":[50],"SummArIzeR":[51,89,103,123],"clusters":[52],"based":[55,114],"on":[56,115],"shared":[57,116],"genes,":[58],"calculates":[59],"pooled":[61],"P-value":[62],"for":[63],"each":[64],"facilitates":[67],"annotation":[70,95],"using":[71,96],"large-language":[72],"models.":[73,99],"It":[74],"further":[75],"allows":[76],"easily":[78],"interpretable":[79],"visualization":[80],"results.":[83],"RESULTS:":[84],"Compared":[85],"existing":[87],"tools,":[88],"provides":[90],"unbiased":[91],"fast":[93],"large":[97],"language":[98],"We":[100],"demonstrate":[101],"that":[102],"achieves":[104],"clustering":[105],"comparable":[106],"manual":[108,136],"curation":[109],"while":[110],"offering":[111],"superior":[112],"grouping":[113],"underlying":[117],"genes.":[118],"AVAILABILITY":[119],"AND":[120],"IMPLEMENTATION:":[121],"The":[122],"is":[125],"available":[126],"as":[127],"open-source":[129],"package,":[131],"with":[132],"comprehensive":[134],"user":[135],"provided":[137],"its":[139],"GitHub":[140],"repository:":[141],"https://github.com/bonellilab/SummArIzeR.":[142]},"counts_by_year":[],"updated_date":"2026-06-18T08:10:14.011955","created_date":"2026-03-03T00:00:00"}
