{"id":"https://openalex.org/W7116795083","doi":"https://doi.org/10.1145/3774976.3774993","title":"From Thousands to a Handful: Streamlining Breast Cancer Pathway Enrichment with LLMs","display_name":"From Thousands to a Handful: Streamlining Breast Cancer Pathway Enrichment with LLMs","publication_year":2025,"publication_date":"2025-09-19","ids":{"openalex":"https://openalex.org/W7116795083","doi":"https://doi.org/10.1145/3774976.3774993"},"language":null,"primary_location":{"id":"doi:10.1145/3774976.3774993","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774976.3774993","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th International Conference on Bioinformatics Research and Applications","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3774976.3774993","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5077580855","display_name":"Mateusz Kania","orcid":"https://orcid.org/0000-0002-3605-0398"},"institutions":[{"id":"https://openalex.org/I119004910","display_name":"Silesian University of Technology","ror":"https://ror.org/02dyjk442","country_code":"PL","type":"education","lineage":["https://openalex.org/I119004910"]}],"countries":["PL"],"is_corresponding":true,"raw_author_name":"Mateusz Kania","raw_affiliation_strings":["Department of Applied Informatics, Silesian University of Technology, Gliwice, Poland"],"raw_orcid":"https://orcid.org/0000-0002-3605-0398","affiliations":[{"raw_affiliation_string":"Department of Applied Informatics, Silesian University of Technology, Gliwice, Poland","institution_ids":["https://openalex.org/I119004910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014860660","display_name":"Joanna \u017by\u0142a","orcid":"https://orcid.org/0000-0002-2895-7969"},"institutions":[{"id":"https://openalex.org/I119004910","display_name":"Silesian University of Technology","ror":"https://ror.org/02dyjk442","country_code":"PL","type":"education","lineage":["https://openalex.org/I119004910"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Joanna Zyla","raw_affiliation_strings":["Department of Data Science and Engineering, Silesian University of Technology, Gliwice, Poland"],"raw_orcid":"https://orcid.org/0000-0002-2895-7969","affiliations":[{"raw_affiliation_string":"Department of Data Science and Engineering, Silesian University of Technology, Gliwice, Poland","institution_ids":["https://openalex.org/I119004910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058144797","display_name":"Karolina Widzisz","orcid":null},"institutions":[{"id":"https://openalex.org/I119004910","display_name":"Silesian University of Technology","ror":"https://ror.org/02dyjk442","country_code":"PL","type":"education","lineage":["https://openalex.org/I119004910"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Karolina Widzisz","raw_affiliation_strings":["Department of Computer Graphics, Vision and Digital Systems, Silesian University of Technology, Gliwice, Poland"],"raw_orcid":"https://orcid.org/0009-0003-2098-2232","affiliations":[{"raw_affiliation_string":"Department of Computer Graphics, Vision and Digital Systems, Silesian University of Technology, Gliwice, Poland","institution_ids":["https://openalex.org/I119004910"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5120996508","display_name":"Andrzej Polanski","orcid":null},"institutions":[{"id":"https://openalex.org/I119004910","display_name":"Silesian University of Technology","ror":"https://ror.org/02dyjk442","country_code":"PL","type":"education","lineage":["https://openalex.org/I119004910"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Andrzej Polanski","raw_affiliation_strings":["Department of Computer Graphics, Vision and Digital Systems, Silesian University of Technology, Gliwice, Poland"],"raw_orcid":"https://orcid.org/0000-0002-1793-9546","affiliations":[{"raw_affiliation_string":"Department of Computer Graphics, Vision and Digital Systems, Silesian University of Technology, Gliwice, Poland","institution_ids":["https://openalex.org/I119004910"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5077580855"],"corresponding_institution_ids":["https://openalex.org/I119004910"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.6082729,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"98","last_page":"102"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.942300021648407,"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":0.942300021648407,"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":0.016899999231100082,"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":0.004800000227987766,"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/breast-cancer","display_name":"Breast cancer","score":0.5127999782562256},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.4690000116825104},{"id":"https://openalex.org/keywords/transcriptome","display_name":"Transcriptome","score":0.4162999987602234},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.41530001163482666},{"id":"https://openalex.org/keywords/pathway-analysis","display_name":"Pathway analysis","score":0.3788999915122986},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.37279999256134033}],"concepts":[{"id":"https://openalex.org/C530470458","wikidata":"https://www.wikidata.org/wiki/Q128581","display_name":"Breast cancer","level":3,"score":0.5127999782562256},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4828000068664551},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.4690000116825104},{"id":"https://openalex.org/C162317418","wikidata":"https://www.wikidata.org/wiki/Q252857","display_name":"Transcriptome","level":4,"score":0.4162999987602234},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.41530001163482666},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.41290000081062317},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.40310001373291016},{"id":"https://openalex.org/C2779230013","wikidata":"https://www.wikidata.org/wiki/Q25303877","display_name":"Pathway analysis","level":4,"score":0.3788999915122986},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.37279999256134033},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.3580000102519989},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.3555999994277954},{"id":"https://openalex.org/C143998085","wikidata":"https://www.wikidata.org/wiki/Q162555","display_name":"Oncology","level":1,"score":0.32820001244544983},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.3059000074863434},{"id":"https://openalex.org/C22029948","wikidata":"https://www.wikidata.org/wiki/Q45089","display_name":"Dice","level":2,"score":0.2969000041484833},{"id":"https://openalex.org/C121608353","wikidata":"https://www.wikidata.org/wiki/Q12078","display_name":"Cancer","level":2,"score":0.29319998621940613},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.29190000891685486},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.27129998803138733},{"id":"https://openalex.org/C12174686","wikidata":"https://www.wikidata.org/wiki/Q1058438","display_name":"Risk assessment","level":2,"score":0.265500009059906}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3774976.3774993","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774976.3774993","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th International Conference on Bioinformatics Research and Applications","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3774976.3774993","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774976.3774993","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th International Conference on Bioinformatics Research and Applications","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Good health and well-being","id":"https://metadata.un.org/sdg/3","score":0.46974438428878784}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2035618305","https://openalex.org/W2096283457","https://openalex.org/W2100761975","https://openalex.org/W2100980426","https://openalex.org/W3177828909","https://openalex.org/W3186179742","https://openalex.org/W4220684489","https://openalex.org/W4404824622","https://openalex.org/W4408389039","https://openalex.org/W4416502596"],"related_works":[],"abstract_inverted_index":{"Over-representation":[0],"of":[1,14,70,79,93,106,120,134,150,158],"pathways":[2,56],"(ORA)":[3],"analysis":[4],"on":[5,36,129],"large":[6],"gene":[7,38],"lists":[8],"from":[9,41],"RNA-seq":[10],"typically":[11],"generates":[12,52],"hundreds":[13],"terms,":[15],"making":[16],"it":[17,116],"difficult":[18],"to":[19,73],"draw":[20],"conclusions.":[21],"In":[22],"our":[23],"work,":[24],"we":[25,102],"compare":[26],"classical":[27],"ORA":[28,145],"(GO":[29],"+":[30],"KEGG),":[31],"with":[32,87],"LLM":[33],"approach":[34],"(llm2geneset)":[35],"16":[37],"clusters":[39],"generated":[40],"TCGA-BRCA":[42],"data.":[43],"Using":[44],"GPT-4-turbo":[45],"and":[46,153],"GPT-4.1-mini":[47,130],"models,":[48],"the":[49,62,67,88,94,104,109,112,121,148,156],"aforementioned":[50],"package":[51],"short,":[53],"biologically":[54],"significant":[55],"whose":[57],"overrepresentation":[58],"is":[59,117],"tested.":[60],"With":[61],"parameter":[63],"npaths":[64],"=":[65],"100":[66,85],"average":[68],"number":[69,105],"results":[71,138],"drops":[72],"5-15":[74],"terms":[75],"per":[76],"cluster,":[77],"each":[78],"which":[80],"appears":[81],"in":[82,97,108],"at":[83,131],"least":[84],"publications":[86],"phrase":[89],"\u201cbreast":[90],"cancer.\u201d":[91],"Instead":[92],"percentage":[95],"reduction":[96],"\u201cnoise\u201d":[98],"or":[99],"Dice":[100],"ratio,":[101],"consider":[103],"citations":[107],"literature":[110],"as":[111],"key":[113],"indicator,":[114],"because":[115],"relatively":[118],"independent":[119],"tool":[122],"parameters.":[123],"The":[124],"entire":[125],"experiment":[126],"was":[127],"conducted":[128],"a":[132],"cost":[133],"about":[135],"$2.50.":[136],"Our":[137],"show":[139],"that":[140],"LLMs":[141],"can":[142],"effectively":[143],"filter":[144],"results,":[146],"simplifying":[147],"interpretation":[149],"transcriptomic":[151],"data":[152],"speeding":[154],"up":[155],"formulation":[157],"biological":[159],"hypotheses.":[160]},"counts_by_year":[],"updated_date":"2025-12-22T23:14:27.083038","created_date":"2025-12-22T00:00:00"}
