{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T23:14:29Z","timestamp":1787008469092,"version":"build-2736575974"},"reference-count":31,"publisher":"Oxford University Press (OUP)","issue":"Supplement_1","license":[{"start":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T00:00:00Z","timestamp":1783382400000},"content-version":"vor","delay-in-days":6,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000002","name":"NIH","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000092","name":"National Library of Medicine","doi-asserted-by":"publisher","award":["1ZIALM237241-02"],"award-info":[{"award-number":["1ZIALM237241-02"]}],"id":[{"id":"10.13039\/100000092","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,7,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Motivation<\/jats:title>\n                    <jats:p>Gene set analysis (GSA) is a foundational approach for interpreting genomic data of diseases by linking genes to biological processes. However, conventional GSA methods overlook clinical context of the analyses, often generating long lists of enriched pathways with redundant, nonspecific, or irrelevant results. Interpreting these requires extensive, ad-hoc manual effort, reducing both reliability and reproducibility.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>We introduce cGSA, a novel AI-driven framework that enhances GSA by incorporating context-aware pathway prioritization. cGSA integrates gene cluster detection, enrichment analysis, and large language models to identify pathways that are not only statistically significant but also biologically meaningful. Benchmarking on 102 curated gene sets across 19 diseases and ten disease-related biological mechanisms shows that cGSA outperforms baseline methods by over 30%, with expert validation confirming its increased precision and interpretability. Two independent case studies in melanoma and breast cancer further demonstrate its potential to uncover context-specific insights and support targeted hypothesis.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Availability and Implementation<\/jats:title>\n                    <jats:p>The demo website is publicly available at https:\/\/www.ncbi.nlm.nih.gov\/CBBresearch\/Lu\/Demo\/cGSA\/, while the data and code can be accessed at https:\/\/github.com\/ncbi-nlp\/cGSA.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btag214","type":"journal-article","created":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T16:33:13Z","timestamp":1783441993000},"source":"Crossref","is-referenced-by-count":1,"title":["Knowledge-guided contextual gene set analysis with large language models"],"prefix":"10.1093","volume":"42","author":[{"given":"Zhizheng","family":"Wang","sequence":"first","affiliation":[{"name":"Division of Intramural Research (DIR), National Library of Medicine (NLM), National Institutes of Health (NIH) , Bethesda, MD 20892,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chi-Ping","family":"Day","sequence":"additional","affiliation":[{"name":"Cancer Data Science Laboratory, Center for Cancer Research, National Cancer Institute (NCI), National Institutes of Health (NIH) , Bethesda, MD 20892,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5094-7321","authenticated-orcid":false,"given":"Chih-Hsuan","family":"Wei","sequence":"additional","affiliation":[{"name":"Division of Intramural Research (DIR), National Library of Medicine (NLM), National Institutes of Health (NIH) , Bethesda, MD 20892,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1268-7239","authenticated-orcid":false,"given":"Qiao","family":"Jin","sequence":"additional","affiliation":[{"name":"Division of Intramural Research (DIR), National Library of Medicine (NLM), National Institutes of Health (NIH) , Bethesda, MD 20892,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3296-5766","authenticated-orcid":false,"given":"Robert","family":"Leaman","sequence":"additional","affiliation":[{"name":"Division of Intramural Research (DIR), National Library of Medicine (NLM), National Institutes of Health (NIH) , Bethesda, MD 20892,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yifan","family":"Yang","sequence":"additional","affiliation":[{"name":"Division of Intramural Research (DIR), National Library of Medicine (NLM), National Institutes of Health (NIH) , Bethesda, MD 20892,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6415-1439","authenticated-orcid":false,"given":"Shubo","family":"Tian","sequence":"additional","affiliation":[{"name":"Division of Intramural Research (DIR), National Library of Medicine (NLM), National Institutes of Health (NIH) , Bethesda, MD 20892,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-4575-8364","authenticated-orcid":false,"given":"Aodong","family":"Qiu","sequence":"additional","affiliation":[{"name":"Department of Biomedical Informatics, School of Medicine, University of Pittsburgh , Pittsburgh, PA 15206,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9538-848X","authenticated-orcid":false,"given":"Yin","family":"Fang","sequence":"additional","affiliation":[{"name":"Division of Intramural Research (DIR), National Library of Medicine (NLM), National Institutes of Health (NIH) , Bethesda, MD 20892,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qingqing","family":"Zhu","sequence":"additional","affiliation":[{"name":"Division of Intramural Research (DIR), National Library of Medicine (NLM), National Institutes of Health (NIH) , Bethesda, MD 20892,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8599-2269","authenticated-orcid":false,"given":"Xinghua","family":"Lu","sequence":"additional","affiliation":[{"name":"Department of Biomedical Informatics, School of Medicine, University of Pittsburgh , Pittsburgh, PA 15206,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9998-916X","authenticated-orcid":false,"given":"Zhiyong","family":"Lu","sequence":"additional","affiliation":[{"name":"Division of Intramural Research (DIR), National Library of Medicine (NLM), National Institutes of Health (NIH) , Bethesda, MD 20892,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,7,7]]},"reference":[{"key":"2026071008250136400_btag214-B1","doi-asserted-by":"crossref","first-page":"377","DOI":"10.1038\/s41568-019-0154-4","article-title":"Phenotype plasticity as enabler of melanoma progression and therapy resistance","volume":"19","author":"Arozarena","year":"2019","journal-title":"Nat Rev Cancer"},{"key":"2026071008250136400_btag214-B2","doi-asserted-by":"crossref","first-page":"820","DOI":"10.1038\/s41591-021-01323-8","article-title":"A single-cell map of intratumoral changes during anti-PD1 treatment of patients with breast cancer","volume":"27","author":"Bassez","year":"2021","journal-title":"Nat Med"},{"key":"2026071008250136400_btag214-B3","doi-asserted-by":"crossref","first-page":"149","DOI":"10.1002\/path.2287","article-title":"TNF-mediated inflammatory disease","volume":"214","author":"Bradley","year":"2008","journal-title":"J Pathol"},{"key":"2026071008250136400_btag214-B4","doi-asserted-by":"crossref","first-page":"243","DOI":"10.1038\/s41591-021-01672-4","article-title":"A roadmap to increase diversity in genomic studies","volume":"28","author":"Fatumo","year":"2022","journal-title":"Nat Med"},{"key":"2026071008250136400_btag214-B5","doi-asserted-by":"crossref","first-page":"2132","DOI":"10.1038\/s41467-025-56279-x","article-title":"Cellular interactions within the immune microenvironment underpins resistance to cell cycle inhibition in breast cancers","volume":"16","author":"Griffiths","year":"2025","journal-title":"Nat Commun"},{"key":"2026071008250136400_btag214-B6","doi-asserted-by":"crossref","first-page":"e2110256119","DOI":"10.1073\/pnas.2110256119","article-title":"FKBP52 and FKBP51 differentially regulate the stability of estrogen receptor in breast cancer","volume":"119","author":"Habara","year":"2022","journal-title":"Proc Natl Acad Sci USA"},{"key":"2026071008250136400_btag214-B7","doi-asserted-by":"crossref","first-page":"101156","DOI":"10.1016\/j.cels.2024.11.013","article-title":"Stochastic modeling of single-cell gene expression adaptation reveals non-genomic contribution to evolution of tumor subclones","volume":"16","author":"Hirsch","year":"2025","journal-title":"Cell Syst"},{"key":"2026071008250136400_btag214-B8","doi-asserted-by":"crossref","first-page":"197ra102","DOI":"10.1126\/scitranslmed.3006200","article-title":"Mutational signature of aristolochic acid exposure as revealed by whole-exome sequencing","volume":"5","author":"Hoang","year":"2013","journal-title":"Sci Transl Med"},{"key":"2026071008250136400_btag214-B9","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1038\/s41592-024-02525-x","article-title":"Evaluation of large language models for discovery of gene set function","volume":"22","author":"Hu","year":"2025","journal-title":"Nat Methods"},{"key":"2026071008250136400_btag214-B10","doi-asserted-by":"crossref","first-page":"eabh0609","DOI":"10.1126\/sciadv.abh0609","article-title":"Microglia promote autoimmune inflammation via the noncanonical NF-\u03baB pathway","volume":"7","author":"Jie","year":"2021","journal-title":"Sci Adv"},{"key":"2026071008250136400_btag214-B11","author":"Joachimiak","year":"2024"},{"key":"2026071008250136400_btag214-B12","doi-asserted-by":"crossref","first-page":"W90","DOI":"10.1093\/nar\/gkw377","article-title":"Enrichr: a comprehensive gene set enrichment analysis web server 2016 update","volume":"44","author":"Kuleshov","year":"2016","journal-title":"Nucleic Acids Res"},{"key":"2026071008250136400_btag214-B13","doi-asserted-by":"crossref","first-page":"eaba2489","DOI":"10.1126\/sciadv.aba2489","article-title":"Atac-seq identifies thousands of extrachromosomal circular dna in cancer and cell lines","volume":"6","author":"Kumar","year":"2020","journal-title":"Sci Adv"},{"key":"2026071008250136400_btag214-B14","first-page":"479","author":"Li","year":"2019"},{"key":"2026071008250136400_btag214-B15","doi-asserted-by":"crossref","first-page":"725","DOI":"10.1038\/nri910","article-title":"NF-\u03baB regulation in the immune system","volume":"2","author":"Li","year":"2002","journal-title":"Nat Rev Immunol"},{"key":"2026071008250136400_btag214-B16","doi-asserted-by":"crossref","first-page":"bbac558","DOI":"10.1093\/bib\/bbac558","article-title":"GSCA: an integrated platform for gene set cancer analysis at genomic, pharmacogenomic and immunogenomic levels","volume":"24","author":"Liu","year":"2023","journal-title":"Brief Bioinform"},{"key":"2026071008250136400_btag214-B17","doi-asserted-by":"crossref","first-page":"1424","DOI":"10.1038\/s41591-023-02369-6","article-title":"The tumor immune microenvironment of nasopharyngeal carcinoma after gemcitabine plus cisplatin treatment","volume":"29","author":"Lv","year":"2023","journal-title":"Nat Med"},{"key":"2026071008250136400_btag214-B18","doi-asserted-by":"crossref","first-page":"6707","DOI":"10.1016\/j.cell.2024.08.047","article-title":"Saturation mutagenesis-reinforced functional assays for disease-related genes","volume":"187","author":"Ma","year":"2024","journal-title":"Cell"},{"key":"2026071008250136400_btag214-B19","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1038\/s41419-023-06389-5","article-title":"Mechanisms of immune checkpoint inhibitors: insights into the regulation of circular RNAs involved in cancer hallmarks","volume":"15","author":"Meng","year":"2024","journal-title":"Cell Death Dis"},{"key":"2026071008250136400_btag214-B20","doi-asserted-by":"crossref","first-page":"390","DOI":"10.1016\/j.tig.2014.07.004","article-title":"Functional and genomic context in pathway analysis of gwas data","volume":"30","author":"Mooney","year":"2014","journal-title":"Trends Genet"},{"key":"2026071008250136400_btag214-B21","doi-asserted-by":"crossref","first-page":"548","DOI":"10.1016\/j.cels.2018.10.008","article-title":"Mapping cellular reprogramming via pooled overexpression screens with paired fitness and single-cell rna-sequencing readout","volume":"7","author":"Parekh","year":"2018","journal-title":"Cell Syst"},{"key":"2026071008250136400_btag214-B22","doi-asserted-by":"crossref","first-page":"952","DOI":"10.1038\/s41598-020-78654-y","article-title":"Multiplex gene and phenotype network to characterize shared genetic pathways of epilepsy and autism","volume":"11","author":"Peng","year":"2021","journal-title":"Sci Rep"},{"key":"2026071008250136400_btag214-B23","doi-asserted-by":"crossref","first-page":"768","DOI":"10.1038\/nature08872","article-title":"Understanding mechanisms underlying human gene expression variation with rna sequencing","volume":"464","author":"Pickrell","year":"2010","journal-title":"Nature"},{"key":"2026071008250136400_btag214-B24","doi-asserted-by":"crossref","first-page":"W191","DOI":"10.1093\/nar\/gkz369","article-title":"g:Profiler: a web server for functional enrichment analysis and conversions of gene lists (2019 update)","volume":"47","author":"Raudvere","year":"2019","journal-title":"Nucleic Acids Res"},{"key":"2026071008250136400_btag214-B25","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1093\/jleuko\/qiac005","article-title":"The impact of ADRB2 polymorphisms on immune responses and norepinephrine-induced immunosuppression","volume":"113","author":"Stolk","year":"2023","journal-title":"J Leukoc Biol"},{"key":"2026071008250136400_btag214-B26","doi-asserted-by":"crossref","first-page":"15545","DOI":"10.1073\/pnas.0506580102","article-title":"Gene set enrichment analysis: a knowledge-based approach for interpreting genome-wide expression profiles","volume":"102","author":"Subramanian","year":"2005","journal-title":"Proc Natl Acad Sci USA"},{"key":"2026071008250136400_btag214-B27","doi-asserted-by":"crossref","first-page":"1677","DOI":"10.1038\/s41592-025-02748-6","article-title":"GeneAgent: self-verification language agent for gene-set analysis using domain databases","volume":"22","author":"Wang","year":"2025","journal-title":"Nat Methods"},{"key":"2026071008250136400_btag214-B28","doi-asserted-by":"crossref","first-page":"1543","DOI":"10.1534\/g3.115.018564","article-title":"Exome sequencing: current and future perspectives","volume":"5","author":"Warr","year":"2015","journal-title":"G3 (Bethesda)"},{"key":"2026071008250136400_btag214-B29","doi-asserted-by":"crossref","first-page":"133","DOI":"10.1016\/j.cellsig.2013.08.026","article-title":"Cyr61 induces the expression of monocyte chemoattractant protein-1 via the integrin \u03b1\u03bd\u03b23, FAK, Pi3K\/Akt, and NF-\u03baB pathways in retinal vascular endothelial cells","volume":"26","author":"You","year":"2014","journal-title":"Cell Signal"},{"key":"2026071008250136400_btag214-B30","doi-asserted-by":"crossref","first-page":"6687","DOI":"10.1016\/j.cell.2024.09.014","article-title":"Detection and analysis of complex structural variation in human genomes across populations and in brains of donors with psychiatric disorders","volume":"187","author":"Zhou","year":"2024","journal-title":"Cell"},{"key":"2026071008250136400_btag214-B31","doi-asserted-by":"crossref","first-page":"2024","DOI":"10.1093\/bioinformatics\/btt353","article-title":"Human interactome resource and gene set linkage analysis for the functional interpretation of biologically meaningful gene sets","volume":"29","author":"Zhou","year":"2013","journal-title":"Bioinformatics"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/42\/Supplement_1\/btag214\/68709497\/btag214.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/42\/Supplement_1\/btag214\/68709497\/btag214.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T12:25:11Z","timestamp":1783686311000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btag214\/8726338"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,1]]},"references-count":31,"journal-issue":{"issue":"Supplement_1","published-print":{"date-parts":[[2026,7,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btag214","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,7]]},"published":{"date-parts":[[2026,7,1]]},"article-number":"btag214"}}