{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T10:38:29Z","timestamp":1769855909949,"version":"3.49.0"},"reference-count":44,"publisher":"Oxford University Press (OUP)","issue":"1","license":[{"start":{"date-parts":[[2022,11,17]],"date-time":"2022-11-17T00:00:00Z","timestamp":1668643200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["GM007365"],"award-info":[{"award-number":["GM007365"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["GM102365"],"award-info":[{"award-number":["GM102365"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Knight-Hennessy Scholarships"},{"name":"UnitedHealth Group Research and Development"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,1,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>Gene set analysis methods rely on knowledge-based representations of genetic interactions in the form of both gene set collections and protein\u2013protein interaction (PPI) networks. However, explicit representations of genetic interactions often fail to capture complex interdependencies among genes, limiting the analytic power of such methods.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>We propose an extension of gene set enrichment analysis to a latent embedding space reflecting PPI network topology, called gene set proximity analysis (GSPA). Compared with existing methods, GSPA provides improved ability to identify disease-associated pathways in disease-matched gene expression datasets, while improving reproducibility of enrichment statistics for similar gene sets. GSPA is statistically straightforward, reducing to a version of traditional gene set enrichment analysis through a single user-defined parameter. We apply our method to identify novel drug associations with SARS-CoV-2 viral entry. Finally, we validate our drug association predictions through retrospective clinical analysis of claims data from 8 million patients, supporting a role for gabapentin as a risk factor and metformin as a protective factor for severe COVID-19.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>GSPA is available for download as a command-line Python package at https:\/\/github.com\/henrycousins\/gspa.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Supplementary information<\/jats:title>\n                  <jats:p>Supplementary data are available at Bioinformatics online.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btac735","type":"journal-article","created":{"date-parts":[[2022,11,17]],"date-time":"2022-11-17T12:45:04Z","timestamp":1668689104000},"source":"Crossref","is-referenced-by-count":10,"title":["Gene set proximity analysis: expanding gene set enrichment analysis through learned geometric embeddings, with drug-repurposing applications in COVID-19"],"prefix":"10.1093","volume":"39","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8694-0604","authenticated-orcid":false,"given":"Henry","family":"Cousins","sequence":"first","affiliation":[{"name":"Department of Biomedical Data Science, Stanford University School of Medicine , Stanford, CA 94305, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Taryn","family":"Hall","sequence":"additional","affiliation":[{"name":"Optum Labs at UnitedHealth Group , Minneapolis, MN 55343, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yinglong","family":"Guo","sequence":"additional","affiliation":[{"name":"Optum Labs at UnitedHealth Group , Minneapolis, MN 55343, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Luke","family":"Tso","sequence":"additional","affiliation":[{"name":"Optum Labs at UnitedHealth Group , Minneapolis, MN 55343, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kathy T H","family":"Tzeng","sequence":"additional","affiliation":[{"name":"Optum Labs at UnitedHealth Group , Minneapolis, MN 55343, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4725-8714","authenticated-orcid":false,"given":"Le","family":"Cong","sequence":"additional","affiliation":[{"name":"Department of Genetics, Stanford University School of Medicine , Stanford, CA 94305, USA"},{"name":"Department of Pathology, Stanford University School of Medicine , Stanford, CA 94305, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3859-2905","authenticated-orcid":false,"given":"Russ B","family":"Altman","sequence":"additional","affiliation":[{"name":"Department of Biomedical Data Science, Stanford University School of Medicine , Stanford, CA 94305, USA"},{"name":"Department of Genetics, Stanford University School of Medicine , Stanford, CA 94305, USA"},{"name":"Department of Medicine, Stanford University School of Medicine , Stanford, CA 94305, USA"},{"name":"Department of Bioengineering, Stanford University , Stanford, CA 94305, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2022,11,17]]},"reference":[{"key":"2023010107515920600_btac735-B1","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1038\/75556","article-title":"Gene ontology: tool for the unification of biology. The gene ontology consortium","volume":"25","author":"Ashburner","year":"2000","journal-title":"Nat. Genet"},{"key":"2023010107515920600_btac735-B2","doi-asserted-by":"crossref","first-page":"3710","DOI":"10.1093\/bioinformatics\/bth456","article-title":"GO::TermFinder\u2014open source software for accessing gene ontology information and finding significantly enriched gene ontology terms associated with a list of genes","volume":"20","author":"Boyle","year":"2004","journal-title":"Bioinformatics"},{"key":"2023010107515920600_btac735-B3","doi-asserted-by":"crossref","first-page":"D325","DOI":"10.1093\/nar\/gkaa1113","article-title":"The gene ontology resource: enriching a GOld mine","volume":"49","author":"Carbon","year":"2021","journal-title":"Nucleic Acids Res"},{"key":"2023010107515920600_btac735-B4","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/1471-2105-14-S18-S1","article-title":"Enrichr: interactive and collaborative HTML5 gene list enrichment analysis tool","volume":"14","author":"Chen","year":"2013","journal-title":"BMC Bioinformatics"},{"key":"2023010107515920600_btac735-B5","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1186\/s12918-018-0642-2","article-title":"GSAE: an autoencoder with embedded gene-set nodes for genomics functional characterization","volume":"12","author":"Chen","year":"2018","journal-title":"BMC Syst. Biol"},{"key":"2023010107515920600_btac735-B6","doi-asserted-by":"crossref","first-page":"93","DOI":"10.1038\/nrg.2017.96","article-title":"Cancer transcriptome profiling at the juncture of clinical translation","volume":"19","author":"Cie\u015blik","year":"2017","journal-title":"Nat. Rev. Genet"},{"key":"2023010107515920600_btac735-B7","doi-asserted-by":"crossref","first-page":"1081","DOI":"10.3389\/fendo.2020.600439","article-title":"Metformin use is associated with reduced mortality in a diverse population with COVID-19 and diabetes","volume":"11","author":"Crouse","year":"2021","journal-title":"Front. Endocrinol"},{"key":"2023010107515920600_btac735-B8","doi-asserted-by":"crossref","first-page":"92","DOI":"10.1016\/j.cell.2020.10.030","article-title":"Identification of required host factors for SARS-CoV-2 infection in human cells","volume":"184","author":"Daniloski","year":"2021","journal-title":"Cell"},{"key":"2023010107515920600_btac735-B9","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s12859-016-0884-1","article-title":"Bioconductor\u2019s EnrichmentBrowser: seamless navigation through combined results of set- and network-based enrichment analysis","volume":"17","author":"Geistlinger","year":"2016","journal-title":"BMC Bioinform"},{"key":"2023010107515920600_btac735-B10","doi-asserted-by":"crossref","first-page":"545","DOI":"10.1093\/bib\/bbz158","article-title":"Toward a gold standard for benchmarking gene set enrichment analysis","volume":"22","author":"Geistlinger","year":"2021","journal-title":"Brief. Bioinform"},{"key":"2023010107515920600_btac735-B11","doi-asserted-by":"crossref","first-page":"i451","DOI":"10.1093\/bioinformatics\/bts389","article-title":"EnrichNet: network-based gene set enrichment analysis","volume":"28","author":"Glaab","year":"2012","journal-title":"Bioinformatics"},{"key":"2023010107515920600_btac735-B12","doi-asserted-by":"crossref","first-page":"980","DOI":"10.1093\/bioinformatics\/btm051","article-title":"Analyzing gene expression data in terms of gene sets: methodological issues","volume":"23","author":"Goeman","year":"2007","journal-title":"Bioinformatics"},{"key":"2023010107515920600_btac735-B13","first-page":"855","article-title":"node2vec: scalable feature learning for networks","author":"Grover","year":"2016","journal-title":"KDD Proceedings of the"},{"key":"2023010107515920600_btac735-B14","first-page":"579","article-title":"NGSEA: network-based gene set enrichment analysis for interpreting gene expression phenotypes with functional gene sets","volume":"42","author":"Han","year":"2019","journal-title":"Mol. Cells"},{"key":"2023010107515920600_btac735-B15","doi-asserted-by":"crossref","first-page":"3815","DOI":"10.1093\/bioinformatics\/btw530","article-title":"STAMS: STRING-assisted module search for genome wide association studies and application to autism","volume":"32","author":"Hillenmeyer","year":"2016","journal-title":"Bioinformatics"},{"key":"2023010107515920600_btac735-B16","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1038\/nprot.2008.211","article-title":"Systematic and integrative analysis of large gene lists using DAVID bioinformatics resources","volume":"4","author":"Huang","year":"2009","journal-title":"Nat. Protoc"},{"key":"2023010107515920600_btac735-B17","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s13059-021-02264-8","article-title":"GeneWalk identifies relevant gene functions for a biological context using network representation learning","volume":"22","author":"Ietswaart","year":"2021","journal-title":"Genome Biol"},{"key":"2023010107515920600_btac735-B19","doi-asserted-by":"crossref","first-page":"D353","DOI":"10.1093\/nar\/gkw1092","article-title":"KEGG: new perspectives on genomes, pathways, diseases and drugs","volume":"45","author":"Kanehisa","year":"2017","journal-title":"Nucleic Acids Res"},{"key":"2023010107515920600_btac735-B20","doi-asserted-by":"crossref","DOI":"10.1186\/s12890-021-01607-2","article-title":"Outcomes for hospitalized patients with idiopathic pulmonary fibrosis treated with antifibrotic medications","volume":"21","author":"Kelly","year":"2021","journal-title":"BMC Pulm. Med"},{"key":"2023010107515920600_btac735-B21","doi-asserted-by":"crossref","first-page":"101216","DOI":"10.1016\/j.diabet.2020.101216","article-title":"Metformin use is associated with a reduced risk of mortality in patients with diabetes hospitalised for COVID-19","volume":"47","author":"Lalau","year":"2021","journal-title":"Diabetes Metab"},{"key":"2023010107515920600_btac735-B22","doi-asserted-by":"crossref","first-page":"353","DOI":"10.1038\/nrg.2016.29","article-title":"The statistical properties of gene-set analysis","volume":"17","author":"De Leeuw","year":"2016","journal-title":"Nat. Rev. Genet"},{"key":"2023010107515920600_btac735-B23","doi-asserted-by":"crossref","first-page":"704666","DOI":"10.3389\/fmed.2021.704666","article-title":"Metformin in patients with COVID-19: a systematic review and meta-analysis","volume":"8","author":"Li","year":"2021","journal-title":"Front Med"},{"key":"2023010107515920600_btac735-B24","doi-asserted-by":"crossref","first-page":"69","DOI":"10.4269\/ajtmh.20-0375","article-title":"Metformin treatment was associated with decreased mortality in COVID-19 patients with diabetes in a retrospective analysis","volume":"103","author":"Luo","year":"2020","journal-title":"Am. J. Trop. Med. Hyg"},{"key":"2023010107515920600_btac735-B25","doi-asserted-by":"crossref","first-page":"1075","DOI":"10.1093\/bioinformatics\/btab772","article-title":"Deep graph representations embed network information for robust disease marker identification","volume":"38","author":"Maddouri","year":"2022","journal-title":"Bioinformatics"},{"key":"2023010107515920600_btac735-B26","doi-asserted-by":"crossref","first-page":"654","DOI":"10.3389\/fgene.2020.00654","article-title":"Gene set analysis: challenges, opportunities, and future research","volume":"11","author":"Maleki","year":"2020","journal-title":"Front. Genet"},{"key":"2023010107515920600_btac735-B27","doi-asserted-by":"crossref","first-page":"e13984","DOI":"10.1371\/journal.pone.0013984","article-title":"Enrichment map: a network-based method for gene-set enrichment visualization and interpretation","volume":"5","author":"Merico","year":"2010","journal-title":"PLoS ONE"},{"key":"2023010107515920600_btac735-B28","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1016\/j.gene.2017.11.028","article-title":"Discerning molecular interactions: a comprehensive review on biomolecular interaction databases and network analysis tools","volume":"642","author":"Miryala","year":"2018","journal-title":"Gene"},{"key":"2023010107515920600_btac735-B29","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1038\/ng1180","article-title":"PGC-1alpha-responsive genes involved in oxidative phosphorylation are coordinately downregulated in human diabetes","volume":"34","author":"Mootha","year":"2003","journal-title":"Nat. Genet"},{"key":"2023010107515920600_btac735-B30","doi-asserted-by":"crossref","DOI":"10.1186\/s12859-021-04042-6","article-title":"PIGNON: a protein\u2013protein interaction-guided functional enrichment analysis for quantitative proteomics","volume":"22","author":"Nadeau","year":"2021","journal-title":"BMC Bioinformatics"},{"key":"2023010107515920600_btac735-B31","doi-asserted-by":"crossref","first-page":"120","DOI":"10.1016\/j.cell.2020.12.006","article-title":"Genome-scale identification of SARS-CoV-2 and pan-coronavirus host factor networks","volume":"184","author":"Schneider","year":"2021","journal-title":"Cell"},{"key":"2023010107515920600_btac735-B32","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":"2023010107515920600_btac735-B33","doi-asserted-by":"crossref","first-page":"D362","DOI":"10.1093\/nar\/gkw937","article-title":"The STRING database in 2017: quality-controlled protein\u2013protein association networks, made broadly accessible","volume":"45","author":"Szklarczyk","year":"2017","journal-title":"Nucleic Acids Res"},{"key":"2023010107515920600_btac735-B34","doi-asserted-by":"crossref","first-page":"e79217","DOI":"10.1371\/journal.pone.0079217","article-title":"A comparison of gene set analysis methods in terms of sensitivity, prioritization and specificity","volume":"8","author":"Tarca","year":"2013","journal-title":"PLoS ONE"},{"key":"2023010107515920600_btac735-B35","doi-asserted-by":"crossref","first-page":"75","DOI":"10.1093\/bioinformatics\/btn577","article-title":"A novel signaling pathway impact analysis","volume":"25","author":"Tarca","year":"2009","journal-title":"Bioinformatics"},{"key":"2023010107515920600_btac735-B36","doi-asserted-by":"crossref","first-page":"136","DOI":"10.1186\/1471-2105-13-136","article-title":"Down-weighting overlapping genes improves gene set analysis","volume":"13","author":"Tarca","year":"2012","journal-title":"BMC Bioinformatics"},{"key":"2023010107515920600_btac735-B37","doi-asserted-by":"crossref","first-page":"1187","DOI":"10.1377\/hlthaff.2014.0038","article-title":"Optum labs: building a novel node in the learning health care system","volume":"33","author":"Wallace","year":"2014","journal-title":"Health Aff. (Millwood)"},{"key":"2023010107515920600_btac735-B38","doi-asserted-by":"crossref","first-page":"387","DOI":"10.1038\/s42256-020-0193-2","article-title":"Gaussian embedding for large-scale gene set analysis","volume":"2","author":"Wang","year":"2020","journal-title":"Nat. Mach. Intell"},{"key":"2023010107515920600_btac735-B39","doi-asserted-by":"crossref","first-page":"76","DOI":"10.1016\/j.cell.2020.10.028","article-title":"Genome-wide CRISPR screens reveal host factors critical for SARS-CoV-2 infection","volume":"184","author":"Wei","year":"2021","journal-title":"Cell"},{"key":"2023010107515920600_btac735-B40","doi-asserted-by":"crossref","first-page":"e133\u2013e133","DOI":"10.1093\/nar\/gks461","article-title":"Camera: a competitive gene set test accounting for inter-gene correlation","volume":"40","author":"Wu","year":"2012","journal-title":"Nucleic Acids Res"},{"key":"2023010107515920600_btac735-B41","doi-asserted-by":"crossref","DOI":"10.1161\/JAHA.116.003725","article-title":"Effectiveness and safety of dabigatran, rivaroxaban, and apixaban versus warfarin in nonvalvular atrial fibrillation","volume":"5","author":"Yao","year":"2016","journal-title":"J. Am. Heart Assoc"},{"key":"2023010107515920600_btac735-B42","doi-asserted-by":"crossref","first-page":"3069","DOI":"10.1093\/bioinformatics\/btv313","article-title":"DSigDB: drug signatures database for gene set analysis","volume":"31","author":"Yoo","year":"2015","journal-title":"Bioinformatics"},{"key":"2023010107515920600_btac735-B3562599","doi-asserted-by":"crossref","first-page":"16","DOI":"10.21037\/atm.2018.12.10","article-title":"Balance diagnostics after propensity score matching","volume":"7","author":"Zhang","year":"2019","journal-title":"Ann. Transl. Med."},{"key":"2023010107515920600_btac735-B43","doi-asserted-by":"crossref","first-page":"467","DOI":"10.1021\/acscentsci.1c00039","article-title":"Potent noncovalent inhibitors of the main protease of SARS-CoV-2 from molecular sculpting of the drug perampanel guided by free energy perturbation calculations","volume":"7","author":"Zhang","year":"2021","journal-title":"ACS Cent. Sci"},{"key":"2023010107515920600_btac735-B44","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41467-021-26140-y","article-title":"Learning interpretable cellular and gene signature embeddings from single-cell transcriptomic data","volume":"12","author":"Zhao","year":"2021","journal-title":"Nat. Commun"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btac735\/47464891\/btac735.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/39\/1\/btac735\/48448718\/btac735.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/39\/1\/btac735\/48448718\/btac735.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T10:09:16Z","timestamp":1672567756000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btac735\/6832036"}},"subtitle":[],"editor":[{"given":"Alfonso","family":"Valencia","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2022,11,17]]},"references-count":44,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2022,11,17]]},"published-print":{"date-parts":[[2023,1,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btac735","relation":{},"ISSN":["1367-4811"],"issn-type":[{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2023,1,1]]},"published":{"date-parts":[[2022,11,17]]},"article-number":"btac735"}}