{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T14:43:02Z","timestamp":1772116982772,"version":"3.50.1"},"reference-count":50,"publisher":"Oxford University Press (OUP)","issue":"5","license":[{"start":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T00:00:00Z","timestamp":1761523200000},"content-version":"vor","delay-in-days":57,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"MD Anderson Moonshot Program"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,8,31]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Biomarker discovery for complex diseases, such as cancer, hinges on uncovering molecular signatures that capture intricate, interconnected relationships within biological data\u2014a challenge that traditional statistical and machine learning methods often fail to meet due to the complexity of high-dimensional gene expression profiles. To overcome this, we introduce the expression graph network framework (EGNF). This cutting-edge graph-based approach integrates graph neural networks with network-based feature engineering to enhance the predictive identification of biomarkers. EGNF constructs biologically informed networks by combining gene expression data and clinical attributes within a graph database, utilizing hierarchical clustering to generate dynamic, patient-specific representations of molecular interactions. Leveraging graph learning techniques, including graph convolutional networks and graph attention networks, our framework identifies statistically significant and biologically relevant gene modules for classification. Validated across three independent datasets consisting of contrasting tumor types and clinical scenarios, EGNF consistently outperforms traditional machine learning models, achieving superior classification accuracy and interpretability. Notably, it delivers perfect separation between normal and tumor samples while excelling in nuanced tasks such as classifying disease progression and predicting treatment outcomes. This scalable, interpretable, and robust framework provides a powerful tool for biomarker discovery, with wide-ranging applications in precision medicine and the elucidation of disease mechanisms across diverse clinical contexts.<\/jats:p>","DOI":"10.1093\/bib\/bbaf559","type":"journal-article","created":{"date-parts":[[2025,10,7]],"date-time":"2025-10-07T11:47:48Z","timestamp":1759837668000},"source":"Crossref","is-referenced-by-count":3,"title":["Expression graph network framework for biomarker discovery"],"prefix":"10.1093","volume":"26","author":[{"given":"Yang","family":"Liu","sequence":"first","affiliation":[{"name":"Department of Translational Molecular Pathology, University of Texas MD Anderson Cancer Center , 2130 W Holcombe Blvd, Texas 77030 ,","place":["United States"]},{"name":"Department of Biostatistics and Data Science, University of Texas Health Science Center at Houston , 1200 Pressler Street, Texas 77030 ,","place":["United States"]}]},{"given":"Jason","family":"Huse","sequence":"additional","affiliation":[{"name":"Department of Translational Molecular Pathology, University of Texas MD Anderson Cancer Center , 2130 W Holcombe Blvd, Texas 77030 ,","place":["United States"]},{"name":"Department of Pathology, University of Texas MD Anderson Cancer Center , 1515 Holcombe Blvd, Texas 77030 ,","place":["United States"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8479-0657","authenticated-orcid":false,"given":"Kasthuri","family":"Kannan","sequence":"additional","affiliation":[{"name":"Department of Translational Molecular Pathology, University of Texas MD Anderson Cancer Center , 2130 W Holcombe Blvd, Texas 77030 ,","place":["United States"]}]}],"member":"286","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"2025102700404654900_ref1","doi-asserted-by":"crossref","first-page":"646","DOI":"10.1016\/j.cell.2011.02.013","article-title":"Hallmarks of cancer: the next generation","volume":"144","author":"Hanahan","year":"2011","journal-title":"Cell."},{"key":"2025102700404654900_ref2","doi-asserted-by":"crossref","first-page":"fcae108","DOI":"10.1093\/braincomms\/fcae108","article-title":"Molecular diversity in isocitrate dehydrogenase-wild-type glioblastoma","volume":"6","author":"Fares","year":"2024","journal-title":"Brain Commun"},{"key":"2025102700404654900_ref3","doi-asserted-by":"crossref","first-page":"98","DOI":"10.1016\/j.ccr.2009.12.020","article-title":"Integrated genomic analysis identifies clinically relevant subtypes of glioblastoma characterized by abnormalities in PDGFRA, IDH1, EGFR, and NF1","volume":"17","author":"Verhaak","year":"2010","journal-title":"Cancer Cell"},{"key":"2025102700404654900_ref4","doi-asserted-by":"crossref","first-page":"835","DOI":"10.1016\/j.cell.2019.06.024","article-title":"An integrative model of cellular states, plasticity, and genetics for glioblastoma","volume":"178","author":"Neftel","year":"2019","journal-title":"Cell."},{"key":"2025102700404654900_ref5","first-page":"281","article-title":"Some methods for classification and analysis of multivariate observations","volume-title":"Proceedings of the Fifth Berkeley Symposium on Mathematical Statistics and Probability","author":"MacQueen","year":"1967"},{"key":"2025102700404654900_ref6","first-page":"2973","article-title":"Effect of clustering data in improving machine learning model accuracy","volume":"97","author":"Mostafa","year":"2019","journal-title":"J Theor Appl Inf Technol"},{"key":"2025102700404654900_ref7","article-title":"Semi-supervised classification with graph convolutional networks","author":"Kipf","year":"2017"},{"key":"2025102700404654900_ref8","article-title":"Graph attention networks","author":"Veli\u010dkovi\u0107"},{"key":"2025102700404654900_ref9","article-title":"How attentive are graph attention networks","author":"Brody"},{"key":"2025102700404654900_ref10","doi-asserted-by":"crossref","first-page":"3445","DOI":"10.1038\/s41467-021-23774-w","article-title":"MOGONET integrates multi-omics data using graph convolutional networks allowing patient classification and biomarker identification","volume":"12","author":"Wang","year":"2021","journal-title":"Nat Commun"},{"key":"2025102700404654900_ref11","doi-asserted-by":"crossref","first-page":"203","DOI":"10.3389\/fphy.2020.00203","article-title":"Classification of cancer types using graph convolutional neural networks","volume":"8","author":"Ramirez","year":"2020","journal-title":"Front Phys"},{"key":"2025102700404654900_ref12","doi-asserted-by":"crossref","first-page":"559","DOI":"10.1186\/1471-2105-9-559","article-title":"WGCNA: an R package for weighted correlation network analysis","volume":"9","author":"Langfelder","year":"2008","journal-title":"BMC Bioinformatics."},{"key":"2025102700404654900_ref13","doi-asserted-by":"crossref","first-page":"162","DOI":"10.1186\/s12915-025-02260-5","article-title":"iHofman: a predictive model integrating high-order and low-order features with weighted attention mechanisms for circRNA-miRNA interactions","volume":"23","author":"Yu","year":"2025","journal-title":"BMC Biol"},{"key":"2025102700404654900_ref14","first-page":"bbad111","article-title":"A feature extraction method based on noise reduction for circRNA-miRNA interaction prediction combining multi-structure features in the association networks","volume":"25","author":"Wang","year":"2024","journal-title":"Brief Bioinform"},{"key":"2025102700404654900_ref15","doi-asserted-by":"crossref","first-page":"189104","DOI":"10.1007\/s11432-024-4098-3","article-title":"BioKG-CMI: a multi-source feature fusion model based on biological knowledge graph for predicting circRNA-miRNA interactions","volume":"67","author":"Wei","year":"2024","journal-title":"Sci China Inf Sci"},{"key":"2025102700404654900_ref16","doi-asserted-by":"crossref","first-page":"550","DOI":"10.1186\/s13059-014-0550-8","article-title":"Moderated estimation of fold change and dispersion for RNA-seq data with DESeq2","volume":"15","author":"Love","year":"2014","journal-title":"Genome Biol"},{"key":"2025102700404654900_ref17","doi-asserted-by":"crossref","DOI":"10.1002\/9781118548387","volume-title":"Applied Logistic Regression","author":"Hosmer","year":"2013"},{"key":"2025102700404654900_ref18","doi-asserted-by":"crossref","first-page":"301","DOI":"10.1111\/j.1467-9868.2005.00503.x","article-title":"Regularization and variable selection via the elastic net","volume":"67","author":"Zou","year":"2005","journal-title":"J R Stat Soc Series B Stat Methodol"},{"key":"2025102700404654900_ref19","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach Learn."},{"key":"2025102700404654900_ref20","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1023\/A:1022627411411","article-title":"Support-vector networks","volume":"20","author":"Cortes","year":"1995","journal-title":"Mach Learn"},{"key":"2025102700404654900_ref21","doi-asserted-by":"crossref","first-page":"533","DOI":"10.1038\/323533a0","article-title":"Learning representations by back-propagating errors","volume":"323","author":"Rumelhart","year":"1986","journal-title":"Nature."},{"key":"2025102700404654900_ref22","first-page":"281","article-title":"Random search for hyper-parameter optimization","volume":"13","author":"Bergstra","year":"2012","journal-title":"J Mach Learn Res"},{"key":"2025102700404654900_ref23","first-page":"2951","article-title":"Practical Bayesian optimization of machine learning algorithms","volume":"25","author":"Snoek","year":"2012","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2025102700404654900_ref24","doi-asserted-by":"crossref","first-page":"1","DOI":"10.18637\/jss.v028.i05","article-title":"Building predictive models in R using the caret package","volume":"28","author":"Kuhn","year":"2008","journal-title":"J Stat Softw"},{"key":"2025102700404654900_ref25","doi-asserted-by":"crossref","first-page":"640298","DOI":"10.3389\/fendo.2021.640298","article-title":"Intracellular progesterone receptor and cSrc protein working together to promote migration and invasion of human glioblastoma cells","volume":"12","author":"Cortese","year":"2021","journal-title":"Front Endocrinol"},{"key":"2025102700404654900_ref26","first-page":"9453549","article-title":"Integrated analysis of ECT2 and COL17A1 as potential biomarkers of glioblastoma multiforme","volume":"2022","author":"Yan","year":"2022","journal-title":"Biomed Res Int"},{"key":"2025102700404654900_ref27","doi-asserted-by":"crossref","first-page":"109317","DOI":"10.1016\/j.isci.2024.109317","article-title":"Machine learning unveils immune-related signature in multicenter glioma studies","volume":"27","author":"Yang","year":"2024","journal-title":"iScience."},{"key":"2025102700404654900_ref28","doi-asserted-by":"crossref","first-page":"3913","DOI":"10.1073\/pnas.0810617106","article-title":"Lipocalin 2 promotes breast cancer progression","volume":"106","author":"Yang","year":"2009","journal-title":"Proc Natl Acad Sci U S A"},{"key":"2025102700404654900_ref29","doi-asserted-by":"crossref","first-page":"725","DOI":"10.1007\/s10549-012-2206-2","article-title":"Expression of CXCL14 and its anticancer role in breast cancer","volume":"135","author":"Gu","year":"2012","journal-title":"Breast Cancer Res Treat"},{"key":"2025102700404654900_ref30","doi-asserted-by":"crossref","first-page":"799","DOI":"10.1007\/s10549-012-2018-4","article-title":"Mesothelin, a novel immunotherapy target for triple negative breast cancer","volume":"133","author":"Tchou","year":"2012","journal-title":"Breast Cancer Res Treat"},{"key":"2025102700404654900_ref31","doi-asserted-by":"crossref","first-page":"e70641","DOI":"10.1371\/journal.pone.0070641","article-title":"Silencing MED1 sensitizes breast cancer cells to pure anti-estrogen fulvestrant in vitro and in vivo","volume":"8","author":"Zhang","year":"2013","journal-title":"PloS One"},{"key":"2025102700404654900_ref32","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1007\/s12013-013-9701-x","article-title":"Values of MMP-2 and MMP-9 in tumor tissue of basal-like breast cancer patients","volume":"68","author":"Radenkovic","year":"2014","journal-title":"Cell Biochem Biophys"},{"key":"2025102700404654900_ref33","doi-asserted-by":"crossref","first-page":"3484","DOI":"10.1096\/fj.201601341RRR","article-title":"Different expression levels of DLK1 inversely modulate the oncogenic potential of human MDA-MB-231 breast cancer cells through inhibition of NOTCH1 signaling","volume":"31","author":"Nueda","year":"2017","journal-title":"FASEB J"},{"key":"2025102700404654900_ref34","doi-asserted-by":"crossref","first-page":"390","DOI":"10.1186\/s12859-022-04951-0","article-title":"A pan-cancer analysis of collagen VI family on prognosis, tumor microenvironment, and its potential therapeutic effect","volume":"23","author":"Li","year":"2022","journal-title":"BMC Bioinformatics"},{"key":"2025102700404654900_ref35","doi-asserted-by":"crossref","first-page":"513","DOI":"10.3390\/jpm13030513","article-title":"An angiogenesis-related lncRNA signature is associated with prognosis and tumor immune microenvironment in breast cancer","volume":"13","author":"Gao","year":"2023","journal-title":"J Pers Med"},{"key":"2025102700404654900_ref36","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1186\/s12943-025-02226-9","article-title":"Single-cell RNA sequencing identifies molecular biomarkers predicting late progression to CDK4\/6 inhibition in patients with HR+\/HER2- metastatic breast cancer","volume":"24","author":"Luo","year":"2025","journal-title":"Mol Cancer"},{"key":"2025102700404654900_ref37","doi-asserted-by":"crossref","first-page":"2498","DOI":"10.3390\/cells12202498","article-title":"Progesterone receptor membrane component 1 (PGRMC1) modulates tumour progression, the immune microenvironment and the response to therapy in glioblastoma","volume":"12","author":"Dumitru","year":"2023","journal-title":"Cells."},{"key":"2025102700404654900_ref38","doi-asserted-by":"crossref","first-page":"e315","DOI":"10.1016\/S1470-2045(17)30194-8","article-title":"European Association for Neuro-Oncology (EANO) guideline on the diagnosis and treatment of adult astrocytic and oligodendroglial gliomas","volume":"18","author":"Weller","year":"2017","journal-title":"Lancet Oncol"},{"key":"2025102700404654900_ref39","doi-asserted-by":"crossref","first-page":"1949","DOI":"10.1038\/s41388-017-0077-z","article-title":"Wild-type and mutated IDH1\/2 enzymes and therapy responses","volume":"37","author":"Molenaar","year":"2018","journal-title":"Oncogene."},{"key":"2025102700404654900_ref40","doi-asserted-by":"crossref","first-page":"1117","DOI":"10.1038\/bjc.2016.104","article-title":"Expression of the chemokine CXCL14 in the tumour stroma is an independent marker of survival in breast cancer","volume":"114","author":"Sj\u00f6berg","year":"2016","journal-title":"Br J Cancer"},{"key":"2025102700404654900_ref41","doi-asserted-by":"crossref","first-page":"3702","DOI":"10.1158\/1078-0432.CCR-18-1294","article-title":"A novel ACKR2-dependent role of fibroblast-derived CXCL14 in epithelial-to-mesenchymal transition and metastasis of breast cancer","volume":"25","author":"Sj\u00f6berg","year":"2019","journal-title":"Clin Cancer Res"},{"key":"2025102700404654900_ref42","doi-asserted-by":"crossref","first-page":"9314","DOI":"10.3390\/ijms23169314","article-title":"CXCL14 attenuates triple-negative breast cancer progression by regulating immune profiles of the tumor microenvironment in a T cell-dependent manner","volume":"23","author":"Gibbs","year":"2022","journal-title":"Int J Mol Sci"},{"key":"2025102700404654900_ref43","doi-asserted-by":"crossref","first-page":"592","DOI":"10.1038\/nrc2442","article-title":"Modes of resistance to anti-angiogenic therapy","volume":"8","author":"Bergers","year":"2008","journal-title":"Nat Rev Cancer"},{"key":"2025102700404654900_ref44","first-page":"9240","article-title":"GNNExplainer: Generating explanations for graph neural networks","volume":"32","author":"Ying","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2025102700404654900_ref45","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1186\/s13073-021-00845-7","article-title":"Explaining decisions of graph convolutional neural networks: Patient-specific molecular subnetworks responsible for metastasis prediction in breast cancer","volume":"13","author":"Chereda","year":"2021","journal-title":"Genome Med"},{"key":"2025102700404654900_ref46","article-title":"FastGCN: fast learning with graph convolutional networks via importance sampling","author":"Chen","year":"2020","journal-title":"Int Conf Learn Represent"},{"key":"2025102700404654900_ref47","first-page":"3527","article-title":"Hybrid approach of relation network and localized graph convolutional filtering for breast cancer subtype classification","author":"Rhee","year":"2018","journal-title":"Proceedingsofthe Twenty-Seventh International Joint Conference on Artificial Intelligence"},{"key":"2025102700404654900_ref48","article-title":"Towards gene expression convolutions using gene interaction graphs","author":"Dutil","year":"2018","journal-title":"Int Conf Mach Learn Workshop Comput Biol"},{"key":"2025102700404654900_ref49","doi-asserted-by":"crossref","first-page":"616","DOI":"10.1038\/s41586-023-06139-9","article-title":"Transfer learning enables predictions in network biology","volume":"618","author":"Theodoris","year":"2023","journal-title":"Nature."},{"key":"2025102700404654900_ref50","first-page":"1878","article-title":"Noise injection to control false discoveries in single-cell differential expression","volume":"41","author":"Shah","year":"2023","journal-title":"Nat Biotechnol"}],"container-title":["Briefings in Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/26\/5\/bbaf559\/64951589\/bbaf559.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/26\/5\/bbaf559\/64951589\/bbaf559.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T04:41:00Z","timestamp":1761540060000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bib\/article\/doi\/10.1093\/bib\/bbaf559\/8303424"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,31]]},"references-count":50,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2025,8,31]]}},"URL":"https:\/\/doi.org\/10.1093\/bib\/bbaf559","relation":{},"ISSN":["1467-5463","1477-4054"],"issn-type":[{"value":"1467-5463","type":"print"},{"value":"1477-4054","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2025,9]]},"published":{"date-parts":[[2025,8,31]]},"article-number":"bbaf559"}}