{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T07:16:55Z","timestamp":1784099815824,"version":"3.55.0"},"reference-count":50,"publisher":"Oxford University Press (OUP)","issue":"5","license":[{"start":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T00:00:00Z","timestamp":1757548800000},"content-version":"vor","delay-in-days":11,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62472129"],"award-info":[{"award-number":["62472129"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62473119"],"award-info":[{"award-number":["62473119"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"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>The integration of single-cell RNA sequencing (scRNA-seq) and bulk transcriptomic data has become essential for deciphering the complex heterogeneity of cancer and identifying clinical cancer subtypes. However, the inherent challenges posed by the high dimensionality, sparsity, and noise characteristics of scRNA-seq data have significantly hindered its widespread clinical translation. To address these limitations, we introduce single-cell and bulk transcriptomic graph deep learning, a graph-based deep learning method that synergistically integrates scRNA-seq and bulk transcriptomic data to precisely identify cancer subtypes and predict clinical outcomes. scBGDL constructs sample-specific gene graphs modeling complex gene\u2013gene interactions and cellular relationships. The architecture employs Graph Attention Networks for feature aggregation, MinCutPool layers for dimensionality reduction, and Transformer modules to capture high-order biological dependencies. Independently validated in each of 16 distinct The Cancer Genome Atlas cancer types, scBGDL significantly outperformed existing methods in prognostic accuracy (mean C-index: 0.7060 versus 0.6709 max competitor), demonstrating robustness and generalizability to diverse transcriptional architectures. To demonstrate clinical versatility, we further evaluated scBGDL in three therapeutic contexts using multicenter cohorts: lung adenocarcinoma survival prediction (n\u2009=\u20091099), epithelial ovarian cancer platinum-based chemotherapy response (n\u2009=\u2009762), skin cutaneous melanoma immunotherapy outcome (n\u2009=\u2009305). scBGDL consistently delivered robust risk stratification (log-rank P\u2009&amp;lt;\u20090.05 across cohorts), identified key driver edges, and uncovered clinically relevant biological interpretations. By enabling multimodal data integration and interpretable biological insights, scBGDL advances precision oncology for prognosis prediction, therapy optimization, and biomarker discovery. The source code for scBGDL model is available online (https:\/\/github.com\/NEFLab\/scBGDL).<\/jats:p>","DOI":"10.1093\/bib\/bbaf467","type":"journal-article","created":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T11:36:34Z","timestamp":1755948994000},"source":"Crossref","is-referenced-by-count":8,"title":["Graph-based deep learning for integrating single-cell and bulk transcriptomic data to identify clinical cancer subtypes"],"prefix":"10.1093","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5988-722X","authenticated-orcid":false,"given":"Yixin","family":"Liu","sequence":"first","affiliation":[{"name":"Modern Education Technology Center, Harbin Medical University , 157 Baojian Road, Nangang District, Harbin 150080 ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dandan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Obstetrics and Gynecology, The First Affiliated Hospital of Harbin Medical University , 199 Dazhi Street, Nangang District, Harbin 150007 ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianyu","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Computer and Control Engineering, Northeast Forestry University , 26 Hexing Road, Xiangfang District, Harbin 150040 ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ao","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Computer and Control Engineering, Northeast Forestry University , 26 Hexing Road, Xiangfang District, Harbin 150040 ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7381-2374","authenticated-orcid":false,"given":"Guohua","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Computer and Control Engineering, Northeast Forestry University , 26 Hexing Road, Xiangfang District, Harbin 150040 ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7219-0999","authenticated-orcid":false,"given":"Yuming","family":"Zhao","sequence":"additional","affiliation":[{"name":"College of Computer and Control Engineering, Northeast Forestry University , 26 Hexing Road, Xiangfang District, Harbin 150040 ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2025,9,11]]},"reference":[{"key":"2025091102214788400_ref1","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1016\/j.molcel.2019.05.003","article-title":"Single-cell RNA sequencing in cancer: Lessons learned and emerging challenges","volume":"75","author":"Suva","year":"2019","journal-title":"Mol Cell"},{"key":"2025091102214788400_ref2","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1038\/s41576-019-0093-7","article-title":"Integrative single-cell analysis","volume":"20","author":"Stuart","year":"2019","journal-title":"Nat Rev Genet"},{"key":"2025091102214788400_ref3","doi-asserted-by":"publisher","first-page":"8509","DOI":"10.1200\/JCO.2021.39.15_suppl.8509","article-title":"Signatures of plasticity, metastasis, and immunosuppression in an atlas of human small cell lung cancer","volume":"39","author":"Chan","year":"2021","journal-title":"Cancer Cell"},{"key":"2025091102214788400_ref4","doi-asserted-by":"publisher","first-page":"410","DOI":"10.1038\/s41576-020-0223-2","article-title":"Lineage tracing meets single-cell omics: Opportunities and challenges","volume":"21","author":"Wagner","year":"2020","journal-title":"Nat Rev Genet"},{"key":"2025091102214788400_ref5","doi-asserted-by":"publisher","first-page":"527","DOI":"10.1038\/s41587-021-01091-3","article-title":"Identifying phenotype-associated subpopulations by integrating bulk and single-cell sequencing data","volume":"40","author":"Sun","year":"2022","journal-title":"Nat Biotechnol"},{"key":"2025091102214788400_ref6","doi-asserted-by":"publisher","first-page":"12112","DOI":"10.1093\/nar\/gkac1109","article-title":"scAB detects multiresolution cell states with clinical significance by integrating single-cell genomics and bulk sequencing data","volume":"50","author":"Zhang","year":"2022","journal-title":"Nucleic Acids Res"},{"key":"2025091102214788400_ref7","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1186\/s13073-022-01012-2","article-title":"Diagnostic evidence gauge of single cells (DEGAS): A flexible deep transfer learning framework for prioritizing cells in relation to disease","volume":"14","author":"Johnson","year":"2022","journal-title":"Genome Med"},{"key":"2025091102214788400_ref8","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbad424","article-title":"Identifying phenotype-associated subpopulations through LP_SGL","volume":"25","author":"Li","year":"2023","journal-title":"Brief Bioinform"},{"key":"2025091102214788400_ref9","doi-asserted-by":"publisher","first-page":"3573","DOI":"10.1016\/j.cell.2021.04.048","article-title":"Integrated analysis of multimodal single-cell data","volume":"184","author":"Hao","year":"2021","journal-title":"Cell"},{"key":"2025091102214788400_ref10","doi-asserted-by":"publisher","first-page":"1083","DOI":"10.1038\/nmeth.4463","article-title":"SCENIC: Single-cell regulatory network inference and clustering","volume":"14","author":"Aibar","year":"2017","journal-title":"Nat Methods"},{"key":"2025091102214788400_ref11","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1093\/bib\/bbab024","article-title":"Advances in bulk and single-cell multi-omics approaches for systems biology and precision medicine","author":"Li","year":"2021","journal-title":"Brief Bioinform"},{"key":"2025091102214788400_ref12","doi-asserted-by":"publisher","first-page":"1484","DOI":"10.1038\/s41596-020-0292-x","volume":"15","author":"Efremova","year":"2020","journal-title":"Nat Protoc"},{"key":"2025091102214788400_ref13","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1109\/TNNLS.2020.2978386","article-title":"A comprehensive survey on graph neural networks","volume":"32","author":"Wu","year":"2021","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"2025091102214788400_ref14","doi-asserted-by":"publisher","first-page":"411","DOI":"10.1038\/nbt.4096","article-title":"Integrating single-cell transcriptomic data across different conditions, technologies, and species","volume":"36","author":"Butler","year":"2018","journal-title":"Nat Biotechnol"},{"key":"2025091102214788400_ref15","doi-asserted-by":"publisher","first-page":"108107","DOI":"10.1016\/j.compbiomed.2024.108107","article-title":"Computational identification of DNA damage-relevant lncRNAs for predicting therapeutic efficacy and clinical outcomes in cancer","volume":"171","author":"Liu","year":"2024","journal-title":"Comput Biol Med"},{"key":"2025091102214788400_ref16","doi-asserted-by":"publisher","first-page":"1277","DOI":"10.1038\/s41591-018-0096-5","article-title":"Phenotype molding of stromal cells in the lung tumor microenvironment","volume":"24","author":"Lambrechts","year":"2018","journal-title":"Nat Med"},{"key":"2025091102214788400_ref17","doi-asserted-by":"crossref","first-page":"3039","DOI":"10.1038\/s41467-021-23171-3","article-title":"Evolution of core archetypal phenotypes in progressive high grade serous ovarian cancer","volume":"12","author":"Nath","year":"2021","journal-title":"Nat Commun"},{"key":"2025091102214788400_ref18","doi-asserted-by":"publisher","DOI":"10.1084\/jem.20200920","article-title":"Single-cell analyses identify circulating anti-tumor CD8 T cells and markers for their enrichment","volume":"218","author":"Pauken","year":"2021","journal-title":"J Exp Med"},{"key":"2025091102214788400_ref19","doi-asserted-by":"publisher","first-page":"1916","DOI":"10.1038\/s41591-019-0654-5","article-title":"Integrative molecular and clinical modeling of clinical outcomes to PD1 blockade in patients with metastatic melanoma","volume":"25","author":"Liu","year":"2019","journal-title":"Nat Med"},{"key":"2025091102214788400_ref20","doi-asserted-by":"publisher","first-page":"238","DOI":"10.1016\/j.ccell.2019.01.003","article-title":"Distinct immune cell populations define response to anti-PD-1 monotherapy and anti-PD-1\/anti-CTLA-4 combined therapy","volume":"35","author":"Gide","year":"2019","journal-title":"Cancer Cell"},{"key":"2025091102214788400_ref21","first-page":"aad8366","article-title":"Erratum for the Report Genomic correlates of response to CTLA-4 blockade in metastatic melanoma","volume":"350","author":"Van Allen","year":"2016","journal-title":"Science"},{"key":"2025091102214788400_ref22","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1016\/j.cell.2016.02.065","article-title":"Genomic and transcriptomic features of response to anti-PD-1 therapy in metastatic melanoma","volume":"165","author":"Hugo","year":"2016","journal-title":"Cell"},{"key":"2025091102214788400_ref23","doi-asserted-by":"publisher","first-page":"934","DOI":"10.1016\/j.cell.2017.09.028","article-title":"Tumor and microenvironment evolution during immunotherapy with nivolumab","volume":"171","author":"Riaz","year":"2017","journal-title":"Cell"},{"key":"2025091102214788400_ref24","doi-asserted-by":"publisher","first-page":"1073","DOI":"10.1136\/bmj.328.7447.1073","article-title":"The logrank test","volume":"328","author":"Bland","year":"2004","journal-title":"BMJ"},{"key":"2025091102214788400_ref25","doi-asserted-by":"publisher","first-page":"361","DOI":"10.1002\/(SICI)1097-0258(19960229)15:4&lt;361::AID-SIM168&gt;3.0.CO;2-4","article-title":"Multivariable prognostic models: Issues in developing models, evaluating assumptions and adequacy, and measuring and reducing errors","volume":"15","author":"Harrell","year":"1996","journal-title":"Stat Med"},{"key":"2025091102214788400_ref26","doi-asserted-by":"publisher","first-page":"4879","DOI":"10.1158\/1078-0432.CCR-13-0542","article-title":"A 26-gene hypoxia signature predicts benefit from hypoxia-modifying therapy in laryngeal cancer but not bladder cancer","volume":"19","author":"Eustace","year":"2013","journal-title":"Clin Cancer Res"},{"key":"2025091102214788400_ref27","doi-asserted-by":"publisher","first-page":"9020","DOI":"10.1073\/pnas.1818210116","article-title":"Cancer stemness, intratumoral heterogeneity, and immune response across cancers","volume":"116","author":"Miranda","year":"2019","journal-title":"Proc Natl Acad Sci U S A"},{"key":"2025091102214788400_ref28","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1038\/nrc1802","article-title":"Common markers of proliferation","volume":"6","author":"Whitfield","year":"2006","journal-title":"Nat Rev Cancer"},{"key":"2025091102214788400_ref29","doi-asserted-by":"publisher","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 U S A"},{"key":"2025091102214788400_ref30","doi-asserted-by":"publisher","first-page":"399","DOI":"10.1016\/j.jtho.2021.10.013","article-title":"Diminished efficacy of programmed death-(ligand)1 inhibition in STK11- and KEAP1-mutant lung adenocarcinoma is affected by KRAS mutation status","volume":"17","author":"Ricciuti","year":"2022","journal-title":"J Thorac Oncol"},{"key":"2025091102214788400_ref31","doi-asserted-by":"publisher","first-page":"e2313137120","DOI":"10.1073\/pnas.2313137120","article-title":"SOS1 and KSR1 modulate MEK inhibitor responsiveness to target resistant cell populations based on PI3K and KRAS mutation status","volume":"120","author":"Daley","year":"2023","journal-title":"Proc Natl Acad Sci U S A"},{"key":"2025091102214788400_ref32","doi-asserted-by":"publisher","first-page":"282","DOI":"10.1038\/s41419-024-06635-4","article-title":"FBXO32-mediated degradation of PTEN promotes lung adenocarcinoma progression","volume":"15","author":"Wu","year":"2024","journal-title":"Cell Death Dis"},{"key":"2025091102214788400_ref33","author":"Kuhlmann-Hogan","year":"2024"},{"key":"2025091102214788400_ref34","doi-asserted-by":"crossref","first-page":"e4340","DOI":"10.1016\/j.cell.2021.07.016","article-title":"A proteogenomic portrait of lung squamous cell carcinoma","volume":"184","author":"Satpathy","year":"2021","journal-title":"Cell"},{"key":"2025091102214788400_ref35","doi-asserted-by":"publisher","first-page":"186","DOI":"10.1016\/j.ccr.2012.12.020","article-title":"Integrated analyses identify a master microRNA regulatory network for the mesenchymal subtype in serous ovarian cancer","volume":"23","author":"Yang","year":"2013","journal-title":"Cancer Cell"},{"key":"2025091102214788400_ref36","doi-asserted-by":"publisher","first-page":"200","DOI":"10.1016\/j.ygyno.2013.03.019","article-title":"Notch3 induces epithelial-mesenchymal transition and attenuates carboplatin-induced apoptosis in ovarian cancer cells","volume":"130","author":"Gupta","year":"2013","journal-title":"Gynecol Oncol"},{"key":"2025091102214788400_ref37","doi-asserted-by":"publisher","first-page":"878","DOI":"10.1038\/s41577-024-01061-1","article-title":"CD28 co-stimulation: Novel insights and applications in cancer immunotherapy","volume":"24","author":"Lotze","year":"2024","journal-title":"Nat Rev Immunol"},{"key":"2025091102214788400_ref38","doi-asserted-by":"crossref","first-page":"eadj5097","DOI":"10.1126\/sciimmunol.adj5097","article-title":"Cancer immunotherapy via synergistic coactivation of myeloid receptors CD40 and Dectin-1","volume":"8","author":"Wattenberg","year":"2023","journal-title":"Sci Immunol"},{"key":"2025091102214788400_ref39","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1136\/jitc-2023-007305","article-title":"Divergent tumor and immune cell reprogramming underlying immunotherapy response and immune-related adverse events in lung squamous cell carcinoma","volume":"11","author":"Chen","year":"2023","journal-title":"J Immunother Cancer"},{"key":"2025091102214788400_ref40","doi-asserted-by":"publisher","first-page":"1247","DOI":"10.1038\/s41467-023-36892-4","article-title":"CDK4\/6 inhibition triggers ICAM1-driven immune response and sensitizes LKB1 mutant lung cancer to immunotherapy","volume":"14","author":"Bai","year":"2023","journal-title":"Nat Commun"},{"key":"2025091102214788400_ref41","doi-asserted-by":"publisher","first-page":"116","DOI":"10.1186\/s13045-020-00950-x","article-title":"HMGB1 in inflammation and cancer","volume":"13","author":"Wang","year":"2020","journal-title":"J Hematol Oncol"},{"key":"2025091102214788400_ref42","doi-asserted-by":"publisher","first-page":"1105","DOI":"10.1016\/j.ajpath.2019.02.003","article-title":"MRPL35 is up-regulated in colorectal cancer and regulates colorectal cancer cell growth and apoptosis","volume":"189","author":"Zhang","year":"2019","journal-title":"Am J Pathol"},{"key":"2025091102214788400_ref43","doi-asserted-by":"publisher","first-page":"162","DOI":"10.1186\/s13046-023-02734-w","article-title":"Cellular hierarchy framework based on single-cell\/multi-patient sample sequencing reveals metabolic biomarker PYGL as a therapeutic target for HNSCC","volume":"42","author":"Guan","year":"2023","journal-title":"J Exp Clin Cancer Res"},{"key":"2025091102214788400_ref44","doi-asserted-by":"publisher","first-page":"200","DOI":"10.1007\/s12022-015-9373-8","article-title":"Latent pathways identification by microarray expression profiles in thyroid-associated ophthalmopathy patients","volume":"26","author":"Zhao","year":"2015","journal-title":"Endocr Pathol"},{"key":"2025091102214788400_ref45","doi-asserted-by":"publisher","first-page":"e1632","DOI":"10.1002\/ctm2.1632","article-title":"PROM2 overexpression induces metastatic potential through epithelial-to-mesenchymal transition and ferroptosis resistance in human cancers","volume":"14","author":"Paris","year":"2024","journal-title":"Clin Transl Med"},{"key":"2025091102214788400_ref46","doi-asserted-by":"publisher","first-page":"101928","DOI":"10.1016\/j.redox.2021.101928","article-title":"PARP inhibition promotes ferroptosis via repressing SLC7A11 and synergizes with ferroptosis inducers in BRCA-proficient ovarian cancer","volume":"42","author":"Hong","year":"2021","journal-title":"Redox Biol"},{"key":"2025091102214788400_ref47","doi-asserted-by":"publisher","first-page":"e04436","DOI":"10.1126\/sciadv.adw2756","article-title":"Exosomal CMTM4 induces immunosuppressive macrophages to promote ovarian cancer progression and attenuate anti-PD-1 immunotherapy","volume":"30","author":"Yin","year":"2025","journal-title":"Adv Sci (Weinh)"},{"key":"2025091102214788400_ref48","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1186\/s12964-020-00547-4","article-title":"Interleukin-12 elicits a non-canonical response in B16 melanoma cells to enhance survival","volume":"18","author":"Byrne-Hoffman","year":"2020","journal-title":"Cell Commun Signal"},{"key":"2025091102214788400_ref49","doi-asserted-by":"publisher","first-page":"1285","DOI":"10.1016\/j.immuni.2023.05.003","article-title":"Human skin-resident CD8(+) T cells require RUNX2 and RUNX3 for induction of cytotoxicity and expression of the integrin CD49a","volume":"56","author":"Zitti","year":"2023","journal-title":"Immunity"},{"key":"2025091102214788400_ref50","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1016\/j.gendis.2023.02.047","article-title":"C19MC miRNA-520G induces SP100 antiviral gene transcription and inhibits melanin production in skin cutaneous melanoma","volume":"11","author":"Jinesh","year":"2024","journal-title":"Genes Dis"}],"container-title":["Briefings in Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/26\/5\/bbaf467\/64238020\/bbaf467.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/26\/5\/bbaf467\/64238020\/bbaf467.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T06:21:57Z","timestamp":1757571717000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bib\/article\/doi\/10.1093\/bib\/bbaf467\/8250821"}},"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\/bbaf467","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":"bbaf467"}}