{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T07:44:27Z","timestamp":1767339867539,"version":"3.44.0"},"reference-count":45,"publisher":"Oxford University Press (OUP)","issue":"4","license":[{"start":{"date-parts":[[2025,8,15]],"date-time":"2025-08-15T00:00:00Z","timestamp":1755216000000},"content-version":"vor","delay-in-days":45,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100023236","name":"International Institute of Information Technology, Hyderabad","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100023236","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,7,2]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Cancer remains a leading cause of morbidity and mortality worldwide. Despite advances in genomics, identifying clinically relevant subtypes of cancer remains challenging due to its complex and heterogeneous nature. In this work, we propose DeepGraphMut (DGM), a novel graph-based deep-learning pipeline that integrates somatic mutation data with protein\u2013protein interaction (PPI) networks. By employing a graph autoencoder with a graph attention layer and a node-level attention decoder, DGM generates patient-specific clinically relevant encodings for unsupervised and supervised tasks. We demonstrate the effectiveness of DGM across 16 cancer types comprising of 7352 samples from The Cancer Genome Atlas (TCGA). Unsupervised clustering reveals distinct subtypes with significant survival differences in 11 cancer types. In supervised analysis using a Cox regression model, DGM demonstrates excellent performance in predicting survival outcomes, achieving a high concordance index (C-index) value in the range of 0.7 across most cancers, underscoring its robust predictive performance using only somatic mutation data. Furthermore, DGM outperforms its lightweight variant and network-based stratification methods in both unsupervised and supervised analyses. In summary, this study presents a promising approach for cancer subtype identification and prognosis, especially in resource-limited settings where multi-omics data may not be readily available. By leveraging the strengths of graph learning and network biology, DGM offers a valuable tool for advancing personalized medicine.<\/jats:p>","DOI":"10.1093\/bib\/bbaf409","type":"journal-article","created":{"date-parts":[[2025,7,29]],"date-time":"2025-07-29T11:30:41Z","timestamp":1753788641000},"source":"Crossref","is-referenced-by-count":2,"title":["DeepGraphMut: a graph-based deep learning method for cancer prognosis using somatic mutation profile"],"prefix":"10.1093","volume":"26","author":[{"given":"Aswin","family":"Jose","sequence":"first","affiliation":[{"name":"Centre for Computational Natural Sciences and Bioinformatics , IIIT Hyderabad, Prof. C R Rao Road, Gachibowli, Hyderabad 500032,","place":["India"]}]},{"given":"Akansha","family":"Srivastava","sequence":"additional","affiliation":[{"name":"Centre for Computational Natural Sciences and Bioinformatics , IIIT Hyderabad, Prof. C R Rao Road, Gachibowli, Hyderabad 500032,","place":["India"]}]},{"given":"Ariba","family":"Ansari","sequence":"additional","affiliation":[{"name":"Centre for Computational Natural Sciences and Bioinformatics , IIIT Hyderabad, Prof. C R Rao Road, Gachibowli, Hyderabad 500032,","place":["India"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2968-498X","authenticated-orcid":false,"given":"Palakkad Krishnanunni","family":"Vinod","sequence":"additional","affiliation":[{"name":"Centre for Computational Natural Sciences and Bioinformatics , IIIT Hyderabad, Prof. C R Rao Road, Gachibowli, Hyderabad 500032,","place":["India"]}]}],"member":"286","published-online":{"date-parts":[[2025,8,15]]},"reference":[{"key":"2025081501413464300_ref1","doi-asserted-by":"publisher","first-page":"229","DOI":"10.3322\/caac.21834","article-title":"Global cancer statistics 2022: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries","volume":"74","author":"Bray","year":"2024","journal-title":"CA Cancer J Clin"},{"key":"2025081501413464300_ref2","doi-asserted-by":"crossref","first-page":"980","DOI":"10.3390\/cancers12040980","article-title":"Cancer classification at the crossroads","volume":"12","author":"Carbone","year":"2020","journal-title":"Cancers"},{"key":"2025081501413464300_ref3","doi-asserted-by":"publisher","first-page":"659","DOI":"10.1038\/nrc2193","article-title":"Modelling breast cancer: one size does not fit all","volume":"7","author":"Vargo-Gogola","year":"2007","journal-title":"Nat Rev Cancer"},{"key":"2025081501413464300_ref4","doi-asserted-by":"publisher","first-page":"87","DOI":"10.9734\/jpri\/2021\/v33i28A31513","article-title":"One size does not fit all: an overview of personalized treatment in cancer","author":"Kulavi","year":"2021","journal-title":"J Pharm Res Int"},{"key":"2025081501413464300_ref5","volume-title":"The Cell: A Molecular Approach","author":"Cooper","year":"2000"},{"key":"2025081501413464300_ref6","doi-asserted-by":"publisher","first-page":"586","DOI":"10.1016\/j.molcel.2015.05.004","article-title":"High-throughput sequencing technologies","volume":"58","author":"Reuter","year":"2015","journal-title":"Mol Cell"},{"key":"2025081501413464300_ref7","doi-asserted-by":"publisher","first-page":"6660","DOI":"10.1158\/0008-5472.CAN-09-1133","article-title":"Cancer-specific high-throughput annotation of somatic mutations: computational prediction of driver missense mutations","volume":"69","author":"Carter","year":"2009","journal-title":"Cancer Res"},{"key":"2025081501413464300_ref8","doi-asserted-by":"publisher","first-page":"101","DOI":"10.1038\/nrg1272","article-title":"Network biology: understanding the cell\u2019s functional organization","volume":"5","author":"Barabasi","year":"2004","journal-title":"Nat Rev Genet"},{"key":"2025081501413464300_ref9","doi-asserted-by":"publisher","first-page":"381","DOI":"10.1016\/B978-0-323-89775-4.00024-9","article-title":"Network biology and applications","author":"Redhu","year":"2022","journal-title":"Bioinformatics"},{"key":"2025081501413464300_ref10","doi-asserted-by":"publisher","first-page":"797","DOI":"10.3390\/genes10100797","article-title":"Biological network approaches and applications in rare disease studies","volume":"10","author":"Zhang","year":"2019","journal-title":"Genes"},{"key":"2025081501413464300_ref11","doi-asserted-by":"publisher","first-page":"1108","DOI":"10.1038\/nmeth.2651","article-title":"Network-based stratification of tumor mutations","volume":"10","author":"Hofree","year":"2013","journal-title":"Nat Methods"},{"key":"2025081501413464300_ref12","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/1471-2164-16-S7-S7","article-title":"Network-based stratification analysis of 13 major cancer types using mutations in panels of cancer genes","volume":"16","author":"Zhong","year":"2015","journal-title":"BMC Genomics"},{"key":"2025081501413464300_ref13","doi-asserted-by":"publisher","first-page":"2859","DOI":"10.1093\/bioinformatics\/bty186","article-title":"pyNBS: a python implementation for network-based stratification of tumor mutations","volume":"34","author":"Huang","year":"2018","journal-title":"Bioinformatics"},{"key":"2025081501413464300_ref14","doi-asserted-by":"crossref","first-page":"488641","DOI":"10.3389\/fgene.2020.00106","article-title":"Network diffusion promotes the integrative analysis of multiple omics","volume":"11","author":"Di Nanni","year":"2020","journal-title":"Front Genet"},{"key":"2025081501413464300_ref15","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1093\/bioinformatics\/btaa1099","article-title":"A network-based deep learning methodology for stratification of tumor mutations","volume":"37","author":"Liu","year":"2021","journal-title":"Bioinformatics"},{"key":"2025081501413464300_ref16","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1109\/TAI.2021.3076021","article-title":"Graph learning: a survey","volume":"2","author":"Xia","year":"2021","journal-title":"IEEE Trans Artif Intell"},{"key":"2025081501413464300_ref17","doi-asserted-by":"publisher","first-page":"1199087","DOI":"10.3389\/fgene.2023.1199087","article-title":"A review of multi-omics data integration through deep learning approaches for disease diagnosis, prognosis, and treatment","volume":"14","author":"Wekesa","year":"2023","journal-title":"Front Genet"},{"key":"2025081501413464300_ref18","doi-asserted-by":"publisher","first-page":"4779","DOI":"10.1093\/bioinformatics\/btab535","article-title":"Cancer subtype identification by consensus guided graph autoencoders","volume":"37","author":"Liang","year":"2021","journal-title":"Bioinformatics"},{"key":"2025081501413464300_ref19","doi-asserted-by":"publisher","first-page":"10220","DOI":"10.3390\/ijms231810220","article-title":"omicsGAT: graph attention network for cancer subtype analyses","volume":"23","author":"Baul","year":"2022","journal-title":"Int J Mol Sci"},{"key":"2025081501413464300_ref20","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1016\/j.cels.2018.03.001","article-title":"Systematic evaluation of molecular networks for discovery of disease genes","volume":"6","author":"Huang","year":"2018","journal-title":"Cell Syst"},{"key":"2025081501413464300_ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098061","article-title":"struc2vec: learning node representations from structural identity","volume-title":"Proceedings of the 23rd ACM SIGKDD international conference on knowledge discovery and data mining","author":"Ribeiro"},{"key":"2025081501413464300_ref22","doi-asserted-by":"publisher","first-page":"5637","DOI":"10.1016\/j.csbj.2021.10.013","article-title":"Multiomics analysis of tumor mutational burden across cancer types","volume":"19","author":"Li","year":"2021","journal-title":"Comput Struct Biotechnol J"},{"key":"2025081501413464300_ref23","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1186\/s13073-017-0424-2","article-title":"Analysis of 100,000 human cancer genomes reveals the landscape of tumor mutational burden","volume":"9","author":"Chalmers","year":"2017","journal-title":"Genome Med"},{"key":"2025081501413464300_ref24","doi-asserted-by":"publisher","first-page":"1390","DOI":"10.3390\/curroncol29030117","article-title":"Urothelial bladder carcinomas with high tumor mutation burden have a better prognosis and targetable molecular defects beyond immunotherapies","volume":"29","author":"Voutsadakis","year":"2022","journal-title":"Curr Oncol"},{"key":"2025081501413464300_ref25","article-title":"A systematic review and meta-analysis of the impact of tumour mutational burden on survival outcomes in solid tumours"},{"key":"2025081501413464300_ref26","doi-asserted-by":"publisher","first-page":"1184","DOI":"10.1186\/s12885-019-6384-8","article-title":"EGFR mutation: novel prognostic factor associated with immune infiltration in lower-grade glioma; an exploratory study","volume":"19","author":"Hao","year":"2019","journal-title":"BMC Cancer"},{"key":"2025081501413464300_ref27","doi-asserted-by":"publisher","first-page":"297","DOI":"10.3390\/cancers10090297","article-title":"The p53 pathway in glioblastoma","volume":"10","author":"Zhang","year":"2018","journal-title":"Cancers"},{"key":"2025081501413464300_ref28","doi-asserted-by":"publisher","first-page":"i446","DOI":"10.1093\/bioinformatics\/btz342","article-title":"Deep learning with multimodal representation for pancancer prognosis prediction","volume":"35","author":"Cheerla","year":"2019","journal-title":"Bioinformatics"},{"key":"2025081501413464300_ref29","doi-asserted-by":"publisher","first-page":"1109","DOI":"10.1056\/NEJMp1607591","article-title":"Toward a shared vision for cancer genomic data","volume":"375","author":"Grossman","year":"2016","journal-title":"N Eng J Med"},{"key":"2025081501413464300_ref30","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1038\/nmeth.3252","article-title":"Orchestrating high-throughput genomic analysis with bioconductor","volume":"12","author":"Huber","year":"2015","journal-title":"Nat Methods"},{"key":"2025081501413464300_ref31","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13059-018-1612-0","article-title":"The network of cancer genes (NCG): a comprehensive catalogue of known and candidate cancer genes from cancer sequencing screens","volume":"20","author":"Repana","year":"2019","journal-title":"Genome Biol"},{"key":"2025081501413464300_ref32","doi-asserted-by":"publisher","first-page":"1548","DOI":"10.24963\/ijcai.2021\/214","article-title":"Masked label prediction: unified message passing model for semi-supervised classification","volume-title":"Proceedings of the 30th International Joint Conference on Artificial Intelligence","author":"Shi"},{"key":"2025081501413464300_ref33","article-title":"Inductive representation learning on large graphs","volume-title":"NIPS'17: Proceedings of the 31st Conference on Neural Information Processing Systems","author":"Hamilton","year":"2017"},{"key":"2025081501413464300_ref34","article-title":"GraphNorm: a principled approach to accelerating graph neural network training","volume-title":"ICML'21: Proceedings of the 38th International Conference on Machine Learning","author":"Cai"},{"key":"2025081501413464300_ref35","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1611.07308","article-title":"Variational graph auto-encoders.","author":"Kipf","year":"2016"},{"key":"2025081501413464300_ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324","article-title":"Focal loss for dense object detection","volume-title":"Proceedings of the IEEE international conference on computer vision","author":"Lin"},{"key":"2025081501413464300_ref37","article-title":"On the bottleneck of graph neural networks and its practical implications","volume-title":"International Conference on Learning Representations","author":"Alon","year":"2021"},{"key":"2025081501413464300_ref38","doi-asserted-by":"publisher","first-page":"3336","DOI":"10.1016\/j.eswa.2008.01.039","article-title":"A simple and fast algorithm for K-medoids clustering","volume":"36","author":"Park","year":"2009","journal-title":"Expert Syst Appl"},{"key":"2025081501413464300_ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-30164-8_425","article-title":"K-means clustering","author":"Jin","year":"2011","journal-title":"Encyclopedia of Machine Learning"},{"key":"2025081501413464300_ref40","first-page":"583","article-title":"Cluster ensembles\u2014a knowledge reuse framework for combining multiple partitions","volume":"3","author":"Strehl","year":"2002","journal-title":"J Mach Learn Res"},{"key":"2025081501413464300_ref41","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1016\/0377-0427(87)90125-7","article-title":"Silhouettes: a graphical aid to the interpretation and validation of cluster analysis","volume":"20","author":"Rousseeuw","year":"1987","journal-title":"J Comput Appl Math"},{"key":"2025081501413464300_ref42","doi-asserted-by":"publisher","first-page":"457","DOI":"10.1080\/01621459.1958.10501452","article-title":"Nonparametric estimation from incomplete observations","volume":"53","author":"Kaplan","year":"1958","journal-title":"J Am Stat Assoc"},{"key":"2025081501413464300_ref43","doi-asserted-by":"publisher","first-page":"1317","DOI":"10.21105\/joss.01317","article-title":"Lifelines: survival analysis in python","volume":"4","author":"Davidson-Pilon","year":"2019","journal-title":"J Open Source Software"},{"key":"2025081501413464300_ref44","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1111\/j.2517-6161.1972.tb00899.x","article-title":"Regression models and life-tables","volume":"34","author":"Cox","year":"1972","journal-title":"J R Stat Soc B Methodol"},{"key":"2025081501413464300_ref45","doi-asserted-by":"publisher","DOI":"10.1145\/2623330.2623732","article-title":"DeepWalk: online learning of social representations","volume-title":"Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining","author":"Perozzi"}],"container-title":["Briefings in Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/26\/4\/bbaf409\/64054749\/bbaf409.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/26\/4\/bbaf409\/64054749\/bbaf409.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,15]],"date-time":"2025-08-15T05:41:43Z","timestamp":1755236503000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bib\/article\/doi\/10.1093\/bib\/bbaf409\/8235626"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7]]},"references-count":45,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,7,2]]}},"URL":"https:\/\/doi.org\/10.1093\/bib\/bbaf409","relation":{},"ISSN":["1467-5463","1477-4054"],"issn-type":[{"value":"1467-5463","type":"print"},{"value":"1477-4054","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2025,7]]},"published":{"date-parts":[[2025,7]]},"article-number":"bbaf409"}}