{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T19:37:41Z","timestamp":1782848261761,"version":"3.54.5"},"reference-count":42,"publisher":"Oxford University Press (OUP)","issue":"11","license":[{"start":{"date-parts":[[2023,11,14]],"date-time":"2023-11-14T00:00:00Z","timestamp":1699920000000},"content-version":"vor","delay-in-days":13,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,11,1]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec><jats:title>Motivation<\/jats:title><jats:p>Common human diseases result from the interplay of genes and their biologically associated pathways. Genetic pathway analyses provide more biological insight as compared to conventional gene-based analysis. In this article, we propose a framework combining genetic data into pathway structure and using an ensemble of convolutional neural networks (CNNs) along with a Canonical Correlation Regularizer layer for comprehensive prediction of disease risk. The novelty of our approach lies in our two-step framework: (i) utilizing the CNN\u2019s effectiveness to extract the complex gene associations within individual genetic pathways and (ii) fusing features from ensemble of CNNs through Canonical Correlation Regularization layer to incorporate the interactions between pathways which share common genes. During prediction, we also address the important issues of interpretability of neural network models, and identifying the pathways and genes playing an important role in prediction.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>Implementation of our methodology into three real cancer genetic datasets for different prediction tasks validates our model\u2019s generalizability and robustness. Comparing with conventional models, our methodology provides consistently better performance with AUC improvement of 11% on predicting early\/late-stage kidney cancer, 10% on predicting kidney versus liver cancer type and 7% on predicting survival status in ovarian cancer as compared to the next best conventional machine learning model. The robust performance of our deep learning algorithm indicates that disease prediction using neural networks in multiple functionally related genes across different pathways improves genetic data-based prediction and understanding molecular mechanisms of diseases.<\/jats:p><\/jats:sec><jats:sec><jats:title>Availability and implementation<\/jats:title><jats:p>https:\/\/github.com\/divya031090\/ReGeNNe.<\/jats:p><\/jats:sec>","DOI":"10.1093\/bioinformatics\/btad679","type":"journal-article","created":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T22:19:04Z","timestamp":1699913944000},"source":"Crossref","is-referenced-by-count":13,"title":["ReGeNNe: genetic pathway-based deep neural network using canonical correlation regularizer for disease prediction"],"prefix":"10.1093","volume":"39","author":[{"given":"Divya","family":"Sharma","sequence":"first","affiliation":[{"name":"Biostatistics Department, Princess Margaret Cancer Center, University Health Network , Toronto, ON M5G2C4, Canada"},{"name":"Division of Biostatistics, Dalla Lana School of Public Health, University of Toronto , Toronto, ON M5T 3M7, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Xu","sequence":"additional","affiliation":[{"name":"Biostatistics Department, Princess Margaret Cancer Center, University Health Network , Toronto, ON M5G2C4, Canada"},{"name":"Division of Biostatistics, Dalla Lana School of Public Health, University of Toronto , Toronto, ON M5T 3M7, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2023,11,14]]},"reference":[{"key":"2023112311355586900_btad679-B1","doi-asserted-by":"crossref","first-page":"392","DOI":"10.1093\/bioinformatics\/btp630","article-title":"Robust biomarker identification for cancer diagnosis with ensemble feature selection methods","volume":"26","author":"Abeel","year":"2010","journal-title":"Bioinformatics"},{"key":"2023112311355586900_btad679-B2","doi-asserted-by":"crossref","first-page":"e0208626","DOI":"10.1371\/journal.pone.0208626","article-title":"Identifying disease genes using machine learning and gene functional similarities, assessed through gene ontology","volume":"13","author":"Asif","year":"2018","journal-title":"PLoS One"},{"key":"2023112311355586900_btad679-B3","doi-asserted-by":"crossref","first-page":"bbaa303","DOI":"10.1093\/bib\/bbaa303","article-title":"Recent advances in network-based methods for disease gene prediction","volume":"22","author":"Ata","year":"2021","journal-title":"Brief Bioinform"},{"key":"2023112311355586900_btad679-B4","doi-asserted-by":"crossref","first-page":"1962","DOI":"10.1109\/TNN.2009.2034144","article-title":"Regularized negative correlation learning for neural network ensembles","volume":"20","author":"Chen","year":"2009","journal-title":"IEEE Trans Neural Netw"},{"key":"2023112311355586900_btad679-B5","doi-asserted-by":"crossref","first-page":"331","DOI":"10.1186\/s12935-020-01405-6","article-title":"Identifying the novel key genes in renal cell carcinoma by bioinformatics analysis and cell experiments","volume":"20","author":"Chen","year":"2020","journal-title":"Cancer Cell Int"},{"key":"2023112311355586900_btad679-B6","doi-asserted-by":"crossref","first-page":"E1","DOI":"10.1111\/hepr.12459","article-title":"New molecularly targeted therapies against advanced hepatocellular carcinoma: from molecular pathogenesis to clinical trials and future directions","volume":"45","author":"Chuma","year":"2015","journal-title":"Hepatol Res"},{"key":"2023112311355586900_btad679-B7","doi-asserted-by":"crossref","first-page":"179","DOI":"10.1038\/s41586-019-1879-7","article-title":"A brief history of human disease genetics","volume":"577","author":"Claussnitzer","year":"2020","journal-title":"Nature"},{"key":"2023112311355586900_btad679-B8","doi-asserted-by":"crossref","first-page":"S5","DOI":"10.1002\/gepi.20642","article-title":"Brief review of regression-based and machine learning methods in genetic epidemiology: the genetic analysis workshop 17 experience","volume":"35","author":"Dasgupta","year":"2011","journal-title":"Genet Epidemiol"},{"key":"2023112311355586900_btad679-B9","doi-asserted-by":"crossref","first-page":"2595","DOI":"10.1242\/dev.147397","article-title":"Three-dimensional structural analysis reveals a Cdk5-mediated kinase Cascade regulating hepatic biliary network branching in zebrafish","volume":"144","author":"Dimri","year":"2017","journal-title":"Development"},{"key":"2023112311355586900_btad679-B10","doi-asserted-by":"crossref","first-page":"491","DOI":"10.3390\/cancers12020491","article-title":"Molecular signaling pathways and therapeutic targets in hepatocellular carcinoma","volume":"12","author":"Dimri","year":"2020","journal-title":"Cancers (Basel)"},{"key":"2023112311355586900_btad679-B11","doi-asserted-by":"crossref","first-page":"4727","DOI":"10.1096\/fj.201701465RR","article-title":"The tumor secretory factor zag promotes white adipose tissue browning and energy wasting","volume":"32","author":"Elattar","year":"2018","journal-title":"FASEB J"},{"key":"2023112311355586900_btad679-B12","doi-asserted-by":"crossref","first-page":"348","DOI":"10.1038\/s41586-021-03922-4","article-title":"Biologically informed deep neural network for prostate cancer discovery","volume":"598","author":"Elmarakeby","year":"2021","journal-title":"Nature"},{"key":"2023112311355586900_btad679-B13","doi-asserted-by":"crossref","first-page":"423","DOI":"10.1038\/nature06758","article-title":"Genetics of gene expression and its effect on disease","volume":"452","author":"Emilsson","year":"2008","journal-title":"Nature"},{"key":"2023112311355586900_btad679-B14","volume-title":"Deep Learning","author":"Goodfellow","year":"2016"},{"key":"2023112311355586900_btad679-B15","first-page":"2177","article-title":"Regularizing deep neural networks with an ensemble-based decorrelation method","volume":"1","author":"Gu","year":"2018","journal-title":"IJCAI"},{"key":"2023112311355586900_btad679-B16","doi-asserted-by":"crossref","first-page":"845","DOI":"10.1038\/modpathol.2015.6","article-title":"Tceb1-mutated renal cell carcinoma: a distinct genomic and morphological subtype","volume":"28","author":"Hakimi","year":"2015","journal-title":"Mod Pathol"},{"key":"2023112311355586900_btad679-B17","doi-asserted-by":"crossref","first-page":"283","DOI":"10.1586\/14737140.8.2.283","article-title":"mtor pathway in renal cell carcinoma","volume":"8","author":"Hanna","year":"2008","journal-title":"Expert Rev Anticancer Ther"},{"key":"2023112311355586900_btad679-B18","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1080\/00401706.1970.10488634","article-title":"Ridge regression: biased estimation for nonorthogonal problems","volume":"12","author":"Hoerl","year":"1970","journal-title":"Technometrics"},{"key":"2023112311355586900_btad679-B19","doi-asserted-by":"crossref","first-page":"162","DOI":"10.1007\/978-1-4612-4380-9_14","volume-title":"Breakthroughs in Statistics","author":"Hotelling","year":"1992"},{"key":"2023112311355586900_btad679-B20","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1186\/s12920-018-0349-7","article-title":"Integrative pathway-based survival prediction utilizing the interaction between gene expression and dna methylation in breast cancer","volume":"11","author":"Kim","year":"2018","journal-title":"BMC Med Genomics"},{"key":"2023112311355586900_btad679-B21","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","volume":"25","author":"Krizhevsky","year":"2012","journal-title":"Adv Neural Inf Process Syst"},{"key":"2023112311355586900_btad679-B22","doi-asserted-by":"crossref","first-page":"4752","DOI":"10.1158\/0008-5472.CAN-13-3531","article-title":"Antitumor effects in hepatocarcinoma of isoform-selective inhibition of hdac2","volume":"74","author":"Lee","year":"2014","journal-title":"Cancer Res"},{"key":"2023112311355586900_btad679-B23","first-page":"18","article-title":"Classification and regression by randomforest","volume":"2","author":"Liaw","year":"2002","journal-title":"R News"},{"key":"2023112311355586900_btad679-B24","doi-asserted-by":"crossref","first-page":"245","DOI":"10.1186\/1471-2105-14-245","article-title":"Group sparse canonical correlation analysis for genomic data integration","volume":"14","author":"Lin","year":"2013","journal-title":"BMC Bioinformatics"},{"key":"2023112311355586900_btad679-B25","doi-asserted-by":"crossref","first-page":"539","DOI":"10.1038\/s41585-019-0211-5","article-title":"The cancer genome atlas of renal cell carcinoma: findings and clinical implications","volume":"16","author":"Linehan","year":"2019","journal-title":"Nat Rev Urol"},{"key":"2023112311355586900_btad679-B26","doi-asserted-by":"crossref","first-page":"400","DOI":"10.1016\/j.cell.2018.02.052","article-title":"An integrated tcga pan-cancer clinical data resource to drive high-quality survival outcome analytics","volume":"173","author":"Liu","year":"2018","journal-title":"Cell"},{"key":"2023112311355586900_btad679-B27","doi-asserted-by":"crossref","first-page":"i60","DOI":"10.1093\/bioinformatics\/btu269","article-title":"Inductive matrix completion for predicting gene\u2013disease associations","volume":"30","author":"Natarajan","year":"2014","journal-title":"Bioinformatics"},{"key":"2023112311355586900_btad679-B28","doi-asserted-by":"crossref","first-page":"646","DOI":"10.1016\/j.eururo.2015.08.007","article-title":"Hypoxia, hypoxia-inducible transcription factors, and renal cancer","volume":"69","author":"Sch\u00f6del","year":"2016","journal-title":"Eur Urol"},{"key":"2023112311355586900_btad679-B29","doi-asserted-by":"crossref","first-page":"4544","DOI":"10.1093\/bioinformatics\/btaa542","article-title":"Taxonn: ensemble of neural networks on stratified microbiome data for disease prediction","volume":"36","author":"Sharma","year":"2020","journal-title":"Bioinformatics"},{"key":"2023112311355586900_btad679-B30","doi-asserted-by":"crossref","first-page":"951","DOI":"10.1136\/gutjnl-2020-320930","article-title":"Exploring prognostic indicators in the pathological images of hepatocellular carcinoma based on deep learning","volume":"70","author":"Shi","year":"2021","journal-title":"Gut"},{"key":"2023112311355586900_btad679-B31","doi-asserted-by":"crossref","first-page":"9536","DOI":"10.3390\/ijms14059536","article-title":"Targeting signaling pathways in epithelial ovarian cancer","volume":"14","author":"Smolle","year":"2013","journal-title":"Int J Mol Sci"},{"key":"2023112311355586900_btad679-B32","first-page":"3319","author":"Sundararajan","year":"2017"},{"key":"2023112311355586900_btad679-B33","doi-asserted-by":"crossref","first-page":"541","DOI":"10.2741\/e268","article-title":"Therapeutic approaches targeting tumor vasculature in gastrointestinal cancers","volume":"3","author":"Takahashi","year":"2011","journal-title":"Front Biosci (Elite Ed)"},{"key":"2023112311355586900_btad679-B34","doi-asserted-by":"crossref","first-page":"845","DOI":"10.1093\/bioinformatics\/bts051","article-title":"A gene-based test of association using canonical correlation analysis","volume":"28","author":"Tang","year":"2012","journal-title":"Bioinformatics"},{"key":"2023112311355586900_btad679-B35","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1111\/j.2517-6161.1996.tb02080.x","article-title":"Regression shrinkage and selection via the lasso","volume":"58","author":"Tibshirani","year":"1996","journal-title":"J R Stat Soc Ser B (Methodological)"},{"key":"2023112311355586900_btad679-B36","doi-asserted-by":"crossref","first-page":"265","DOI":"10.1016\/j.ygeno.2008.07.011","article-title":"Pathway analysis of seven common diseases assessed by genome-wide association","volume":"92","author":"Torkamani","year":"2008","journal-title":"Genomics"},{"key":"2023112311355586900_btad679-B37","doi-asserted-by":"crossref","first-page":"116745","DOI":"10.1016\/j.neuroimage.2020.116745","article-title":"Finding the needle in a high-dimensional haystack: canonical correlation analysis for neuroscientists","volume":"216","author":"Wang","year":"2020","journal-title":"Neuroimage"},{"key":"2023112311355586900_btad679-B38","doi-asserted-by":"crossref","first-page":"3299","DOI":"10.1093\/jxb\/eru183","article-title":"Spx1 is an important component in the phosphorus signalling network of common bean regulating root growth and phosphorus homeostasis","volume":"65","author":"Yao","year":"2014","journal-title":"J Exp Bot"},{"key":"2023112311355586900_btad679-B39","doi-asserted-by":"crossref","first-page":"491","DOI":"10.1186\/s12859-021-04400-4","article-title":"Deep learning for cancer type classification and driver gene identification","volume":"22","author":"Zeng","year":"2021","journal-title":"BMC Bioinformatics"},{"key":"2023112311355586900_btad679-B40","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1186\/s12014-017-9150-4","article-title":"Downregulation of atp1a1 promotes cancer development in renal cell carcinoma","volume":"14","author":"Zhang","year":"2017","journal-title":"Clin Proteomics"},{"key":"2023112311355586900_btad679-B41","first-page":"83","volume-title":"Artificial Intelligence and Statistics","author":"Zhang","year":"2017"},{"key":"2023112311355586900_btad679-B42","doi-asserted-by":"crossref","first-page":"477","DOI":"10.3389\/fgene.2018.00477","article-title":"Deep learning-based multi-omics data integration reveals two prognostic subtypes in high-risk neuroblastoma","volume":"9","author":"Zhang","year":"2018","journal-title":"Front Genet"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btad679\/53403484\/btad679.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/39\/11\/btad679\/53689321\/btad679.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/39\/11\/btad679\/53689321\/btad679.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T23:02:53Z","timestamp":1730502173000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btad679\/7420211"}},"subtitle":[],"editor":[{"given":"Pier Luigi","family":"Martelli","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2023,11,1]]},"references-count":42,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2023,11,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btad679","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2023,11,1]]},"published":{"date-parts":[[2023,11,1]]},"article-number":"btad679"}}