{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T11:28:30Z","timestamp":1781177310549,"version":"3.54.1"},"reference-count":53,"publisher":"Oxford University Press (OUP)","issue":"8","license":[{"start":{"date-parts":[[2022,2,14]],"date-time":"2022-02-14T00:00:00Z","timestamp":1644796800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,4,12]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec><jats:title>Motivation<\/jats:title><jats:p>Advanced deep learning techniques have been widely applied in disease diagnosis and prognosis with clinical omics, especially gene expression data. In the regulation of biological processes and disease progression, genes often work interactively rather than individually. Therefore, investigating gene association information and co-functional gene modules can facilitate disease state prediction.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>To explore the gene modules and inter-gene relational information contained in the omics data, we propose a novel multi-level attention graph neural network (MLA-GNN) for disease diagnosis and prognosis. Specifically, we format omics data into co-expression graphs via weighted correlation network analysis, and then construct multi-level graph features, finally fuse them through a well-designed multi-level graph feature fully fusion module to conduct predictions. For model interpretation, a novel full-gradient graph saliency mechanism is developed to identify the disease-relevant genes. MLA-GNN achieves state-of-the-art performance on transcriptomic data from TCGA-LGG\/TCGA-GBM and proteomic data from coronavirus disease 2019 (COVID-19)\/non-COVID-19 patient sera. More importantly, the relevant genes selected by our model are interpretable and are consistent with the clinical understanding.<\/jats:p><\/jats:sec><jats:sec><jats:title>Availabilityand implementation<\/jats:title><jats:p>The codes are available at https:\/\/github.com\/TencentAILabHealthcare\/MLA-GNN.<\/jats:p><\/jats:sec>","DOI":"10.1093\/bioinformatics\/btac088","type":"journal-article","created":{"date-parts":[[2022,2,9]],"date-time":"2022-02-09T20:14:23Z","timestamp":1644437663000},"page":"2178-2186","source":"Crossref","is-referenced-by-count":56,"title":["Multi-level attention graph neural network based on co-expression gene modules for disease diagnosis and prognosis"],"prefix":"10.1093","volume":"38","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9992-3387","authenticated-orcid":false,"given":"Xiaohan","family":"Xing","sequence":"first","affiliation":[{"name":"Department of Electronic Engineering, The Chinese University of Hong Kong , Shatin, Hong Kong 999077, China"},{"name":"AI Lab, Tencent , Shenzhen 518000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fan","family":"Yang","sequence":"additional","affiliation":[{"name":"AI Lab, Tencent , Shenzhen 518000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hang","family":"Li","sequence":"additional","affiliation":[{"name":"AI Lab, Tencent , Shenzhen 518000, China"},{"name":"School of Informatics, Xiamen University , Xiamen 361005, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Zhang","sequence":"additional","affiliation":[{"name":"AI Lab, Tencent , Shenzhen 518000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Zhao","sequence":"additional","affiliation":[{"name":"AI Lab, Tencent , Shenzhen 518000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingxuan","family":"Gao","sequence":"additional","affiliation":[{"name":"AI Lab, Tencent , Shenzhen 518000, China"},{"name":"School of Informatics, Xiamen University , Xiamen 361005, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junzhou","family":"Huang","sequence":"additional","affiliation":[{"name":"AI Lab, Tencent , Shenzhen 518000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianhua","family":"Yao","sequence":"additional","affiliation":[{"name":"AI Lab, Tencent , Shenzhen 518000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2022,2,14]]},"reference":[{"key":"2023020109030225400_btac088-B1","doi-asserted-by":"crossref","first-page":"3544","DOI":"10.3390\/ijms21103544","article-title":"The role of lipid metabolism in COVID-19 virus infection and as a drug target","volume":"21","author":"Abu-Farha","year":"2020","journal-title":"Int. J. Mol. Sci"},{"key":"2023020109030225400_btac088-B2","doi-asserted-by":"crossref","first-page":"453","DOI":"10.1038\/nature02624","article-title":"Predicting disease using genomics","volume":"429","author":"Bell","year":"2004","journal-title":"Nature"},{"key":"2023020109030225400_btac088-B3","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41467-020-17090-y","article-title":"Predicting and affecting response to cancer therapy based on pathway-level biomarkers","volume":"11","author":"Ben-Hamo","year":"2020","journal-title":"Nat. Commun"},{"key":"2023020109030225400_btac088-B4","doi-asserted-by":"crossref","first-page":"101092","DOI":"10.1016\/j.plipres.2021.101092","article-title":"Dissecting lipid metabolism alterations in SARS-CoV-2","volume":"82","author":"Casari","year":"2021","journal-title":"Progress Lipid Res"},{"key":"2023020109030225400_btac088-B5","doi-asserted-by":"crossref","DOI":"10.1158\/2159-8290.CD-12-0095","article-title":"The cBio Cancer Genomics Portal: an open platform for exploring multidimensional cancer genomics data","author":"Cerami","year":"2012"},{"key":"2023020109030225400_btac088-B6","volume-title":"IEEE Transactions on Medical Imaging"},{"key":"2023020109030225400_btac088-B7","doi-asserted-by":"crossref","first-page":"e1006076","DOI":"10.1371\/journal.pcbi.1006076","article-title":"Cox-nnet: an artificial neural network method for prognosis prediction of high-throughput omics data","volume":"14","author":"Ching","year":"2018","journal-title":"PLoS Comput. Biol"},{"key":"2023020109030225400_btac088-B8","doi-asserted-by":"crossref","first-page":"140","DOI":"10.1038\/msb4100180","article-title":"Network-based classification of breast cancer metastasis","volume":"3","author":"Chuang","year":"2007","journal-title":"Mol. Syst. Biol"},{"key":"2023020109030225400_btac088-B9","doi-asserted-by":"crossref","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. Ser. B (Methodological)"},{"key":"2023020109030225400_btac088-B10","doi-asserted-by":"crossref","first-page":"1820","DOI":"10.1016\/j.ajpath.2015.02.023","article-title":"Molecular and genomic alterations in glioblastoma multiforme","volume":"185","author":"Crespo","year":"2015","journal-title":"Am. J. Pathol"},{"key":"2023020109030225400_btac088-B11","doi-asserted-by":"crossref","first-page":"92","DOI":"10.1186\/1752-0509-6-92","article-title":"Hint: high-quality protein interactomes and their applications in understanding human disease","volume":"6","author":"Das","year":"2012","journal-title":"BMC Syst. Biol"},{"key":"2023020109030225400_btac088-B12","doi-asserted-by":"crossref","first-page":"133","DOI":"10.1177\/0268580905052366","article-title":"When less is more: selection problems in large-n and small-n cross-national comparisons","volume":"20","author":"Ebbinghaus","year":"2005","journal-title":"Int. Sociol"},{"key":"2023020109030225400_btac088-B13","doi-asserted-by":"crossref","first-page":"250","DOI":"10.1016\/j.ebiom.2019.05.010","article-title":"Pathway-based biomarker identification with crosstalk analysis for robust prognosis prediction in hepatocellular carcinoma","volume":"44","author":"Fa","year":"2019","journal-title":"EBioMedicine"},{"key":"2023020109030225400_btac088-B14","author":"Fey","year":"2019"},{"key":"2023020109030225400_btac088-B15","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41389-019-0157-8","article-title":"DeepCC: a novel deep learning-based framework for cancer molecular subtype classification","volume":"8","author":"Gao","year":"2019","journal-title":"Oncogenesis"},{"key":"2023020109030225400_btac088-B16","doi-asserted-by":"crossref","first-page":"200","DOI":"10.1016\/j.cell.2020.06.013","article-title":"Proteogenomic characterization reveals therapeutic vulnerabilities in lung adenocarcinoma","volume":"182","author":"Gillette","year":"2020","journal-title":"Cell"},{"key":"2023020109030225400_btac088-B17","first-page":"249","author":"Glorot","year":"2010"},{"key":"2023020109030225400_btac088-B18","doi-asserted-by":"crossref","first-page":"728409","DOI":"10.3389\/fmolb.2021.728409","article-title":"The molecular basis of gender variations in mortality rates associated with the novel coronavirus (COVID-19) outbreak","volume":"8","author":"Hachim","year":"2021","journal-title":"Front. Mol. Biosci"},{"key":"2023020109030225400_btac088-B19","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s13059-017-1215-1","article-title":"Multi-omics approaches to disease","volume":"18","author":"Hasin","year":"2017","journal-title":"Genome Biol"},{"key":"2023020109030225400_btac088-B20","doi-asserted-by":"crossref","first-page":"97","DOI":"10.1186\/1478-811X-11-97","article-title":"Targeting the PDGF signaling pathway in tumor treatment","volume":"11","author":"Heldin","year":"2013","journal-title":"Cell Commun. Signal"},{"key":"2023020109030225400_btac088-B21","doi-asserted-by":"crossref","first-page":"1025","DOI":"10.1186\/s12864-016-3317-7","article-title":"A machine learning approach for the identification of key markers involved in brain development from single-cell transcriptomic data","volume":"17","author":"Hu","year":"2016","journal-title":"BMC Genomics"},{"key":"2023020109030225400_btac088-B22","doi-asserted-by":"crossref","first-page":"re6\u2013re6","DOI":"10.1126\/scisignal.287re6","article-title":"Oncogenic EGFR signaling networks in glioma","volume":"2","author":"Huang","year":"2009","journal-title":"Sci. Signal"},{"key":"2023020109030225400_btac088-B24","doi-asserted-by":"crossref","first-page":"D573","DOI":"10.1093\/nar\/gky1126","article-title":"Humannet v2: human gene networks for disease research","volume":"47","author":"Hwang","year":"2019","journal-title":"Nucleic Acids Res"},{"key":"2023020109030225400_btac088-B25","doi-asserted-by":"crossref","first-page":"3727","DOI":"10.1093\/bioinformatics\/bty429","article-title":"A graph-embedded deep feedforward network for disease outcome classification and feature selection using gene expression data","volume":"34","author":"Kong","year":"2018","journal-title":"Bioinformatics"},{"key":"2023020109030225400_btac088-B26","doi-asserted-by":"crossref","first-page":"W90","DOI":"10.1093\/nar\/gkw377","article-title":"Enrichr: a comprehensive gene set enrichment analysis web server 2016 update","volume":"44","author":"Kuleshov","year":"2016","journal-title":"Nucleic Acids Res"},{"key":"2023020109030225400_btac088-B27","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":"2023020109030225400_btac088-B28","doi-asserted-by":"crossref","first-page":"694","DOI":"10.1089\/cmb.2012.0065","article-title":"Network-induced classification kernels for gene expression profile analysis","volume":"19","author":"Lavi","year":"2012","journal-title":"J. Comput. Biol"},{"key":"2023020109030225400_btac088-B29","doi-asserted-by":"crossref","first-page":"a004820","DOI":"10.1101\/cshperspect.a004820","article-title":"Role of lipids in virus replication","volume":"3","author":"Lorizate","year":"2011","journal-title":"Cold Spring Harbor Perspect. Biol"},{"key":"2023020109030225400_btac088-B30","first-page":"1","article-title":"EGFR-mediated cell cycle regulation","volume":"22","author":"Lui","year":"2002","journal-title":"Anticancer Res"},{"key":"2023020109030225400_btac088-B31","article-title":"Neural Network Intelligence","year":"2018"},{"key":"2023020109030225400_btac088-B32","doi-asserted-by":"crossref","first-page":"1515","DOI":"10.1093\/bib\/bbaa257","article-title":"Biological network analysis with deep learning","volume":"22","author":"Muzio","year":"2021","journal-title":"Brief. Bioinf"},{"key":"2023020109030225400_btac088-B33","first-page":"67","article-title":"The concentration of thyroid hormones and activities of iodothyronine deiodinases are altered in human brain gliomas","volume":"42","author":"Nauman","year":"2004","journal-title":"Folia Neuropathol"},{"key":"2023020109030225400_btac088-B34","doi-asserted-by":"crossref","first-page":"1133","DOI":"10.1126\/science.aar3819","article-title":"Noninvasive blood tests for fetal development predict gestational age and preterm delivery","volume":"360","author":"Ngo","year":"2018","journal-title":"Science"},{"key":"2023020109030225400_btac088-B35","first-page":"3910","article-title":"Expression of messenger RNAs for platelet-derived growth factor and transforming growth factor-\u03b1 and their receptors in human malignant glioma cell lines","volume":"48","author":"Nister","year":"1988","journal-title":"Cancer Res"},{"key":"2023020109030225400_btac088-B36","author":"Paszke","year":"2017"},{"key":"2023020109030225400_btac088-B37","author":"Rhee","year":"2017"},{"key":"2023020109030225400_btac088-B38","doi-asserted-by":"crossref","first-page":"bbaa241","DOI":"10.1093\/bib\/bbaa241","article-title":"DiSNEP: a disease-specific gene network enhancement to improve prioritizing candidate disease genes","volume":"22","author":"Ruan","year":"2021","journal-title":"Brief. Bioinf"},{"key":"2023020109030225400_btac088-B39","doi-asserted-by":"crossref","first-page":"2965","DOI":"10.1093\/bioinformatics\/bty224","article-title":"VSClust: feature-based variance-sensitive clustering of omics data","volume":"34","author":"Schw\u00e4mmle","year":"2018","journal-title":"Bioinformatics"},{"key":"2023020109030225400_btac088-B40","first-page":"618","author":"Selvaraju","year":"2017"},{"key":"2023020109030225400_btac088-B41","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1016\/j.cell.2020.05.032","article-title":"Proteomic and metabolomic characterization of COVID-19 patient sera","volume":"182","author":"Shen","year":"2020","journal-title":"Cell"},{"key":"2023020109030225400_btac088-B42","first-page":"4124","author":"Srinivas","year":"2019"},{"key":"2023020109030225400_btac088-B43","doi-asserted-by":"crossref","first-page":"D447","DOI":"10.1093\/nar\/gku1003","article-title":"String v10: protein\u2013protein interaction networks, integrated over the tree of life","volume":"43","author":"Szklarczyk","year":"2015","journal-title":"Nucleic Acids Res"},{"key":"2023020109030225400_btac088-B44","doi-asserted-by":"crossref","first-page":"100129","DOI":"10.1016\/j.jlr.2021.100129","article-title":"The roles of lipids in SARS-CoV-2 viral replication and the host immune response","volume":"62","author":"Theken","year":"2021","journal-title":"J. Lipid Res"},{"key":"2023020109030225400_btac088-B45","article-title":"Graph attention networks","author":"Veli\u010dkovi\u0107","year":"2017"},{"key":"2023020109030225400_btac088-B46","first-page":"758","author":"Verleysen","year":"2005"},{"key":"2023020109030225400_btac088-B47","first-page":"1814","article-title":"Pathway-based single-cell RNA-Seq classification, clustering, and construction of gene\u2013gene interactions networks using random forests","volume":"24","author":"Wang","year":"2019","journal-title":"IEEE J. Biomed. Inf"},{"key":"2023020109030225400_btac088-B48","article-title":"MORONET: multi-omics integration via graph convolutional networks for biomedical data classification and biomarker identification. Nat. Commu., 12:1\u201313","author":"Wang","year":"2020"},{"key":"2023020109030225400_btac088-B49","first-page":"1847","article-title":"The role of high-density lipoprotein in COVID-19","volume":"12","author":"Wang","year":"2021","journal-title":"Front. Pharmacol"},{"key":"2023020109030225400_btac088-B50","doi-asserted-by":"crossref","first-page":"404","DOI":"10.1093\/bioinformatics\/btm612","article-title":"Incorporating gene networks into statistical tests for genomic data via a spatially correlated mixture model","volume":"24","author":"Wei","year":"2008","journal-title":"Bioinformatics"},{"key":"2023020109030225400_btac088-B51","doi-asserted-by":"crossref","first-page":"580","DOI":"10.1038\/nature06917","article-title":"Imaging in the era of molecular oncology","volume":"452","author":"Weissleder","year":"2008","journal-title":"Nature"},{"key":"2023020109030225400_btac088-B52","doi-asserted-by":"crossref","first-page":"1276","DOI":"10.1038\/s41596-020-00462-5","article-title":"Detection of aberrant gene expression events in RNA sequencing data","volume":"16","author":"Y\u00e9pez","year":"2021","journal-title":"Nat. Protoc"},{"key":"2023020109030225400_btac088-B53","doi-asserted-by":"crossref","first-page":"30232","DOI":"10.18632\/oncotarget.4920","article-title":"IDH1\/2 mutation status combined with ki-67 labeling index defines distinct prognostic groups in glioma","volume":"6","author":"Zeng","year":"2015","journal-title":"Oncotarget"},{"key":"2023020109030225400_btac088-B54","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/1471-2105-10-S1-S21","article-title":"Network-based support vector machine for classification of microarray samples","volume":"10","author":"Zhu","year":"2009","journal-title":"BMC Bioinformatics"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btac088\/42515622\/btac088.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/38\/8\/2178\/49009961\/btac088.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/38\/8\/2178\/49009961\/btac088.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,18]],"date-time":"2024-09-18T05:53:32Z","timestamp":1726638812000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/38\/8\/2178\/6528315"}},"subtitle":[],"editor":[{"given":"Inanc","family":"Birol","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2022,2,14]]},"references-count":53,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2022,4,12]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btac088","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2022,4,15]]},"published":{"date-parts":[[2022,2,14]]}}}