{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T16:44:46Z","timestamp":1780764286265,"version":"3.54.1"},"reference-count":38,"publisher":"Oxford University Press (OUP)","issue":"Supplement_1","license":[{"start":{"date-parts":[[2023,6,30]],"date-time":"2023-06-30T00:00:00Z","timestamp":1688083200000},"content-version":"vor","delay-in-days":29,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"public\u2013private partnership","award":["2021-1047"],"award-info":[{"award-number":["2021-1047"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,30]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec><jats:title>Motivation<\/jats:title><jats:p>The increasing availability of high-throughput omics data allows for considering a new medicine centered on individual patients. Precision medicine relies on exploiting these high-throughput data with machine-learning models, especially the ones based on deep-learning approaches, to improve diagnosis. Due to the high-dimensional small-sample nature of omics data, current deep-learning models end up with many parameters and have to be fitted with a limited training set. Furthermore, interactions between molecular entities inside an omics profile are not patient specific but are the same for all patients.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>In this article, we propose AttOmics, a new deep-learning architecture based on the self-attention mechanism. First, we decompose each omics profile into a set of groups, where each group contains related features. Then, by applying the self-attention mechanism to the set of groups, we can capture the different interactions specific to a patient. The results of different experiments carried out in this article show that our model can accurately predict the phenotype of a patient with fewer parameters than deep neural networks. Visualizing the attention maps can provide new insights into the essential groups for a particular phenotype.<\/jats:p><\/jats:sec><jats:sec><jats:title>Availability and implementation<\/jats:title><jats:p>The code and data are available at https:\/\/forge.ibisc.univ-evry.fr\/abeaude\/AttOmics. TCGA data can be downloaded from the Genomic Data Commons Data Portal.<\/jats:p><\/jats:sec>","DOI":"10.1093\/bioinformatics\/btad232","type":"journal-article","created":{"date-parts":[[2023,6,30]],"date-time":"2023-06-30T08:19:34Z","timestamp":1688113174000},"page":"i94-i102","source":"Crossref","is-referenced-by-count":9,"title":["AttOmics: attention-based architecture for diagnosis and prognosis from omics data"],"prefix":"10.1093","volume":"39","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7199-5242","authenticated-orcid":false,"given":"Aur\u00e9lien","family":"Beaude","sequence":"first","affiliation":[{"name":"IBISC, Universit\u00e9 Paris-Saclay, Univ Evry , 23 Boulevard de France , Evry-Courcouronnes 91020, France"},{"name":"Artificial Intelligence & Deep Analytics, Omics Data Science, Sanofi R&D Data and Data Science , 1 Av. Pierre Brossolette , Chilly-Mazarin 91385, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1785-0234","authenticated-orcid":false,"given":"Milad","family":"Rafiee Vahid","sequence":"additional","affiliation":[{"name":"Sanofi R&D Data and Data Science, Artificial Intelligence & Deep Analytics, Omics Data Science , 450 Water Street, Cambridge, MA 02142, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5641-4152","authenticated-orcid":false,"given":"Franck","family":"Aug\u00e9","sequence":"additional","affiliation":[{"name":"Artificial Intelligence & Deep Analytics, Omics Data Science, Sanofi R&D Data and Data Science , 1 Av. Pierre Brossolette , Chilly-Mazarin 91385, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6278-1680","authenticated-orcid":false,"given":"Farida","family":"Zehraoui","sequence":"additional","affiliation":[{"name":"IBISC, Universit\u00e9 Paris-Saclay, Univ Evry , 23 Boulevard de France , Evry-Courcouronnes 91020, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5606-8296","authenticated-orcid":false,"given":"Blaise","family":"Hanczar","sequence":"additional","affiliation":[{"name":"IBISC, Universit\u00e9 Paris-Saclay, Univ Evry , 23 Boulevard de France , Evry-Courcouronnes 91020, France"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2023,6,30]]},"reference":[{"key":"2023063008163054600_btad232-B1","doi-asserted-by":"crossref","first-page":"289","DOI":"10.1111\/j.2517-6161.1995.tb02031.x","article-title":"Controlling the false discovery rate: a practical and powerful approach to multiple testing","volume":"57","author":"Benjamini","year":"1995","journal-title":"J R Stat Soc Ser B Methodol"},{"key":"2023063008163054600_btad232-B2","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1186\/s12920-020-0658-5","article-title":"DeepTRIAGE: interpretable and individualised biomarker scores using attention mechanism for the classification of breast cancer sub-types","volume":"13","author":"Beykikhoshk","year":"2020","journal-title":"BMC Med Genomics"},{"key":"2023063008163054600_btad232-B3","doi-asserted-by":"crossref","first-page":"455","DOI":"10.1186\/s12859-021-04370-7","article-title":"Deep GONet: self-explainable deep neural network based on gene ontology for phenotype prediction from gene expression data","volume":"22","author":"Bourgeais","year":"2021","journal-title":"BMC Bioinformatics"},{"key":"2023063008163054600_btad232-B4","author":"Bradley","year":"2000"},{"key":"2023063008163054600_btad232-B5","author":"Child","year":"2021"},{"key":"2023063008163054600_btad232-B6","doi-asserted-by":"crossref","first-page":"185338","DOI":"10.1109\/ACCESS.2019.2960722","article-title":"Lightweight convolutional neural network for breast cancer classification using RNA-Seq gene expression data","volume":"7","author":"Elbashir","year":"2019","journal-title":"IEEE Access"},{"key":"2023063008163054600_btad232-B7","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":"2023063008163054600_btad232-B8","doi-asserted-by":"crossref","first-page":"D325","DOI":"10.1093\/nar\/gkaa1113","article-title":"The gene ontology resource: enriching a GOld mine","volume":"49","author":"Gene Ontology Consortium","year":"2021","journal-title":"Nucleic Acids Res"},{"key":"2023063008163054600_btad232-B9","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1186\/s12859-022-04783-y","article-title":"CancerNet: a unified deep learning network for pan-cancer diagnostics","volume":"23","author":"Gore","year":"2022","journal-title":"BMC Bioinformatics"},{"key":"2023063008163054600_btad232-B10","doi-asserted-by":"crossref","first-page":"2297","DOI":"10.3390\/cells9102297","article-title":"Role of the JAK\/STAT pathway in cervical cancer: its relationship with HPV E6\/E7 oncoproteins","volume":"9","author":"Guti\u00e9rrez-Hoya","year":"2020","journal-title":"Cells"},{"key":"2023063008163054600_btad232-B11","doi-asserted-by":"crossref","DOI":"10.1186\/s12859-022-04807-7","article-title":"Assessment of deep learning and transfer learning for cancer prediction based on gene expression data","volume":"23","author":"Hanczar","year":"2022","journal-title":"BMC Bioinformatics"},{"key":"2023063008163054600_btad232-B12","doi-asserted-by":"crossref","first-page":"510","DOI":"10.1186\/s12859-018-2500-z","article-title":"PASNet: pathway-associated sparse deep neural network for prognosis prediction from high-throughput data","volume":"19","author":"Hao","year":"2021","journal-title":"BMC Bioinformatics"},{"key":"2023063008163054600_btad232-B13","doi-asserted-by":"crossref","first-page":"361","DOI":"10.1002\/(SICI)1097-0258(19960229)15:4<361::AID-SIM168>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":"Statist Med"},{"key":"2023063008163054600_btad232-B14","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1186\/s12874-018-0482-1","article-title":"DeepSurv: personalized treatment recommender system using a cox proportional hazards deep neural network","volume":"18","author":"Katzman","year":"2018","journal-title":"BMC Med Res Methodol"},{"key":"2023063008163054600_btad232-B15","doi-asserted-by":"publisher","first-page":"120047","DOI":"10.1016\/j.eswa.2023","article-title":"DeepGene transformer: Transformer for the gene expression-based classification of cancer subtypes","volume":"226","author":"Khan","year":"2023","journal-title":"Expert Systems with Applications"},{"key":"2023063008163054600_btad232-B16","doi-asserted-by":"crossref","first-page":"8","DOI":"10.1016\/j.csbj.2014.11.005","article-title":"Machine learning applications in cancer prognosis and prediction","volume":"13","author":"Kourou","year":"2015","journal-title":"Comput Struct Biotechnol J"},{"key":"2023063008163054600_btad232-B17","doi-asserted-by":"crossref","DOI":"10.3389\/fcell.2021.650772","article-title":"The role of notch, hedgehog, and Wnt signaling pathways in the resistance of tumors to anticancer therapies","volume":"9","author":"Kumar","year":"2021","journal-title":"Front Cell Dev Biol"},{"key":"2023063008163054600_btad232-B18","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"2023063008163054600_btad232-B19","doi-asserted-by":"crossref","first-page":"586","DOI":"10.3390\/biology11040586","article-title":"An ensemble deep learning model with a gene attention mechanism for estimating the prognosis of low-grade glioma","volume":"11","author":"Lee","year":"2022","journal-title":"Biology"},{"key":"2023063008163054600_btad232-B20","doi-asserted-by":"crossref","first-page":"108","DOI":"10.1186\/s12859-020-3443-8","article-title":"MethylNet: an automated and modular deep learning approach for DNA methylation analysis","volume":"21","author":"Levy","year":"2020","journal-title":"BMC Bioinformatics"},{"key":"2023063008163054600_btad232-B21","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41540-021-00193-7","article-title":"MethylSPWNet and MethylCapsNet: biologically motivated organization of DNAm neural networks, inspired by capsule networks","volume":"7","author":"Levy","year":"2021","journal-title":"NPJ Syst Biol Appl"},{"key":"2023063008163054600_btad232-B22","doi-asserted-by":"crossref","first-page":"417","DOI":"10.1016\/j.cels.2015.12.004","article-title":"The molecular signatures database hallmark gene set collection","volume":"1","author":"Liberzon","year":"2015","journal-title":"Cell Syst"},{"key":"2023063008163054600_btad232-B23","doi-asserted-by":"crossref","first-page":"18","DOI":"10.3390\/e23010018","article-title":"Explainable AI: a review of machine learning interpretability methods","volume":"23","author":"Linardatos","year":"2021","journal-title":"Entropy"},{"key":"2023063008163054600_btad232-B24","doi-asserted-by":"crossref","first-page":"778","DOI":"10.3390\/genes10100778","article-title":"DNA methylation markers for Pan-Cancer prediction by deep learning","volume":"10","author":"Liu","year":"2019","journal-title":"Genes"},{"key":"2023063008163054600_btad232-B25","author":"Ma","year":"2019"},{"key":"2023063008163054600_btad232-B26","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1186\/s12920-020-0677-2","article-title":"Convolutional neural network models for cancer type prediction based on gene expression","volume":"13","author":"Mostavi","year":"2020","journal-title":"BMC Med Genomics"},{"key":"2023063008163054600_btad232-B27","author":"Rabe","year":"2021"},{"key":"2023063008163054600_btad232-B28","doi-asserted-by":"crossref","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":"2023063008163054600_btad232-B29","doi-asserted-by":"crossref","first-page":"120","DOI":"10.1016\/j.ymeth.2021.01.004","article-title":"Prediction and interpretation of cancer survival using graph convolution neural networks","volume":"192","author":"Ramirez","year":"2021","journal-title":"Methods"},{"key":"2023063008163054600_btad232-B30","doi-asserted-by":"crossref","first-page":"1850","DOI":"10.3390\/app12041850","article-title":"Analyzing RNA-Seq gene expression data using deep learning approaches for cancer classification","volume":"12","author":"Rukhsar","year":"2021","journal-title":"Appl Sci"},{"key":"2023063008163054600_btad232-B31","doi-asserted-by":"crossref","first-page":"64","DOI":"10.1016\/j.bbrc.2012.07.051","article-title":"Hedgehog pathway regulators influence cervical cancer cell proliferation, survival and migration","volume":"425","author":"Samarzija","year":"2012","journal-title":"Biochem Biophys Res Commun"},{"key":"2023063008163054600_btad232-B32","doi-asserted-by":"crossref","first-page":"D605","DOI":"10.1093\/nar\/gkaa1074","article-title":"The STRING database in 2021: customizable protein\u2013protein networks, and functional characterization of user-uploaded gene\/measurement sets","volume":"49","author":"Szklarczyk","year":"2020","journal-title":"Nucleic Acids Res"},{"key":"2023063008163054600_btad232-B33","author":"Vaswani","year":"2017"},{"key":"2023063008163054600_btad232-B34","first-page":"1286","author":"Wang","year":"2018"},{"key":"2023063008163054600_btad232-B35","author":"Xiong","year":"2021"},{"key":"2023063008163054600_btad232-B36","doi-asserted-by":"crossref","first-page":"1277","DOI":"10.7150\/jca.22005","article-title":"Wnt signaling in cervical cancer?","volume":"9","author":"Yang","year":"2018","journal-title":"J Cancer"},{"key":"2023063008163054600_btad232-B37","doi-asserted-by":"crossref","first-page":"167","DOI":"10.1186\/s12864-019-5546-z","article-title":"Architectures and accuracy of artificial neural network for disease classification from omics data","volume":"20","author":"Yu","year":"2021","journal-title":"BMC Genomics"},{"key":"2023063008163054600_btad232-B38","doi-asserted-by":"crossref","first-page":"103030","DOI":"10.1016\/j.ebiom.2020.103030","article-title":"CUP-AI-Dx: a tool for inferring cancer tissue of origin and molecular subtype using RNA gene-expression data and artificial intelligence","volume":"61","author":"Zhao","year":"2020","journal-title":"EBioMedicine"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/39\/Supplement_1\/i94\/50741889\/btad232.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/39\/Supplement_1\/i94\/50741889\/btad232.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,21]],"date-time":"2024-10-21T01:23:10Z","timestamp":1729473790000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/39\/Supplement_1\/i94\/7210508"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,1]]},"references-count":38,"journal-issue":{"issue":"Supplement_1","published-print":{"date-parts":[[2023,6,30]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btad232","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2023,6,1]]},"published":{"date-parts":[[2023,6,1]]}}}