{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,2]],"date-time":"2025-11-02T20:59:50Z","timestamp":1762117190844,"version":"build-2065373602"},"reference-count":61,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2021,11,1]],"date-time":"2021-11-01T00:00:00Z","timestamp":1635724800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2021,11,1]],"date-time":"2021-11-01T00:00:00Z","timestamp":1635724800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2021,9,7]],"date-time":"2021-09-07T00:00:00Z","timestamp":1630972800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/100008536","name":"Amazon Web Services","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100008536","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["clinicalkey.com","clinicalkey.com.au","clinicalkey.es","clinicalkey.fr","clinicalkey.jp","elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computers in Biology and Medicine"],"published-print":{"date-parts":[[2021,11]]},"DOI":"10.1016\/j.compbiomed.2021.104850","type":"journal-article","created":{"date-parts":[[2021,9,10]],"date-time":"2021-09-10T10:35:45Z","timestamp":1631270145000},"page":"104850","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":5,"special_numbering":"C","title":["Reducing variability of breast cancer subtype predictors by grounding deep learning models in prior knowledge"],"prefix":"10.1016","volume":"138","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8408-3944","authenticated-orcid":false,"given":"Paul","family":"Anderson","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5469-1212","authenticated-orcid":false,"given":"Richa","family":"Gadgil","sequence":"additional","affiliation":[]},{"given":"William A.","family":"Johnson","sequence":"additional","affiliation":[]},{"given":"Ella","family":"Schwab","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5951-5955","authenticated-orcid":false,"given":"Jean M.","family":"Davidson","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.compbiomed.2021.104850_bib1","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0091225","article-title":"Accuracy evaluation of the unified P-value from combining correlated P-values","volume":"9","author":"Alves","year":"2014","journal-title":"PloS One"},{"key":"10.1016\/j.compbiomed.2021.104850_bib2","doi-asserted-by":"crossref","first-page":"245","DOI":"10.1146\/annurev-pathol-052016-100127","article-title":"The varied roles of notch in cancer","volume":"12","author":"Aster","year":"2017","journal-title":"Annu. Rev. Pathol."},{"author":"Bui","key":"10.1016\/j.compbiomed.2021.104850_bib3"},{"key":"10.1016\/j.compbiomed.2021.104850_bib4","doi-asserted-by":"crossref","first-page":"1688","DOI":"10.1158\/1078-0432.CCR-14-0432","article-title":"Comprehensive genomic analysis identifies novel subtypes and targets of triple-negative breast cancer","volume":"21","author":"Burstein","year":"2015","journal-title":"Clin. Canc. Res."},{"key":"10.1016\/j.compbiomed.2021.104850_bib5","doi-asserted-by":"crossref","first-page":"330","DOI":"10.1038\/nature11252","article-title":"Comprehensive molecular characterization of human colon and rectal cancer","volume":"487","author":"Cancer","year":"2012","journal-title":"Nature"},{"key":"10.1016\/j.compbiomed.2021.104850_bib6","doi-asserted-by":"crossref","first-page":"1115","DOI":"10.1074\/mcp.R600016-MCP200","article-title":"Cancer immunomics using autoantibody signatures for biomarker discovery","volume":"6","author":"Caron","year":"2007","journal-title":"Mol. Cell. Proteomics"},{"key":"10.1016\/j.compbiomed.2021.104850_bib7","doi-asserted-by":"crossref","first-page":"14071","DOI":"10.1038\/s41598-020-70832-2","article-title":"Machine learning for RNA sequencing-based intrinsic subtyping of breast cancer","volume":"10","author":"Cascianelli","year":"2020","journal-title":"Sci. Rep."},{"key":"10.1016\/j.compbiomed.2021.104850_bib8","doi-asserted-by":"crossref","first-page":"1476","DOI":"10.1093\/bioinformatics\/btz769","article-title":"Deep-learning approach to identifying cancer subtypes using high-dimensional genomic data","volume":"36","author":"Chen","year":"2020","journal-title":"Bioinformatics"},{"key":"10.1016\/j.compbiomed.2021.104850_bib9","doi-asserted-by":"crossref","first-page":"4465","DOI":"10.1158\/1078-0432.CCR-12-0286","article-title":"A 50-gene intrinsic subtype classifier for prognosis and prediction of benefit from adjuvant tamoxifen","author":"Chia","year":"2012","journal-title":"Clin. Canc. Res. : an official journal of the American Association for Cancer Research 18"},{"key":"10.1016\/j.compbiomed.2021.104850_bib10","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0081843","article-title":"Candidate luminal b breast cancer genes identified by genome, gene expression and dna methylation profiling","volume":"9","author":"Cornen","year":"2014","journal-title":"PloS One"},{"key":"10.1016\/j.compbiomed.2021.104850_bib11","doi-asserted-by":"crossref","first-page":"551","DOI":"10.1038\/nrg.2017.38","article-title":"Network propagation: a universal amplifier of genetic associations","volume":"18","author":"Cowen","year":"2017","journal-title":"Nat. Rev. Genet."},{"key":"10.1016\/j.compbiomed.2021.104850_bib12","doi-asserted-by":"crossref","first-page":"126","DOI":"10.1016\/j.copbio.2019.12.021","article-title":"Incorporating biological structure into machine learning models in biomedicine","volume":"63","author":"Crawford","year":"2020","journal-title":"Curr. Opin. Biotechnol."},{"year":"2020","series-title":"Underspecification Presents Challenges for Credibility in Modern Machine Learning","author":"D'Amour","key":"10.1016\/j.compbiomed.2021.104850_bib13"},{"key":"10.1016\/j.compbiomed.2021.104850_bib14","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41523-019-0104-z","article-title":"Esr1 mutations in metastatic lobular breast cancer patients","volume":"5","author":"Desmedt","year":"2019","journal-title":"NPJ breast cancer"},{"key":"10.1016\/j.compbiomed.2021.104850_bib15","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1111\/jlme.12160","article-title":"Clinical integration of next generation sequencing: coverage and reimbursement challenges","volume":"42","author":"Deverka","year":"2014","journal-title":"J. Law Med. Ethics"},{"key":"10.1016\/j.compbiomed.2021.104850_bib16","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s13073-019-0689-8","article-title":"Artificial intelligence in clinical and genomic diagnostics","volume":"11","author":"Dias","year":"2019","journal-title":"Genome Med."},{"key":"10.1016\/j.compbiomed.2021.104850_bib17","doi-asserted-by":"crossref","first-page":"3473","DOI":"10.1158\/1078-0432.CCR-09-3092","article-title":"Diverse associations between esr1 polymorphism and breast cancer development and progression","volume":"16","author":"Ding","year":"2010","journal-title":"Clin. Canc. Res."},{"key":"10.1016\/j.compbiomed.2021.104850_bib18","first-page":"774","article-title":"Discovery through clinical sequencing in oncology","volume":"1","author":"Donoghue","year":"2020","journal-title":"Nat. Can. (Que.)"},{"key":"10.1016\/j.compbiomed.2021.104850_bib19","doi-asserted-by":"crossref","first-page":"3714","DOI":"10.1002\/cncr.32345","article-title":"Esr1 mutations in breast cancer","volume":"125","author":"Dustin","year":"2019","journal-title":"Cancer"},{"key":"10.1016\/j.compbiomed.2021.104850_bib20","doi-asserted-by":"crossref","first-page":"80","DOI":"10.1016\/j.humpath.2020.10.007","article-title":"ESR1 genetic alterations and their association with clinicopathologic characteristics in advanced breast cancer: a single academic institution experience","volume":"107","author":"Freitag","year":"2021","journal-title":"Hum. Pathol."},{"key":"10.1016\/j.compbiomed.2021.104850_bib21","doi-asserted-by":"crossref","first-page":"311","DOI":"10.1093\/jnci\/djr545","article-title":"A three-gene model to robustly identify breast cancer molecular subtypes","volume":"104","author":"Haibe-Kains","year":"2012","journal-title":"J. Natl. Cancer Inst."},{"key":"10.1016\/j.compbiomed.2021.104850_bib22","doi-asserted-by":"crossref","first-page":"91","DOI":"10.2174\/1389202911314020003","article-title":"Integrated analysis of transcriptomic and proteomic data","volume":"14","author":"Haider","year":"2013","journal-title":"Curr. Genom."},{"key":"10.1016\/j.compbiomed.2021.104850_bib23","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1016\/S0092-8674(00)81683-9","article-title":"The hallmarks of cancer","volume":"100","author":"Hanahan","year":"2000","journal-title":"Cell"},{"key":"10.1016\/j.compbiomed.2021.104850_bib24","doi-asserted-by":"crossref","first-page":"646","DOI":"10.1016\/j.cell.2011.02.013","article-title":"Hallmarks of cancer: the next generation","volume":"144","author":"Hanahan","year":"2011","journal-title":"Cell"},{"key":"10.1016\/j.compbiomed.2021.104850_bib25","doi-asserted-by":"crossref","first-page":"149","DOI":"10.1038\/ng.295","article-title":"Repeatability of published microarray gene expression analyses","volume":"41","author":"Ioannidis","year":"2009","journal-title":"Nat. Genet."},{"key":"10.1016\/j.compbiomed.2021.104850_bib26","doi-asserted-by":"crossref","first-page":"573","DOI":"10.1038\/nrclinonc.2015.117","article-title":"Esr1 mutations\u2014a mechanism for acquired endocrine resistance in breast cancer","volume":"12","author":"Jeselsohn","year":"2015","journal-title":"Nat. Rev. Clin. Oncol."},{"key":"10.1016\/j.compbiomed.2021.104850_bib27","doi-asserted-by":"crossref","first-page":"D457","DOI":"10.1093\/nar\/gkv1070","article-title":"KEGG as a reference resource for gene and protein annotation","volume":"44","author":"Kanehisa","year":"2015","journal-title":"Nucleic Acids Res."},{"key":"10.1016\/j.compbiomed.2021.104850_bib28","doi-asserted-by":"crossref","first-page":"415","DOI":"10.1038\/nrg3493","article-title":"Molecular genetic testing and the future of clinical genomics","volume":"14","author":"Katsanis","year":"2013","journal-title":"Nat. Rev. Genet."},{"key":"10.1016\/j.compbiomed.2021.104850_bib29","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s12916-019-1426-2","article-title":"Key challenges for delivering clinical impact with artificial intelligence","volume":"17","author":"Kelly","year":"2019","journal-title":"BMC Med."},{"year":"2014","series-title":"Adam: A Method for Stochastic Optimization","author":"Kingma","key":"10.1016\/j.compbiomed.2021.104850_bib30"},{"key":"10.1016\/j.compbiomed.2021.104850_bib31","doi-asserted-by":"crossref","first-page":"1509","DOI":"10.4155\/bio-2016-0090","article-title":"Analytical pitfalls and challenges in clinical metabolomics","volume":"8","author":"Kohler","year":"2016","journal-title":"Bioanalysis"},{"key":"10.1016\/j.compbiomed.2021.104850_bib32","article-title":"Integrating transcriptome and proteome profiling: strategies and applications","volume":"1","author":"Kumar","year":"2016","journal-title":"Proteomics"},{"key":"10.1016\/j.compbiomed.2021.104850_bib33","doi-asserted-by":"crossref","first-page":"64","DOI":"10.1186\/1752-0509-7-64","article-title":"3Omics: a web-based systems biology tool for analysis, integration and visualization of human transcriptomic, proteomic and metabolomic data","volume":"7","author":"Kuo","year":"2013","journal-title":"BMC Syst. Biol."},{"key":"10.1016\/j.compbiomed.2021.104850_bib34","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s12902-019-0436-6","article-title":"Predictive models for diabetes mellitus using machine learning techniques","volume":"19","author":"Lai","year":"2019","journal-title":"BMC Endocr. Disord."},{"key":"10.1016\/j.compbiomed.2021.104850_bib35","first-page":"38","article-title":"ESR1 alterations and metastasis in estrogen receptor positive breast cancer","volume":"5","author":"Lei","year":"2019","journal-title":"Journal of Cancer Metastasis and Treatment"},{"key":"10.1016\/j.compbiomed.2021.104850_bib36","doi-asserted-by":"crossref","first-page":"176","DOI":"10.1109\/JPROC.2015.2494198","article-title":"Machine learning in genomic medicine: a review of computational problems and data sets","volume":"104","author":"Leung","year":"2015","journal-title":"Proc. IEEE"},{"key":"10.1016\/j.compbiomed.2021.104850_bib37","doi-asserted-by":"crossref","first-page":"5832","DOI":"10.1073\/pnas.1201105109","article-title":"Seventeen-gene signature from enriched her2\/neu mammary tumor-initiating cells predicts clinical outcome for human her2+: er\u03b1- breast cancer","volume":"109","author":"Liu","year":"2012","journal-title":"Proc. Natl. Acad. Sci. Unit. States Am."},{"key":"10.1016\/j.compbiomed.2021.104850_bib38","doi-asserted-by":"crossref","first-page":"955","DOI":"10.4161\/cbt.10.10.13879","article-title":"Histological, molecular and functional subtypes of breast cancers","volume":"10","author":"Malhotra","year":"2010","journal-title":"Canc. Biol. Ther."},{"key":"10.1016\/j.compbiomed.2021.104850_bib39","first-page":"D24","article-title":"Database resources of the national genomics data center in 2020","volume":"48","author":"Members","year":"2020","journal-title":"Nucleic Acids Res."},{"key":"10.1016\/j.compbiomed.2021.104850_bib40","doi-asserted-by":"crossref","first-page":"346","DOI":"10.1038\/nature10983","article-title":"The genomic and transcriptomic architecture of 2,000 breast tumours reveals novel subgroups","volume":"486","author":"Metabric Group","year":"2012","journal-title":"Nature"},{"key":"10.1016\/j.compbiomed.2021.104850_bib41","doi-asserted-by":"crossref","first-page":"1562","DOI":"10.1016\/j.cell.2018.05.056","article-title":"Visible machine learning for biomedicine","volume":"173","author":"Michael","year":"2018","journal-title":"Cell"},{"key":"10.1016\/j.compbiomed.2021.104850_bib42","doi-asserted-by":"crossref","first-page":"440","DOI":"10.1038\/s41582-020-0377-8","article-title":"Applications of machine learning to diagnosis and treatment of neurodegenerative diseases","volume":"16","author":"Myszczynska","year":"2020","journal-title":"Nat. Rev. Neurol."},{"key":"10.1016\/j.compbiomed.2021.104850_bib43","doi-asserted-by":"crossref","first-page":"1422","DOI":"10.1101\/gad.342287.120","article-title":"The many facets of notch signaling in breast cancer: toward overcoming therapeutic resistance","volume":"34","author":"Nandi","year":"2020","journal-title":"Genes Dev."},{"key":"10.1016\/j.compbiomed.2021.104850_bib44","doi-asserted-by":"crossref","first-page":"621","DOI":"10.1586\/erm.12.46","article-title":"How many molecular subtypes? Implications of the unique tumor principle in personalized medicine","volume":"12","author":"Ogino","year":"2012","journal-title":"Expert Rev. Mol. Diagn."},{"key":"10.1016\/j.compbiomed.2021.104850_bib45","doi-asserted-by":"crossref","first-page":"1830","DOI":"10.1039\/c0an00105h","article-title":"Mass-spectrometry-based clinical proteomics\u2013a review and prospective","volume":"135","author":"Parker","year":"2010","journal-title":"Analyst"},{"key":"10.1016\/j.compbiomed.2021.104850_bib46","doi-asserted-by":"crossref","first-page":"770","DOI":"10.1038\/nmeth.3940","article-title":"Revealing disease-associated pathways by network integration of untargeted metabolomics","volume":"13","author":"Pirhaji","year":"2016","journal-title":"Nat. Methods"},{"key":"10.1016\/j.compbiomed.2021.104850_bib47","doi-asserted-by":"crossref","first-page":"26","DOI":"10.3389\/fonc.2017.00026","article-title":"Clinical implications of esr1 mutations in hormone receptor-positive advanced breast cancer","volume":"7","author":"Reinert","year":"2017","journal-title":"Frontiers in oncology"},{"key":"10.1016\/j.compbiomed.2021.104850_bib48","first-page":"1","article-title":"Improving the accuracy of medical diagnosis with causal machine learning","volume":"11","author":"Richens","year":"2020","journal-title":"Nat. Commun."},{"key":"10.1016\/j.compbiomed.2021.104850_bib49","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1146\/annurev.pa.25.040185.002525","article-title":"Steroid hormone regulation of gene expression","volume":"25","author":"Ringold","year":"1985","journal-title":"Annu. Rev. Pharmacol. Toxicol."},{"year":"2016","series-title":"Diet Networks: Thin Parameters for Fat Genomics","author":"Romero","key":"10.1016\/j.compbiomed.2021.104850_bib50"},{"key":"10.1016\/j.compbiomed.2021.104850_bib51","doi-asserted-by":"crossref","first-page":"516","DOI":"10.1038\/ncponc0908","article-title":"Origins of breast cancer subtypes and therapeutic implications","volume":"4","author":"Sims","year":"2007","journal-title":"Nat. Clin. Pract. Oncol."},{"key":"10.1016\/j.compbiomed.2021.104850_bib52","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s40246-015-0049-8","article-title":"Cancer classification in the genomic era: five contemporary problems","volume":"9","author":"Song","year":"2015","journal-title":"Hum. Genom."},{"key":"10.1016\/j.compbiomed.2021.104850_bib53","doi-asserted-by":"crossref","first-page":"D330","DOI":"10.1093\/nar\/gky1055","article-title":"The gene ontology resource: 20 years and still GOing strong","volume":"47","author":"The Gene Ontology Consortium","year":"2018","journal-title":"Nucleic Acids Res."},{"key":"10.1016\/j.compbiomed.2021.104850_bib54","doi-asserted-by":"crossref","first-page":"D13","DOI":"10.1093\/nar\/gkm1000","article-title":"Database resources of the national center for biotechnology information","volume":"36","author":"Wheeler","year":"2007","journal-title":"Nucleic Acids Res."},{"key":"10.1016\/j.compbiomed.2021.104850_bib55","doi-asserted-by":"crossref","first-page":"149","DOI":"10.1093\/cid\/cix731","article-title":"Machine learning for healthcare: on the verge of a major shift in healthcare epidemiology","volume":"66","author":"Wiens","year":"2018","journal-title":"Clin. Infect. Dis."},{"key":"10.1016\/j.compbiomed.2021.104850_bib56","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/bcr2124","article-title":"Meta-analysis of gene expression profiles in breast cancer: toward a unified understanding of breast cancer subtyping and prognosis signatures","volume":"10","author":"Wirapati","year":"2008","journal-title":"Breast Canc. Res."},{"key":"10.1016\/j.compbiomed.2021.104850_bib57","doi-asserted-by":"crossref","DOI":"10.2196\/16709","article-title":"Reproducible machine learning methods for lung cancer detection using computed tomography images: algorithm development and validation","volume":"22","author":"Yu","year":"2020","journal-title":"J. Med. Internet Res."},{"key":"10.1016\/j.compbiomed.2021.104850_bib58","doi-asserted-by":"crossref","first-page":"298","DOI":"10.1016\/j.tig.2009.05.005","article-title":"Complex human chromosomal and genomic rearrangements","volume":"25","author":"Zhang","year":"2009","journal-title":"Trends Genet."},{"key":"10.1016\/j.compbiomed.2021.104850_bib59","doi-asserted-by":"crossref","first-page":"572","DOI":"10.1093\/bib\/bby026","article-title":"Molecular subtyping of cancer: current status and moving toward clinical applications","volume":"20","author":"Zhao","year":"2019","journal-title":"Briefings Bioinf."},{"year":"2002","series-title":"Learning from Labeled and Unlabeled Data with Label Propagation","author":"Zhu","key":"10.1016\/j.compbiomed.2021.104850_bib60"},{"key":"10.1016\/j.compbiomed.2021.104850_bib61","first-page":"1","article-title":"Esr1 mutations are frequent in newly diagnosed metastatic and loco-regional recurrence of endocrine-treated breast cancer and carry worse prognosis","volume":"22","author":"Zundelevich","year":"2020","journal-title":"Breast Canc. Res."}],"container-title":["Computers in Biology and Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0010482521006442?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0010482521006442?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,11,2]],"date-time":"2025-11-02T20:56:09Z","timestamp":1762116969000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0010482521006442"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,11]]},"references-count":61,"alternative-id":["S0010482521006442"],"URL":"https:\/\/doi.org\/10.1016\/j.compbiomed.2021.104850","relation":{},"ISSN":["0010-4825"],"issn-type":[{"type":"print","value":"0010-4825"}],"subject":[],"published":{"date-parts":[[2021,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Reducing variability of breast cancer subtype predictors by grounding deep learning models in prior knowledge","name":"articletitle","label":"Article Title"},{"value":"Computers in Biology and Medicine","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.compbiomed.2021.104850","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2021 The Author(s). Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"104850"}}