{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T13:09:19Z","timestamp":1788786559373,"version":"build-2803163510"},"reference-count":46,"publisher":"Oxford University Press (OUP)","issue":"5","license":[{"start":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T00:00:00Z","timestamp":1788739200000},"content-version":"vor","delay-in-days":6,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Jianbing&Lingyan Research and Development Program of Zhejiang Province","award":["2024C03239"],"award-info":[{"award-number":["2024C03239"]}]},{"name":"High-level Talent Special Support Program of Zhejiang Province"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,9,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Identifying essential biomarkers remains a core challenge in elucidating the pathogenic mechanisms and achieving precise diagnosis of complex diseases. Deep neural networks offer immense predictive power, yet their lack of interpretability severely limits downstream biological insight. Here, we introduce DeepVaris, an explainable deep learning framework that reframes feature selection as the interpretation of a pretrained convolutional neural network via surrogate modeling. In extensive simulations and real-world datasets, DeepVaris successfully identifies important features and reveals deeper insight into different diseases. Specifically, it overcomes extreme feature sparsity to identify crucial microbial biomarkers in preterm birth pregnancies. In single-cell RNA sequencing data, it reveals key transcriptional drivers governing myelin regeneration in neurodegenerative diseases missed by traditional differential expression analysis. Furthermore, in complex breast cancer cohorts, DeepVaris moves beyond generic pan-cancer signals to precise subtype-specific microenvironmental targets. In summary, we believe that DeepVaris will serve as a robust tool for biomarker discovery.<\/jats:p>","DOI":"10.1093\/bib\/bbag476","type":"journal-article","created":{"date-parts":[[2026,8,12]],"date-time":"2026-08-12T11:45:07Z","timestamp":1786535107000},"source":"Crossref","is-referenced-by-count":0,"title":["Interpretable deep neural network identifies robust biomarkers for diseases with mechanistic insights from omics data"],"prefix":"10.1093","volume":"27","author":[{"given":"Xiaoyue","family":"Hu","sequence":"first","affiliation":[{"name":"Center for Data Science, Zhejiang University , 866 Yuhangtang Road, Xihu District, Hangzhou, Zhejiang 310058 ,","place":["China"]},{"name":"School of Mathematical Sciences, Zhejiang University , 866 Yuhangtang Road, Xihu District, Hangzhou, Zhejiang 310058 ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuhao","family":"Ma","sequence":"additional","affiliation":[{"name":"School of Statistics and Mathematics, Zhejiang Gongshang University , 18 Xuezheng Street, Xiasha Higher Education Zone, Hangzhou, Zhejiang 310018 ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruixing","family":"Ming","sequence":"additional","affiliation":[{"name":"School of Statistics and Mathematics, Zhejiang Gongshang University , 18 Xuezheng Street, Xiasha Higher Education Zone, Hangzhou, Zhejiang 310018 ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Heping","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Biostatistics, Yale University , 60 College Street, New Haven, CT ,","place":["USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hangjin","family":"Jiang","sequence":"additional","affiliation":[{"name":"State Key Laboratory for Vegetation Structure, Function and Construction (VegLab), Center for Data Science, Zhejiang University , 866 Yuhangtang Road, Xihu District, Hangzhou, Zhejiang 310058 ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,9,7]]},"reference":[{"key":"2026090708274059600_ref1","doi-asserted-by":"crossref","first-page":"5043","DOI":"10.1200\/JCO.2006.06.7330","article-title":"Meta-analysis and meta-review of thyroid cancer gene expression profiling studies identifies important diagnostic biomarkers","volume":"24","author":"Griffith","year":"2006","journal-title":"J Clin Oncol"},{"key":"2026090708274059600_ref2","doi-asserted-by":"crossref","first-page":"537","DOI":"10.1038\/nbt1203","article-title":"Gene prioritization through genomic data fusion","volume":"24","author":"Aerts","year":"2006","journal-title":"Nat Biotechnol"},{"key":"2026090708274059600_ref3","doi-asserted-by":"crossref","first-page":"932","DOI":"10.1038\/s41587-021-01179-w","article-title":"Using deep learning to annotate the protein universe","volume":"40","author":"Bileschi","year":"2022","journal-title":"Nat Biotechnol"},{"key":"2026090708274059600_ref4","doi-asserted-by":"crossref","first-page":"56","DOI":"10.38094\/jastt1224","article-title":"A comprehensive review of dimensionality reduction techniques for feature selection and feature extraction","volume":"1","author":"Zebari","year":"2020","journal-title":"J Appl Sci Technol Trends"},{"key":"2026090708274059600_ref5"},{"key":"2026090708274059600_ref6","article-title":"Integrated plasma proteomic and single-cell immune signaling network signatures demarcate mild, moderate, and severe Covid-19","volume":"3","author":"Feyaerts","year":"2022","journal-title":"Cell Rep Med"},{"key":"2026090708274059600_ref7","doi-asserted-by":"crossref","DOI":"10.1038\/s41587-023-02033-x","article-title":"Discovery of sparse, reliable omic biomarkers with stabl","volume":"42","author":"H\u00e9dou","year":"2024","journal-title":"Nat Biotechnol"},{"key":"2026090708274059600_ref8","doi-asserted-by":"crossref","first-page":"nwaf189","DOI":"10.1093\/nsr\/nwaf189","article-title":"sPGGM: a sample-perturbed Gaussian graphical model for identifying pre-disease stages and signaling molecules of disease progression","volume":"12","author":"Zhong","year":"2025","journal-title":"Natl Sci Rev"},{"key":"2026090708274059600_ref9","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1038\/s41421-026-00879-4","article-title":"Hallmarks of the pre-disease state: prevention and control of the pre-disease state, a tipping point between health and disease","volume":"12","author":"Chen","year":"2026","journal-title":"Cell Discov"},{"key":"2026090708274059600_ref10","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 B"},{"key":"2026090708274059600_ref11","doi-asserted-by":"crossref","first-page":"301","DOI":"10.1111\/j.1467-9868.2005.00503.x","article-title":"Regularization and variable selection via the elastic net","volume":"67","author":"Zou","year":"2005","journal-title":"J R Stat Soc B"},{"key":"2026090708274059600_ref12","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach Learn"},{"key":"2026090708274059600_ref13","doi-asserted-by":"crossref","first-page":"831","DOI":"10.1093\/bioinformatics\/btq038","article-title":"Maximal conditional chi-square importance in random forests","volume":"26","author":"Wang","year":"2010","journal-title":"Bioinformatics"},{"key":"2026090708274059600_ref14","article-title":"Feature selection using deep neural networks","volume-title":"2015 international joint conference on neural networks (IJCNN)","author":"Debaditya"},{"key":"2026090708274059600_ref15","doi-asserted-by":"crossref","first-page":"426","DOI":"10.1038\/s42256-021-00308-z","article-title":"Variable selection with false discovery rate control in deep neural networks","volume":"3","author":"Song","year":"2021","journal-title":"Nat Mach Intell"},{"key":"2026090708274059600_ref16","doi-asserted-by":"crossref","first-page":"e2104683118","DOI":"10.1073\/pnas.2104683118","article-title":"DeepLINK: deep learning inference using knockoffs with applications to genomics","volume":"118","author":"Zhu","year":"2021","journal-title":"Proc Natl Acad Sci"},{"key":"2026090708274059600_ref17","doi-asserted-by":"crossref","first-page":"761","DOI":"10.1038\/s42256-022-00525-0","article-title":"Deep neural networks with controlled variable selection for the identification of putative causal genetic variants","volume":"4","author":"Kassani","year":"2022","journal-title":"Nat Mach Intell"},{"key":"2026090708274059600_ref18","doi-asserted-by":"crossref","first-page":"2272","DOI":"10.1128\/IAI.72.4.2272-2279.2004","article-title":"Fusobacterium nucleatum induces premature and term stillbirths in pregnant mice: Implication of oral bacteria in preterm birth","volume":"72","author":"Han","year":"2004","journal-title":"Infect Immun"},{"key":"2026090708274059600_ref19","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s40168-018-0502-8","article-title":"Increased richness and diversity of the vaginal microbiota and spontaneous preterm birth","volume":"6","author":"Freitas","year":"2018","journal-title":"Microbiome"},{"key":"2026090708274059600_ref20","doi-asserted-by":"crossref","first-page":"713","DOI":"10.1128\/JCM.42.2.713-717.2004","article-title":"Identification and H2O2 production of vaginal lactobacilli from pregnant women at high risk of preterm birth and relation with outcome","volume":"42","author":"Wilks","year":"2004","journal-title":"J Clin Microbiol"},{"key":"2026090708274059600_ref21","doi-asserted-by":"crossref","first-page":"F101","DOI":"10.1136\/fn.76.2.F101","article-title":"Early administration of bifidobacterium breve to preterm infants: Randomised controlled trial","volume":"76","author":"Kitajima","year":"1997","journal-title":"Arch Dis Child Fetal Neonatal Ed"},{"key":"2026090708274059600_ref22","doi-asserted-by":"crossref","first-page":"e0162734","DOI":"10.1371\/journal.pone.0162734","article-title":"Association of chorioamnionitis with aberrant neonatal gut colonization and adverse clinical outcomes","volume":"11","author":"Puri","year":"2016","journal-title":"PLoS One"},{"key":"2026090708274059600_ref23","doi-asserted-by":"crossref","first-page":"1021","DOI":"10.1007\/s12275-022-2180-2","article-title":"Early gut microbiota in very low and extremely low birth weight preterm infants with feeding intolerance: a prospective case-control study","volume":"60","author":"Liu","year":"2022","journal-title":"J Microbiol"},{"key":"2026090708274059600_ref24","doi-asserted-by":"crossref","first-page":"617","DOI":"10.1038\/nrd.2017.115","article-title":"Remyelination therapies: a new direction and challenge in multiple sclerosis","volume":"16","author":"Plemel","year":"2017","journal-title":"Nat Rev Drug Discov"},{"key":"2026090708274059600_ref25","doi-asserted-by":"crossref","first-page":"4386","DOI":"10.1523\/JNEUROSCI.4962-14.2015","article-title":"Olig1 function is required for oligodendrocyte differentiation in the mouse brain","volume":"35","author":"Dai","year":"2015","journal-title":"J Neurosci"},{"key":"2026090708274059600_ref26","doi-asserted-by":"crossref","first-page":"1333","DOI":"10.1523\/JNEUROSCI.2477-13.2014","article-title":"Expression of proteolipid protein gene in spinal cord stem cells and early oligodendrocyte progenitor cells is dispensable for normal cell migration and myelination","volume":"34","author":"Harlow","year":"2014","journal-title":"J Neurosci"},{"key":"2026090708274059600_ref27","doi-asserted-by":"crossref","first-page":"153","DOI":"10.1194\/jlr.M700400-JLR200","article-title":"FA2H is responsible for the formation of 2-hydroxy galactolipids in peripheral nervous system myelin","volume":"49","author":"Maldonado","year":"2008","journal-title":"J Lipid Res"},{"key":"2026090708274059600_ref28","doi-asserted-by":"crossref","DOI":"10.1016\/j.celrep.2023.112841","article-title":"Astrocytic response mediated by the CLU risk allele inhibits OPC proliferation and myelination in a human iPSC model","volume":"42","author":"Liu","year":"2023","journal-title":"Cell Rep"},{"key":"2026090708274059600_ref29","doi-asserted-by":"crossref","first-page":"12162","DOI":"10.1523\/JNEUROSCI.2127-15.2015","article-title":"Inactivation of protein tyrosine phosphatase receptor Type Z by pleiotrophin promotes remyelination through activation of differentiation of oligodendrocyte precursor cells","volume":"35","author":"Kuboyama","year":"2015","journal-title":"J Neurosci"},{"key":"2026090708274059600_ref30","doi-asserted-by":"crossref","first-page":"1605","DOI":"10.1002\/glia.22381","article-title":"Autotaxin\/ENPP2 regulates oligodendrocyte differentiation in vivo in the developing zebrafish hindbrain","volume":"60","author":"Yuelling","year":"2012","journal-title":"Glia"},{"key":"2026090708274059600_ref31","doi-asserted-by":"crossref","first-page":"465","DOI":"10.1042\/BST20160022","article-title":"Tspan2: a tetraspanin protein involved in oligodendrogenesis and cancer metastasis","volume":"45","author":"Yaseen","year":"2017","journal-title":"Biochem Soc Trans"},{"key":"2026090708274059600_ref32","doi-asserted-by":"crossref","first-page":"238","DOI":"10.1002\/(SICI)1097-4547(19971015)50:2<238::AID-JNR12>3.0.CO;2-4","article-title":"CNP overexpression induces aberrant oligodendrocyte membranes and inhibits MBP accumulation and myelin compaction","volume":"50","author":"Yin","year":"1997","journal-title":"J Neurosci Res"},{"key":"2026090708274059600_ref33","doi-asserted-by":"crossref","first-page":"820","DOI":"10.1038\/s41591-021-01323-8","article-title":"A single-cell map of intratumoral changes during anti-PD1 treatment of patients with breast cancer","volume":"27","author":"Bassez","year":"2021","journal-title":"Nat Med"},{"key":"2026090708274059600_ref34","doi-asserted-by":"crossref","first-page":"860","DOI":"10.1200\/JCO.2011.41.0902","article-title":"Prognostic and predictive value of tumor-infiltrating lymphocytes in a phase III randomized adjuvant breast cancer trial in node-positive breast cancer comparing the addition of docetaxel to doxorubicin with doxorubicin-based chemotherapy: BIG 02-98","volume":"31","author":"Loi","year":"2013","journal-title":"J Clin Oncol"},{"key":"2026090708274059600_ref35","doi-asserted-by":"crossref","first-page":"40","DOI":"10.1016\/S1470-2045(17)30904-X","article-title":"Tumour-infiltrating lymphocytes and prognosis in different subtypes of breast cancer: a pooled analysis of 3771 patients treated with neoadjuvant therapy","volume":"19","author":"Denkert","year":"2018","journal-title":"Lancet Oncol"},{"key":"2026090708274059600_ref36","doi-asserted-by":"crossref","first-page":"28","DOI":"10.1158\/1078-0432.CCR-11-2701","article-title":"Molecular pathways: involvement of immune pathways in the therapeutic response and outcome in breast cancer","volume":"19","author":"Andre","year":"2013","journal-title":"Clin Cancer Res"},{"key":"2026090708274059600_ref37","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1186\/s13058-019-1176-2","article-title":"Cancer-immune interactions in ER-positive breast cancers: PI3K pathway alterations and tumor-infiltrating lymphocytes","volume":"21","author":"Sobral-Leite","year":"2019","journal-title":"Breast Cancer Res"},{"key":"2026090708274059600_ref38","doi-asserted-by":"crossref","first-page":"1746","DOI":"10.1093\/jnci\/dji400","article-title":"Intrinsic mechanism of estradiol-induced apoptosis in breast cancer cells resistant to estrogen deprivation","volume":"97","author":"Lewis","year":"2005","journal-title":"J Natl Cancer Inst"},{"key":"2026090708274059600_ref39","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1016\/j.bbrc.2010.07.132","article-title":"ER regulates an evolutionarily conserved apoptosis pathway","volume":"400","author":"Liu","year":"2010","journal-title":"Biochem Biophys Res Commun"},{"key":"2026090708274059600_ref40","first-page":"003","article-title":"Regulation of apoptosis by HER2 in breast cancer","volume":"2013","author":"Carpenter","year":"2013","journal-title":"J Carcinog Mutagen"},{"key":"2026090708274059600_ref41","doi-asserted-by":"crossref","first-page":"972664","DOI":"10.3389\/fgene.2022.972664","article-title":"Differential expression of HAVCR2 gene in pan-cancer: a potential biomarker for survival and immunotherapy","volume":"13","author":"Li","year":"2022","journal-title":"Front Genet"},{"key":"2026090708274059600_ref42","doi-asserted-by":"crossref","first-page":"1479","DOI":"10.1007\/s00262-022-03343-w","article-title":"CXCL9 influences the tumor immune microenvironment by stimulating JAK\/STAT pathway in triple-negative breast cancer","volume":"72","author":"Lei","year":"2023","journal-title":"Cancer Immunol Immunother"},{"key":"2026090708274059600_ref43","doi-asserted-by":"crossref","first-page":"6365","DOI":"10.7150\/jca.46301","article-title":"Identification of CTLA-4 associated with tumor microenvironment and competing interactions in triple negative breast cancer by co-expression network analysis","volume":"11","author":"Peng","year":"2020","journal-title":"J Cancer"},{"key":"2026090708274059600_ref44","doi-asserted-by":"crossref","first-page":"154","DOI":"10.1158\/2326-6066.CIR-20-0649","article-title":"NKG7 is required for optimal antitumor t-cell immunity","volume":"10","author":"Li","year":"2022","journal-title":"Cancer Immunol Res"},{"key":"2026090708274059600_ref45","article-title":"Microbiome preterm birth dream challenge: crowdsourcing machine learning approaches to advance preterm birth research","volume":"5","author":"Golob","year":"2024","journal-title":"Cell Rep Med"},{"key":"2026090708274059600_ref46","doi-asserted-by":"crossref","first-page":"3227","DOI":"10.1016\/j.celrep.2017.03.004","article-title":"Single-cell RNA-seq reveals hypothalamic cell diversity","volume":"18","author":"Chen","year":"2017","journal-title":"Cell Rep"}],"container-title":["Briefings in Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/27\/5\/bbag476\/70981184\/bbag476.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/27\/5\/bbag476\/70981184\/bbag476.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T12:27:55Z","timestamp":1788784075000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bib\/article\/doi\/10.1093\/bib\/bbag476\/8787140"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,1]]},"references-count":46,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2026,9,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bib\/bbag476","relation":{},"ISSN":["1467-5463","1477-4054"],"issn-type":[{"value":"1467-5463","type":"print"},{"value":"1477-4054","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,9]]},"published":{"date-parts":[[2026,9,1]]},"article-number":"bbag476"}}