{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T21:06:47Z","timestamp":1773781607962,"version":"3.50.1"},"update-to":[{"DOI":"10.1371\/journal.pcbi.1014074","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T00:00:00Z","timestamp":1773705600000}}],"reference-count":40,"publisher":"Public Library of Science (PLoS)","issue":"3","license":[{"start":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T00:00:00Z","timestamp":1773273600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"General Project of Ningbo Public Welfare Research Program","award":["2023S043"],"award-info":[{"award-number":["2023S043"]}]},{"name":"Innovation Project of Distinguished Medical Team in Ningbo","award":["2022020405"],"award-info":[{"award-number":["2022020405"]}]},{"name":"Key Technology Breakthrough Program of \u00e2\u20ac\u02dcNingbo Sci-Tech Innovation YONGJIANG 2035\u00e2\u20ac\u2122","award":["2024Z222"],"award-info":[{"award-number":["2024Z222"]}]},{"name":"NINGBO Leading Medical &Health Discipline","award":["2026-A34"],"award-info":[{"award-number":["2026-A34"]}]},{"name":"Social Development Public Welfare Foundation of Ningbo","award":["2022S035"],"award-info":[{"award-number":["2022S035"]}]},{"name":"Ningbo Science and Technology Project","award":["2023Z178"],"award-info":[{"award-number":["2023Z178"]}]},{"name":"Major Research Project of Ningbo Clinical Medical Research Center","award":["2024L002"],"award-info":[{"award-number":["2024L002"]}]},{"name":"Key Technology Breakthrough Program of \u00e2\u20ac\u02dcNingbo Sci-Tech Innovation YONGJIANG 2035\u00e2\u20ac\u2122","award":["2024Z221"],"award-info":[{"award-number":["2024Z221"]}]},{"name":"Ningbo Medical and Health Brand Discipline","award":["PPXK2024-06"],"award-info":[{"award-number":["PPXK2024-06"]}]},{"name":"Key Technology Breakthrough Program of Ningbo Sci-Tech Innovation YONGJIANG 2035","award":["2025Z160"],"award-info":[{"award-number":["2025Z160"]}]},{"name":"Clinical Innovation Team Talent Project","award":["CXTD202502005"],"award-info":[{"award-number":["CXTD202502005"]}]}],"content-domain":{"domain":["www.ploscompbiol.org"],"crossmark-restriction":false},"short-container-title":["PLoS Comput Biol"],"abstract":"<jats:p>Alzheimer\u2019s disease (AD) is a progressive neurodegenerative disorder with limited diagnostic tools and poorly understood molecular underpinnings. Although multi-omics technologies hold promise for early detection, integrating unpaired transcriptomic and epigenetic data remains a major challenge due to modality heterogeneity and small sample sizes. We present AE-Trans, an interpretable dual-channel Transformer framework that aligns RNA and DNA methylation data through cross-modal reconstruction and multi-head attention. AE-Trans achieves superior performance on prefrontal cortex datasets (accuracy\u2009=\u20090.9736, AUC\u2009=\u20090.9910) and demonstrates strong generalizability to external regions temporal cortex cohorts across brain regions (accuracy\u2009=\u20090.7389, AUC\u2009=\u20090.8432). To validate the performance within the same brain region, we tested AE-Trans on an external unpaired multi-omics dataset from the prefrontal cortex. Additionally, we validated the model on a paired multi-omics dataset to assess whether it could achieve good results in real-world scenarios. In the unpaired dataset from the external same brain region, AE-Trans achieved an accuracy of (accuracy\u2009=\u20090.87) and AUC of (AUC\u2009=\u20090.94), while in the real-world paired multi-omics dataset, the accuracy was (accuracy\u2009=\u20090.88) and AUC was (AUC\u2009=\u20090.93). These results demonstrate that AE-Trans not only validates well on external unpaired datasets, but also generalizes effectively to real-world multi-omics paired datasets, highlighting its robustness in practical applications. Through counterfactual integrated gradients, we identified key features associated with immune regulation, hormonal signaling, and neuronal metabolism. These were validated via pathway enrichment and logistic regression (AUC\u2009=\u20090.9749), confirming the biological relevance of model-derived markers. Furthermore, AE-Trans generalized well to two independent RNA datasets, where latent representations not only improved classification (AUCs\u2009=\u20090.92 and 0.89) but also stratified patients into subgroups with significantly different prognoses. These results highlight AE-Trans as a robust and explainable tool for multi-omics integration, supporting early diagnosis, biomarker discovery, and individualized risk prediction in Alzheimer\u2019s disease.<\/jats:p>","DOI":"10.1371\/journal.pcbi.1014074","type":"journal-article","created":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T17:36:13Z","timestamp":1773336973000},"page":"e1014074","update-policy":"https:\/\/doi.org\/10.1371\/journal.pcbi.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Interpretable integration of unpaired multi-omics for Alzheimer\u2019s diagnosis via cross-modal transformer reconstruction"],"prefix":"10.1371","volume":"22","author":[{"given":"Kai","family":"Liao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Danfeng","family":"Du","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiawei","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaodan","family":"Fan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Changshui","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shanshan","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bowei","family":"Yan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8353-579X","authenticated-orcid":true,"given":"Haibo","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"340","published-online":{"date-parts":[[2026,3,12]]},"reference":[{"issue":"1","key":"pcbi.1014074.ref001","doi-asserted-by":"crossref","first-page":"2637","DOI":"10.1038\/s41598-024-51985-w","article-title":"An explainable machine learning approach for Alzheimer\u2019s disease classification","volume":"14","author":"AS Alatrany","year":"2024","journal-title":"Sci Rep"},{"issue":"1","key":"pcbi.1014074.ref002","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1186\/s13195-022-01047-y","article-title":"Early diagnosis of Alzheimer\u2019s disease using machine learning: a multi-diagnostic, generalizable approach","volume":"14","author":"VS Diogo","year":"2022","journal-title":"Alzheimers Res Ther"},{"key":"pcbi.1014074.ref003","doi-asserted-by":"crossref","first-page":"111","DOI":"10.1016\/j.media.2019.01.007","article-title":"Multi-task exclusive relationship learning for alzheimer\u2019s disease progression prediction with longitudinal data","volume":"53","author":"M Wang","year":"2019","journal-title":"Med Image Anal"},{"issue":"1","key":"pcbi.1014074.ref004","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1186\/s13024-019-0333-5","article-title":"The neuropathological diagnosis of Alzheimer\u2019s disease","volume":"14","author":"MA DeTure","year":"2019","journal-title":"Mol Neurodegener"},{"key":"pcbi.1014074.ref005","doi-asserted-by":"crossref","first-page":"107328","DOI":"10.1016\/j.compbiomed.2023.107328","article-title":"Multi-modal graph neural network for early diagnosis of Alzheimer\u2019s disease from sMRI and PET scans","volume":"164","author":"Y Zhang","year":"2023","journal-title":"Comput Biol Med"},{"key":"pcbi.1014074.ref006","doi-asserted-by":"crossref","first-page":"363","DOI":"10.1016\/j.inffus.2022.11.028","article-title":"Prediction of Alzheimer\u2019s progression based on multimodal Deep-Learning-based fusion and visual Explainability of time-series data","volume":"92","author":"N Rahim","year":"2023","journal-title":"Information Fusion"},{"key":"pcbi.1014074.ref007","doi-asserted-by":"crossref","first-page":"104536","DOI":"10.1016\/j.chemolab.2022.104536","article-title":"Alzheimer\u2019s disease prediction based on continuous feature representation using multi-omics data integration","volume":"223","author":"Z Abbas","year":"2022","journal-title":"Chemometrics and Intelligent Laboratory Systems"},{"key":"pcbi.1014074.ref008","article-title":"A machine learning method for identifying critical interactions between gene pairs in Alzheimer\u2019s disease prediction","author":"H Chen","year":"2019","journal-title":"Front Neurol"},{"issue":"6","key":"pcbi.1014074.ref009","article-title":"Integrative-omics for discovery of network-level disease biomarkers: a case study in Alzheimer\u2019s disease","volume":"22","author":"L Xie","year":"2021","journal-title":"Brief Bioinform"},{"key":"pcbi.1014074.ref010","doi-asserted-by":"crossref","first-page":"976","DOI":"10.3389\/fgene.2019.00976","article-title":"Effective diagnosis of Alzheimer\u2019s disease via multimodal fusion analysis framework","volume":"10","author":"XA Bi","year":"2019","journal-title":"Front Genet"},{"issue":"8","key":"pcbi.1014074.ref011","doi-asserted-by":"crossref","first-page":"686","DOI":"10.3390\/jpm11080686","article-title":"JDSNMF: Joint Deep Semi-Non-Negative Matrix Factorization for Learning Integrative Representation of Molecular Signals in Alzheimer\u2019s Disease","volume":"11","author":"S Moon","year":"2021","journal-title":"J Pers Med"},{"key":"pcbi.1014074.ref012","doi-asserted-by":"crossref","first-page":"112873","DOI":"10.1016\/j.eswa.2019.112873","article-title":"Prediction of Alzheimer\u2019s disease based on deep neural network by integrating gene expression and DNA methylation dataset","volume":"140","author":"C Park","year":"2020","journal-title":"Expert Systems with Applications"},{"key":"pcbi.1014074.ref013","doi-asserted-by":"crossref","first-page":"1651","DOI":"10.1016\/j.csbj.2023.02.021","article-title":"Deep belief network-based approach for detecting Alzheimer\u2019s disease using the multi-omics data","volume":"21","author":"N Mahendran","year":"2023","journal-title":"Comput Struct Biotechnol J"},{"issue":"5","key":"pcbi.1014074.ref014","doi-asserted-by":"crossref","first-page":"1472","DOI":"10.1109\/TMI.2022.3230750","article-title":"Deep Multi-Modal Discriminative and Interpretability Network for Alzheimer\u2019s Disease Diagnosis","volume":"42","author":"Q Zhu","year":"2023","journal-title":"IEEE Trans Med Imaging"},{"issue":"7","key":"pcbi.1014074.ref015","doi-asserted-by":"crossref","first-page":"743","DOI":"10.15252\/msb.20145304","article-title":"Common dysregulation network in the human prefrontal cortex underlies two neurodegenerative diseases","volume":"10","author":"M Narayanan","year":"2014","journal-title":"Mol Syst Biol"},{"issue":"3","key":"pcbi.1014074.ref016","doi-asserted-by":"crossref","first-page":"707","DOI":"10.1016\/j.cell.2013.03.030","article-title":"Integrated systems approach identifies genetic nodes and networks in late-onset Alzheimer\u2019s disease","volume":"153","author":"B Zhang","year":"2013","journal-title":"Cell"},{"issue":"12","key":"pcbi.1014074.ref017","doi-asserted-by":"crossref","first-page":"1580","DOI":"10.1016\/j.jalz.2018.01.017","article-title":"Elevated DNA methylation across a 48-kb region spanning the HOXA gene cluster is associated with Alzheimer\u2019s disease neuropathology","volume":"14","author":"RG Smith","year":"2018","journal-title":"Alzheimers Dement"},{"issue":"3","key":"pcbi.1014074.ref018","doi-asserted-by":"crossref","first-page":"691","DOI":"10.3233\/JAD-181113","article-title":"Transcriptome Changes in the Alzheimer\u2019s Disease Middle Temporal Gyrus: Importance of RNA Metabolism and Mitochondria-Associated Membrane Genes","volume":"70","author":"IS Piras","year":"2019","journal-title":"J Alzheimers Dis"},{"key":"pcbi.1014074.ref019","doi-asserted-by":"crossref","first-page":"644","DOI":"10.1016\/j.bbi.2019.05.009","article-title":"Transcriptomic analysis of probable asymptomatic and symptomatic alzheimer brains","volume":"80","author":"H Patel","year":"2019","journal-title":"Brain Behav Immun"},{"issue":"5","key":"pcbi.1014074.ref020","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1186\/gm452","article-title":"Genes and pathways underlying regional and cell type changes in Alzheimer\u2019s disease","volume":"5","author":"JA Miller","year":"2013","journal-title":"Genome Med"},{"issue":"14","key":"pcbi.1014074.ref021","article-title":"Age-related decline in hippocampal tyrosine phosphatase PTPRO is a mechanistic factor in chemotherapy-related cognitive impairment","volume":"8","author":"Z Yao","year":"2023","journal-title":"JCI Insight"},{"issue":"6","key":"pcbi.1014074.ref022","first-page":"8069","article-title":"Combined bioinformatics analysis reveals gene expression and DNA methylation patterns in osteoarthritis","volume":"17","author":"D Song","year":"2018","journal-title":"Mol Med Rep"},{"issue":"5","key":"pcbi.1014074.ref023","first-page":"2637","article-title":"An integrated methylation and gene expression microarray analysis reveals significant prognostic biomarkers in oral squamous cell carcinoma","volume":"40","author":"C Zhao","year":"2018","journal-title":"Oncol Rep"},{"key":"pcbi.1014074.ref024","doi-asserted-by":"crossref","first-page":"1332928","DOI":"10.3389\/frdem.2024.1332928","article-title":"Alzheimer\u2019s disease detection using data fusion with a deep supervised encoder","volume":"3","author":"M Trinh","year":"2024","journal-title":"Front Dement"},{"issue":"8","key":"pcbi.1014074.ref025","doi-asserted-by":"crossref","first-page":"1430","DOI":"10.1038\/s41592-024-02353-z","article-title":"Transformers in single-cell omics: a review and new perspectives","volume":"21","author":"A Sza\u0142ata","year":"2024","journal-title":"Nat Methods"},{"key":"pcbi.1014074.ref026"},{"issue":"2","key":"pcbi.1014074.ref027","doi-asserted-by":"crossref","first-page":"101","DOI":"10.1016\/j.ydbio.2012.04.026","article-title":"KLC3 is involved in sperm tail midpiece formation and sperm function","volume":"366","author":"Y Zhang","year":"2012","journal-title":"Dev Biol"},{"issue":"1","key":"pcbi.1014074.ref028","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1007\/s00125-014-3395-5","article-title":"Roles of TBC1D1 and TBC1D4 in insulin- and exercise-stimulated glucose transport of skeletal muscle","volume":"58","author":"GD Cartee","year":"2015","journal-title":"Diabetologia"},{"issue":"11","key":"pcbi.1014074.ref029","doi-asserted-by":"crossref","first-page":"4512","DOI":"10.1038\/s41380-023-02239-0","article-title":"Targeting NLRP3 inflammasome for neurodegenerative disorders","volume":"28","author":"J Yao","year":"2023","journal-title":"Mol Psychiatry"},{"issue":"1","key":"pcbi.1014074.ref030","doi-asserted-by":"crossref","first-page":"80","DOI":"10.1186\/s12974-023-02766-1","article-title":"The short isoform of MS4A7 is a novel player in glioblastoma microenvironment, M2 macrophage polarization, and tumor progression","volume":"20","author":"B Ni","year":"2023","journal-title":"J Neuroinflammation"},{"issue":"5","key":"pcbi.1014074.ref031","doi-asserted-by":"crossref","first-page":"429","DOI":"10.1038\/ng.803","article-title":"Common variants at ABCA7, MS4A6A\/MS4A4E, EPHA1, CD33 and CD2AP are associated with Alzheimer\u2019s disease","volume":"43","author":"P Hollingworth","year":"2011","journal-title":"Nat Genet"},{"issue":"5","key":"pcbi.1014074.ref032","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1186\/gm249","article-title":"The membrane-spanning 4-domains, subfamily A (MS4A) gene cluster contains a common variant associated with Alzheimer\u2019s disease","volume":"3","author":"C Ant\u00fanez","year":"2011","journal-title":"Genome Med"},{"issue":"1","key":"pcbi.1014074.ref033","doi-asserted-by":"crossref","first-page":"2314","DOI":"10.1038\/s41467-023-37437-5","article-title":"Single-nucleus RNA-sequencing of autosomal dominant Alzheimer disease and risk variant carriers","volume":"14","author":"L Brase","year":"2023","journal-title":"Nat Commun"},{"issue":"1","key":"pcbi.1014074.ref034","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1016\/j.biopsych.2014.05.006","article-title":"Alzheimer\u2019s disease risk genes and mechanisms of disease pathogenesis","volume":"77","author":"CM Karch","year":"2015","journal-title":"Biol Psychiatry"},{"key":"pcbi.1014074.ref035","doi-asserted-by":"crossref","first-page":"895181","DOI":"10.3389\/fnins.2022.895181","article-title":"Detecting Brain Structure-Specific Methylation Signatures and Rules for Alzheimer\u2019s Disease","volume":"16","author":"Z Li","year":"2022","journal-title":"Front Neurosci"},{"issue":"9","key":"pcbi.1014074.ref036","doi-asserted-by":"crossref","first-page":"1236","DOI":"10.1038\/nn.4608","article-title":"Necroptosis activation in Alzheimer\u2019s disease","volume":"20","author":"A Caccamo","year":"2017","journal-title":"Nat Neurosci"},{"issue":"1","key":"pcbi.1014074.ref037","doi-asserted-by":"crossref","first-page":"205","DOI":"10.1186\/s12974-022-02567-y","article-title":"Hyperphosphorylated tau mediates neuronal death by inducing necroptosis and inflammation in Alzheimer\u2019s disease","volume":"19","author":"Y Dong","year":"2022","journal-title":"J Neuroinflammation"},{"issue":"2","key":"pcbi.1014074.ref038","doi-asserted-by":"crossref","first-page":"153","DOI":"10.1515\/rns.2011.018","article-title":"The role of CREB signaling in Alzheimer\u2019s disease and other cognitive disorders","volume":"22","author":"CA Saura","year":"2011","journal-title":"Rev Neurosci"},{"issue":"1","key":"pcbi.1014074.ref039","doi-asserted-by":"crossref","first-page":"3417","DOI":"10.1038\/s41467-021-22491-8","article-title":"Common variants in Alzheimer\u2019s disease and risk stratification by polygenic risk scores","volume":"12","author":"I de Rojas","year":"2021","journal-title":"Nat Commun"},{"issue":"505","key":"pcbi.1014074.ref040","doi-asserted-by":"crossref","DOI":"10.1126\/scitranslmed.aau2291","article-title":"The MS4A gene cluster is a key modulator of soluble TREM2 and Alzheimer\u2019s disease risk","volume":"11","author":"Y Deming","year":"2019","journal-title":"Sci Transl Med"}],"updated-by":[{"DOI":"10.1371\/journal.pcbi.1014074","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T00:00:00Z","timestamp":1773705600000}}],"container-title":["PLOS Computational Biology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1014074","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T17:42:43Z","timestamp":1773769363000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1014074"}},"subtitle":[],"editor":[{"given":"Samuel V.","family":"Scarpino","sequence":"first","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2026,3,12]]},"references-count":40,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2026,3,12]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pcbi.1014074","relation":{},"ISSN":["1553-7358"],"issn-type":[{"value":"1553-7358","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,12]]}}}