{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,29]],"date-time":"2026-08-29T05:19:05Z","timestamp":1787980745591,"version":"build-2784847793"},"reference-count":50,"publisher":"MDPI AG","issue":"9","license":[{"start":{"date-parts":[[2026,8,27]],"date-time":"2026-08-27T00:00:00Z","timestamp":1787788800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Beijing Natural Science Foundation","award":["7252169"],"award-info":[{"award-number":["7252169"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["82270721"],"award-info":[{"award-number":["82270721"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"award":["82270721"],"award-info":[{"award-number":["82270721"]}],"id":[{"id":"https:\/\/ror.org\/01h0zpd94","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Genes"],"abstract":"<jats:p>Background: Prostate cancer (PCa) is a leading cause of cancer-related mortality worldwide, highlighting the need for improved prognostic tools. The integration of artificial intelligence (AI) and machine learning (ML) with multi-omics data offers new opportunities for biomarker discovery and risk stratification. Methods: We integrated bulk transcriptomic data from GSE116918 (training, n = 248) and three cross-cohort consistency evaluation cohorts (TCGA-PRAD, GSE70769, GSE46602), focusing on 1087 epithelial\u2013mesenchymal transition (EMT)-associated genes. Using consensus clustering, weighted gene co-expression network analysis (WGCNA), and 91 machine learning algorithm combinations (including Random Forest, Lasso, and CoxBoost), we constructed a prognostic signature. SHAP analysis was used for model interpretability. Single-cell RNA sequencing (scRNA-seq, GSE268307, 10,672 cells) and spatial transcriptomics (10\u00d7 Genomics Visium FFPE) provided hypothesis-generating evidence; spatial analysis was based on one tissue section. Results: A three-gene signature (INHBA, FAP, ITGBL1) effectively stratified patients into high- and low-risk groups, with the high-risk group showing significantly worse metastasis-free survival (HR = 1.61, 95% CI: 1.39\u20131.87; 4-year AUC = 0.93 in the training cohort; external AUCs ranged from 0.62 to 0.77). CytoTRACE inferred high differentiation potential of COMP+ fibroblasts, and Monocle3 inferred a transcriptional transition from COMP+ toward NELL2+ fibroblasts. BayesPrism deconvolution suggested that high inferred COMP+ fibroblast abundance was associated with poor prognosis and advanced T stage. NicheNet analysis prioritized BMP7 as a key upstream ligand, with downstream targets enriched in TGF-\u03b2 signaling and stem cell pluripotency pathways. Conclusions: This study presents a machine learning-based multi-omics framework for prostate cancer risk stratification. The three-gene signature provides a new exploratory prognostic model while inferring a COMP+ to NELL2+ transcriptional transition. These findings may inform future hypothesis-driven studies of treatment sensitivity, pending experimental validation, and demonstrate the value of AI-driven multi-omics integration for precision oncology.<\/jats:p>","DOI":"10.3390\/genes17091015","type":"journal-article","created":{"date-parts":[[2026,8,27]],"date-time":"2026-08-27T10:58:21Z","timestamp":1787828301000},"page":"1015","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Integrating Multi-Omics and Machine Learning to Reveal a Prognostic Model for Prostate Cancer Metastatic Recurrence Associated with Epithelial\u2013Mesenchymal Transition Features"],"prefix":"10.3390","volume":"17","author":[{"given":"Xueqian","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Medicine, Nankai University, 94 Weijin Road, Tianjin 300071, China"},{"name":"Department of Urology, PLA General Hospital, Beijing 100039, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Medicine, Nankai University, 94 Weijin Road, Tianjin 300071, China"},{"name":"Department of Urology, PLA General Hospital, Beijing 100039, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zheng","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Urology, PLA General Hospital, Beijing 100039, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinyang","family":"Shi","sequence":"additional","affiliation":[{"name":"School of Medicine, Nankai University, 94 Weijin Road, Tianjin 300071, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenghao","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Medicine, Nankai University, 94 Weijin Road, Tianjin 300071, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yan","family":"Gao","sequence":"additional","affiliation":[{"name":"School of Medical Technology, Hebei Medical University, Shijiazhuang 050031, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiheng","family":"Deng","sequence":"additional","affiliation":[{"name":"School of Medicine, Nankai University, 94 Weijin Road, Tianjin 300071, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianyu","family":"Shen","sequence":"additional","affiliation":[{"name":"School of Medicine, Nankai University, 94 Weijin Road, Tianjin 300071, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6054-1015","authenticated-orcid":false,"given":"Ziyan","family":"An","sequence":"additional","affiliation":[{"name":"Department of Urology, Beijing Shijitan Hospital, Capital Medical University, Beijing 100038, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weijun","family":"Fu","sequence":"additional","affiliation":[{"name":"Department of Urology, PLA General Hospital, Beijing 100039, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,8,27]]},"reference":[{"key":"ref_1","first-page":"394","article-title":"Global cancer statistics 2018: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries","volume":"68","author":"Bray","year":"2018","journal-title":"CA Cancer J. Clin."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"155","DOI":"10.1016\/j.canlet.2021.09.025","article-title":"Mechanistic insights into genetic susceptibility to prostate cancer","volume":"522","author":"Tian","year":"2021","journal-title":"Cancer Lett."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"e390396","DOI":"10.1200\/EDBK_390396","article-title":"Management of Prostate Cancer in Older Adults","volume":"43","author":"Graham","year":"2023","journal-title":"Am. Soc. Clin. Oncol. Educ. Book"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"527","DOI":"10.4111\/icu.20240229","article-title":"Prostate cancer theragnostics biomarkers: An update","volume":"65","author":"Am","year":"2024","journal-title":"Investig. Clin. Urol."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"837","DOI":"10.1016\/j.ijrobp.2021.06.043","article-title":"In Regard to Choudhury et al","volume":"111","author":"Chowdhry","year":"2021","journal-title":"Int. J. Radiat. Oncol. Biol. Phys."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"845","DOI":"10.1158\/1055-9965.EPI-16-1046","article-title":"A Review of Prostate Cancer Genome-Wide Association Studies (GWAS)","volume":"27","author":"Benafif","year":"2018","journal-title":"Cancer Epidemiol. Biomark. Prev."},{"key":"ref_7","first-page":"e70016","article-title":"Prostate Cancer: A Review of Genetics, Current Biomarkers and Personalised Treatments","volume":"7","author":"Wilson","year":"2024","journal-title":"Cancer Rep."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"652","DOI":"10.1001\/jamaoncol.2016.5983","article-title":"Surrogate End Points for All-Cause Mortality in Men with Localized Unfavorable-Risk Prostate Cancer Treated with Radiation Therapy vs Radiation Therapy Plus Androgen Deprivation Therapy: A Secondary Analysis of a Randomized Clinical Trial","volume":"3","author":"Royce","year":"2017","journal-title":"JAMA Oncol."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"341","DOI":"10.1038\/s41580-020-0237-9","article-title":"Guidelines and definitions for research on epithelial-mesenchymal transition","volume":"21","author":"Yang","year":"2020","journal-title":"Nat. Rev. Mol. Cell Biol."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"391","DOI":"10.1186\/s12967-021-03065-0","article-title":"Comprehensive analysis of EMT-related genes and lncRNAs in the prognosis, immunity, and drug treatment of colorectal cancer","volume":"19","author":"Yang","year":"2021","journal-title":"J. Transl. Med."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"69","DOI":"10.1038\/s41580-018-0080-4","article-title":"New insights into the mechanisms of epithelial-mesenchymal transition and implications for cancer","volume":"20","author":"Dongre","year":"2019","journal-title":"Nat. Rev. Mol. Cell Biol."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"417","DOI":"10.1016\/j.cels.2015.12.004","article-title":"The Molecular Signatures Database (MSigDB) hallmark gene set collection","volume":"1","author":"Liberzon","year":"2015","journal-title":"Cell Syst."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1572","DOI":"10.1093\/bioinformatics\/btq170","article-title":"ConsensusClusterPlus: A class discovery tool with confidence assessments and item tracking","volume":"26","author":"Wilkerson","year":"2010","journal-title":"Bioinformatics"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"e47","DOI":"10.1093\/nar\/gkv007","article-title":"Limma powers differential expression analyses for RNA-sequencing and microarray studies","volume":"43","author":"Ritchie","year":"2015","journal-title":"Nucleic Acids Res."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"816","DOI":"10.1038\/s41467-022-28421-6","article-title":"Machine learning-based integration develops an immune-derived lncRNA signature for improving outcomes in colorectal cancer","volume":"13","author":"Liu","year":"2022","journal-title":"Nat. Commun."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"228","DOI":"10.4258\/hir.2023.29.3.228","article-title":"Understanding Arteriosclerotic Heart Disease Patients Using Electronic Health Records: A Machine Learning and Shapley Additive exPlanations Approach","volume":"29","author":"Miranda","year":"2023","journal-title":"Healthc. Inform. Res."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"W234","DOI":"10.1093\/nar\/gkz240","article-title":"NetworkAnalyst 3.0: A visual analytics platform for comprehensive gene expression profiling and meta-analysis","volume":"47","author":"Zhou","year":"2019","journal-title":"Nucleic Acids Res."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"823","DOI":"10.1038\/nprot.2015.052","article-title":"NetworkAnalyst for statistical, visual and network-based meta-analysis of gene expression data","volume":"10","author":"Xia","year":"2015","journal-title":"Nat. Protoc."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"W167","DOI":"10.1093\/nar\/gku443","article-title":"NetworkAnalyst\u2014Integrative approaches for protein-protein interaction network analysis and visual exploration","volume":"42","author":"Xia","year":"2014","journal-title":"Nucleic Acids Res."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"3232","DOI":"10.1093\/bioinformatics\/btt562","article-title":"INVEX\u2014A web-based tool for integrative visualization of expression data","volume":"29","author":"Xia","year":"2013","journal-title":"Bioinformatics"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"W63","DOI":"10.1093\/nar\/gkt338","article-title":"INMEX\u2014A web-based tool for integrative meta-analysis of expression data","volume":"41","author":"Xia","year":"2013","journal-title":"Nucleic Acids Res."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"248","DOI":"10.1016\/j.celrep.2016.12.019","article-title":"Pan-cancer Immunogenomic Analyses Reveal Genotype-Immunophenotype Relationships and Predictors of Response to Checkpoint Blockade","volume":"18","author":"Charoentong","year":"2017","journal-title":"Cell Rep."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"453","DOI":"10.1038\/nmeth.3337","article-title":"Robust enumeration of cell subsets from tissue expression profiles","volume":"12","author":"Newman","year":"2015","journal-title":"Nat. Methods"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"2612","DOI":"10.1038\/ncomms3612","article-title":"Inferring tumour purity and stromal and immune cell admixture from expression data","volume":"4","author":"Yoshihara","year":"2013","journal-title":"Nat. Commun."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"bbab260","DOI":"10.1093\/bib\/bbab260","article-title":"oncoPredict: An R package for predicting in vivo or cancer patient drug response and biomarkers from cell line screening data","volume":"22","author":"Maeser","year":"2021","journal-title":"Brief. Bioinform."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"1289","DOI":"10.1038\/s41592-019-0619-0","article-title":"Fast, sensitive and accurate integration of single-cell data with Harmony","volume":"16","author":"Korsunsky","year":"2019","journal-title":"Nat. Methods"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"1121","DOI":"10.1186\/s12967-024-05934-w","article-title":"Integrating single-cell RNA-Seq and machine learning to dissect tryptophan metabolism in ulcerative colitis","volume":"22","author":"Chen","year":"2024","journal-title":"J. Transl. Med."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"517","DOI":"10.1038\/s41587-021-00830-w","article-title":"Robust decomposition of cell type mixtures in spatial transcriptomics","volume":"40","author":"Cable","year":"2021","journal-title":"Nat. Biotechnol."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"1088","DOI":"10.1038\/s41467-021-21246-9","article-title":"Inference and analysis of cell-cell communication using CellChat","volume":"12","author":"Jin","year":"2021","journal-title":"Nat. Commun."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"505","DOI":"10.1038\/s43018-022-00356-3","article-title":"Cell type and gene expression deconvolution with BayesPrism enables Bayesian integrative analysis across bulk and single-cell RNA sequencing in oncology","volume":"3","author":"Chu","year":"2022","journal-title":"Nat. Cancer"},{"key":"ref_31","first-page":"17","article-title":"Cancer statistics, 2023","volume":"73","author":"Siegel","year":"2023","journal-title":"CA Cancer J. Clin."},{"key":"ref_32","first-page":"10","article-title":"Cancer statistics, 2025","volume":"75","author":"Siegel","year":"2025","journal-title":"CA Cancer J. Clin."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"130","DOI":"10.1016\/j.phrs.2017.07.009","article-title":"Arenobufagin inhibits prostate cancer epithelial-mesenchymal transition and metastasis by down-regulating \u03b2-catenin","volume":"123","author":"Chen","year":"2017","journal-title":"Pharmacol. Res."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"442","DOI":"10.1038\/nrc822","article-title":"Epithelial-mesenchymal transitions in tumour progression","volume":"2","author":"Thiery","year":"2002","journal-title":"Nat. Rev. Cancer"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"720","DOI":"10.1038\/s41580-024-00733-z","article-title":"Epithelial-mesenchymal transition in tissue repair and degeneration","volume":"25","author":"Youssef","year":"2024","journal-title":"Nat. Rev. Mol. Cell Biol."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"107144","DOI":"10.1016\/j.phrs.2024.107144","article-title":"The role of epithelial cells in fibrosis: Mechanisms and treatment","volume":"202","author":"Luo","year":"2024","journal-title":"Pharmacol. Res."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"106866","DOI":"10.1016\/j.phrs.2023.106866","article-title":"Lycorine suppresses the malignancy of breast carcinoma by modulating epithelial mesenchymal transition and \u03b2-catenin signaling","volume":"195","author":"Sun","year":"2023","journal-title":"Pharmacol. Res."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1186\/s13045-022-01347-8","article-title":"The molecular mechanisms and therapeutic strategies of EMT in tumor progression and metastasis","volume":"15","author":"Huang","year":"2022","journal-title":"J. Hematol. Oncol."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Telecan, T., Chiorean, A., Sipos-Lascu, R., Caraiani, C., Boca, B., Hendea, R.M., Buliga, T., Andras, I., Crisan, N., and Lupsor-Platon, M. (2025). ISUP Grade Prediction of Prostate Nodules on T2WI Acquisitions Using Clinical Features, Textural Parameters and Machine Learning-Based Algorithms. Cancers, 17.","DOI":"10.3390\/cancers17122035"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"294","DOI":"10.1002\/humu.22489","article-title":"Germline mutations of inhibins in early-onset ovarian epithelial tumors","volume":"35","author":"Tournier","year":"2014","journal-title":"Hum. Mutat."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"2","DOI":"10.1016\/j.mce.2011.06.030","article-title":"New insights into the mechanisms of activin action and inhibition","volume":"359","author":"Walton","year":"2012","journal-title":"Mol. Cell. Endocrinol."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"464","DOI":"10.1093\/cvr\/cvt265","article-title":"Damage-associated molecular pattern activated Toll-like receptor 4 signalling modulates blood pressure in L-NAME-induced hypertension","volume":"101","author":"Sollinger","year":"2014","journal-title":"Cardiovasc. Res."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Zhao, K., Yi, Y., Ma, Z., and Zhang, W. (2021). INHBA is a Prognostic Biomarker and Correlated with Immune Cell Infiltration in Cervical Cancer. Front. Genet., 12.","DOI":"10.3389\/fgene.2021.705512"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"36505","DOI":"10.1074\/jbc.274.51.36505","article-title":"Fibroblast activation protein, a dual specificity serine protease expressed in reactive human tumor stromal fibroblasts","volume":"274","author":"Park","year":"1999","journal-title":"J. Biol. Chem."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"475","DOI":"10.1186\/s12967-023-04303-3","article-title":"TGF-\u03b21 dominates stromal fibroblast-mediated EMT via the FAP\/VCAN axis in bladder cancer cells","volume":"21","author":"Ping","year":"2023","journal-title":"J. Transl. Med."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"169","DOI":"10.1006\/geno.1998.5707","article-title":"Cloning and characterization of a novel beta integrin-related cDNA coding for the protein TIED (\u201cten beta integrin EGF-like repeat domains\u201d) that maps to chromosome band 13q33: A divergent stand-alone integrin stalk structure","volume":"56","author":"Berg","year":"1999","journal-title":"Genomics"},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"3302","DOI":"10.1158\/0008-5472.CAN-15-0240","article-title":"ITGBL1 Is a Runx2 Transcriptional Target and Promotes Breast Cancer Bone Metastasis by Activating the TGF\u03b2 Signaling Pathway","volume":"75","author":"Li","year":"2015","journal-title":"Cancer Res."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1016\/j.biopha.2016.03.053","article-title":"Extracellular matrix protein ITGBL1 promotes ovarian cancer cell migration and adhesion through Wnt\/PCP signaling and FAK\/SRC pathway","volume":"81","author":"Sun","year":"2016","journal-title":"Biomed. Pharmacother."},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"172","DOI":"10.1016\/j.biopha.2018.05.033","article-title":"ITGBL1 promotes migration, invasion and predicts a poor prognosis in colorectal cancer","volume":"104","author":"Qiu","year":"2018","journal-title":"BioMed Pharmacother."},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"1663","DOI":"10.1007\/s13277-015-3919-8","article-title":"Epigenetic downregulated ITGBL1 promotes non-small cell lung cancer cell invasion through Wnt\/PCP signaling","volume":"37","author":"Gan","year":"2016","journal-title":"Tumor Biol."}],"container-title":["Genes"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-4425\/17\/9\/1015\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,29]],"date-time":"2026-08-29T04:48:14Z","timestamp":1787978894000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-4425\/17\/9\/1015"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,27]]},"references-count":50,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2026,9]]}},"alternative-id":["genes17091015"],"URL":"https:\/\/doi.org\/10.3390\/genes17091015","relation":{},"ISSN":["2073-4425"],"issn-type":[{"value":"2073-4425","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,27]]}}}