{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T23:13:33Z","timestamp":1771024413913,"version":"3.50.1"},"reference-count":43,"publisher":"MDPI AG","issue":"21","license":[{"start":{"date-parts":[[2025,10,28]],"date-time":"2025-10-28T00:00:00Z","timestamp":1761609600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Scientific Research at Northern Border University, Arar, KSA","award":["NBU-FFR-2025-1180-03"],"award-info":[{"award-number":["NBU-FFR-2025-1180-03"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Diagnostics"],"abstract":"<jats:p>Background\/Objectives: Cancer is a chronic and heterogeneous disease, possessing molecular variation within a single type, resulting in its molecular subtypes. Cancer molecular subtyping offers biological insights into cancer variability, facilitating the development of personalized medicines. Various models have been proposed for cancer molecular subtyping, utilizing the high-dimensional transcriptomic, genomic, or proteomic data. The issue of data scarcity, characterized by high feature dimensionality and a limited sample size, remains a persistent problem.The objective of this research is to propose a deep learning framework, DeepCMS, that leverages the capabilities of feed-forward neural networks, gene set enrichment analysis, and feature selection to construct a well-representative subset of the feature space, thereby producing promising results. Methods: The gene expression data were transformed into enrichment scores, resulting in over 22,000 features. From those, the top 2000 features were selected, and deep learning was applied to these features. The encouraging outcomes indicate the efficacy of the proposed framework in terms of defining a well-representative feature space and accurately classifying cancer molecular subtypes. Results: DeepCMS consistently outperformed state-of-the-art models in aggregated accuracy, sensitivity, specificity, and balanced accuracy. The aggregated metrics surpassed 0.90 for all efficiency measures on independent test datasets, showing the generalizability and robustness of our framework. Although developed using colon cancer\u2019s gene expression data, this approach may be applied to any gene expression data; a case study is also devised for illustration. Conclusions: Overall, the proposed DeepCMS framework enables the accurate and robust classification of cancer molecular subtypes using a compact and informative feature set, facilitating improved precision in oncology applications.<\/jats:p>","DOI":"10.3390\/diagnostics15212730","type":"journal-article","created":{"date-parts":[[2025,10,28]],"date-time":"2025-10-28T14:29:34Z","timestamp":1761661774000},"page":"2730","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["DeepCMS: A Feature Selection-Driven Model for Cancer Molecular Subtyping with a Case Study on Testicular Germ Cell Tumors"],"prefix":"10.3390","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-7115-0290","authenticated-orcid":false,"given":"Mehwish Wahid","family":"Khan","sequence":"first","affiliation":[{"name":"Department of Computer Science, National University of Computer and Emerging Sciences, Karachi 75030, Pakistan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0077-9638","authenticated-orcid":false,"given":"Ghufran","family":"Ahmed","sequence":"additional","affiliation":[{"name":"Department of Computer Science, National University of Computer and Emerging Sciences, Karachi 75030, Pakistan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1031-552X","authenticated-orcid":false,"given":"Muhammad","family":"Shahzad","sequence":"additional","affiliation":[{"name":"Department of Computer Science, GU Tech, Al Ghazali University, Karachi 75340, Pakistan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7050-0532","authenticated-orcid":false,"given":"Abdallah","family":"Namoun","sequence":"additional","affiliation":[{"name":"AI Center, Faculty of Computer and Information Systems, Islamic University of Madinah, Madinah 42351, Saudi Arabia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3722-8100","authenticated-orcid":false,"given":"Shahid","family":"Hussain","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Software Engineering, Penn State University, Behrend, Erie, PA 16563, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-9256-3665","authenticated-orcid":false,"given":"Meshari Huwaytim","family":"Alanazi","sequence":"additional","affiliation":[{"name":"Computer Science Department, College of Sciences, Northern Border University, Arar 73213, Saudi Arabia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,10,28]]},"reference":[{"key":"ref_1","first-page":"100782","article-title":"Automated Alzheimer\u2019s disease classification using deep learning models with Soft-NMS and improved ResNet50 integration","volume":"17","author":"Chen","year":"2024","journal-title":"J. Radiat. Res. Appl. Sci."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Choi, Y.A., Park, S.J., Jun, J.A., Pyo, C.S., Cho, K.H., Lee, H.S., and Yu, J.H. (2021). Deep learning-based stroke disease prediction system using real-time bio signals. Sensors, 21.","DOI":"10.3390\/s21134269"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"113978","DOI":"10.1016\/j.ab.2020.113978","article-title":"DeepACTION: A deep learning-based method for predicting novel drug-target interactions","volume":"610","author":"Mahmud","year":"2020","journal-title":"Anal. Biochem."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"923","DOI":"10.1016\/j.aej.2022.10.053","article-title":"A deep learning architecture for multi-class lung diseases classification using chest X-ray (CXR) images","volume":"64","author":"Alshmrani","year":"2023","journal-title":"Alex. Eng. J."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"lqab015","DOI":"10.1093\/nargab\/lqab015","article-title":"Two-stage Cox-nnet: Biologically interpretable neural-network model for prognosis prediction and its application in liver cancer survival using histopathology and transcriptomic data","volume":"3","author":"Zhan","year":"2021","journal-title":"NAR Genom. Bioinform."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"837","DOI":"10.1007\/s10209-018-0618-4","article-title":"The application of internet of things in healthcare: A systematic literature review and classification","volume":"18","author":"Ahmadi","year":"2019","journal-title":"Univers. Access Inf. Soc."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"249","DOI":"10.1007\/s10462-024-10876-2","article-title":"A review of deep learning models and online healthcare databases for electronic health records and their use for health prediction","volume":"57","author":"Nasarudin","year":"2024","journal-title":"Artif. Intell. Rev."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"1199087","DOI":"10.3389\/fgene.2023.1199087","article-title":"A review of multi-omics data integration through deep learning approaches for disease diagnosis, prognosis, and treatment","volume":"14","author":"Wekesa","year":"2023","journal-title":"Front. Genet."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Singh, R., Fazal, Z., Freemantle, S.J., and Spinella, M.J. (2021). Between a rock and a hard place: An epigenetic-centric view of testicular germ cell tumors. Cancers, 13.","DOI":"10.3390\/cancers13071506"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"110704","DOI":"10.1016\/j.mehy.2021.110704","article-title":"The cell of cancer origin provides the most reliable roadmap to its diagnosis, prognosis (biology) and therapy","volume":"157","author":"Pandya","year":"2021","journal-title":"Med. Hypotheses"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"227","DOI":"10.1080\/15384047.2018.1523853","article-title":"Molecular classification and subtype-specific drug sensitivity research of uterine carcinosarcoma under multi-omics framework","volume":"20","author":"Lu","year":"2019","journal-title":"Cancer Biol. Ther."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"100781","DOI":"10.1016\/j.crmeth.2024.100781","article-title":"Subtype-WGME enables whole-genome-wide multi-omics cancer subtyping","volume":"4","author":"Yang","year":"2024","journal-title":"Cell Rep. Methods"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"553587","DOI":"10.3389\/fgene.2020.553587","article-title":"Classifying breast cancer molecular subtypes by using deep clustering approach","volume":"11","author":"Rohani","year":"2020","journal-title":"Front. Genet."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Paz-Cabezas, M., Calvo-L\u00f3pez, T., Romera-Lopez, A., Tabas-Madrid, D., Ogando, J., Fern\u00e1ndez-Ace\u00f1ero, M.J., Sastre, J., Pascual-Montano, A., Ma\u00f1es, S., and D\u00edaz-Rubio, E. (2022). Molecular classification of colorectal cancer by microRNA profiling: Correlation with the Consensus Molecular Subtypes (CMS) and validation of miR-30b targets. Cancers, 14.","DOI":"10.3390\/cancers14215175"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Chen, L., Zeng, T., Pan, X., Zhang, Y.H., Huang, T., and Cai, Y.D. (2019). Identifying methylation pattern and genes associated with breast cancer subtypes. Int. J. Mol. Sci., 20.","DOI":"10.3390\/ijms20174269"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"62","DOI":"10.1016\/j.irbm.2020.12.002","article-title":"A hybrid deep learning model for predicting molecular subtypes of human breast cancer using multimodal data","volume":"43","author":"Liu","year":"2022","journal-title":"Irbm"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"100400","DOI":"10.1016\/j.xcrm.2021.100400","article-title":"Predicting endometrial cancer subtypes and molecular features from histopathology images using multi-resolution deep learning models","volume":"2","author":"Hong","year":"2021","journal-title":"Cell Rep. Med."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"3673","DOI":"10.1007\/s00330-020-07544-8","article-title":"Deep learning with convolutional neural network in the assessment of breast cancer molecular subtypes based on US images: A multicenter retrospective study","volume":"31","author":"Jiang","year":"2021","journal-title":"Eur. Radiol."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"866005","DOI":"10.3389\/fgene.2022.866005","article-title":"Molecular subtyping of cancer based on distinguishing co-expression modules and machine learning","volume":"13","author":"Sun","year":"2022","journal-title":"Front. Genet."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1186\/s13040-020-00222-x","article-title":"Deep learning-based ovarian cancer subtypes identification using multi-omics data","volume":"13","author":"Guo","year":"2020","journal-title":"BioData Min."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"756340","DOI":"10.3389\/fcell.2021.756340","article-title":"Identification and validation of the pyroptosis-related molecular subtypes of lung adenocarcinoma by bioinformatics and machine learning","volume":"9","author":"Liu","year":"2021","journal-title":"Front. Cell Dev. Biol."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"2231","DOI":"10.1093\/bioinformatics\/btab109","article-title":"Subtype-GAN: A deep learning approach for integrative cancer subtyping of multi-omics data","volume":"37","author":"Yang","year":"2021","journal-title":"Bioinformatics"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"2185","DOI":"10.1016\/j.csbj.2020.08.005","article-title":"An integrative deep learning framework for classifying molecular subtypes of breast cancer","volume":"18","author":"Islam","year":"2020","journal-title":"Comput. Struct. Biotechnol. J."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"100410","DOI":"10.1016\/j.jpi.2024.100410","article-title":"Deep learning-based classification of breast cancer molecular subtypes from H&E whole-slide images","volume":"16","author":"Tafavvoghi","year":"2025","journal-title":"J. Pathol. Inform."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"430","DOI":"10.1186\/s12859-022-04980-9","article-title":"Deep learning approach for cancer subtype classification using high-dimensional gene expression data","volume":"23","author":"Shen","year":"2022","journal-title":"BMC Bioinform."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1186\/s13040-022-00295-w","article-title":"Colorectal cancer subtype identification from differential gene expression levels using minimalist deep learning","volume":"15","author":"Li","year":"2022","journal-title":"BioData Min."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1007\/s11060-019-03376-9","article-title":"Prediction of lower-grade glioma molecular subtypes using deep learning","volume":"146","author":"Matsui","year":"2020","journal-title":"J. Neuro-Oncol."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"256","DOI":"10.1016\/j.eururo.2020.04.023","article-title":"Deep learning predicts molecular subtype of muscle-invasive bladder cancer from conventional histopathological slides","volume":"78","author":"Woerl","year":"2020","journal-title":"Eur. Urol."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"3715","DOI":"10.1093\/bioinformatics\/btab625","article-title":"Deep subspace mutual learning for cancer subtypes prediction","volume":"37","author":"Yang","year":"2021","journal-title":"Bioinformatics"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1613\/jair.953","article-title":"SMOTE: Synthetic minority over-sampling technique","volume":"16","author":"Chawla","year":"2002","journal-title":"J. Artif. Intell. Res."},{"key":"ref_31","unstructured":"(2025, October 09). Colorectal Cancer Subtyping Consortium (CRCSC), 2014. Available online: https:\/\/repo-prod.prod.sagebase.org\/repo\/v1\/doi\/locate?id=syn2623706&type=ENTITY."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"1350","DOI":"10.1038\/nm.3967","article-title":"The consensus molecular subtypes of colorectal cancer","volume":"21","author":"Guinney","year":"2015","journal-title":"Nat. Med."},{"key":"ref_33","unstructured":"Synapse (2025, March 26). Synapse Project Wiki. Available online: https:\/\/www.synapse.org\/#!Synapse:syn2623706\/wiki\/."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"1113","DOI":"10.1038\/ng.2764","article-title":"The Cancer Genome Atlas Pan-Cancer analysis project","volume":"45","author":"Network","year":"2013","journal-title":"Nat. Genet."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"15545","DOI":"10.1073\/pnas.0506580102","article-title":"Gene set enrichment analysis: A knowledge-based approach for interpreting genome-wide expression profiles","volume":"102","author":"Subramanian","year":"2005","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"44","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":"ref_37","first-page":"209","article-title":"Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries","volume":"71","author":"Sung","year":"2021","journal-title":"CA A Cancer J. Clin."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"842","DOI":"10.1016\/j.trecan.2024.06.007","article-title":"Transcriptomic subtyping of gastrointestinal malignancies","volume":"10","author":"Sommeijer","year":"2024","journal-title":"Trends Cancer"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1016\/j.imed.2023.04.002","article-title":"A hierarchical clustering approach for colorectal cancer molecular subtypes identification from gene expression data","volume":"4","author":"Raghav","year":"2024","journal-title":"Intell. Med."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"151","DOI":"10.4137\/CIN.S40088","article-title":"Pathway-informed classification system (PICS) for cancer analysis using gene expression data","volume":"15","author":"Young","year":"2016","journal-title":"Cancer Inform."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"2320","DOI":"10.1002\/cncr.30597","article-title":"Future of testicular germ cell tumor incidence in the United States: Forecast through 2026","volume":"123","author":"Ghazarian","year":"2017","journal-title":"Cancer"},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"111","DOI":"10.1016\/j.mce.2008.02.018","article-title":"Origin of pluripotent germ cell tumours: The role of microenvironment during embryonic development","volume":"288","author":"Kristensen","year":"2008","journal-title":"Mol. Cell. Endocrinol."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"1071","DOI":"10.1080\/15592294.2020.1834926","article-title":"Hypermethylation and global remodelling of DNA methylation is associated with acquired cisplatin resistance in testicular germ cell tumours","volume":"16","author":"Fazal","year":"2021","journal-title":"Epigenetics"}],"container-title":["Diagnostics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2075-4418\/15\/21\/2730\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,28]],"date-time":"2025-10-28T14:31:39Z","timestamp":1761661899000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2075-4418\/15\/21\/2730"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,28]]},"references-count":43,"journal-issue":{"issue":"21","published-online":{"date-parts":[[2025,11]]}},"alternative-id":["diagnostics15212730"],"URL":"https:\/\/doi.org\/10.3390\/diagnostics15212730","relation":{},"ISSN":["2075-4418"],"issn-type":[{"value":"2075-4418","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,28]]}}}