{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T16:29:34Z","timestamp":1784392174652,"version":"3.55.0"},"reference-count":36,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2026,1,25]],"date-time":"2026-01-25T00:00:00Z","timestamp":1769299200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Provost\u2019s Office at Lakehead University"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Algorithms"],"abstract":"<jats:p>The rapid advancement of sequencing technologies has led to the generation of complex multi-omics data, which are often high-dimensional, noisy, and imbalanced, posing significant challenges for traditional machine learning methods. The novelty of this work resides in the architecture-level integration of autoencoders with Generative Adversarial Network (GAN) and Conditional Tabular Generative Adversarial Network (CTGAN) models, where the autoencoder is employed for latent feature extraction and noise reduction, while GAN-based models are used for realistic sample generation and class imbalance mitigation in multi-omics cancer datasets. This study proposes a novel framework that combines an autoencoder for dimensionality reduction and a CTGAN for generating synthetic samples to balance underrepresented classes. The process starts with selecting the most discriminative features, then extracting latent representations for each omic type, merging them, and generating new minority samples. Finally, all samples are used to train a neural network to predict specific cancer outcomes, defined here as clinically relevant biomarkers or patient characteristics. In this work, the considered outcome in the bladder cancer is Tumor Mutational Burden (TMB), while the breast cancer outcome is menopausal status, a key factor in treatment planning. Experimental results show that the proposed model achieves high precision, with an average precision of 0.9929 for TMB prediction in bladder cancer and 0.9748 for menopausal status in breast cancer, and reaches perfect precision (1.000) for the positive class in both cases. In addition, the proposed AE\u2013CTGAN framework consistently outperformed an autoencoder combined with a standard GAN across all evaluation metrics, achieving average accuracies of 0.9929 and 0.9748, recall values of 0.9846 and 0.9777, and F1-scores of 0.9922 for bladder and breast cancer datasets, respectively. A comparative fidelity analysis in the latent space further demonstrated the superiority of CTGAN, reducing the average Euclidean distance between real and synthetic samples by approximately 72% for bladder cancer and by up to 84% for breast cancer compared to a standard GAN. These findings confirm that CTGAN generates high-fidelity synthetic samples that preserve the structural characteristics of real multi-omics data, leading to more reliable class balancing and improved predictive performance. Overall, the proposed framework provides an effective and robust solution for handling class imbalance in multi-omics cancer data and enhances the accuracy of clinically relevant outcome prediction.<\/jats:p>","DOI":"10.3390\/a19020095","type":"journal-article","created":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T09:21:40Z","timestamp":1769505700000},"page":"95","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["AE-CTGAN: Autoencoder\u2013Conditional Tabular GAN for Multi-Omics Imbalanced Class Handling and Cancer Outcome Prediction"],"prefix":"10.3390","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-4164-9651","authenticated-orcid":false,"given":"Ibrahim","family":"Al-Hurani","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, Lakehead University, Thunder Bay, ON P7B 5E1, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-3194-9191","authenticated-orcid":false,"given":"Sara H.","family":"ElFar","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Lakehead University, Thunder Bay, ON P7B 5E1, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1751-7570","authenticated-orcid":false,"given":"Abedalrhman","family":"Alkhateeb","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Lakehead University, Thunder Bay, ON P7B 5E1, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Salama","family":"Ikki","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Lakehead University, Thunder Bay, ON P7B 5E1, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,1,25]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"157","DOI":"10.2217\/pme-2018-0085","article-title":"Toward multiomics-based next-generation diagnostics for precision medicine","volume":"16","author":"Wang","year":"2019","journal-title":"Pers. Med."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Alghanim, F., Al-Hurani, I., Qattous, H., Al-Refai, A., Batiha, O., Alkhateeb, A., and Ikki, S. (2023). Machine Learning Model for Multiomics Biomarkers Identification for Menopause Status in Breast Cancer. Algorithms, 17.","DOI":"10.3390\/a17010013"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"e23195","DOI":"10.1016\/j.heliyon.2023.e23195","article-title":"PaCMAP-embedded convolutional neural network for multi-omics data integration","volume":"10","author":"Qattous","year":"2024","journal-title":"Heliyon"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"26","DOI":"10.1007\/s13721-024-00460-7","article-title":"NMF-guided feature selection and genetic algorithm-driven framework for tumor mutational burden classification in bladder cancer using multi-omics data","volume":"13","author":"AlAfeshat","year":"2024","journal-title":"Netw. Model. Anal. Health Inform. Bioinform."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"28","DOI":"10.1007\/s10462-023-10662-6","article-title":"Autoencoders and their applications in machine learning: A survey","volume":"57","author":"Berahmand","year":"2024","journal-title":"Artif. Intell. Rev."},{"key":"ref_6","first-page":"599","article-title":"Learning Internal Representations by Error Propagation, Parallel Distributed\n\t\t\t\t\t\tProcessing, Explorations in the Microstructure of Cognition, ed. DE Rumelhart and J. McClelland. Vol. 1. 1986","volume":"71","author":"Rumelhart","year":"1986","journal-title":"Biometrika"},{"key":"ref_7","unstructured":"Xhafa, F. (2021). Machine Learning, Big Data, and IoT for Medical Informatics, Academic Press."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Zhang, X., Xing, Y., Sun, K., and Guo, Y. (2021). OmiEmbed: A unified multi-task deep learning framework for multi-omics data. Cancers, 13.","DOI":"10.3390\/cancers13123047"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"074020","DOI":"10.1103\/PhysRevD.110.074020","article-title":"Streamlining latent spaces in machine learning using moment pooling","volume":"110","author":"Gambhir","year":"2024","journal-title":"Phys. Rev. D"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Batista, G.E., Carvalho, A.C., and Monard, M.C. (2000). Applying one-sided selection to unbalanced datasets. Proceedings of the Mexican International Conference on Artificial Intelligence, Springer.","DOI":"10.1007\/10720076_29"},{"key":"ref_11","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_12","unstructured":"He, H., Bai, Y., Garcia, E.A., and Li, S. (2008). ADASYN: Adaptive synthetic sampling approach for imbalanced learning. Proceedings of the 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence), IEEE."},{"key":"ref_13","first-page":"2672","article-title":"Generative adversarial nets","volume":"27","author":"Goodfellow","year":"2014","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_14","first-page":"7335","article-title":"Modeling tabular data using conditional gan","volume":"32","author":"Xu","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_15","unstructured":"\u00c5gren, W., and Sosa, V.\u00da. (2024). Hierarchical Conditional Tabular GAN for Multi-Tabular Synthetic Data Generation. arXiv."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"bbaa226","DOI":"10.1093\/bib\/bbaa226","article-title":"Synthetic observations from deep generative models and binary omics data with limited sample size","volume":"22","author":"Boesel","year":"2021","journal-title":"Briefings Bioinform."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"179","DOI":"10.1093\/bioinformatics\/btab608","article-title":"Multi-omics data integration by generative adversarial network","volume":"38","author":"Ahmed","year":"2022","journal-title":"Bioinformatics"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"105669","DOI":"10.1016\/j.engappai.2022.105669","article-title":"Imbalanced tabular data modelization using CTGAN and machine learning to improve IoT Botnet attacks detection","volume":"118","author":"Habibi","year":"2023","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_19","unstructured":"Arjovsky, M., Chintala, S., and Bottou, L. (2017, January 6\u201311). Wasserstein generative adversarial networks. Proceedings of the International Conference on Machine Learning. PMLR, Sydney, Australia."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"bbae325","DOI":"10.1093\/bib\/bbae325","article-title":"ctGAN: Combined transformation of gene expression and survival data with generative adversarial network","volume":"25","author":"Kim","year":"2024","journal-title":"Briefings Bioinform."},{"key":"ref_21","first-page":"1","article-title":"LASSO\u2013MOGAT: A multi-omics graph attention framework for cancer classification","volume":"2","author":"Alharbi","year":"2024","journal-title":"Acad. Biol."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1038\/s41514-024-00163-3","article-title":"Precious2GPT: The combination of multiomics pretrained transformer and conditional diffusion for artificial multi-omics multi-species multi-tissue sample generation","volume":"10","author":"Sidorenko","year":"2024","journal-title":"Npj Aging"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Zhang, X., Zhang, J., Sun, K., Yang, X., Dai, C., and Guo, Y. (2019). Integrated multi-omics analysis using variational autoencoders: Application to pan-cancer classification. Proceedings of the 2019 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), IEEE.","DOI":"10.1109\/BIBM47256.2019.8983228"},{"key":"ref_24","unstructured":"CiteDrive, I. (2025, January 01). Deep Dive: Multi-Omics Variational Autoencoding. Available online: https:\/\/www.broadinstitute.org\/videos\/deep-dive-multi-omics-variational-autoencoding-variational-autoencoders-analysis-and."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1186\/s13059-023-02850-y","article-title":"siVAE: Interpretable deep generative models for single-cell transcriptomes","volume":"24","author":"Choi","year":"2023","journal-title":"Genome Biol."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"1614","DOI":"10.3390\/ai5030078","article-title":"Generative Models Utilizing Padding Can Efficiently Integrate and Generate Multi-Omics Data","volume":"5","author":"Lee","year":"2024","journal-title":"AI"},{"key":"ref_27","unstructured":"Xin, L., Huang, C., Li, H., Huang, S., Feng, Y., Kong, Z., Liu, Z., Li, S., Yu, C., and Shen, F. (2024). Artificial intelligence for central dogma-centric multi-omics: Challenges and breakthroughs. arXiv."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"506","DOI":"10.1016\/j.cell.2015.09.033","article-title":"Comprehensive molecular portraits of invasive lobular breast cancer","volume":"163","author":"Ciriello","year":"2015","journal-title":"Cell"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"401","DOI":"10.1158\/2159-8290.CD-12-0095","article-title":"The cBio cancer genomics portal: An open platform for exploring multidimensional cancer genomics data","volume":"2","author":"Cerami","year":"2012","journal-title":"Cancer Discov."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"pl1","DOI":"10.1126\/scisignal.2004088","article-title":"Integrative analysis of complex cancer genomics and clinical profiles using the cBioPortal","volume":"6","author":"Gao","year":"2013","journal-title":"Sci. Signal."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"289","DOI":"10.1111\/j.2517-6161.1995.tb02031.x","article-title":"Controlling the false discovery rate: A practical and powerful approach to multiple testing","volume":"57","author":"Benjamini","year":"1995","journal-title":"J. R. Stat. Soc. Ser. B (Methodol.)"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1007\/BF02478220","article-title":"A theory of steady-state activity in nerve-fiber networks: I. Definitions and preliminary lemmas","volume":"3","author":"Householder","year":"1941","journal-title":"Bull. Math. Biophys."},{"key":"ref_33","unstructured":"Kingma, D.P., and Ba, J. (2014). Adam: A method for stochastic optimization. arXiv."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Mehrbakhsh, Z., Hassanzadeh, R., Behnampour, N., Tapak, L., Zarrin, Z., Khazaei, S., and Dinu, I. (2024). Machine learning-based evaluation of prognostic factors for mortality and relapse in patients with acute lymphoblastic leukemia: A comparative simulation study. Bmc Med. Inform. Decis. Mak., 24.","DOI":"10.1186\/s12911-024-02645-6"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Zhou, J., Lu, X., Chang, W., Wan, C., Lu, X., Zhang, C., and Cao, S. (2022). PLUS: Predicting cancer metastasis potential based on positive and unlabeled learning. PLoS Comput. Biol., 18.","DOI":"10.1371\/journal.pcbi.1009956"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"109477","DOI":"10.1016\/j.buildenv.2022.109477","article-title":"Generative Adversarial Networks in the built environment: A comprehensive review of the application of GANs across data types and scales","volume":"223","author":"Wu","year":"2022","journal-title":"Build. Environ."}],"container-title":["Algorithms"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-4893\/19\/2\/95\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T09:24:04Z","timestamp":1769505844000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-4893\/19\/2\/95"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,25]]},"references-count":36,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2026,2]]}},"alternative-id":["a19020095"],"URL":"https:\/\/doi.org\/10.3390\/a19020095","relation":{},"ISSN":["1999-4893"],"issn-type":[{"value":"1999-4893","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,25]]}}}