Background: It is generally believed that DNA methylation, as one of the most important epigenetic modifications, participates in the regulation of gene expression and plays an important role in the development of cancer, and there exits epigenetic heterogeneity among cancers. Therefore, this study tried to screen for reliable prognostic markers for different cancers, providing further explanation for the heterogeneity of cancers, and more targets for clinical transformation studies of cancer from epigenetic perspective. Methods: This article discusses the epigenetic heterogeneity of cancer in detail. Firstly, DNA methylation data of seven cancer types were obtained from Illumina Infinium HumanMethylation 450 K platform of TCGA database. Then, differential methylation analysis was performed in the promotor region. Secondly, pivotal gene markers were obtained by constructing the DNA methylation correlation network and the gene interaction network in the KEGG pathway, and 317 marker genes obtained from two networks were integrated as candidate markers for the prognosis model. Finally, we used the univariate and multivariate COX regression models to select specific independent prognostic markers for each cancer, and studied the risk factor of these genes by doing survival analysis. Results: First, the cancer type-specific gene markers were obtained by differential methylation analysis and they were found to be involved in different biological functions by enrichment analysis. Moreover, specific and common diagnostic markers for each type of cancer was sorted out and Kaplan-Meier survival analysis showed that there was significant difference in survival between the two risk groups. Conclusions: This study screened out reliable prognostic markers for different cancers, providing a further explanation for the heterogeneity of cancer at the DNA methylation level and more targets for clinical conversion studies of cancer.

Bladder cancer is a highly complex and heterogeneous malignancy. Tumor heterogeneity is a barrier to effective diagnosis and treatment of bladder cancer. Human carcinogenesis is closely related to abnormal gene expression, and DNA methylation is an important regulatory factor of gene expression. Therefore, it is of great significance for bladder cancer research to characterize tumor heterogeneity by integrating genetic and epigenetic characteristics. This study explored specific molecular subtypes based on DNA methylation status and identified subtype-specific characteristics using patient samples from the TCGA database with DNA methylation and gene expression were measured simultaneously. The results were validated using an independent cohort from GEO database. Four DNA methylation molecular subtypes of bladder cancer were obtained with different prognostic states. In addition, subtype-specific DNA methylation markers were identified using an information entropy-based algorithm to represent the unique molecular characteristics of the subtype and verified in the test set. The results of this study can provide an important reference for clinicians to make treatment decisions.

Liver-tumor segmentation must handle differences in computed tomography (CT) phases and annotation completeness. We evaluated the missing-phase-tolerant mu

Intra-tumor molecular heterogeneity contributes substantially to survival differences among patients with breast cancer. Although deep learning-based multi-omics integration has shown promise for prognostic modeling, existing approaches may be affected by information leakage during model evaluation and often focus on either survival prediction or molecular subtype discovery. In this study, we developed the Deep Multi-modal Fusion Framework (DMFF), an integrated computational framework that supports continuous patient-level survival risk estimation and downstream de novo molecular subtype discovery within a unified analytical workflow. DMFF uses modality-specific denoising autoencoders to learn compact representations from mRNA and miRNA data, while a protein–protein interaction network-guided graph convolutional network is used to encode proteomic features. The resulting modality-specific representations are adaptively integrated through an attention-based fusion module. A Cox partial likelihood loss and a pairwise ranking loss are jointly optimized to generate continuous survival risk scores. To minimize information leakage, data imputation, standardization, feature preselection, hyperparameter optimization, and model checkpoint selection were performed within a nested five-fold cross-validation framework. Under nested cross-validation, the pure-omics DMFF model achieved a C-index of 0.656. After integrating the learned multi-omics representations with clinical characteristics using a Random Survival Forest, the joint model achieved a C-index of 0.706 and outperformed the evaluated baseline models in prognostic discrimination. Multivariable Cox regression further indicated that the DMFF-derived pure-omics risk score provided prognostic information independent of conventional clinical variables. Unsupervised clustering of the fused multi-omics representations identified three molecular subtypes with distinct survival outcomes, and repeated subsampling analysis supported the internal stability of the three-subtype solution. Tumor microenvironment analysis revealed distinct immune-cell enrichment patterns across the three subtypes. Comparison with PAM50 intrinsic subtypes suggested that the DMFF-derived and PAM50 classifications capture partially complementary aspects of breast cancer heterogeneity. Because the present study did not include immunotherapy exposure or treatment-response data, the potential relationship between the identified immune profiles and immunotherapy response should be regarded as exploratory and hypothesis-generating. Overall, DMFF provides a leakage-controlled framework for multi-omics survival prediction and downstream molecular subtype discovery, although its generalizability requires further validation in independent multi-center cohorts.