Multiple types of omics data contain a wealth of biomedical information which reflect different aspects of clinical samples. Multi-omics integrated analysis is more likely to lead to more accurate clinical decisions. Existing cancer diagnostic methods based on multi-omics data integration mainly focus on the classification accuracy of the model, while neglecting the interpretability of the internal mechanism and the reliability of the results, which are crucial in specific domains such as precision medicine and the life sciences. To overcome this limitation, we propose a trustworthy multi-omics dynamic learning framework (TMODINET) for cancer diagnostic. The framework employs multi-omics adaptive dynamic learning to process each sample to provide patient-centered personality diagnosis by using self-attentional learning of features and modalities. To characterize the correlation between samples well, we introduce a graph dynamic learning method which can adaptively adjust the graph structure according to the specific classification results for specific graph convolutional networks (GCN) learning. Moreover, we utilize an uncertainty mechanism by employing Dirichlet distribution and Dempster-Shafer theory to obtain uncertainty and integrate multi-omics data at the decision level, ensuring trustworthy for cancer diagnosis. Extensive experiments on four real-world multimodal medical datasets are conducted. Compared to state-of-the-art methods, the superior performance and trustworthiness of our proposed algorithm are clearly validated. Our model has great potential for clinical diagnosis.

BACKGROUND: Accurate identification of cancer subtypes is crucial for disease prognosis evaluation and personalized patient management. Recent advances in computational methods have demonstrated that multi-omics data provides valuable insights into tumor molecular subtyping. However, the high dimensionality and small sample size of the data may result in ambiguous and overlapping cancer subtypes during clustering. In this study, we propose a novel contrastive-learning-based approach to address this issue. The proposed end-to-end deep learning method can extract crucial information from the multi-omics features by self-supervised learning for patient clustering.
RESULTS: By applying our method to nine public cancer datasets, we have demonstrated superior performance compared to existing methods in separating patients with different survival outcomes (p < 0.05). To further evaluate the impact of various omics data on cancer survival, we developed an XGBoost classification model and found that mRNA had the highest importance score, followed by DNA methylation and miRNA. In the presented case study, our method successfully clustered subtypes and identified 14 cancer-related genes, of which 12 (85.7%) were validated through literature review.
CONCLUSIONS: Our findings demonstrate that our method is capable of identifying cancer subtypes that are both statistically and biologically significant. The code about COLCS is given at: https://github.com/Mercuriiio/COLCS .

BACKGROUND: Predictive modeling based on multi-omics data, which incorporates several types of omics data for the same patients, has shown potential to outperform single-omics predictive modeling. Most research in this domain focuses on incorporating numerous data types, despite the complexity and cost of acquiring them. The prevailing assumption is that increasing the number of data types necessarily improves predictive performance. However, the integration of less informative or redundant data types could potentially hinder this performance. Therefore, identifying the most effective combinations of omics data types that enhance predictive performance is critical for cost-effective and accurate predictions.
METHODS: In this study, we systematically evaluated the predictive performance of all 31 possible combinations including at least one of five genomic data types (mRNA, miRNA, methylation, DNAseq, and copy number variation) using 14 cancer datasets with right-censored survival outcomes, publicly available from the TCGA database. We employed various prediction methods and up-weighted clinical data in every model to leverage their predictive importance. Harrell\'s C-index and the integrated Brier Score were used as performance measures. To assess the robustness of our findings, we performed a bootstrap analysis at the level of the included datasets. Statistical testing was conducted for key results, limiting the number of tests to ensure a low risk of false positives.
RESULTS: Contrary to expectations, we found that using only mRNA data or a combination of mRNA and miRNA data was sufficient for most cancer types. For some cancer types, the additional inclusion of methylation data led to improved prediction results. Far from enhancing performance, the introduction of more data types most often resulted in a decline in performance, which varied between the two performance measures.
CONCLUSIONS: Our findings challenge the prevailing notion that combining multiple omics data types in multi-omics survival prediction improves predictive performance. Thus, the widespread approach in multi-omics prediction of incorporating as many data types as possible should be reconsidered to avoid suboptimal prediction results and unnecessary expenditure.

Colorectal cancer is one of the most common cancers around the world, which is a severe threat to people\'s health. SMAD4 belongs to the dwarfin/SMAD family, which plays a crucial role in TGF-β and BMP signal pathways. As the molecular characterization of colon cancer patients following SMAD4 mutations remains unclear, we integrated multi-omics data of SMAD4 mutant patients to reveal the profile of molecular characterization of SMAD4 mutation. A missense mutation is the most common mutant type of SMAD4. Patients with SMAD4 mutation had worse survival. Tumor tissues from patients carrying the SMAD4 mutation showed a reduction in various immune cells, such as CD4 + memory T cells and memory B cells. Many differential genes were identified compared to the SMAD4 mutation-free group and could be significantly enriched for tumor- and immune-related signaling pathways. In addition, the mutant group had different drug sensitivities than the non-mutant group.

BACKGROUND: Computational techniques for drug-disease prediction are essential in enhancing drug discovery and repositioning. While many methods utilize multimodal networks from various biological databases, few integrate comprehensive multi-omics data, including transcriptomes, proteomes, and metabolomes. We introduce STRGNN, a novel graph deep learning approach that predicts drug-disease relationships using extensive multimodal networks comprising proteins, RNAs, metabolites, and compounds. We have constructed a detailed dataset incorporating multi-omics data and developed a learning algorithm with topological regularization. This algorithm selectively leverages informative modalities while filtering out redundancies.
RESULTS: STRGNN demonstrates superior accuracy compared to existing methods and has identified several novel drug effects, corroborating existing literature. STRGNN emerges as a powerful tool for drug prediction and discovery. The source code for STRGNN, along with the dataset for performance evaluation, is available at https://github.com/yuto-ohnuki/STRGNN.git .

The integration of multi-omics data offers a robust approach to understanding the complexity of diseases by combining information from various biological levels, such as genomics, transcriptomics, proteomics, and metabolomics. This integrated approach is essential for a comprehensive understanding of disease mechanisms and for developing more effective diagnostic and therapeutic strategies. Nevertheless, most current methodologies fail to effectively extract both shared and specific representations from omics data. This study introduces MOSDNET, a multi-omics classification framework that effectively extracts shared and specific representations. This framework leverages Simplified Multi-view Deep Discriminant Representation Learning (S-MDDR) and Dynamic Edge GCN (DEGCN) to enhance the accuracy and efficiency of disease classification. Initially, MOSDNET utilizes S-MDDR to establish similarity and orthogonal constraints for extracting these representations, which are then concatenated to integrate the multi-omics data. Subsequently, MOSDNET constructs a comprehensive view of the sample data by employing patient similarity networks. By incorporating similarity networks into DEGCN, MOSDNET learns intricate network structures and node representations, which enables superior classification outcomes. MOSDNET is trained through a multitask learning approach, effectively leveraging the complementary knowledge from both the data integration and classification components. After conducting extensive comparative experiments, we have conclusively demonstrated that MOSDNET outperforms leading state-of-the-art multi-omics classification models in terms of classification accuracy. Simultaneously, we employ MOSDNET to identify pivotal biomarkers within the multi-omics data, providing insights into disease etiology and progression.

Introduction: Developing effective breast cancer survival prediction models is critical to breast cancer prognosis. With the widespread use of next-generation sequencing technologies, numerous studies have focused on survival prediction. However, previous methods predominantly relied on single-omics data, and survival prediction using multi-omics data remains a significant challenge. Methods: In this study, considering the similarity of patients and the relevance of multi-omics data, we propose a novel multi-omics stacked fusion network (MSFN) based on a stacking strategy to predict the survival of breast cancer patients. MSFN first constructs a patient similarity network (PSN) and employs a residual graph neural network (ResGCN) to obtain correlative prognostic information from PSN. Simultaneously, it employs convolutional neural networks (CNNs) to obtain specificity prognostic information from multi-omics data. Finally, MSFN stacks the prognostic information from these networks and feeds into AdaboostRF for survival prediction. Results: Experiments results demonstrated that our method outperformed several state-of-the-art methods, and biologically validated by Kaplan-Meier and t-SNE.

UNASSIGNED: Glycosyltransferase-associated genes play a crucial role in hepatocellular carcinoma (HCC) pathogenesis. This study investigates their impact on the tumor microenvironment and molecular mechanisms, offering insights into innovative immunotherapeutic strategies for HCC.
UNASSIGNED: We utilized cutting-edge single-cell and spatial transcriptomics to examine HCC heterogeneity. Four single-cell scoring techniques were employed to evaluate glycosyltransferase genes. Spatial transcriptomic findings were validated, and bulk RNA-seq analysis was conducted to identify prognostic glycosyltransferase-related genes and potential immunotherapeutic targets. MGAT1\'s role was further explored through various functional assays.
UNASSIGNED: Our analysis revealed diverse cell subpopulations in HCC with distinct glycosyltransferase gene activities, particularly in macrophages. Key glycosyltransferase genes specific to macrophages were identified. Temporal analysis illustrated macrophage evolution during tumor progression, while spatial transcriptomics highlighted reduced expression of these genes in core tumor macrophages. Integrating scRNA-seq, bulk RNA-seq, and spatial transcriptomics, MGAT1 emerged as a promising therapeutic target, showing significant potential in HCC immunotherapy.
UNASSIGNED: This comprehensive study delves into glycosyltransferase-associated genes in HCC, elucidating their critical roles in cellular dynamics and immune cell interactions. Our findings open new avenues for immunotherapeutic interventions and personalized HCC management, pushing the boundaries of HCC immunotherapy.

Based on the systematic deconstruction of multi-dimensional and multi-target biological networks, modular pharmacology explains the complex mechanism of diseases and the interactions of multi-target drugs. It has made progress in the fields of pathogenesis of disease, biological basis of disease and traditional Chinese medicine(TCM) syndrome, pharmacological mechanism of multi-target herbs, compatibility of formulas, and discovery of new drug of TCM compound. However, the complexity of multi-omics data and biological networks brings challenges to the modular deconstruction and analysis of the drug networks. Here, we constructed the "Computing Platform for Modular Pharmacology" online analysis system, which can implement the function of network construction, module identification, module discriminant analysis, hub-module analysis, intra-module and inter-module relationship analysis, and topological visualization of network based on quantitative expression profiles and protein-protein interaction(PPI) data. This tool provides a powerful tool for the research on complex diseases and multi-target drug mechanisms by means of modular pharmacology. The platform may have broad range of application in disease modular identification and correlation mechanism, interpretation of scientific principles of TCM, analysis of complex mechanisms of TCM and formulas, and discovery of multi-target drugs.

OBJECTIVE: Lung adenocarcinoma (LUAD) is the most common subtype of non-small cell lung cancer. Understanding the molecular mechanisms underlying tumor progression is of great clinical significance. This study aims to identify novel molecular markers associated with LUAD subtypes, with the goal of improving the precision of LUAD subtype classification. Additionally, optimization efforts are directed towards enhancing insights from the perspective of patient survival analysis.
METHODS: We propose an innovative feature-selection approach that focuses on LUAD classification, which is comprehensive and robust. The proposed method integrates multi-omics data from The Cancer Genome Atlas (TCGA) and leverages a synergistic combination of max-relevance and min-redundancy, least absolute shrinkage and selection operator, and Boruta algorithms. These selected features were deployed in six machine-learning classifiers: logistic regression, random forest, support vector machine, naive Bayes, k-Nearest Neighbor, and XGBoost.
RESULTS: The proposed approach achieved an area under the receiver operating characteristic curve (AUC) of 0.9958 for LR. Notably, the accuracy and AUC of a composite model incorporating copy number, methylation, as well as RNA- sequencing data for expression of exons, genes, and miRNA mature strands surpassed the accuracy and AUC metrics of models with single-omics data or other multi-omics combinations. Survival analyses, revealed the SVM classifier to elicit optimal classification, outperforming that achieved by TCGA. To enhance model interpretability, SHapley Additive exPlanations (SHAP) values were utilized to elucidate the impact of each feature on the predictions. Gene Ontology (GO) enrichment analysis identified significant biological processes, molecular functions, and cellular components associated with LUAD subtypes.
CONCLUSIONS: In summary, our feature selection process, based on TCGA multi-omics data and combined with multiple machine learning classifiers, proficiently identifies molecular subtypes of lung adenocarcinoma and their corresponding significant genes. Our method could enhance the early detection and diagnosis of LUAD, expedite the development of targeted therapies and, ultimately, lengthen patient survival.