A multi-scale biological network framework for discovering MiRNA-Disease associations

Integrating lncRNA data for prediction of miRNA-disease association using network fusion and matrix completion

Predicting miRNA-disease associations based on adaptive neighborhood propagation and feature spatial recombination.

MicroRNAs (miRNAs) are critical regulators in biological processes such as cell proliferation, differentiation, and apoptosis, with their aberrant expression strongly linked to a range of complex diseases. Because traditional experimental methods for predicting miRNA-disease associations (MDAs) are both time-intensive and costly, computational models offer an efficient alternative. Graph neural networks (GNNs) have shown promise in MDAs prediction. However, existing models often suffer from limitations, including inadequate neighborhood information aggregation, inflexible propagation schemes, and an imbalance between global and local information. To address these issues, this paper presents a novel GNN framework, APKAGN, designed for predicting miRNA-disease associations. APKAGN enhances performance through three innovative mechanisms: 1) Adaptive local propagation, leveraging a gated recursion module to dynamically adjust propagation depth while employing residual connections to preserve multi-scale features. 2) Multi-subspace global aggregation, capturing global topology information via multi-dimensional projection and density-aware KNN selection. 3) Dynamic feature fusion, integrating local and global representations using an attention-based gating mechanism. Evaluated on the updated HMDD v3.2 dataset across multiple independent random seeds, APKAGN achieved an outstanding average AUC of 95.09%, an accuracy of 88.23%, and an F1-score of 88.34%, outperforming seven state-of-the-art baseline models. Case studies on lymphoma, prostate, and breast tumors further demonstrated the predictive performance of the proposed model, with 26, 25, and 27 of the top 30 predicted miRNAs validated in the dbDEMC and miR2Disease databases, respectively. By leveraging adaptive propagation and dynamic KNN mechanisms, APKAGN significantly enhances the accuracy of MDAs prediction, offering a powerful tool for investigating disease mechanisms and identifying biomarkers.

MRGBMDAT: a multi-relational graph encoder network with bilinear fusion for miRNA-disease association type prediction

Abstract Motivation MicroRNAs (miRNAs) are key post-transcriptional regulators involved in diverse biological processes, and their dysregulation is closely associated with the onset and progression of many diseases. Accurate prediction of miRNA-disease association types is therefore essential for understanding disease mechanisms and advancing precision medicine. Although computational methods provide efficient alternatives to wet-lab experiments, existing approaches often focus on binary association prediction, inadequately integrate local semantic dependencies and global topological structures, and suffer from class imbalance. Results To address these limitations, we propose MRGBMDAT, a multi-relational graph encoder network with bilinear fusion for miRNA-disease association type prediction. Specifically, a multi-relational graph convolution module with bidirectional cross-attention captures global topological structures, while a local subgraph sampling module extracts local semantic dependencies. A bilinear fusion decoder with element-wise attention jointly models their linear and nonlinear interactions. In addition, an iterative feature similarity-based negative sample selection strategy is introduced to alleviate class imbalance. Experimental results on the HMDD v3.2 dataset demonstrate that MRGBMDAT significantly outperforms five state-of-the-art methods across multiple evaluation metrics, exhibiting strong discriminative power and generalization capability. Availability and implementation The source code is publicly available at https://github.com/CDMBlab/MRGBMDAT.

A Hybrid Graph Convolutional Network and XGBoost Framework for miRNA–Disease Association Prediction

Predicting potential associations between microRNAs (miRNAs) and diseases is essential for deciphering complex pathogenic mechanisms and advancing personalized medicine. However, many existing computational methods fail to adequately capture high-order topological structures within heterogeneous biological networks, limiting their predictive performance. In this study, we propose GCN-XGB, a novel hybrid computational framework that integrates a two-layer Graph Convolutional Network (GCN) with Extreme Gradient Boosting (XGBoost) to improve the accuracy of miRNA-disease association prediction. Specifically, we first input k-mer derived initial features of miRNAs, BioBERT-derived initial features of diseases, and the computed miRNA-miRNA similarity, disease-disease similarity, and miRNA-disease association information into the two-layer GCN. Through deep feature propagation and aggregation of second-order neighbor information, the GCN integrates these inputs to generate enhanced discriminative high-dimensional embeddings, providing more informative and discriminative features for the downstream XGBoost classifier. Experimental results under rigorous 10-fold cross-validation demonstrate that GCN-XGB consistently outperforms several state-of-the-art baseline models when all models are trained on the same GCN-enhanced features, achieving a superior AUC of 0.9601 and AUPR of 0.9587. Furthermore, case studies on prevalent neoplasms (e.g., Breast, Colon, and Lung Cancer) confirm the framework's efficacy in discovering novel associations even in the absence of prior clinical data. Our findings suggest that GCN-XGB is a powerful and reliable tool for identifying potential disease-related miRNAs and prioritizing candidates for experimental validation.

MFCAMNet: predicting miRNA-disease associations by multi-feature cascade attention mechanism network

Drive by the rapid envolution of deep-learning techniques, a large body of biological experiments bas has uncovered extensive associations between microRNAs (miRNAs) and complex human diseases, hig- hlighting the pivotal roles of miRNAs in pathogenesis. Elucidating these associations is essential for understanding disease mechanisms and developing preventive strategies. Traditional wet-lab validati- on, however, is notoriously labor- and resource-intensive, creating an urgent demand for efficient computational tools that can prioritize the most promising miRNA–disease candidates. Existing predictors predominantly rely on a single category of handcrafted features, thereby overlooking the complementary information embedded in multiple, heterogeneous data sources. Although a few recent attempts integrate diverse features, they usually exploit only a limited subset and fail to capture the intricate, non-linear relationships among them. To address these limitations, we propose MFCAMNet, a Multi-Feature fusion and Cross-Self-Attention model for MiRNA–Disease association prediction. Firstly, we construct multiple similarity matrices and employ two independent autoencoders with multi-source feature attention to obtain deep features of miRNA and disease to extract the inherent relationships between multiple features. Secondly, the proposed model employs element-level addition, element-level multiplication, and concatenation operations to generate miRNA-disease pair features with rich information. Finally, we use the encoder structure of the transformer to fuse the three deep features and predict all potential miRNA disease associations. We conducted comprehensive evaluations on the public HMDD v2.0 and HMDD v3.2 benchmark datasets. MFCAMNet achieved average AUCs of 0.9455 and 0.9420 under 5-fold and 10-fold cross-validation on HMDD v2.0, respectively, and an AUC of 0.9578 under 5-fold cross-validation on HMDD v3.2, outperforming state-of-the-art competitors. Case studies on breast, esophageal, and lung cancers further corroborate the reliability and practical utility of the proposed method.

Dual-granularity feature learning reveals static and dynamic mechanisms of ncRNA-drug interactions.

Accurately identifying interactions between non-coding RNAs (ncRNAs) and drugs is crucial for elucidating drug mechanisms and advancing drug repositioning. Existing deep learning-based methods for ncRNA-drug association prediction typically leverage multi-source biological information to learn informative representations, thereby alleviating the cold-start issue arising from the scarcity of experimentally validated associations. However, the direct fusion of multi-source features often introduces feature redundancy, semantic conflicts, and high-dimensional feature sparsity, thereby hindering model convergence and degrading predictive performance. To address these challenges, this study proposes DC-MetaMG, a deep learning framework based on a causal disentanglement strategy that models association responses as the synergistic interplay between two complementary mechanisms: static binding and dynamic regulation. By characterizing the principal patterns underlying differential responses between drugs and ncRNAs across multiple dimensions, the proposed framework effectively suppresses spurious associations arising from irrelevant feature interactions and mitigates the adverse effects introduced during model training with multi-source biomedical information, thereby improving the reliability of association prediction. Experiments conducted on lncRNA-drug and miRNA-drug datasets demonstrate the superior performance of the proposed model. Under five-fold cross-validation, the proposed model achieves an average AUC improvement of 0.41% over competing methods. Under the cold evaluation experiments, the AUC, ACC, and AUPR metrics show average increases of 1.22%, 0.51%, and 0.35%, respectively. Case studies further demonstrate the interpretability of the model. Furthermore, visualization analyses confirm the effective characterization of the two underlying association mechanisms, highlighting the model's ability to disentangle and integrate multi-source biological information, thereby demonstrating its suitability for training scenarios involving complex biological information.