CircRNA-miRNA interaction (CMI) plays a pivotal role in disease therapeutics and drug discovery. However, existing methods face several challenges in modeling complex biological networks and zero-shot learning scenarios. Biological networks encapsulate rich biological information, yet current approaches often fail to fully exploit this depth. Moreover, zero-shot prediction requires models to identify new interactions without relying on previously observed samples, imposing stringent requirements on generalization capabilities. To address these limitations, we propose a dual-channel learning framework leveraging State space modeling for Zero-shot CMI prediction (ZeroStem). ZeroStem first enhances the biological relevance of node using prior knowledge, and employs a graph Transformer to extract macro-topological representations. Subsequently, it generates semantic subgraphs based on meta-paths to focus on specific biological relationships, utilizing the Mamba to extract micro-semantic representations via state space modeling. Finally, macro-topological and micro-semantic representations are seamlessly integrated through linear transformation and residual connections, enabling high-precision zero-shot CMI prediction. Extensive experiments on multiple benchmark datasets demonstrate that ZeroStem significantly outperforms existing methods, validating its efficiency and robust generalization in CMI prediction. Case studies further illustrate that ZeroStem offers novel insights into the molecular mechanisms underlying intricate disease-associated networks.

Circular RNAs (circRNAs) are non-coding RNA molecules that play a crucial role in regulating genes and contributing to disease progression. CircRNAs can function as sponges for microRNAs (miRNAs), thereby regulating gene expression and influencing disease outcomes. Identifying associations between circRNAs and miRNAs through computational methods enhances the understanding of complex disease mechanisms and offers a reliable tool for pre-selecting candidates for experimental validation. Existing models, however, are limited in their ability to capture either global or local node information, the prediction of circRNA and miRNA interactions is still challenging. In order to effectively deal with this problem, we propose a novel framework for predicting circRNA-miRNA interactions (CMIs), known as MuGNet-CMI, which leverages multi-head hybrid graph neural network and global high-order and local low-order information. The model employs the MetaPath2Vec algorithm to generate high-quality node embeddings within the circRNA-miRNA heterogeneous matrix. The multi-head dynamic attention mechanism, combined with GraphSAGE, is incorporated to efficiently capture both global high-order and local low-order node information. Additionally, we integrate neural aggregators into the multi-head dynamic attention mechanism to aggregate feature information from the captured nodes. Validation using three real datasets demonstrates that MuGNet-CMI delivers good performance in predicting CMIs, offering valuable insights to guide experimental research in gene regulation.

Recent studies have revealed that circular RNAs (circRNAs) play crucial roles in disease pathogenesis. Investigating circRNA-disease associations (CDA) holds significant potential for elucidating disease mechanisms and advancing precision medicine. However, existing methods predominantly rely on single data sources, limiting their ability to comprehensively capture the complex relationships between circRNAs and diseases. We propose a multi-source information fusion model, named HGTMCDA for CDA prediction. First, we construct a heterogeneous graph by integrating node attribute information derived from Gaussian Interaction Profile Kernel similarity based on known CDAs. Subsequently, heterogeneous graph transformation performs multi-layer message passing on the heterogeneous relational graph. It achieves multi-source information fusion through neighborhood information aggregation to generate embedding representations that encapsulate both local and global topological features. Finally, these fused features are fed into a Gradient Boosting Decision Tree classifier for accurate prediction, with model performance evaluated via 5-fold cross-validation. Experimental results demonstrate that HGTMCDA achieves AUC scores of 0.9217, 0.9183, and 0.9173 on three benchmark datasets, outperforming existing models. Ablation experiments further validate the effectiveness of multi-source information fusion. HGTMCDA provides a robust computational framework for association prediction and biomarker screening in biomedical research.

Accurate prediction of circRNA-disease associations (CDAs) is essential for elucidating disease mechanisms and identifying potential biomarkers. However, existing computational methods often struggle to fully capture multi-scale topological patterns and molecular attribute information within biological networks. To address this, we introduce MuseCDA, a novel framework designed to predict CDAs via multi-scale structure embedding. MuseCDA first leverages bidirectional transformer to generate bio-semantics from circRNA sequences, while incorporating disease similarities based on Gaussian kernel distance. It then employs random walks to capture both local neighborhood structures and global high-order network patterns, enabling comprehensive modeling of biological relationships across hierarchical levels. Finally, MuseCDA utilizes a multilayer perceptron to predict association scores. Through the seamless integration of sequence bio-semantics, Gaussian similarities, and multiscale structural features, MuseCDA achieves highly accurate CDA predictions. Evaluated on the CircR2Disease 2.0 dataset, MuseCDA demonstrates superior performance with an AUC of 0.9147, significantly surpassing baseline methods. Case studies further confirm its capability to identify novel candidates, offering valuable insights for biomarker discovery and the exploration of regulatory networks.

The study of human microbe-disease associations (MDAs) contributes to early diagnosis, personalized treatment, and novel drug and biomarker discovery. However, experimental verification is time-consuming and labor-intensive, underscoring the need for efficient computational prediction methods. However, existing methods have some limitations in dealing with data sparsity and effectively modeling global dependencies. To address these issues, we propose a sparseaware topology reconstruction and global dependencyenhanced method (STAGE) for MDA prediction. STAGE firstly employs an encoder-decoder structure combining Graph Attention Networks (GAT) and Graph Convolutional Networks (GCN). The GAT encoder captures key features from sparse networks, while the GCN decoder reconstructs potential associations to supplement missing information. An adaptive gating mechanism dynamically fuses original and reconstructed information to strengthen representation learning. Furthermore, an improved domain transformer, DAFormer, integrates relative position encoding, biased multi-head attention, and soft masking to enhance global dependency modeling while preserving graph topology. Finally, a multilayer perceptron (MLP) produces the final prediction scores. Experimental results demonstrate that STAGE outperforms existing methods, and case studies further validate its effectiveness and generalization capability.

Many experiments have shown that circular RNA (circRNA) can act as biomarkers for complex diseases and play significant regulatory roles in multiple pathological processes. However, most circRNA-disease associations remain unknown, and discovering these associations through biological experimental approach is expensive and time-consuming. Taking into account the shortcomings of current methods, we introduce a new collaborative framework that utilizes multi-heterogeneous graphs, along with variational graph auto-encoders (VGAE) to predict associations between circRNA and diseases. First, we build multi-similarity networks using various biological attributes of circRNA and diseases, and integrate these similarity networks. Two subnetworks are constructed from association matrix and combined similarity network, which included a circRNA-based network and a disease-based network. We then employ random walk with restart and Singular Value Decomposition, for feature extraction from the similarity matrix. Finally, we use collaborative framework to predict the circRNAdisease association scores based on the two subnetworks. We integrate the two score matrices to obtain a final prediction scoring matrix. Using 5-fold cross-validation on the CircR2Disease dataset, our model achieved an AUC score of 0.9828 and an AUPR score of 0.9820. Additionally, among the top 30 highest-scoring circRNA-disease association pairs, 26 associations have already been validated. Our model shows strong performance and can accurately predict associations between circRNA and diseases, according to experimental results.

CircRNA-miRNA interaction (CMI) plays a crucial role in the gene regulatory network of the cell. Numerous experiments have shown that abnormalities in CMI can impact molecular functions and physiological processes, leading to the occurrence of specific diseases. Current computational models for predicting CMI typically focus on local molecular entity relationships, thereby neglecting inherent molecular attributes and global structural information. To address these limitations, we propose a multi-feature fusion prediction model based on the transformer and graph attention network, named EGATCMI. Specifically, EGATCMI combines the transformer architecture with Word2vec to pre-train the sequence of circRNA and miRNA, capturing their sequence feature representation and sequence similarity. By leveraging the self-attention mechanism, EGATCMI extracts global structural feature from the CMI network. EGATCMI effectively integrates the obtained multi-feature for prediction, achieving AUC values of 0.9106 and 0.9470 on the CMI-9905 and CircBank datasets, respectively, outperforming existing methods. In case studies that the prediction of interactions between three miRNAs that are closely related to diseases and circRNAs, 8 out of 10 pairs were accurately predicted and validated. Extensive experimental results demonstrate the potential of EGATCMI as a reliable tool for candidate screening in biological investigations.

Circular RNA (circRNA) is an RNA molecule that plays an important role in both pathology and physiology. Accurate identification of associations between circRNAs and diseases is crucial for further physiology research. However, verifying the circRNA-disease associations (CDA) through biological experimental methods is time-consuming. Here, we propose a novel method combines Non-negative Matrix Factorization (NMF) and Adversarially Regularized Variational Graph Autoencoder (ARVGA) to accurately predict CDA. Our model first fuses multi-source information in order to build circRNA similarity, disease similarity and circRNA-disease association matrices. Thereby our model constructs graphs for circRNA and disease respectively and optimize them using a K-means clustering algorithm. We obtain linear features using NMF and non-linear features using ARVGA. Finally, an Extremely Randomized Trees classifier is employed to predict CDA. On the gold standard dataset CircR2Disease, our model achieved a prediction accuracy of 94.8% and an AUC of 0.984 under 5-fold cross-validation. In case study, 19 of top 20 predicted circRNAs associated with Hepatocellular Carcinoma were confirmed in relevant literature. Furthermore, ablation experiment, classifier experiment and independent datasets test fully demonstrate the effectiveness and robustness of our model.

In drug discovery and combination therapy, drug-drug interactions can lead to adverse reactions, affecting not only disease treatment but also risking the market withdrawal of new drugs. Traditional experiments in vitro and in vivo are labor-intensive and time-consuming for identifying potential DDIs. Although existing computational methods offer new perspectives for DDIs identification, they still have limitations. This paper innovatively uses the probability transfer matrix combined with Stacked Denoising Autoencoder to propose a model named MultiPT-DDI to calculate the correlation of edge nodes in the adjacency matrix, which effectively learns the multi-level representation of nodes and mitigates the probabilistic bias of the edge nodes in the sparse matrices and the noise of the original data. Specifically, the method first samples multiple bipartite graph networks using random surfing thus obtaining multiple probabilistic transfer matrices. Subsequently, multiple denoising autoencoder modules are employed for layer-wise unsupervised pre-training of the network. Finally, we infer the relationships between drug pairs using the Random Forest algorithm. The experiment obtains the AUC score of 0.9433 and the AUPR score of 0.9372 in the 5-fold cross-validation, significantly outperforming existing models. In the case studies, 26 of the top 30 drug pairs with the highest scores were validated. The empirical evidence indicates that MultiPT-DDI is an effective complementary model for predicting potential DDIs, providing a reliable reference for traditional experimental methods.