Cancer is a complex and heterogeneous disease, where even patients with the same cancer type may respond differently to treatment regimens. Predicting the therapeutic effects of drugs on cancer based on cancer characteristics is a critical aspect of precision oncology. Currently, most anticancer drug response(CDR) prediction methods rely on extracting features from the cell line-drug bipartite composition. However, these methods often fail to adequately capture the features of both drugs and cell lines, ignoring the homogeneous features of cell lines and drugs and their correlation with deep heterogeneous features. To address these challenges, we propose a novel prediction framework that leverages a heterogeneous and homogeneous hybrid graph neural network named H$^{3}$CDR. H$^{3}$CDR learns the similarity features of cancer cell lines and drugs by fusing their multi-omics data. Additionally, a multi-branch network is employed to extract features from both cell lines and drugs, enabling the identification of potential features. Extensive experiments on the GDSC and CCLE databases demonstrate the superiority of our model. Evaluated by five-fold cross-validation, H$^{3}$CDR achieves an area under the ROC curve (AUC) of 0.8772 and an area under the precision-recall curve (AUPRC) of 0.8819 on the GDSC dataset.

External knowledge provides critical clues for knowledge-based visual question answering (KB-VQA), while the implicit knowledge in images is difficult to capture in order to construct effective queries for knowledge bases. To this end, we propose a visual entity-centric prompting for knowledge retrieval (VEPR) to bridge the gap between the implicit and explicit knowledge driven by visual entities via large language models. More specifically, a visual entity question answering (EQ) module is devised to localize the critical entities from the given images and questions to generate entity-centric questions via a large language model. In particular, EQ obtains several entity-centric question-answer pairs via a visual language model. Furthermore, a question-answer-enhanced retrieval (ER) module is devised to construct a query by summarizing the text including question-answer pairs, captions and questions, in order to require explicit knowledge items. Finally, a multi-branch reader (MR) module is designed to encode the given questions, visual content and retrieved knowledge items, which are decoded to make answer predictions. Extensive experiments conducted on two public datasets demonstrate the effectiveness of the VEPR.

Drug repositioning (DR) presents a cost-effective strategy for drug development by identifying novel therapeutic applications for existing drugs. Current computational approaches remain constrained by their inability to synergize localized substructure patterns with global network semantics, leading to overreliance on data augmentation to mitigate latent drug-disease association (DDA) information gaps. To address these limitations, we present multi-view stacked graph convolutional network (MVSGDR), a novel DR framework featuring three technical innovations: (i) multi-view stacked module that enables depth-wise feature enhancement through hierarchical aggregation of multi-hop neighborhood interactions across distinct graph convolutional layers; (ii) bi-level subgraph transformer module that decomposes DDAs into METIS (a graph partitioning tool) informative subgraphs for breadth-wise analysis of external and internal subgraph drug-disease relationships; and (iii) negative sampling balancing strategy that mitigates sample imbalance through negative sample synthesis. Extensive 10-fold cross-validation experiments across four benchmark datasets confirm MVSGDR's superior performance, demonstrating its statistically significant improvements over existing methods. Moreover, case studies further validate MVSGDR's potential utility through identification of previously unreported DDAs with supporting literature evidence.

Discovering miRNAs associated with diseases can contribute to understanding the pathogenesis and treatment strategies of diseases. In the commonly used graph regularized non-negative matrix factorization methods for miRNA-disease association prediction, there exist issues such as interference from low-dimensional matrix noise and loss of network topology information from partial original data. To solve these issues, we propose a method called L$_{21}$ S-NPFM, which combines L$_{21}$ similarity constrain graph matrix factorization and network projection fusion for miRNA-disease association prediction. First, we introduce a similarity constraint term based on the L$_{21}$-norm (L$_{21}$ SGMF) into matrix factorization, effectively suppressing noise in the low-dimensional matrix. Second, we design a network projection fusion method (NPFM) to integrate the consistency projection matrices of miRNA/disease networks and initial score matrices, compensating for the lost network topology information. Experimental results from LOOCV and 5-fold CV findings show that L$_{21}$ S-NPFM works better than six other mainstream methods. Additionally, case studies show its accuracies of up to 100% for 10 miRNAs associated with diabetic nephropathy (DN) and 80% for 10 miRNAs associated with thoracic aortic aneurysm (TAA), respectively.

In this paper, we propose a two-stage network with modality-specific and -shared contrastive learning (MMCL) for multimodal sentiment analysis. MMCL comprises a category-aware modality-specific contrastive (CMC) module and a self-decoupled modality-shared contrastive (SMC) module. In the first stage, the CMC module guides the encoders to extract modality-specific representations by constructing positive-negative pairs according to sample categories. In the second stage, the SMC module guides the encoders to extract modality-shared representations by constructing positive-negative pairs based on modalities and decoupling the self-contrast of all modalities. In the aforementioned modules, we leverage self-modulation factors to focus more on hard positive pairs through assigning different loss weights to positive pairs depending on their distance. In particular, we introduce a dynamic routing algorithm to cluster the inputs of the contrastive modules during training, where a gradient stopping strategy is utilized to isolate the backpropagation process of the CMC and SMC modules. Extensive experiments on the CMU-MOSI and CMU-MOSEI datasets show that MMCL achieves the state-of-the-art performance.

Recent studies have revealed that long noncoding RNAs (lncRNAs) are closely linked to several human diseases, providing new opportunities for their use in detection and therapy. Many graph propagation and similarity fusion approaches can be used for predicting potential lncRNA-disease associations. However, existing similarity fusion approaches suffer from noise and self-similarity loss in the fusion process. To address these problems, a new prediction approach, termed SSMF-BLNP, based on organically combining selective similarity matrix fusion (SSMF) and bidirectional linear neighborhood label propagation (BLNP), is proposed in this paper to predict lncRNA-disease associations. In SSMF, self-similarity networks of lncRNAs and diseases are obtained by selective preprocessing and nonlinear iterative fusion. The fusion process assigns weights to each initial similarity network and introduces a unit matrix that can reduce noise and compensate for the loss of self-similarity. In BLNP, the initial lncRNA-disease associations are employed in both lncRNA and disease directions as label information for linear neighborhood label propagation. The propagation was then performed on the self-similarity network obtained from SSMF to derive the scoring matrix for predicting the relationships between lncRNAs and diseases. Experimental results showed that SSMF-BLNP performed better than seven other state of-the-art approaches. Furthermore, a case study demonstrated up to 100% and 80% accuracy in 10 lncRNAs associated with hepatocellular carcinoma and 10 lncRNAs associated with renal cell carcinoma, respectively. The source code and datasets used in this paper are available at: https://github.com/RuiBingo/SSMF-BLNP.

Previous studies have confirmed microRNA (miRNA), small single-stranded non-coding RNA, participates in various biological processes and plays vital roles in many complex human diseases. Therefore, developing an efficient method to infer potential miRNA disease associations could greatly help understand operational mechanisms for diseases at the molecular level. However, during these early stages for miRNA disease prediction, traditional biological experiments are laborious and expensive. Therefore, this study proposes a novel method called AGAEMD (node-level Attention Graph Auto-Encoder to predict potential MiRNA Disease associations). We first create a heterogeneous matrix incorporating miRNA similarity, disease similarity, and known miRNA-disease associations. Then these matrixes are input into a node-level attention encoder-decoder network which utilizes low dimensional dense embeddings to represent nodes and calculate association scores. To verify the effectiveness of the proposed method, we conduct a series of experiments on two benchmark datasets (the Human MicroRNA Disease Database v2.0 and v3.2) and report the averages over 10 runs in comparison with several state-of-the-art methods. Experimental results have demonstrated the excellent performance of AGAEMD in comparison with other methods. Three important diseases (Colon Neoplasms, Lung Neoplasms, Lupus Vulgaris) were applied in case studies. The results comfirm the reliable predictive performance of AGAEMD.

The importance of microbe-drug associations (MDA) prediction is evidenced in research. Since traditional wet-lab experiments are both time-consuming and costly, computational methods are widely adopted. However, existing research has yet to consider the cold-start scenarios that commonly seen in clinical research and practices where confirmed MDA data are highly sparse. Therefore, we aim to contribute by developing two novel computational approaches, the GNAEMDA (Graph Normalized Auto-Encoder to predict MDA), and its variational extension (called VGNAEMDA), to provide effective and efficient solutions for well-annotated cases and cold-start scenarios. Multi-modal attribute graphs are constructed by collecting multiple features of microbes and drugs, and then input into a graph normalized convolutional network, where a $\ell _{2}$-normalization is introduced to avoid the norm-towards-zero tendency of isolated nodes in embedding space. Then the reconstructed graph output by the network is used to infer undiscovered MDA. The difference between the two proposed models lays in the way to generate the latent variables in network. To verify their effectiveness, we conduct a series of experiments on three benchmark datasets in comparison with six state-of-the-art methods. The comparison results indicate that both GNAEMDA and VGNAEMDA have strong prediction performances in all cases, especially in identifying associations for new microbes or drugs. In addition, we conduct case studies on two drugs and two microbes and find that more than 75% of the predicted associations have been reported in PubMed. The comprehensive experimental results validate the reliability of our models in accurately inferring potential MDA.

Multi-contrast magnetic resonance imaging (MRI) is widely used in clinical diagnosis. However, it is time-consuming to obtain MR data of multi-contrasts and the long scanning time may bring unexpected physiological motion artifacts. To obtain MR images of higher quality within limited acquisition time, we propose an effective model to reconstruct images from under-sampled k-space data of one contrast by utilizing another fully-sampled contrast of the same anatomy. Specifically, multiple contrasts from the same anatomical section exhibit similar structures. Enlightened by the fact that co-support of an image provides an appropriate characterization of morphological structures, we develop a similarity regularization of the co-supports across multi-contrasts. In this case, the guided MRI reconstruction problem is naturally formulated as a mixed integer optimization model consisting of three terms, the data fidelity of k-space, smoothness-enforcing regularization, and co-support regularization. An effective algorithm is developed to solve this minimization model alternatively. In the numerical experiments, T2-weighted images are used as the guidance to reconstruct T1-weighted/T2-weighted-Fluid-Attenuated Inversion Recovery (T2-FLAIR) images and PD-weighted images are used as the guidance to reconstruct PDFS-weighted images, respectively, from their under-sampled k-space data. The experimental results demonstrate that the proposed model outperforms other state-of-the-art multi-contrast MRI reconstruction methods in terms of both quantitative metrics and visual performance at various sampling ratios.

Increasing number of experiments show that lncRNAs are involved in many biological processes, and their mutations and disorders are associated with many diseases. However, verifying the relationships between lncRNAs and diseases is time consuming and laborio. Searching for effective computational methods will contribute to our understanding of the underlying mechanisms of disease and identifying biomarkers of diseases. Therefore, we proposed a method called lncRNA-disease association prediction based on linear neighborhood similarity and unbalanced bi-random walk (LDA-LNSUBRW). Given that the known lncRNA-disease associations are rare, a pretreatment step should be performed to obtain the interaction possibility of unknown cases, so as to help us predict the potential associations. In the framework of leave-one-out cross-validation (LOOCV)and fivefold cross-validation (5-fold CV), LDA-LNSUBRW achieved effective performance with AUC of 0.8874 and 0.8632 ± 0.0051, respectively. The experimental results in this paper show that the proposed method is superior to five other state-of-the-art methods. In addition, case studies of three diseases (lung cancer, breast cancer, and osteosarcoma)were carried out to illustrate that LDA-LNSUBRW could predict the relevant lncRNAs.

The emergence of coronavirus disease 2019 (COVID-19) has had a significant impact on healthcare and the economy. With representation learning applied in constructing COVID-19 knowledge graphs, abundant COVID-19-related knowledge collected by clinicians and scientists all over the world can be utilized to deepen their understanding of the mechanism and related biological functions of the disease. However, most existing representation learning models cannot deal well with COVID-19 knowledge graph due to its low-connected star-like structure and various complex nonlinear relationships. Besides, lacking reliable negative triplets is also a difficult problem, yet to be adequately resolved. In this article, we propose a novel representation learning model called translation on hyperplanes with an activation operation and similar semantic sampling (SimH) for COVID-19 knowledge graphs. In our proposed SimH, an activation operation is designed to provide additional interaction features for low-in-degree entities. Then the hyperplane projection technique is introduced to the distance-based scoring function so that those complex nonlinear relationships can be modeled with lower complexity maintained in comparison with other nonlinear models. Moreover, a negative triplet sampling method that adaptively replaces entities with similar semantics is introduced to generate reliable negative triplets. To verify the effectiveness of SimH, extensive experiments are conducted on the COVID-19-Concepts dataset. The experimental results show that our SimH model achieves significant improvements in prediction and classification accuracy over existing knowledge representation learning models.

Summary A new estimation of distribution algorithm based on normalized mutual information (NMIEDA) is proposed for overcoming the premature convergence of bivariate estimation of distribution algorithms. NMIEDA first uses normalized mutual information to measure the interaction between two variables and then generate a dependency forest model. Second, based on the concept of sporadic model building and a reward and punishment scheme in Selfish Gene, NMIEDA provides a new updating mechanism that accelerates the convergence speed. Finally, a new sampling mechanism is adopted in NMIEDA to improve the efficiency of sampling, which combines stochastic sampling, the opposition‐based learning scheme and the mutation operator. The simulation results on benchmark problems and real‐world problems demonstrate that NMIEDA often outperforms several other bivariate algorithms.