Jinmiao Song

Multimodal intent detection leverages complementary information from diverse sensors to achieve precise semantic understanding; however, existing methodologies predominantly operate under the ideal assumption of modality completeness. In practical deployments, missing modalities, stemming from sensor failure, background noise, or privacy constraints, are inevitable and uncertain, leading to severe performance degradation. To address this challenge, we propose SADF, a Structure Aware Distillation Framework designed to facilitate robust cross-level knowledge transfer from a full-modality teacher to a partial-modality student. At the semantic level, semantic topology distillation aligns prototype similarity distributions between the teacher and the student, capturing class topology and hierarchical relations. At the discriminative level, boundary aware distillation decouples predictions into target and nontarget classes, enforcing alignment with the teacher to enhance discriminability and suppress noise. By integrating these strategies, SADF enables the student to learn robust representations and decisions when uncertain modalities are missing. The results of experiments based on two benchmarks demonstrate that SADF consistently outperforms strong baselines.

The efficient design of drug candidates requires simultaneous consideration of synthetic feasibility and pharmacokinetic safety. However, current computational tools typically address retrosynthetic planning and ADMET evaluation as separate tasks, requiring users to manually transfer data between platforms and evaluate candidate molecules in a sequential and time-consuming manner. Here, we present SynCraft, a web server that integrates template-based retrosynthesis with real-time ADMET evaluation within a unified workflow. SynCraft accepts molecular input via SMILES, interactive drawing, or file upload, and performs automated multi-step retrosynthetic planning while simultaneously assessing the safety and drug-likeness of all intermediate compounds. ADMET properties are predicted using a multi-view learning framework, and potentially hazardous intermediates are automatically highlighted with intuitive, colour-coded warnings during route exploration. The server further provides integrated analysis tools, including synthetic accessibility and complexity scoring, drug-likeness evaluation, and interactive 2D/3D visualization, enabling users to seamlessly transition from route generation to detailed molecular assessment. Results are presented through an interactive interface that allows comparison of alternative synthetic routes, with downloadable outputs in standard formats. In a case study of imatinib, SynCraft automatically identifies genotoxic intermediates that are typically overlooked in conventional retrosynthesis workflows, demonstrating its practical utility for safety-aware route design. The web server is freely accessible at https://syncraft.denglab.org.

High-resolution remote sensing images (HRRSI) exhibit significant differences in the scale of objects, and effectively extracting multi-scale features is key to describing objects of different sizes. Existing methods mostly aggregate features from specific levels, making it difficult to balance local details and global dependencies. To address this, this paper proposes MFESegNet, a land cover semantic segmentation network based on an encoder-decoder architecture, aimed at synergistically enhancing multi-scale feature representation and adaptive context modelling. The encoder uses a dual-branch architecture. The Adaptive Grouping Gated Convolution Block (AGGCB) uses innovative hierarchical channel grouping and dynamic gating mechanisms to suppress background noise and extract fine-grained local details. The Dual Attention Efficient Transformer Block (DAETB) uses spatial-channel decoupled attention and a frequency-domain feedforward network to efficiently model long-range dependencies while preserving high-frequency edge information. The Global-Local Feature Fusion (GLFF) module incorporates bidirectional attention gating to bridge the semantic gap between local and global features, enabling adaptive weight calibration for the two branches. The Multi-Scale Feature Attention Fusion (MFAF) module resolves cross-level semantic misalignment through synergistic, semantic-aligned convolutions and dual attention, thereby enhancing the model's adaptability to multi-scale objects. The decoder uses Mamba with a deformable scanning strategy (DSSM), which dynamically adjusts the sequence scanning path of Mamba based on the target geometry, achieving high-precision reconstruction of irregular boundaries. We carry out extensive comparison and ablation experiments on three representative datasets. The results show that compared with other methods, the MFESegNet has significant advantages in multi-scale feature extraction and contextual information representation, and provides a more effective solution for semantic segmentation of land cover.

Compared with monotherapy, combination drug therapy plays a crucial role in clinical treatment. However, the exponential expansion of the drug combination space has rendered traditional exploration methods for synergistic drug combinations inadequate. Recently, numerous efficient and accurate computational approaches have been developed to predict anticancer drug synergy, particularly those leveraging hypergraphs to model the multifaceted relationships between drug combinations and cell lines, which have demonstrated remarkable potential. Nevertheless, existing hypergraph-based methods fail to account for the heterogeneity of anticancer synergy hypergraphs and overlook the underlying similarities among drugs and cell lines, thereby limiting their ability to fully capture the complex interactions between drug combinations and cell lines. To address these limitations, we propose an Adaptive Heterogeneous Hypergraph Representation Learning Method (HHGSynergy) for predicting anticancer drug synergy, enabling more precise identification of synergistic drug combinations. Specifically, our framework first constructs drug/cell line similarity-based synergy hypergraphs based on the foundational anticancer synergy hypergraph, thereby establishing a comprehensive heterogeneous hypergraph. Next, a node importance calculation module is employed to learn both local and global importance weights of nodes, effectively capturing the structural characteristics of the hypergraph. Finally, a type-specific multi-head attention mechanism is utilized to iteratively update node embeddings, adaptively learning the significance of heterogeneous hyperedges. Experimental results demonstrate that HHGSynergy achieves state-of-the-art performance in both classification and regression tasks across diverse experimental scenarios, outperforming existing leading models. Case studies further underscore its potential for discovering novel synergistic drug combinations. The source code and the datasets are available at https://github.com/lasxmy/HHGSynergy.

Circular RNA (circRNA) is a widely distributed class of non-coding RNA molecules that have been shown to play a significant role in cancer development and drug resistance, significantly influencing cellular sensitivity to therapeutic drugs and treatment outcomes. However, traditional biomedical experimental methods are limited by low efficiency and high costs when verifying the association between circular RNA and drug sensitivity. Therefore, developing an efficient and accurate computational method to predict new associations between circRNA and drug sensitivity has become an urgent need in current research. To address this, this study proposes HECLCDA, a novel method based on heterogeneous cross-scale contrastive learning. To construct a comprehensive initial information base for drugs and circRNAs, circRNA gene sequence similarity, drug structural inclusion similarity (SIS), and Gaussian kernel similarity were integrated. Based on the integrated and complete known information of circRNAs and drugs, a heterogeneous graph was built. The model used the Heterogeneous Graph Transformer to extract heterogeneous network topological information, effectively distinguishing the heterogeneity of nodes and edges. The model broke through the information relationship between node attributes and network topology at two scales, and innovatively introduced a cross-scale contrastive learning mechanism in a sparse labeling scenario. Using self-supervised signals, we aimed to enhance the discriminative power of node embeddings and maximize the mutual information between paired nodes at different scales. Cross-validation experiments demonstrated that HECLCDA performs excellently on real data and can efficiently predict drug sensitivity. Additionally, case studies further validate the model's effectiveness in predicting potential circRNA-drug sensitivity associations.

Survival prediction serves as a pivotal component in precision oncology, enabling the optimization of treatment strategies through mortality risk assessment. While the integration of histopathological images and genomic profiles offers enhanced potential for patient stratification, existing methodologies are constrained by two fundamental limitations: (i) insufficient attention to fine-grained local features in favor of global representations, and (ii) suboptimal cross-modal fusion strategies that either neglect intrinsic correlations or discard modality-specific information. To address these challenges, we propose DSCASurv, a novel cross-modal fusion alignment framework designed to explore and integrate intrinsic correlations across multimodal data, thereby improving the accuracy of survival prediction. Specifically, DSCASurv leverages the local feature extraction capabilities of convolutional layers and the long-range dependency modeling of scanning state space models to extract intra-modal representations, while generating cross-modal representations through dual parallel mixer architectures. A cross-modal attention module functions as a bridge for inter-modal information exchange and complementary information transfer. The framework ultimately integrates all intra-modal representations to generate survival predictions by enhancing and recalibrating complementary information. Extensive experiments on five benchmark cancer datasets demonstrate the superior performance of our approach compared to existing methods.

Predicting potential drug-disease associations (RDAs) plays a pivotal role in elucidating therapeutic strategies for diseases and facilitating drug repositioning, making it of paramount importance. However, existing methods are constrained and rely heavily on limited domain-specific knowledge, impeding their ability to effectively predict candidate associations between drugs and diseases. Moreover, the simplistic definition of unknown information pertaining to drug-disease relationships as negative samples presents inherent limitations. To overcome these challenges, we introduce a novel hierarchical negative sampling-based graph contrastive model, termed HSGCLRDA, which aims to forecast latent associations between drugs and diseases. In this study, HSGCLRDA integrates the association information as well as similarity between drugs, diseases and proteins. Meanwhile, the model constructs a drug-disease-protein heterogeneous network. Subsequently, employing a hierarchical structural sampling technique, we establish reliable negative drug-disease samples utilizing PageRank algorithms. Utilizing meta-path aggregation within the heterogeneous network, we derive low-dimensional representations for drugs and diseases, thereby constructing global and local feature graphs that capture their interactions comprehensively. To obtain representation information, we adopt a self-supervised graph contrastive approach that leverages graph convolutional networks (GCNs) and second-order GCNs to extract feature graph information. Furthermore, we integrate a contrastive cost function derived from the cross-entropy cost function, facilitating holistic model optimization. Experimental results obtained from benchmark datasets not only showcase the superior performance of HSGCLRDA compared to various baseline methods in predicting RDAs but also emphasize its practical utility in identifying novel potential diseases associated with existing drugs through meticulous case studies.

The search for potential drug–disease associations (DDA) can speed up drug development cycles, reduce costly wasted resources, and accelerate disease

Studies have shown that IncRNA-miRNA interactions can affect cellular expression at the level of gene molecules through a variety of regulatory mechanisms and have important effects on the biological activities of living organisms. Several biomolecular network-based approaches have been proposed to accelerate the identification of lncRNA-miRNA interactions. However, most of the methods cannot fully utilize the structural and topological information of the lncRNA-miRNA interaction network. In this article, we proposed a new method, ISLMI, a prediction model based on information injection and second order graph convolution network(SOGCN). The model calculated the sequence similarity and Gaussian interaction profile kernel similarity between lncRNA and miRNA, fused them to enhance the intrinsic interaction between the nodes, using SOGCN to learn second-order representations of similarity matrix information. At the same time, multiple feature representations obtain using different graph embedding methods were also injected into the second-order graph representation. Finally, matrix complementation was used to increase the model accuracy. The model combined the advantages of different methods and achieved reliable performance in 5-fold cross-validation, significantly improved the performance of predicting lncRNA-miRNA interactions. In addition, our model successfully confirmed the superiority of ISLMI by comparing it with several other model algorithm.