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.

Deep learning-based methods have shown promising results in multi-label chest X-ray (CXR) image classification. However, most existing methods rely on large-scale fully-annotated datasets, which are costly and laborious to obtain. Therefore, training a high-performance model with limited annotation remains a significant challenge in practice. To address this issue, we propose a Generalized Nesterov-Boosted Adversarial Data Augmentation (GN-ADA) framework for multi-label CXR image classification. First, we generate pseudo labels based on the model predictions on weakly-augmented images. Next, we propose a Generalized Nesterov Iterative Fast Gradient Sign Method (GNI-FGSM) to generate effective adversarial examples as strongly-augmented data. Then, we introduce an adversarial-augmentation-based consistency regularization to perform supervision of model predictions on the above adversarial examples. We note that the proposed GNI-FGSM is a higher-order FGSM variant, which is capable of generating more effective adversarial examples for model training within a constrained time frame, thereby improving the overall classification performance. Extensive experiments on two large CXR datasets (CheXpert and MIMIC-CXR) demonstrate the effectiveness of the proposed GN-ADA framework for multi-label CXR image classification under limited-annotation scenario.

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.

Wildfires pose a critical threat to human life, property safety, and ecological systems. Weather radar has demonstrated significant potential as an effective wildfire monitoring tool. However, as the dominant sources of radar backscattering signatures, the mechanisms of particle scattering are unclear. In this study, the microwave scattering characteristics of pyrometeors (lofted above wildfires that are composed of the byproducts of fuel combustion) were systematically investigated through integrated experimental measurements and numerical simulations. The complex permittivity of pyrometeors was measured across 1–18 GHz using the coaxial transmission/reflection method. The scattering properties of pyrometeors at microwave frequencies were determined using the discrete dipole approximation method. Results indicate that the scattering polarization characteristics of pyrometeors are regulated by particle size and aspect ratio within microwave frequencies. The magnitude ofF11(π) is positively correlated with particle aspect ratio under horizontal orientation. The backscattering cross section exhibits an inverse proportionality to incident wavelength across L–Ku-bands and a positive proportionality to particle size. C-, X-, and Ku-band radars show high sensitivity to pyrometeor morphology, necessitating precise shape modeling for accurate echo interpretation. Differential reflectivity ZDR exhibits nonmonotonic frequency dependence within the Mie scattering regime, confirming the joint influence of particle size and shape on polarimetric response. The effective reflectivity factor derived from this experiment falls within the range of observed measurements, supporting the feasibility of this study method in modeling the microwave scattering properties of pyrometeor particles.

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.

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.

Discriminative sparse coding has emerged as a promising technique in image analysis and recognition, which couples the process of classifier training and the process of dictionary learning for improving the discriminability of sparse codes. Many existing approaches consider only a simple single linear classifier whose discriminative power is rather weak. In this paper, we proposed a discriminative sparse coding method which jointly learns a dictionary for sparse coding and an ensemble classifier for discrimination. The ensemble classifier is composed of a set of linear predictors and constructed via both subsampling on data and subspace projection on sparse codes. The advantages of the proposed method over the existing ones are multi-fold: better discriminability of sparse codes, weaker dependence on peculiarities of training data, and more expressibility of classifier for classification. These advantages are also justified in the experiments, as our method outperformed several recent methods in several recognition tasks.

This paper addresses the challenge of reliably capturing the temporal characteristics of local space-time patterns in dynamic texture (DT). A powerful DT descriptor is proposed, which enjoys strong robustness to viewpoint changes, illumination changes, and video deformation. Observing that local DT patterns are spatial-temporally distributed with stationary irregularities, we proposed to characterize the distributions of local binarized DT patterns along both the temporal and the spatial axes via lacunarity analysis. We also observed such irregularities are similar on the DT slices along the same axis but distinct between axes. Thus, the resulting lacunarity based features are averaged along each axis and concatenated as the final DT descriptor. We applied the proposed DT descriptor to DT classification and evaluated its performance on several benchmark datasets. The experimental results have demonstrated the power of the proposed descriptor in comparison with existing ones.

Based on the concept of lacunarity in fractal geometry, we developed a statistical approach to texture description, which yields highly discriminative feature with strong robustness to a wide range of transformations, including pho- tometric changes and geometric changes. The texture feature is constructed by concatenating the lacunarity-related parameters estimated from the multi-scale local binary patterns of image. Benefiting from the ability of lacunarity analysis to distinguish spatial patterns, our method is able to characterize the spatial distribution of local image structures from multiple scales. The proposed feature was applied to texture classification and has demonstrated excellent performance in comparison with several state-of-the- art approaches on four benchmark datasets.