Search

Recent advancements in spatial transcriptomics (ST) technologies offer unprecedented opportunities to unveil the spatial heterogeneity of gene expression and cell states within tissues. Despite these capabilities of the ST data, accurately dissecting spatiotemporal structures (e.g., spatial domains, temporal trajectories, and functional interactions) remains challenging. Here, we introduce a computational framework, PearlST (partial differential equation [PDE]-enhanced adversarial graph autoencoder of ST), for accurate inference of spatiotemporal structures from the ST data using PDE-enhanced adversarial graph autoencoder. PearlST employs contrastive learning to extract histological image features, integrates a PDE-based diffusion model to enhance characterization of spatial features at domain boundaries, and learns the latent low-dimensional embeddings via Wasserstein adversarial regularized graph autoencoders. Comparative analyses across multiple ST datasets with varying resolutions demonstrate that PearlST outperforms existing methods in spatial clustering, trajectory inference, and pseudotime analysis. Furthermore, PearlST elucidates functional regulations of the latent features by linking intercellular ligand-receptor interactions to most contributing genes of the low-dimensional embeddings, as illustrated in a human breast cancer dataset. Overall, PearlST proves to be a powerful tool for extracting interpretable latent features and dissecting intricate spatiotemporal structures in ST data across various biological contexts.

Abstract The doubly-fed induction generator (DFIG) with virtual inertia control and reactive damping control gives a renewable energy generation system inertia and damping characteristics similar to those of a thermal power plant, and the parameters of the control strategy have a direct impact on the small-signal stability of the system. This paper firstly introduces the operating characteristics and control strategies of DFIG-based damping control and virtual inertia control, establishes a small-signal model of the control-based DFIG integrated interconnected system, and investigates the effects of virtual inertia and reactive damping values on the small-signal stability of the system; then, the maximum damping ratio of the interval oscillation mode in small disturbance analysis is taken as the optimization objective, and the control parameters are the optimization variables. An optimization method of inertia and damping parameters is established for improving the small disturbance stability of the system. The results show that the optimization procedure could improve the damping ratio of the interval oscillation mode while ensuring the system frequency. The effects of virtual inertia and reactive damping values on the small signal stability of the system are investigated, and an optimal allocation model and method for virtual inertia used to improve the small disturbance stability of the system is proposed.

Ti-based bulk metallic glass composites (BMGMCs) containing an in situ formed metastable β phase normally exhibit enhanced plasticity attributed to induced phase transformation or twinning. However, the underlying deformation micromechanism remains controversial. This study investigates a novel deformation mechanism of Ti-based BMGMCs with a composition of Ti42.3Zr28Cu8.3Nb4.7Ni1.7Be15 (at%). The microstructures after tension were analyzed using advanced electron microscopy. The dendrites were homogeneously distributed in the glassy matrix with a volume fraction of 55 ± 2% and a size of 1~5 μm. The BMGMCs deformed in a serrated manner with a fracture strength (σf) of ~1710 MPa and a fracture strain of ~7.1%, accompanying strain hardening. The plastic deformation beyond yielding was achieved by a synergistic action, which includes shear banding, localized amorphization and a localized BCC (β-Ti) to HCP (α-Ti) structural transition. The localized amorphization was caused by high local strain rates during shear band extension from the amorphous matrix to the crystalline reinforcements. The localized structural transition from BCC to HCP resulted from accumulating concentrated stress during deformation. The synergistic action enriches our understanding of the deformation mechanism of Ti-based BMGMCs and also sheds light on material design and performance improvement. [ABSTRACT FROM AUTHOR]

Accurately detecting voltage faults is essential for ensuring the safe and stable operation of energy storage power station systems. To swiftly identify operational faults in energy storage batteries, this study introduces a voltage anomaly prediction method based on a Bayesian optimized (BO)-Informer neural network. Firstly, the temporal characteristics and actual data collected by the battery management system (BMS) are considered to establish a long-term operational dataset for the energy storage station. The Pearson correlation coefficient (PCC) is used to quantify the correlations between these data. Secondly, an Informer neural network with BO hyperparameters is used to build the voltage prediction model. The performance of the proposed model is assessed by comparing it with several state-of-the-art models. With a 1 min sampling interval and one-step prediction, trained on 70% of the available data, the proposed model reduces the root mean square error (RMSE), mean square error (MSE), and mean absolute error (MAE) of the predictions to 9.18 mV, 0.0831 mV, and 6.708 mV, respectively. Furthermore, the influence of different sampling intervals and training set ratios on prediction results is analyzed using actual grid operation data, leading to a dataset that balances efficiency and accuracy. The proposed BO-based method achieves more precise voltage abnormity prediction than the existing methods. [ABSTRACT FROM AUTHOR]

Cell–cell communications is crucial for the regulation of cellular life and the establishment of cellular relationships. Most approaches of inferring intercellular communications from single-cell RNA sequencing (scRNA-seq) data lack a comprehensive global network view of multilayered communications. In this context, we propose scHyper, a new method that can infer intercellular communications from a global network perspective and identify the potential impact of all cells, ligand, and receptor expression on the communication score. scHyper designed a new way to represent tripartite relationships, by extracting a heterogeneous hypergraph that includes the source (ligand expression), the target (receptor expression), and the relevant ligand–receptor (L-R) pairs. scHyper is based on hypergraph representation learning, which measures the degree of match between the intrinsic attributes (static embeddings) of nodes and their observed behaviors (dynamic embeddings) in the context (hyperedges), quantifies the probability of forming hyperedges, and thus reconstructs the cell–cell communication score. Additionally, to effectively mine the key mechanisms of signal transmission, we collect a rich dataset of multisubunit complex L-R pairs and propose a nonparametric test to determine significant intercellular communications. Comparing with other tools indicates that scHyper exhibits superior performance and functionality. Experimental results on the human tumor microenvironment and immune cells demonstrate that scHyper offers reliable and unique capabilities for analyzing intercellular communication networks. Therefore, we introduced an effective strategy that can build high-order interaction patterns, surpassing the limitations of most methods that can only handle low-order interactions, thus more accurately interpreting the complexity of intercellular communications. [ABSTRACT FROM AUTHOR]