Single-cell RNA sequencing (scRNA-seq) enables high-resolution analysis of gene expression at the individual cell level, with clustering serving as a critical step for identifying distinct cell populations. Due to the high dimensionality and sparsity of scRNA-seq data, existing approaches typically perform gene selection prior to clustering. However, treating feature selection as a separate preprocessing step can overlook latent clustering structure and often results in suboptimal outcomes, as it does not guarantee that the selected genes are informative for clustering. To address this limitation, we propose FSSC (Feature Selection for scRNA-seq Clustering), a unified framework for joint feature selection and clustering in scRNA-seq analysis. FSSC integrates a zero-inflated negative binomial (ZINB) autoencoder with a group Lasso penalty and a dedicated clustering loss. This joint optimization enables the model to simultaneously learn low-dimensional representations and select a compact set of cluster-discriminatory genes, preserving both the statistical characteristics of scRNA-seq data and its underlying cluster structure. Extensive experiments on both simulated and real scRNA-seq datasets demonstrate that FSSC consistently outperforms state-of-the-art methods in clustering accuracy and effectively identifies a compact, biologically meaningful set of marker genes.

Single-cell technologies enable researchers to investigate cell functions at an individual cell level and study cellular processes with higher resolution. Several multi-omics single-cell sequencing techniques have been developed to explore various aspects of cellular behavior. Using NEAT-seq as an example, this method simultaneously obtains three kinds of omics data for each cell: gene expression, chromatin accessibility, and protein expression of transcription factors (TFs). Consequently, NEAT-seq offers a more comprehensive understanding of cellular activities in multiple modalities. However, there is a lack of tools available for effectively integrating the three types of omics data. To address this gap, we propose a novel pipeline called MultiSC for the analysis of MULTIomic Single-Cell data. Our pipeline leverages a multimodal constraint autoencoder (single-cell hierarchical constraint autoencoder) to integrate the multi-omics data during the clustering process and a matrix factorization-based model (scMF) to predict target genes regulated by a TF. Moreover, we utilize multivariate linear regression models to predict gene regulatory networks from the multi-omics data. Additional functionalities, including differential expression, mediation analysis, and causal inference, are also incorporated into the MultiSC pipeline. Extensive experiments were conducted to evaluate the performance of MultiSC. The results demonstrate that our pipeline enables researchers to gain a comprehensive view of cell activities and gene regulatory networks by fully leveraging the potential of multiomics single-cell data. By employing MultiSC, researchers can effectively integrate and analyze diverse omics data types, enhancing their understanding of cellular processes.

This work investigates the problem of finite blocklength covert communications with relay assistance in Internet of Things (IoT) to extend the communications range. We reconstruct the framework for analyzing covert communications under decoded and forwarded protocols based on Willie’s optimal detection method. The analytic expression of Kullback-Leibler (KL) divergence is derived, the upper bound of KL divergence is solved by using the convexity of KL divergence, and the strict covertness constraint of the system is obtained. Meanwhile, to maximize the effective throughput, a covert communication parameter configuration scheme is proposed. Theoretical analysis and simulation results indicate that the compromised relationship of transmit power between Alice and relay nodes, and a reasonable power allocation scheme can enhance the effective throughput of the system.

Low-Earth orbit (LEO) satellites are recognized as one of the most promising infrastructures for realizing global Internet of Things (IoT) services. With the explosive growth of user terminals (UTs) and data traffic, the integration of massive multiple-input multiple-output (mMIMO) techniques and LEO satellite communication systems has been regarded as a novel idea to enhance system capacity and realize global seamless high-speed interconnection. However, obtaining effective downlink channel state information (CSI) and establishing a simple and efficient hybrid beamforming mechanism are challenging tasks due to the limitations of objective factors, such as high dynamic, long delay, and low payload in LEO satellite scenarios. It is embodied in three aspects: 1) the untenable channel reciprocity in time division duplex (TDD) systems; 2) the training feedback costs and feedback delay in frequency division duplex (FDD) systems; and 3) the complex nonconvex optimization process faced by hybrid beamforming design. Driven by the performance advantages of the deep learning (DL) technology to deal with various problems in the field of physical layer communications, this article proposes to use a deep neural network (DNN) to solve the above challenges, and constructs SatCP and SatHB schemes for realizing downlink CSI acquirement and hybrid beamforming design, respectively. By deeply mining the potential correlation of the uplink-downlink channels between LEO satellites and UTs and exploring the mapping relationship between CSI and beamformers, the SatCP can assist LEO satellites to directly predict the future downlink CSI based on the observed uplink CSI with no need for downlink channel estimation, while the SatHB can easily generate the corresponding beamformers based on the downlink CSI predicted by the SatCP without requiring complex optimization. Numerical results demonstrate that the proposed SatCP and SatHB can play an effective auxiliary role in LEO satellite mMIMO communication systems.

BACKGROUND: Neurons are the basic structural unit of the brain, and their morphology is a key determinant of their classification. The morphology of a neuronal circuit is a fundamental component in neuron modeling. Recently, single-neuron morphologies of the whole brain have been used in many studies. The correctness and completeness of semimanually traced neuronal morphology are credible. However, there are some inaccuracies in semimanual tracing results. The distance between consecutive nodes marked by humans is very long, spanning multiple voxels. On the other hand, the nodes are marked around the centerline of the neuronal fiber, not on the centerline. Although these inaccuracies do not seriously affect the projection patterns that these studies focus on, they reduce the accuracy of the traced neuronal skeletons. These small inaccuracies will introduce deviations into subsequent studies that are based on neuronal morphology files. RESULTS: We propose a neuronal digital skeleton optimization method to evaluate and make fine adjustments to a digital skeleton after neuron tracing. Provided that the neuronal fiber shape is smooth and continuous, we describe its physical properties according to two shape restrictions. One restriction is designed based on the grayscale image, and the other is designed based on geometry. These two restrictions are designed to finely adjust the digital skeleton points to the neuronal fiber centerline. With this method, we design the three-dimensional shape restriction workflow of neuronal skeleton adjustment computation. The performance of the proposed method has been quantitatively evaluated using synthetic and real neuronal image data. The results show that our method can reduce the difference between the traced neuronal skeleton and the centerline of the neuronal fiber. Furthermore, morphology metrics such as the neuronal fiber length and radius become more precise. CONCLUSIONS: This method can improve the accuracy of a neuronal digital skeleton based on traced results. The greater the accuracy of the digital skeletons that are acquired, the more precise the neuronal morphologies that are analyzed will be.