With the rapid advances in single-cell sequencing technology, it is now feasible to conduct in-depth genetic analysis in individual cells. Study on the dynamics of single cells in response to perturbations is of great significance for understanding the functions and behaviors of living organisms. However, the acquisition of post-perturbation cellular states via biological experiments is frequently cost-prohibitive. Predicting the single-cell perturbation responses poses a critical challenge in the field of computational biology. In this work, we propose a novel deep learning method called coupled variational autoencoders (CoupleVAE), devised to predict the postperturbation single-cell RNA-Seq data. CoupleVAE is composed of two coupled VAEs connected by a coupler, initially extracting latent features for controlled and perturbed cells via two encoders, subsequently engaging in mutual translation within the latent space through two nonlinear mappings via a coupler, and ultimately generating controlled and perturbed data by two separate decoders to process the encoded and translated features. CoupleVAE facilitates a more intricate state transformation of single cells within the latent space. Experiments in three real datasets on infection, stimulation and cross-species prediction show that CoupleVAE surpasses the existing comparative models in effectively predicting single-cell RNA-seq data for perturbed cells, achieving superior accuracy.

With the advent of Vehicular Ad Hoc Networks (VANETs), Vehicular Edge Computing (VEC) facilitates the execution of vehicular tasks through the Internet. In the VEC architecture, vehicles request task offloading, and a central decision center allocates resources. Effective task offloading algorithms provide optimal and equitable decisions based on objectives such as task latency and system overhead; however, current task offloading algorithms for VEC face challenges in adapting to complex and dynamic road environments. This paper proposes a task-offloading algorithm based on deep reinforcement learning to address the challenges of task offloading in vehicular edge computing. During the task offloading process, the privacy of vehicular task data may be compromised. This study introduces a novel task-offloading algorithm for Vehicular Edge Computing (VEC) that employs differential privacy principles to safeguard the confidentiality of vehicular tasks during the offloading process. The proposed algorithm introduces noise in accordance with the privacy budget during the training process. The study provides a theoretical analysis of privacy, and experimental results based on Attari demonstrate that the proposed differential privacy-based reinforcement learning algorithm exhibits superior convergence compared to existing algorithms. Veins-based simulation experiments on VEC demonstrate that the proposed differential privacy-based task-offloading algorithm can achieve practical offloading while preserving privacy.

Cell-cell communication (CCC) is a fundamental biological process essential for maintaining the functionality of multicellular organisms. It allows cells to coordinate their activities, sustain tissue homeostasis, and adapt to environmental changes. However, understanding the mechanisms underlying intercellular communication remains challenging. The rapid advancements in spatial transcriptomics (ST) have enabled the analysis of CCC within its spatial context. Despite the development of several computational methods for inferring CCCs from ST data, most rely on literature-curated gene or protein interaction lists, which are often inadequate due to the restricted gene coverage. In this work, we propose OrgaCCC, an orthogonal graph autoencoders approach for cell-cell communication inference based on deep generative models. OrgaCCC leverages the information of gene expression profiles, spatial locations and ligand-receptor relationships. It captures both cell/spot and gene features using two orthogonally coupled variational graph autoencoders across cell/spot and gene dimensions and combines them by maximizing the similarity between their reconstructed cell/spot features. Numerical experiments on five ST datasets demonstrate the superiority of OrgaCCC compared with state-of-the-art methods in CCC inference at the cell-type level, cell/spot level, and ligand-receptor level, in terms of inference accuracy and reliability.

Tensor decompositions have been successfully applied to multidimensional data recovery. However, classical tensor decompositions are not suitable for emerging spatio-irregular multidimensional data (i.e., spatio-irregular tensor), whose spatial domain is non-rectangular, e.g., spatial transcriptomics data from bioinformatics and semantic units from computer vision. By using preprocessing (e.g., zero-padding or element-wise 0-1 weighting), the spatio-irregular tensor can be converted to a spatio-regular tensor and then classical tensor decompositions can be applied, but this strategy inevitably introduces bias information, leading to artifacts. How to design a tensor-based method suitable for emerging spatio-irregular tensors is an imperative challenge. To address this challenge, we propose a learnable transform-assisted tensor singular value decomposition (LTA-TSVD) for spatio-irregular tensor recovery, which allows us to leverage the intrinsic structure behind the spatio-irregular tensor. Specifically, we design a learnable transform to project the original spatio-irregular tensor into its latent spatio-regular tensor, and then the latent low-rank structure is captured by classical TSVD on the resulting regular tensor. Empowered by LTA-TSVD, we develop spatio-irregular low-rank tensor completion (SIR-LRTC) and spatio-irregular tensor robust principal component analysis (SIR-TRPCA) models for the spatio-irregular tensor imputation and denoising respectively, and we design corresponding solving algorithms with theoretical convergence. Extensive experiments including the spatial transcriptomics data imputation and hyperspectral image denoising show SIR-LRTC and SIR-TRPCA are superior performance to competing approaches and benefit downstream applications.

The advancement of the Internet of Vehicles (IoV) has facilitated the integration of intelligent vehicles with Internet connectivity, providing access to a wide range of services that significantly enhance vehicular applications. However, this connectivity also brings about an increased vulnerability to cyber attacks from the internet. Given the limited computing and communication resources available in vehicles, existing intrusion detection methods are ill-suited for vehicular networks. In this paper, we propose a lightweight vehicular intrusion detection method based on Edge Intelligence. The proposed method utilizes edge intelligence to achieve real-time intrusion detection in vehicles. To ensure efficient intrusion detection, we design a lightweight Convolutional Neural Networks (CNN) intrusion detection model and incorporate Auxiliary Classifier Generative Adversarial Networks (ACGAN) for model training. The CNN component will be offloaded to the Edge Cloud to further enhance intrusion detection performance. To address the task offloading optimization problem in edge computing, we introduce a deep reinforcement learning-based task offloading algorithm to allocate the resources of edge cloud for vehicles with limited computing resources. Simulation experiments demonstrate the superiority of proposed vehicular intrusion detection method over existing state-of-the-art methods. The simulation experiments by Veins also show the efficiency of the proposed vehicular intrusion detection.

MOTIVATION: The development of single-cell RNA sequencing (scRNA-seq) technology makes it possible to study the cellular dynamic processes such as cell cycle and cell differentiation. Due to the difficulties in generating genuine time-series scRNA-seq data, it is of great importance to computationally infer the pseudotime of the cells along differentiation trajectory based on their gene expression patterns. The existing pseudotime prediction methods often suffer from the high level noise of single-cell data, thus it is still necessary to study the single-cell trajectory inference methods. RESULTS: In this study, we propose a branched local tangent space alignment (BLTSA) method to infer single-cell pseudotime for multi-furcation trajectories. By assuming that single cells are sampled from a low-dimensional self-intersecting manifold, BLTSA first identifies the tip and branching cells in the trajectory based on cells' local Euclidean neighborhoods. Local coordinates within the tangent spaces are then determined by each cell's local neighborhood after clustering all the cells to different branches iteratively. The global coordinates for all the single cells are finally obtained by aligning the local coordinates based on the tangent spaces. We evaluate the performance of BLTSA on four simulation datasets and five real datasets. The experimental results show that BLTSA has obvious advantages over other comparison methods. AVAILABILITY AND IMPLEMENTATION: R codes are available at https://github.com/LiminLi-xjtu/BLTSA. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

With the rapid growth and popularization of Internet of Things (IoT), more and more devices are deployed in homes, enterprises, cities, etc. The existed methods to classify types and relations of devices are usually two separate tasks. So, it is difficult to quickly provide attributes of devices in the smart network for operators at the same time. At this situation, the paper presents a framework JCIDR for Joint Classification of IoT Device and Relations In the Internet with Network Traffic. By fusing the numerical features and binary image features of traffic, the devices and relations of devices can be recognized simultaneously. The experiment is carried out in a real IoT environment and the accuracy of JCIDR is over 86% with about half time reduction. Therefore, JCIDR could provide operators with a fast, easy, low-cost network device monitoring method without professional equipment or protocols.

Confounding factors exist widely in various biological data owing to technical variations, population structures and experimental conditions. Such factors may mask the true signals and lead to spurious associations in the respective biological data, making it necessary to adjust confounding factors accordingly. However, existing confounder correction methods were mainly developed based on the original data or the pairwise Euclidean distance, either one of which is inadequate for analyzing different types of data, such as sequencing data. In this work, we proposed a method called Adjustment for Confounding factors using Principal Coordinate Analysis, or AC-PCoA, which reduces data dimension and extracts the information from different distance measures using principal coordinate analysis, and adjusts confounding factors across multiple datasets by minimizing the associations between lower-dimensional representations and confounding variables. Application of the proposed method was further extended to classification and prediction. We demonstrated the efficacy of AC-PCoA on three simulated datasets and five real datasets. Compared to the existing methods, AC-PCoA shows better results in visualization, statistical testing, clustering, and classification.

MOTIVATION: Single-cell RNA sequencing (scRNA-seq) technology has been widely applied to capture the heterogeneity of different cell types within complex tissues. An essential step in scRNA-seq data analysis is the annotation of cell types. Traditional cell-type annotation is mainly clustering the cells first, and then using the aggregated cluster-level expression profiles and the marker genes to label each cluster. Such methods are greatly dependent on the clustering results, which are insufficient for accurate annotation. RESULTS: In this article, we propose a semi-supervised learning method for cell-type annotation called CALLR. It combines unsupervised learning represented by the graph Laplacian matrix constructed from all the cells and supervised learning using sparse logistic regression. By alternately updating the cell clusters and annotation labels, high annotation accuracy can be achieved. The model is formulated as an optimization problem, and a computationally efficient algorithm is developed to solve it. Experiments on 10 real datasets show that CALLR outperforms the compared (semi-)supervised learning methods, and the popular clustering methods. AVAILABILITY AND IMPLEMENTATION: The implementation of CALLR is available at https://github.com/MathSZhang/CALLR. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Multiview clustering has attracted much attention in recent years. Several models and algorithms have been proposed for finding the clusters. However, these methods are developed either to find the consistent/common clusters across different views, or to identify the differential clusters among different views. In reality, both consistent and differential clusters may exist in multiview datasets. Thus, development of simultaneous clustering methods such that both the consistent and the differential clusters can be identified is of great importance. RESULTS: In this paper, we proposed one method for simultaneous clustering of multiview data based on manifold optimization. The binary optimization model for finding the clusters is relaxed to a real value optimization problem on the Stiefel manifold, which is solved by the line-search algorithm on manifold. We applied the proposed method to both simulation data and four real datasets from TCGA. Both studies show that when the underlying clusters are consistent, our method performs competitive to the state-of-the-art algorithms. When there are differential clusters, our method performs much better. In the real data study, we performed experiments on cancer stratification and differential cluster (module) identification across multiple cancer subtypes. For the patients of different subtypes, both consistent clusters and differential clusters are identified at the same time. The proposed method identifies more clusters that are enriched by gene ontology and KEGG pathways. The differential clusters could be used to explain the different mechanisms for the cancer development in the patients of different subtypes. AVAILABILITY AND IMPLEMENTATION: Codes can be downloaded from: http://homepage.fudan.edu.cn/sqzhang/files/2018/12/MVCMOcode.zip. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Network has been a general tool for studying the complex interactions between different genes, proteins, and other small molecules. Module as a fundamental property of many biological networks has been widely studied and many computational methods have been proposed to identify the modules in an individual network. However, in many cases, a single network is insufficient for module analysis due to the noise in the data or the tuning of parameters when building the biological network. The availability of a large amount of biological networks makes network integration study possible. By integrating such networks, more informative modules for some specific disease can be derived from the networks constructed from different tissues, and consistent factors for different diseases can be inferred. In this paper, we have developed an effective method for module identification from multiple networks under different conditions. The problem is formulated as an optimization model, which combines the module identification in each individual network and alignment of the modules from different networks together. An approximation algorithm based on eigenvector computation is proposed. Our method outperforms the existing methods, especially when the underlying modules in multiple networks are different in simulation studies. We also applied our method to two groups of gene coexpression networks for humans, which include one for three different cancers, and one for three tissues from the morbidly obese patients. We identified 13 modules with three complete subgraphs, and 11 modules with two complete subgraphs, respectively. The modules were validated through Gene Ontology enrichment and KEGG pathway enrichment analysis. We also showed that the main functions of most modules for the corresponding disease have been addressed by other researchers, which may provide the theoretical basis for further studying the modules experimentally.

MOTIVATION: Expression quantitative trait loci (eQTL) studies investigate how gene expression levels are affected by DNA variants. A major challenge in inferring eQTL is that a number of factors, such as unobserved covariates, experimental artifacts and unknown environmental perturbations, may confound the observed expression levels. This may both mask real associations and lead to spurious association findings. RESULTS: In this article, we introduce a LOw-Rank representation to account for confounding factors and make use of Sparse regression for eQTL mapping (LORS). We integrate the low-rank representation and sparse regression into a unified framework, in which single-nucleotide polymorphisms and gene probes can be jointly analyzed. Given the two model parameters, our formulation is a convex optimization problem. We have developed an efficient algorithm to solve this problem and its convergence is guaranteed. We demonstrate its ability to account for non-genetic effects using simulation, and then apply it to two independent real datasets. Our results indicate that LORS is an effective tool to account for non-genetic effects. First, our detected associations show higher consistency between studies than recently proposed methods. Second, we have identified some new hotspots that can not be identified without accounting for non-genetic effects. AVAILABILITY: The software is available at: http://bioinformatics.med.yale.edu/software.aspx. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

We consider the restoration of piecewise constant images where the number of the regions and their values are not fixed in advance, with a good difference of piecewise constant values between neighboring regions, from noisy data obtained at the output of a linear operator (e.g., a blurring kernel or a Radon transform). Thus we also address the generic problem of unsupervised segmentation in the context of linear inverse problems. The segmentation and the restoration tasks are solved jointly by minimizing an objective function (an energy) composed of a quadratic data-fidelity term and a nonsmooth nonconvex regularization term. The pertinence of such an energy is ensured by the analytical properties of its minimizers. However, its practical interest used to be limited by the difficulty of the computational stage which requires a nonsmooth nonconvex minimization. Indeed, the existing methods are unsatisfactory since they (implicitly or explicitly) involve a smooth approximation of the regularization term and often get stuck in shallow local minima. The goal of this paper is to design a method that efficiently handles the nonsmooth nonconvex minimization. More precisely, we propose a continuation method where one tracks the minimizers along a sequence of approximate nonsmooth energies $\{J_\eps\}$, the first of which being strictly convex and the last one the original energy to minimize. Knowing the importance of the nonsmoothness of the regularization term for the segmentation task, each $J_\eps$ is nonsmooth and is expressed as the sum of an $\ell_1$ regularization term and a smooth nonconvex function. Furthermore, the local minimization of each $J_{\eps}$ is reformulated as the minimization of a smooth function subject to a set of linear constraints. The latter problem is solved by the modified primal-dual interior point method, which guarantees the descent direction at each step. Experimental results are presented and show the effectiveness and the efficiency of the proposed method. Comparison with simulated annealing methods further shows the advantage of our method.

MOTIVATION: Probabilistic Boolean networks (PBNs) have been proposed to model genetic regulatory interactions. The steady-state probability distribution of a PBN gives important information about the captured genetic network. The computation of the steady-state probability distribution usually includes construction of the transition probability matrix and computation of the steady-state probability distribution. The size of the transition probability matrix is 2(n)-by-2(n) where n is the number of genes in the genetic network. Therefore, the computational costs of these two steps are very expensive and it is essential to develop a fast approximation method. RESULTS: In this article, we propose an approximation method for computing the steady-state probability distribution of a PBN based on neglecting some Boolean networks (BNs) with very small probabilities during the construction of the transition probability matrix. An error analysis of this approximation method is given and theoretical result on the distribution of BNs in a PBN with at most two Boolean functions for one gene is also presented. These give a foundation and support for the approximation method. Numerical experiments based on a genetic network are given to demonstrate the efficiency of the proposed method.