MOTIVATION: Spatial transcriptomics techniques capture gene expression data and spatial coordinates, while simultaneously correlating them with tissue section images. This advantage makes Spatial transcriptomics data highly valuable for research, such as investigating disease mechanisms and cancer prognosis. However, the extended time and high cost of spatial transcriptomic sequencing currently limit further advancements in this field. The development of numerous deep learning methods aimed at predicting spatial transcriptomics from histology images has advanced significantly. However, these approaches often lack the ability to effectively integrate histology images with spatial transcriptomic data. Here, we propose GR2ST, a deep learning model that learns the underlying connections between image features and gene expression to predict spatial transcriptomics. RESULTS: GR2ST leverages a large pre-trained pathology model to extract high-level histological features. We designed a dual-branch graph architecture, consisting of a dynamic threshold-based functional graph and a radius-constrained spatial graph, to capture complex spot interactions within heterogeneous tissues. The model aligns histology images with gene expression representations through a multimodal contrastive learning framework. It achieves adaptive gene expression generation via a Cell-Type Guided Multi-Branch Regression Head supervised by a context-aware weighting network, which is further integrated with cross-sample retrieval to construct an ensemble prediction. The performance of the model is evaluated on three cancer-related spatial transcriptomics datasets, including cutaneous squamous cell carcinoma and two human breast cancer cohorts, to demonstrate its effectiveness and robustness. AVAILABILITY: https://github.com/zjl1109294570/GR2ST.

The rapid proliferation of end devices and their hosted applications has significantly increased the demand for data processing. However, lightweight edge endpoints often suffer from limited computational capabilities due to power and battery constraints. Consequently, computation-intensive tasks are typically offloaded to cloud servers located in data centers for processing. While existing studies often abstract the edge–cloud connection as a direct link, the actual backbone network features complex topologies and constrained bandwidth, which intensify as workload scales up. To address this challenge, this paper investigates routing optimization within the backbone network under task offloading scenarios, and proposes a workload-aware deep reinforcement learning (DRL)-based routing algorithm for joint minimization of transmission and processing delays. Specifically, we first develop a detailed system model using discrete event simulation. Then, we design an integrated DRL-based decision-making scheme that simultaneously determines optimal routing paths and target data centers. Extensive experiments on diverse real-world network topologies and heterogeneous task workloads demonstrate that the proposed algorithm significantly outperforms conventional baselines in reducing both transmission and processing delays.

The Internet today hosts a multitude of communication sessions from diverse vertical industries, each with distinct and increasingly stringent quality-of-service (QoS) requirements across multiple performance metrics. However, QoS-aware routing remains a significant challenge in traffic engineering, as existing solutions struggle to adapt to dynamic network conditions and meet these rigorous QoS demands. To address this issue, this paper proposes a multi-agent graph reinforcement learning-based routing algorithm that provides differentiated treatment for multiple services. First, we explore both nodebased and link-based graph reinforcement learning paradigms for performance comparison. Second, two key mechanisms, i.e., a packet sacrifice mechanism and a Tchebycheff-based reward function, are designed to realize adaptive sacrifice behavior patterns, aiming to optimize the lower bound of service satisfaction rates and enhance fairness across services. Furthermore, to ensure practical applicability, we devise a distributed computing architecture featuring neighborhood-restricted data acquisition and asynchronous historical information retrieval. Extensive simulation results demonstrate that our proposed algorithms significantly outperform benchmark methods regarding the minimum service satisfaction rate, even under unseen networks. Besides, the distributed computing architecture is proven to incur no performance penalty, which can be generalized to other resource-constrained applications.

As network services become more complex, efficient routing has become crucial for ensuring end-user satisfaction. To address this challenge, researchers are increasingly turning to routing algorithms that integrate Graph Neural Networks (GNNs) with Deep Reinforcement Learning (DRL), leveraging the natural graph structure of network topologies. However, a significant challenge with existing algorithms is their inability to generalize across different topologies without requiring retraining, a constraint that is impractical in real-world applications. To overcome this limitation, we propose a novel GNN-DRL-based routing algorithm, Link2Link, designed to decouple DRL-learned knowledge from specific network topologies by focusing on link-level features. Extensive experiments demonstrate that Link2Link achieves robust performance across diverse topologies, consistently outperforming OSPF without requiring retraining, making it a scalable and adaptable solution for modern network routing challenges.

MOTIVATION: Accurately predicting the driver genes of cancer is of great significance for carcinogenesis progress research and cancer treatment. In recent years, more and more deep-learning-based methods have been used for predicting cancer driver genes. However, deep-learning algorithms often have black box properties and cannot interpret the output results. Here, we propose a novel cancer driver gene mining method based on heterogeneous network meta-paths (MCDHGN), which uses meta-path aggregation to enhance the interpretability of predictions. RESULTS: MCDHGN constructs a heterogeneous network by using several types of multi-omics data that are biologically linked to genes. And the differential probabilities of SNV, DNA methylation, and gene expression data between cancerous tissues and normal tissues are extracted as initial features of genes. Nine meta-paths are manually selected, and the representation vectors obtained by aggregating information within and across meta-path nodes are used as new features for subsequent classification and prediction tasks. By comparing with eight homogeneous and heterogeneous network models on two pan-cancer datasets, MCDHGN has better performance on AUC and AUPR values. Additionally, MCDHGN provides interpretability of predicted cancer driver genes through the varying weights of biologically meaningful meta-paths. AVAILABILITY AND IMPLEMENTATION: https://github.com/1160300611/MCDHGN.

This paper presents an empirical study on deep reinforcement learning (DRL) based probabilistic cognitive routing using the OMNeT++ framework and programming protocol-independent packet processors (P4). The proposed algorithm combines the power of DRL and cognitive routing to achieve efficient and adaptive probabilistic routing in software-defined networking (SDN) environments. To facilitate the research, we develop a dedicated network simulation environment using the OMNeT++ framework and a self-developed SDN platform based on P4. The empirical study highlights the importance of a comprehensive training and validation process in both simulation and real-world SDN environments. Through closed-loop training, the cognitive routing framework provides real-time feedback from the actual network environment to the simulation environment, allowing the agent to excel in real-world network environments. Meanwhile, the results demonstrate that solely testing the algorithm in either environment is inadequate for evaluating its performance accurately.

Current peer-to-peer (P2P) swarming systems have been immensely successful for large scale media content distribution with fewer server resources and lower protocol overhead. In order to improve media delivery quality and provide high service availability, network coding techniques have been proposed to help resource propagating through P2P network. Applying network coding over small time-window of video reduces the risks of uploading duplicate content and minimizes the variance in the performance of each node, thus, improving the overall efficiency of the system. However, by combining network coding in video delivery, the bitrates of media stream is usually nonscalable. Since the channel bandwidth between peers may fluctuate in a wide range in P2P swarming system, nonscalable network coding video stream cannot adapt P2P communication channel effectively. In this work, we propose a novel network coding scheme to address the issues. Considering that MPEG-4 video sequences can be presented by multiple layers of bitstreams, including baselayer and enhanced layer, network coding can be applied on base layer for availability, and enhanced layers can be truncated to adapt channel bandwidth. Compared with existing network coding approaches, our simulation experimental results clearly show that the proposed scheme brings higher efficiency and more flexibility to video streaming over P2P swarming system.

This paper presents a new scheme for robust video transmission over packet erasure wireless channels based on Wyner-Ziv coding of motion regions. The multipath fading and shading of the wireless channels usually lead to loss or erroneous video packets which on occasions result in some spontaneous drop in video quality. Existing approaches with forward error correction (FEC) and error concealment have not been able to provide the desired robustness in video transmission. We develop a new scheme with a motion-based Wyner-Ziv coding (MWZC) by leveraging distributed source coding (DSC) ideas for error robustness. This new scheme is based on the fact that motion regions of a given video frame are particularly important in both objective and perceptual video quality and hence should be given preferential Wyner-Ziv coding based embedded protection. To achieve high coding efficiency, we determine the underlining motion regions based on a rate-distortion model. Within the framework of H.264/AVC specification, motion region determination can be efficiently implemented using flexible macroblock ordering (FMO) and data partitioning (DP). The bit stream generated by the proposed scheme consists two parts: the systematic portion generated from conventional H.264/AVC bit stream and the supplementary bit stream for error robust video transmission generated by the Wyner-Ziv coding of motion regions. Experimental results demonstrate that the proposed scheme significantly outperforms both decoder-based error concealment (DBEC) and conventional FEC with DBEC approaches.

In this paper, we propose a new rate allocation algorithm for transform domain Wyner-Ziv video coding (WZVC) without feedback. In contrast to conventional video coding, Wyner-Ziv video coding aims to design simple intra-frame encoding and complex inter-frame decoding based on the Slepian-Wolf and Wyner-Ziv distributed source coding theorems. To allocate proper number of bits to each frame, most existing Wyner-Ziv video coding solutions need a feedback channel (FC) at the decoder. However, in many video coding applications, the FC is not allowed. Moreover, the FC will introduce latency and an increase of decoder complexity because several iterative decoding operations may be needed to decode the data to achieve target video quality. The proposed algorithm predicts the number of bits for each Wyner-Ziv frame at the encoder as a function of the coding mode and the quantization parameters. Such predictions will not significantly increase the complexity at the encoder. However, the prediction will be able to properly select the best mode and quantization parameter for encoding each Wyner-Ziv frame. Experimental results show that the proposed algorithms is able to achieve good encoder rate allocation while still maintains consistent coding efficiency. Comparing to the WZVC coder with FC, this new WZVC coder without FC induces only a small loss in Rate-Distortion performance.

The paper focuses on rate-control scheme on H.264 and proposes an improved scheme on the Basic-Unit (BU) layer, which consists of two steps. Firstly, the new scheme takes account of the relative Mean-Absolute-Different (MAD) complexity of BU and modifies the original scheme of average-allocating-bits in BUs. A factor ì , called relative MAD complexity, is used to refine the number of bits of the current BU calculated by means of average, which helps to logically and adaptively allocate bits for the BU by its complexity. Secondly, considering the scene-change, it modifies the linear prediction model of MAD. Another factor c , called MAD prediction accuracy, is used to refine the MAD predicted by linear model, which helps to eliminate the influencing of the scene change and fast motion and get more accurate prediction of MAD. The tests show that the improved scheme on Basic-Unit layer can predict MAD more accurately and get better subjective quality with PSNR slight raise by about 0.4db.

With the number of users wanting to share and access data across enterprise networks and the Internet is increasing dramatically, network administrators now find that their server and network backbones lack the capacity to handle the increased traffic. To achieve highly efficient connectivity between backbones and servers, and higher bandwidth of server network interface, we provide a method named as Ethernet links bundling technology (EIB). It is a high-speed networking solution that builds upon fast Ethernet technology to provide a dramatic increase in network performance. The implementation methods of the EIB technology are given and performance experiments are conducted. The results show that the network bandwidth can be scaled by the bundling of multiple Ethernet links and more reliable network connectivity can be guaranteed. And we also demonstrated that the EIB technology can be practically used in real applications such as FTP and SAMBA.

A new watermarking scheme for image authentication is introduced. The watermark is generated from the invariant feature of image and the mean quantization method is adopted in watermark embedding. The watermarking scheme has two good qualities: first, two watermarks based on invariant feature are used to provide very good classification of malicious and incidental tampering, second the received image authentication needs no information about the original image and watermark. The algorithm can be implemented simply and practically like a small, individual image processing software associated with all kinds of network software. Experimental results show that the new scheme is indeed effective and practical for image authentication on the Internet.