MOTIVATION: Forecasting the synergistic effects of drug combinations facilitates drug discovery and development, especially regarding cancer therapeutics. While numerous computational methods have emerged, most of them fall short in fully modeling the relationships among clinical entities including drugs, cell lines, and diseases, which hampers their ability to generalize to drug combinations involving unseen drugs. These relationships are complex and multidimensional, requiring sophisticated modeling to capture nuanced interplay that can significantly influence therapeutic efficacy. RESULTS: We present a novel deep hypergraph learning method named Heterogeneous Entity Representation for MEdicinal Synergy (HERMES) prediction to predict the synergistic effects of anti-cancer drugs. Heterogeneous data sources, including drug chemical structures, gene expression profiles, and disease clinical semantics, are integrated into hypergraph neural networks equipped with a gated residual mechanism to enhance high-order relationship modeling. HERMES demonstrates state-of-the-art performance on two benchmark datasets, significantly outperforming existing methods in predicting the synergistic effects of drug combinations, particularly in cases involving unseen drugs. AVAILABILITY AND IMPLEMENTATION: The source code is available at https://github.com/Christina327/HERMES.

Transitional Region Phenomenon leads to the existence of lossy links in wireless networks, which results in a transmission between two users who are theoretically connected under the Deterministic Network Model cannot be guaranteed. Therefore, we focus on a more practical network model - Probabilistic Network Model (PNM) which can better characterize the lossy links in wireless networks. To be specific, we focus on the investigation of accelerating data aggregation process in probabilistic wireless networks with the cognitive radio technology. By involving cognitive radio technology, users in the wireless networks can seek extra transmission opportunity if other spectrum resource is available. Otherwise, the data aggregation process still can be done on the default working spectrum. Particularly, we are interested in the time efficient data aggregation scheduling problem. In this work, a two phase scheduling algorithm is proposed. The first phase is finding an efficient routing structure considering the speciality of the network model under investigation. In the second phase, a dynamic scheduling algorithm is introduced. Theoretical analysis is provided to estimate the lower latency bound for the scheduling algorithm, followed by the experimental simulation verification.

Online social networks have gained significant popularity recently. The problem of influence maximization in online social networks has been extensively studied. However, in prior works, influence propagation in the physical world, which is also an indispensable factor, is not considered. The Location-Based Social Networks (LBSNs) are a special kind of online social networks in which people can share location-embedded information. In this paper, we make use of mobile crowdsourced data obtained from location-based social network services to study influence maximization in LBSNs. A novel network model and an influence propagation model taking influence propagation in both online social networks and the physical world into consideration are proposed. An event activation position selection problem is formalized and a corresponding solution is provided. The experimental results indicate that the proposed influence propagation model is meaningful and the activation position selection algorithm has high performance.

Routing is one of the most important and fundamental issues in cognitive radio networks (CRNs). However, most of the existing routing algorithms for CRNs either cannot fully take account of the spectrum dynamics or are resource aided which might introduce too much cost. Therefore, in this paper, we study to design an effective routing scheme with respect to induced latency and energy consumption for CRNs. Our main contributions are threefold. First, we propose a spectrum-aware semi-structure routing (SSR) framework which also incorporates power control for CRNs. By employing forwarding zones and routing zones, SSR can utilize the local real-time spectrum dynamics effectively and meanwhile guarantee the global routing performance. In addition, without sacrificing spectrum opportunities, SSR achieves energy efficiency by completing each data transmission with the lowest allowed working power. Second, aiming at closing the gap of lacking of analytical models for routing protocol performance [4] in CRNs, we propose a mathematical framework for SSR which includes a latency analytical model and an energy consumption analytical model. Under the dense scaling network distribution model, we demonstrate (i) the upper bound of the induced latency and scalability of SSR; and (ii) the optimality of SSR with respect to energy consumption, which is approximately optimal. Finally, extensive simulations are conducted to validate the performance of SSR. Simulation results indicate that SSR can utilize spectrum dynamics effectively and has better performance than state-of-the-art methods.

Complicated collisions and spectrum uncertainty constrain the usage of Cognitive Radio Networks (CRNs) on heavy transmission and time sensitive applications. On the other hand, data aggregation has been considered as an essential operation in wireless networks. A large amount of effort has been dedicated to the investigation of CRNs and data aggregation in wireless networks. However, the existing literatures rarely concentrate on how to use cognitive radio technique to promote the performance of data aggregation in conventional wireless networks. In this paper, we investigate the Minimum Latency Data Aggregation Scheduling in wireless networks with Cognitive Radio capability (MLDAS-CR) problem. As the first try, an approximation scheduling algorithm based on Integer Linear Programming (ILP) and Linear Programming (LP) is proposed. According to the simulation results, this method performances great, however, it is difficult to theoretically evaluate the solution. Therefore, a heuristic scheduling algorithm with guaranteed latency bound is presented in our further investigation. The performance of the proposed solutions are evaluated through extensive simulations.

ABSTRACT Query scheduling as one of the most important technologies used in query processing has been widely studied recently. In this paper, we investigate the Minimum Latency Multi‐Regional Query Scheduling (ML‐MRQS) problem in wireless Sensor Networks (WSNs), which aims to generate a scheduling plan with minimum latency under a more practical query model called Multi‐Regional Query (MRQ). An MRQ targets at interested data from multiple regions of a WSN, where each region is a subarea. Because the ML‐MRQS problem is NP‐hard, we propose a heuristic scheduling algorithm Multi‐Regional Query Scheduling Algorithm (MRQSA) to solve this problem. Theoretical analysis shows that the latency of MRQSA is upper bounded by 23A + B + Cfor an MRQ withmquery regions , where is the maximum latency for non‐overlapped regions, is the maximum latency for overlapped regions, and is the accumulated latency for data transmission from the accessing nodes to the sink. Simulation results show that MRQSA reduces latency by 42.7%to 51.63%with respect to different number of query regions, network density, region size, and interference/transmission range compared with C‐DCQS, while guaranteeing energy efficiency. Copyright © 2012 John Wiley & Sons, Ltd.

Cognitive Radio Networks (CRNs) have been proposed as a promising technology to alleviate the spectrum shortage and under-utilization problem. A large amount of research effort has been put on CRNs. However, little attention has been paid to data aggregation problem, one of the most important communication protocols in wireless networks due to its efficiency in both energy conservation and latency reduction. In this paper, we investigate the minimum latency data aggregation scheduling problem in CRNs. Considering the difficulty of this problem, two practical distributed algorithms under the Unit Disk Graph interference model and the Physical Interference Model are proposed. Extensive simulation results indicate that the proposed algorithms have good latency performance in various network scenarios.

Routing is one of the most important and fundamental issues in Cognitive Radio Networks (CRNs). In this paper, we propose an effective routing scheme. Our main contributions are threefold. First, we propose a spectrum-aware Semi-Structure Routing (SSR) framework which incorporates power control. By employing forwarding zones and routing zones, SSR can effectively utilize the local real-time spectrum dynamics and meanwhile guarantee the global routing performance. Second, considering the lack of analytical models for routing protocol performance [1] in CRNs, we analyze the upper bound of the induced latency and scalability of SSR. Finally, extensive simulation results are presented to validate the performance of SSR.

Query scheduling as one of the most important technologies used in query processing has been widely studied recently. Unfortunately, to the best of our knowledge, no previous work focuses on the Minimum Latency Multi-Regional Query Scheduling (ML-MRQS) problem. In this paper, we investigate the ML-MRQS problem in Wireless Sensor Networks (WSNs), which aims to generate a scheduling plan with minimum latency for a more practical query model called Multi-Regional Query (MRQ). A MRQ targets at user interested data from multiple region-sofa WSN, where each region is a subarea of the WSN. We claim that the ML-MRQS problem is NP-hard. Therefore, we propose a heuristic scheduling algorithm Multi-Regional Query Scheduling Algorithm (MRQSA) to solve this problem. Theoretical analysis shows that the latency of MRQSA is upper bounded by 23A + B + C for a MRQ with m query regions R1, R2…, Rm, where A = maxi=1mDileft, B = maxi=1m{(23Di+5Δ+21)ki}, C = Σi=1mHi+5Δ−m+17, m is the number of regions, Δ is the maximum node degree in the WSN, A is the diameter of Ri, kiis the maximum overlapped degree of sensor nodes in TU, Hi represents the distance of Riwith respect to the sink, and Dileftis the diameter of the non-overlapped part of Ri. Extensive simulations are conducted to verify the performance of our algorithm, which show that MRQSA significantly reduces the query latency when compared with the most recently published multi-query scheduling algorithm.