作者:
Ye, Shengwei;Zhao, Weizhong;Shen, Xianjun;Jiang, Xingpeng;He, Tingting
期刊:
Methods,2023年218:48-56 ISSN:1046-2023
通讯作者:
Zhao, WZ
作者机构:
[Shen, Xianjun; Zhao, Weizhong; Zhao, WZ; He, Tingting; Jiang, Xingpeng; Ye, Shengwei] Cent China Normal Univ, Hubei Prov Key Lab Artificial Intelligence & Smart, Wuhan 430079, Hubei, Peoples R China.;[Shen, Xianjun; Zhao, Weizhong; He, Tingting; Jiang, Xingpeng; Ye, Shengwei] Cent China Normal Univ, Sch Comp, Wuhan 430079, Hubei, Peoples R China.;[Shen, Xianjun; Zhao, Weizhong; He, Tingting; Jiang, Xingpeng; Ye, Shengwei] Cent China Normal Univ, Natl Language Resources Monitoring & Res Ctr Netwo, Wuhan 430079, Hubei, Peoples R China.
通讯机构:
[Zhao, WZ ] C;Cent China Normal Univ, Hubei Prov Key Lab Artificial Intelligence & Smart, Wuhan 430079, Hubei, Peoples R China.
关键词:
Drug repurposing;Drug-disease associations prediction;Graph convolutional network;Heterogeneous information network;Multi-task learning
摘要:
Drug repurposing, which typically applies the procedure of drug-disease associations (DDAs) prediction, is a feasible solution to drug discovery. Compared with traditional methods, drug repurposing can reduce the cost and time for drug development and advance the success rate of drug discovery. Although many methods for drug repurposing have been proposed and the obtained results are relatively acceptable, there is still some room for improving the predictive performance, since those methods fail to consider fully the issue of sparseness in known drug-disease associations. In this paper, we propose a novel multi-task learning framework based on graph representation learning to identify DDAs for drug repurposing. In our proposed framework, a heterogeneous information network is first constructed by combining multiple biological datasets. Then, a module consisting of multiple layers of graph convolutional networks is utilized to learn low-dimensional representations of nodes in the constructed heterogeneous information network. Finally, two types of auxiliary tasks are designed to help to train the target task of DDAs prediction in the multi-task learning framework. Comprehensive experiments are conducted on real data and the results demonstrate the effectiveness of the proposed method for drug repurposing.
期刊:
IEEE/ACM Transactions on Computational Biology and Bioinformatics,2023年20(6):3635–3647 ISSN:1545-5963
作者机构:
[Xiaohua Hu] College of Computing & Informatics, Drexel University, Philadelphia, PA, USA;[Chuan Shi] School of Computer Science, Beijing University of Posts and Telecommunications, Beijing, China;[Wenjie Yao; Xingpeng Jiang; Tingting He] School of Computer, Central China Normal University, Wuhan, Hubei, China;[Weizhong Zhao] Hubei Provincial Key Laboratory of Artificial Intelligence and Smart Learning, School of Computer, and National Language Resources Monitoring and Research Center for Network Media, Central China Normal University, Wuhan, Hubei, China
摘要:
Side effects of drugs have gained increasing attention in the biomedical field, and accurate identification of drug side effects is essential for drug development and drug safety surveillance. Although the traditional pharmacological experiments can accurately detect the side effects of drugs, the identifying process is time-consuming, costly, and may lead to incomplete identification of side effects. With the expanding of various biomedical databases, many computational methods have been developed for the task of drug-side effect associations (DSAs) prediction. However, existing methods have the following three drawbacks: 1). multiple drug-related databases are not fully used; 2). the complex semantics among drugs and side effects are not effectively captured; 3). the explainability of the predicted DSAs is missed for most existing methods. Therefore, there is an urgent need to find a more effective method for predicting DSAs. To address these issues, we propose a novel meta-path-based graph neural network model for drug-side effect associations prediction (MPGNN-DSA). In MPGNN-DSA, a heterogeneous information network is first constructed by combining multiple biological datasets. Then, a meta-path-based feature learning module is utilized for learning high-quality representations of drugs and side effects by capturing the semantics contained in meta-paths of the constructed HIN. With the learned features, the prediction module is conducted to derive the predicted side effects for drugs. In addition, the explainability of the predicted DSAs can be provided as well with the semantics contained in meta-paths. We conduct comprehensive experiments, and the results demonstrate the effectiveness of MPGNN-DSA, suggesting that the proposed method will be a feasible solution to the task of DSAs prediction.
摘要:
由于容迟网络的间歇性连接等特点,以及节点自身缓存、能量等资源受限的原因,DTN中的节点往往会表现出一定的自私性。自私节点的存在可能会提高网络的开销,降低消息的成功投递率。为了促进自私节点参与合作,提出了一种基于虚拟货币交易的高效率路由算法PVCT(Efficient Routing Protocol Based on Virtual Currency Transaction in DTN),并结合容迟网络的小世界特性,以提高路由算法的效率。该算法利用虚拟货币交易的方式,并根据节点的基本属性、位置属性、社会属性等进行定价,节点根据设计的价格函数给出对应的报价,并利用价格函数合理地分配消息副本数。在PVCT策略中,节点根据判断情况分为正常节点和自私节点,当消息的跳数小于等于两跳时,按照概率路由的策略进行转发;反之,当消息的跳数大于两跳时,若遇到的为自私节点,则执行虚拟货币交易的路由算法。携带消息节点的出价若高于转发节点的价格,则进行交易,更新各自的收益状态;否则,进入二次价格调整阶段来协调节点双方之前的虚拟报价。仿真实验表明,PVCT路由算法在DTN中能更好地促进消息的转发,从而提高网络的整体性能。
作者机构:
[Wan, Cuihong; Peng, Zhao] Cent China Normal Univ, Sch Life Sci, Wuhan 430079, Hubei, Peoples R China.;[Wan, Cuihong; Peng, Zhao] Cent China Normal Univ, Hubei Key Lab Genet Regulat & Integrat Biol, Wuhan 430079, Hubei, Peoples R China.;[Li, Jiaqiang; Jiang, Xingpeng] Cent China Normal Univ, Sch Comp, Wuhan 430079, Hubei, Peoples R China.;[Li, Jiaqiang; Jiang, Xingpeng] Cent China Normal Univ, Hubei Prov Key Lab Artificial Intelligence & Smart, Wuhan 430079, Hubei, Peoples R China.
通讯机构:
[Xingpeng Jiang; Cuihong Wan] S;School of Computer, and Hubei Provincial Key Laboratory of Artificial Intelligence and Smart Learning, Central China Normal University , Wuhan 430079, Hubei , People's Republic of China<&wdkj&>School of Life Sciences, and Hubei Key Laboratory of Genetic Regulation and Integrative Biology, Central China Normal University , Wuhan 430079, Hubei , People's Republic of China
摘要:
As one of the essential life forms in the biosphere, research on cyanobacteria has been growing remarkably for decades. Biological functions in organisms are often accomplished through protein-protein interactions (PPIs), which help to regulate interacting proteins or organize them into an integral machine. However, the study of PPIs in cyanobacteria falls far behind that in mammals and has not been integrated for ease of use. Thus, we built CyanoMapDB (http://www.cyanomapdb.msbio.pro/), a database providing cyanobacterial PPIs with experimental evidence, consisting of 52,304 PPIs among 6,789 proteins from 23 cyanobacterial species. We collected available data in UniProt, STRING, and IntAct, and mined numerous PPIs from co-fractionation MS data in cyanobacteria. The integrated data are accessible in CyanoMapDB (http://www.cyanomapdb.msbio.pro/), enabling users to easily query proteins of interest, investigate interacting proteins with evidence from different sources, and acquire a visual network of the target protein. We believe that CyanoMapDB will promote research involved with cyanobacteria and plants.
期刊:
IEEE Transactions on Cognitive and Developmental Systems,2023年15(3):1183-1195 ISSN:2379-8920
通讯作者:
Liu, J.;Zhou, G.
作者机构:
[Liu, Jin; Xie, Zhiwen; Zhang, Geng] Wuhan University, School of Computer Science, Wuhan, 430072, China;[Zhou, Guangyou] Central China Normal University, School of Computer Science, Wuhan, 430079, China;[Yu, Xiao] Wuhan University of Technology, School of Computer Science and Technology, Wuhan, 430070, China;[Cui, Xiaohui] Wuhan University, School of Cyber Science and Engineering, Wuhan, 430072, China
通讯机构:
[Liu, J.] W;[Zhou, G.] C;Central China Normal University, China;Wuhan University, China
摘要:
Distributed optimization is a powerful paradigm to solve various problems in machine learning over networked systems. Existing first-order optimization methods perform cheap gradient descent by exchanging information per iteration only with single-hop neighbours in a network. However, in many agent networks such as sensor and robotic networks, it is prevalent that each agent can interact with other agents over multi-hop communication. Therefore, distributed optimization method over multi-hop networks is an important but overlooked topic that clearly needs to be developed. Motivated by this observation, in this paper, we apply multi-hop transmission to the outstanding distributed gradient descent (DGD) method and propose two typical versions (i.e., consensus and diffusion) of multi-hop DGD method, which we call CM-DGD and DM-DGD, respectively. Theoretically, we present the convergence guarantee of the proposed methods under mild assumptions. Moreover, we confirm that multi-hop strategy results in higher probability to improve the spectral gap of the underlying network, which has been shown to be a critical factor improving performance of distributed optimizations, thus achieves better convergence metrics. Experimentally, two distributed machine learning problems are picked to verify the theoretical analysis and show the effectiveness of CM-DGD and DM-DGD by using synthesized and real data sets.
作者机构:
[Xia, Zhe] Department of Computer Science , Wuhan University of Technology , 122 Luoshi Road, Wuhan 430071, China;[Chen, Jingxue] Guangxi Key Laboratory of Trusted Software , Guilin University of Electronic Technology , 1 Jinji Road, Guilin 541004, China;[Hsu, Chingfang; Cui, Jianqun] Computer School , Central China Normal University , 152 Luoyu Road, Wuhan 430079, China;[Harn, Lein] Department of Computer Science Electrical Engineering , University of Missouri-Kansas City , 5100 Rockhill Road, Kansas City, MO 64110, USA
通讯机构:
[Chingfang Hsu] C;Computer School , Central China Normal University , 152 Luoyu Road, Wuhan 430079, China
摘要:
The next generation of Internet of Things (IoT) networks and mobile communications (5G IoT networks) has the particularity of being heterogeneous, therefore, it has very strong ability to compute, store, etc. Group-oriented applications demonstrate its potential ability in 5G IoT networks. One of the main challenges for secure group-oriented applications (SGA) in 5G IoT networks is how to secure communication and computation among these heterogeneous devices. Conventional protocols are not suitable for SGA in 5G IoT networks since multiparty joint computation in this environment requires lightweight communication and computation overhead. Furthermore, the primary task of SGA is to securely transmit various types of jointly computing data. Hence, membership authentication and secure multiparty joint arithmetic computation become two fundamental security services in SGA for 5G IoT networks. The membership authentication allows communication entities to authenticate their communication partners and the multiparty joint computations allow a secret output to be shared among all communication entities. The multiparty joint computation result can be used to protect exchange information in the communication or be used as a result that all users jointly compute by using their secret inputs. A novel construction of computation/communications-efficient membership authenticated joint arithmetic computation is proposed in this paper for 5G IoT networks, which not only integrates the function of membership authentication and joint arithmetic computation but also realizes both computation and communication efficiency on each group member side. Our protocol is secure against inside attackers and outside attackers, and also meets all the described security goals. Meanwhile, in this construction the privacy of tokens can be well protected so tokens can be reused multiple times. This proposal is noninteractive and can be easily extended to joint arithmetic computation with any number of inputs. Hence, our design has more attraction for lightweight membership authenticated joint arithmetic computation in 5G IoT networks.
期刊:
Information Processing & Management,2023年60(2):103207 ISSN:0306-4573
通讯作者:
Chen Qiu
作者机构:
[Gu, Jinguang; Qiu, Chen; Xu, Zhaoyang; Liu, Maofu; Fu, Haidong] Wuhan Univ Sci & Technol, Sch Comp Sci & Technol, Wuhan 430081, Peoples R China.;[Gu, Jinguang; Qiu, Chen; Xu, Zhaoyang; Liu, Maofu; Fu, Haidong] Wuhan Univ Sci & Technol, Inst Big Data Sci & Engn, Wuhan 430081, Peoples R China.;[Zhou, Guangyou] Cent China Normal Univ, Sch Comp Sci, Wuhan 430079, Peoples R China.
通讯机构:
[Chen Qiu] S;School of Computer Science and Technology, Wuhan University of Science and Technology, Wuhan, 430081, China<&wdkj&>Institute of Big Data Science and Engineering, Wuhan University of Science and Technology, Wuhan, 430081, China
期刊:
Journal of Computing in Higher Education,2023年:1-24 ISSN:1042-1726
通讯作者:
Yu, S;Wang, JH
作者机构:
[Yu, Shuang; Liu, Qingtang; Yu, S; Zheng, Xinxin; Wu, Linjing] Cent China Normal Univ, Fac Artificial Intelligence Educ, Wuhan, Peoples R China.;[Ye, Junmin] Cent China Normal Univ, Sch Comp, Wuhan, Peoples R China.;[Wang, Jianhu] Xinjiang Normal Univ, Coll Educ Sci, Urumqi, Peoples R China.
通讯机构:
[Yu, S ] C;[Wang, JH ] X;Cent China Normal Univ, Fac Artificial Intelligence Educ, Wuhan, Peoples R China.;Xinjiang Normal Univ, Coll Educ Sci, Urumqi, Peoples R China.
摘要:
Interdisciplinary collaboration is widely used in research, industry, and education. Understanding the differences in cognitive processes between cross-discipline and same-discipline groups can improve instruction in collaborative learning. In this study, students volunteered to participate in cross-discipline or same-discipline collaborative learning groups to collaboratively complete three assignments. Epistemic network analysis was employed to identify the differences in cognitive engagement, the roles of group leaders, and the trajectory differences between these two kinds of groups. The results showed that compared to same-discipline groups, cross-discipline groups have lower-order cognitive engagement. Group leaders in cross-discipline groups invested most of their energy into inquiring or starting the discussion. In addition, cognitive engagement of cross-discipline groups dropped sharply over time in collaborative learning. These differences imply that to achieve better collaboration in cross-discipline groups, teachers should provide more interventions, such as evaluation and analytical support, to help students reach high-level cognitive engagement.
期刊:
IEEE Transactions on Image Processing,2022年31:4251-4265 ISSN:1057-7149
通讯作者:
Lu, X.
作者机构:
[Lu, Xiaoqiang; Zheng, Xiangtao] Xi'An Institute of Optics and Precision Mechanics, Chinese Academy of Sciences, Key Laboratory of Spectral Imaging Technology CAS, Xi'an, 710119, China;University of Chinese Academy of Sciences, Beijing, 100049, China;[Xie, Wei] Central China Normal University, Hubei Provincial Key Laboratory of Artificial Intelligence and Smart Learning, National Language Resources Monitoring and Research Center for Network Media, School of Computer, Wuhan, 430079, China;[Sun, Hao] Xi'An Institute of Optics and Precision Mechanics, Chinese Academy of Sciences, Key Laboratory of Spectral Imaging Technology CAS, Xi'an, 710119, China, University of Chinese Academy of Sciences, Beijing, 100049, China
通讯机构:
[Lu, X.] X;Xi'An Institute of Optics and Precision Mechanics, China
摘要:
Hyperspectral image (HSI) classification refers to identifying land-cover categories of pixels based on spectral signatures and spatial information of HSIs. In recent deep learning-based methods, to explore the spatial information of HSIs, the HSI patch is usually cropped from original HSI as the input. And $3 \times 3$ convolution is utilized as a key component to capture spatial features for HSI classification. However, the $3 \times 3$ convolution is sensitive to the spatial rotation of inputs, which results in that recent methods perform worse in rotated HSIs. To alleviate this problem, a rotation-invariant attention network (RIAN) is proposed for HSI classification. First, a center spectral attention (CSpeA) module is designed to avoid the influence of other categories of pixels to suppress redundant spectral bands. Then, a rectified spatial attention (RSpaA) module is proposed to replace $3 \times 3$ convolution for extracting rotation-invariant spectral-spatial features from HSI patches. The CSpeA module, the $1 \times 1$ convolution and the RSpaA module are utilized to build the proposed RIAN for HSI classification. Experimental results demonstrate that RIAN is invariant to the spatial rotation of HSIs and has superior performance, e.g., achieving an overall accuracy of 86.53% (1.04% improvement) on the Houston database. The codes of this work are available at https://github.com/spectralpublic/RIAN .
期刊:
INTERNET AND HIGHER EDUCATION,2022年55:100875 ISSN:1096-7516
通讯作者:
Jin Zhou
作者机构:
[Ye, Jun -min] Cent China Normal Univ, Sch Comp, Wuhan, Peoples R China.;[Zhou, Jin] Cent China Normal Univ, Fac Artificial Intelligence Educ, Wuhan, Peoples R China.
通讯机构:
[Jin Zhou] F;Faculty of Artificial Intelligence in Education, Central China Normal University, Wuhan, China
摘要:
Evidence suggests that learning sentiments are inextricably related to cognitive processing, and the exploration of the relationship remains to be an important research topic. This study collected discourse data from 40 college students in online collaborative learning activities. Epistemic network analysis (ENA) was employed to explore the connection between learning sentiments and cognitive processing and compare the ENA network characteristics of the higher- and lower-engagement groups. The results indicated that there was a joint connection between understand-analyze-neutral, and insightful sentiments had more association with neutral sentiments and understanding. Besides, distinctions existed between higher- and lower-engagement groups with respect to the association between learning sentiments and cognitive processing. The higher-engagement group had stronger associations around positive and confused sentiments, while the lower-engagement group had stronger associations around off-topic discussion. The findings of this research may serve as a reference for designing and implementing collaborative learning activities to increase cognitive levels.
期刊:
Information and Software Technology,2022年150:106987 ISSN:0950-5849
通讯作者:
Po Hu<&wdkj&>Ran Mo
作者机构:
[Hu, Po; Wei, Shaozhi; Cheng, Wuyan; Mo, Ran] Cent China Normal Univ, Sch Comp, Wuhan, Hubei, Peoples R China.;[Hu, Po; Mo, Ran] Cent China Normal Univ, Hubei Prov Key Lab Artificial Intelligence & Smart, Wuhan, Hubei, Peoples R China.;[Hu, Po] Cent China Normal Univ, Natl Language Resources Monitoring & Res Ctr Netwo, Wuhan, Hubei, Peoples R China.
通讯机构:
[Po Hu; Ran Mo] H;Hubei Provincial Key Laboratory of Artificial Intelligence and Smart Learning, Central China Normal University, Wuhan, Hubei, China<&wdkj&>School of Computer, Central China Normal University, Wuhan, Hubei, China<&wdkj&>National Language Resources Monitoring & Research Center for Network Media, Central China Normal University, Wuhan, Hubei, China<&wdkj&>Hubei Provincial Key Laboratory of Artificial Intelligence and Smart Learning, Central China Normal University, Wuhan, Hubei, China<&wdkj&>School of Computer, Central China Normal University, Wuhan, Hubei, China