检索结果-内蒙古大学图书馆

Gene knockout inference with variational graph autoencoder learning single-cell gene regulatory networks

Nucleic acids research 2023年第13期51卷 6578-6592页

作者： Yongjian Yang Guanxun Li Yan Zhong Qian Xu Bo-Jia Chen Yu-Te Lin Robert S Chapkin James J Cai Department of Electrical and Computer Engineering Texas A&M University College Station TX 77843 USA. Department of Statistics Texas A&M University College Station TX 77843 USA. Key Laboratory of Advanced Theory and Application in Statistics and Data Science-MOE School of Statistics East China Normal University 3663 North Zhongshan Road Shanghai 200062 China. Department of Veterinary Integrative Biosciences Texas A&M University College Station TX 77843 USA. Graduate Institute of Microbiology and Public Health College of Veterinary Medicine National Chung Hsing University Taichung 402 Taiwan. Graduate Institute of Biomedical Electronics and Bioinformatics National Taiwan University Taipei Taiwan. Program in Integrative & Complex Diseases Department of Nutrition Texas A&M University College Station TX 77843 USA. Interdisciplinary Program of Genetics Texas A&M University College Station TX 77843 USA.

In this paper, we introduce Gene Knockout Inference (GenKI), a virtual knockout (KO) tool for gene function prediction using single-cell RNA sequencing (scRNA-seq) data in the absence of KO samples when only wild-type (WT) samples are available. Without using any information from real KO samples, GenKI is designed to capture shifting patterns in gene regulation caused by the KO perturbation in an unsupervised manner and provide a robust and scalable framework for gene function studies. To achieve this goal, GenKI adapts a variational graph autoencoder (VGAE) model to learn latent representations of genes and interactions between genes from the input WT scRNA-seq data and a derived single-cell gene regulatory network (scGRN). The virtual KO data is then generated by computationally removing all edges of the KO gene-the gene to be knocked out for functional study-from the scGRN. The differences between WT and virtual KO data are discerned by using their corresponding latent parameters derived from the trained VGAE model. Our simulations show that GenKI accurately approximates the perturbation profiles upon gene KO and outperforms the state-of-the-art under a series of evaluation conditions. Using publicly available scRNA-seq data sets, we demonstrate that GenKI recapitulates discoveries of real-animal KO experiments and accurately predicts cell type-specific functions of KO genes. Thus, GenKI provides an in-silico alternative to KO experiments that may partially replace the need for genetically modified animals or other genetically perturbed systems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multispectral Pan-sharpening via Dual-Channel Convolutional Network with Convolutional LSTM Based Hierarchical Spatial-Spectral Feature Fusion

arXiv

引用

arXiv 2020年

作者： Wang, Dong Bai, Yunpeng Li, Ying School of Computer Science National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Shaanxi Provincial Key Laboratory of Speech & Image Information Processing Northwestern Polytechnical University Xian China School of Computing and Information Systems University of Melbourne VIC3010 Australia

Multispectral pan-sharpening aims at producing a high resolution (HR) multispectral (MS) image in both spatial and spectral domains by fusing a panchromatic (PAN) image and a corresponding MS image. In this paper, we propose a novel dual-channel network (DCNet) framework for MS pan-sharpening. In our DCNet, the dual-channel backbone involves a spatial channel to capture spatial information with a 2D CNN, and a spectral channel to extract spectral information with a 3D CNN. This heterogeneous 2D/3D CNN architecture can minimize causing spectral information distortion, which typically happens in conventional 2D CNN models. In order to fully integrate the spatial and spectral features captured from different levels, we introduce a multi-level fusion strategy. Specifically, a spatial-spectral CLSTM (S2-CLSTM) module is proposed for fusing the hierarchical spatial and spectral features, which can effectively capture correlations among multi-level features. The S2-CLSTM module attaches two fusion ways: the intra-level fusion via bi-directional lateral connections and inter-level fusion via the cell state in the S2-CLSTM. Finally, the ideal HR-MS image is recovered by a reconstruction module. Extensive experiments have been conducted at both simulated lower scale and the original scale of real-world datasets. Compared with the state-of-the-art methods, the proposed DCNet achieves superior or competitive performance. Copyright © 2020, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Read/write Performance Optimization based on Ceph Heterogeneous Storage

Read/write Performance Optimization based on Ceph Heterogene...

引用

作者： Pengcheng Yao School of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing Engineering Research Center of Mobile Internet Data Application

The arrival of the era of big data has brought great challenges to the storage and management of massive data. Distributed storage is an extremely important solution to storage capacity pressure and cost in the era of big data. As an emerging open source distributed system, Ceph can provide three storage functions: object storage, block storage and file storage. The pseudo-random data mapping function CRUSH is used to complete the mapping of data to storage nodes, eliminating the traditional centralized metadata nodes, while system scalability has no theoretical upper limit. However, Ceph adopts a strong consistency strategy and only reads the primary node when reading objects, which results in low read-write efficiency. At the same time, Ceph does not perceive heterogeneous storage and does not make full use of SSD storage characteristics. Therefore, a combined storage strategy based on weak consistency model and multi-node read optimization is proposed to optimize Ceph storage. The system can effectively reduce the read-write delay of Ceph and improve its storage efficiency. Experiments show that compared with the original mechanism of Ceph, the proposed optimization mechanism can improve the writing efficiency by more than ten times and the reading efficiency by more than six times.

关键词： Ceph CRUSH Heterogeneous storage Weak consistency Multi-node read

来源：评论

学校读者我要写书评

暂无评论

Intrinsic mechanical behavior of MgAgSb thermoelectric material:An ab initio study

引用

Journal of Materiomics 2020年第1期6卷 24-32页

作者： Guodong Li Qi An Umut Aydemir Sergey I.Morozov Bo Duan Pengcheng Zhai Qingjie Zhang William A.Goddard Ⅲ Hubei Key Laboratory of Theory and Application of Advanced Materials Mechanics School of ScienceWuhan University of TechnologyWuhan430070China State Key Laboratory of Advanced Technology for Materials Synthesis and Processing Wuhan University of TechnologyWuhan430070China Department of Chemical and Materials Engineering University of Nevada RenoRenoNV89557USA Department of Chemistry Koc UniversitySariyerIstanbul34450Turkey Boron and Advanced Materials Research Center Koc UniversitySariyerIstanbul34450Turkey Department of Computer Simulation and Nanotechnology South Ural State UniversityChelyabinsk454080Russia Materials and Process Simulation Center California Institute of TechnologyPasadenaCA91125USA

α-MgAgSb based thermoelectric(TE)device attracts much attention for its commercial application because it shows an extremely high conversion efficiency of ~8.5% under a temperature difference of 225 ***,the mechanical behavior of α-MgAgSb is another serious consideration for its engineering ***,we apply density functional theory(DFT)simulations to examine the intrinsic mechanical properties of all three MgAgSb phases,including elastic properties,shear-stress-shear-strain relationships,deformation and failure mechanism under ideal shear and biaxial shear *** find that the ideal shear strength of α-MgAgSb is 3.25 GPa along the most plausible(100)<010>slip *** strength is higher than that of β-MgAgSb(0.80 GPa)and lower than that of γ-MgAgSb(3.43 GPa).The failure of α-MgAgSb arises from the stretching and breakage of MgeSb bond α-MgAgSb under pure shear load,while it arises from the softening of MgeAg bond and the breakage of AgeSb bond under biaxial shear *** suggests that the deformation mechanism changes significantly under different loading conditions.

关键词： MgAgSb thermoelectric materials Density functional theory Ideal strength Deformation mechanism

来源：评论

学校读者我要写书评

暂无评论

Partial Task Shuffle First Strategy for Spark

Partial Task Shuffle First Strategy for Spark

引用

2019 4th International Conference on Automatic Control and Mechatronic engineering(ACME 2019)

作者： Tianlei Zhou Yuyang Wang School of computer science and technology Chongqing University of Posts and Telecommunications Chongqing Engineering Research Center of Mobile Internet Data Application

Apache Spark is an in-memory distributed computing framework,which is more suitable for iterative jobs than ***,the shuffle process needs to synchronize tasks between nodes,which may lead to waste the computing resources of the cluster and ultimately reduce the computing performance of the *** is an important reason to limit the performance of *** this paper,we proposes a Partial Task Shuffle First（PTSF） Strategy to dynamically generate Shuffle Write tasks and perform Shuffle operations on partial completed *** strategy increases the parallel degrees of data calculation and transmission,lowering the peak of the Shuffle stage,allowing the cluster to be more balanced in the course of the ***,experiments show that the proposed strategy can improve Shuffle execution efficiency.

关键词： Big data spark shuffle task

来源：评论

学校读者我要写书评

暂无评论

A Distributed Block Storage Optimization Mechanism Based on Ceph

A Distributed Block Storage Optimization Mechanism Based on ...

引用

2019 4th International Conference on Automatic Control and Mechatronic engineering(ACME 2019)

作者： Yang Pi Zhanglong Wang School of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing Engineering Research Center of Mobile Internet Data Application

RADOS block device（RBD） is the storage service component in Ceph,which provides an important block storage service for OpenStack and other cloud computing *** response to the challenges faced by enterprises in terms of higher resource utilization and read/write rates on block storage services,Ceph provides Cache Tiering to improve cluster performance in heterogeneous storage ***,the least recently used（LRU） algorithm in Cache Tiering would evict more valuable data due to cache pollution which causes higher latency for some requests;Meanwhile,when the data is allocated on the storage node,the Controlled Replication Under Scalable Hashing（CRUSH） algorithm only considers the storage node capacity,which makes Ceph unable to dynamically balance the node’s I/O *** solve these problems,a storage selection strategy based on the prediction model is proposed to increase the hit ratio of object access in the cache pool and improve the overall I/O performance of the cluster;Besides,the cache pool I/O load balancing strategy is also *** with the native mechanism,the proposed block storage optimization mechanism can achieve higher I/O throughput and more balanced I/O load.

关键词： Ceph Block storage Cache Tiering Storage selection Load balancing

来源：评论

学校读者我要写书评

暂无评论

An Optimization Strategy of Shard on Elasticsearch

An Optimization Strategy of Shard on Elasticsearch

引用

2019 4th International Conference on Automatic Control and Mechatronic engineering(ACME 2019)

作者： Zhanglong Wang Yang Pi School of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing Engineering Research Center of Mobile Internet Data Application

With the development of big data application,there are more demands on big data storage and ***,Elasticsearch,a distributed full-text search engine,has appeared,which can well meet these ***,Elasticsearch has the following disadvantages:First,shard settings are based on user experience and may degrade retrieval performance due to human ***,the factors considered in the distribution strategy of shards are *** the last,without effective processing of concurrent access to hot index data,the average performance of each node in the Elasticsearch cluster varies *** this paper,we propose a shard optimization strategy of Elasticsearch,through data and performance analysis,to obtain reasonable shard *** that,the shards are placed in nodes with better performance which are evaluated by the linear weighting ***,the optimized load balancing strategy will migrate hot shards caused by hot data to make the cluster load *** experimental results show that the proposed shard optimization strategy can achieve better index retrieval performance and better cluster load.

关键词： ElasticSearch Index Shard Load balancing Mathematical modeling Linear weighting method

来源：评论

学校读者我要写书评

暂无评论

A Lowest Cost RDD Caching Strategy for Spark

A Lowest Cost RDD Caching Strategy for Spark

引用

2019 4th International Conference on Automatic Control and Mechatronic engineering(ACME 2019)

作者： Yuyang Wang Tianlei Zhou School of computer science and technology Chongqing University of Posts and Telecommunications Chongqing Engineering Research Center of Mobile Internet Data Application

Spark abstracts intermediate results into RDD in memory and manages them with LRU strategy to improve ***,RDD will be reloaded in many cases because RDD for different computing tasks have different lifecycle,which incurs additional system *** this paper we proposed a lowest cost replacement strategy as Spark's cache replacement strategy to eliminate this *** strategy preemptively evicts RDD with small weight values from memory based on the weight *** then,in this process,we select the solution with the lowest cost to replace the RDD in memory to improve the efficiency of ***,experiment results show that strategy we proposed can speed up the efficiency of the whole cluster.

关键词： RDD Spark memory management Memory computing Cache strategy

来源：评论

学校读者我要写书评

暂无评论

LCBNI: Link completion bipartite network inference for predicting new lncRNA-miRNA interactions

LCBNI: Link completion bipartite network inference for predi...

引用

2018 IEEE International Conference of Safety Produce Informatization, IICSPI 2018

作者： Yu, Zhenkun Zhu, Fuxi Tianl, Gang Wang, Hao School of Computer Science Wuhan University Wuhan430072 China AI Application Research Center Wuhan College Wuhan Hubei430211 China State Key Laboratory of Geomechanics and Geotechnical Engineering Institute of Rock and Soil Mechanics Chinese Academy of Sciences Wuhan430071 China

ISBN: (纸本)9781538655139

LncRNAs and miRNAs are two different kinds of non-coding RNAs and are both important for human in the field of health and disease. LncRNAs can interact with miRNAs, and the interactions play key roles in gene regulatory networks. Predicting IncRNA-miRNA interactions is an urgent and significant task and can help to explore the mechanism of involved complicated diseases, but very few computational methods are developed. In this paper, we introduce a computational method named link completion bipartite network inference (LCBNI) to predict the potential interactions between IncRNAs and miRNAs. LCBNI formulates the observed IncRNA-miRNA interactions as a bipartite network. Considering that there is no any known interaction for new IncRNAs or miRNAs, LCBNI calculates the sequence similarity and utilizes weighted nearest neighbor interaction information to construct new interaction scores for these IncRNAs and miRNAs. Then, we implement a resource allocation algorithm on the bipartite network to predict IncRNA-miRNA interactions. The experimental results demonstrate that LCBNI can effectively predict IncRNA-miRNA interactions with higher accuracy compared with other state-of-the-art methods and network-based methods, including random walk with restart (RWR), IncRNA-based collaborative filtering (LncCF) and miRNA-based collaborative filtering (MiCF). Furthermore, case studies are performed to demonstrate the prediction capability of LCBNI using real data. © 2018 IEEE.

关键词： Collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

A Unified Object Motion and Affinity Model for Online Multi-Object Tracking

A Unified Object Motion and Affinity Model for Online Multi-...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Junbo Yin Wenguan Wang Qinghao Meng Ruigang Yang Jianbing Shen Beijing Lab of Intelligent Information Technology School of Computer Science Beijing Institute of Technology China ETH Zurich Switzerland Baidu Research National Engineering Laboratory of Deep Learning Technology and Application China University of Kentucky Kentucky USA Inception Institute of Artificial Intelligence UAE

ISBN: (数字)9781728171685

ISBN: (纸本)9781728171692

Current popular online multi-object tracking (MOT) solutions apply single object trackers (SOTs) to capture object motions, while often requiring an extra affinity network to associate objects, especially for the occluded ones. This brings extra computational overhead due to repetitive feature extraction for SOT and affinity computation. Meanwhile, the model size of the sophisticated affinity network is usually non-trivial. In this paper, we propose a novel MOT framework that unifies object motion and affinity model into a single network, named UMA, in order to learn a compact feature that is discriminative for both object motion and affinity measure. In particular, UMA integrates single object tracking and metric learning into a unified triplet network by means of multi-task learning. Such design brings advantages of improved computation efficiency, low memory requirement and simplified training procedure. In addition, we equip our model with a task-specific attention module, which is used to boost task-aware feature learning. The proposed UMA can be easily trained end-to-end, and is elegant - requiring only one training stage. Experimental results show that it achieves promising performance on several MOT Challenge benchmarks.

关键词： Computational modeling Task analysis Target tracking Feature extraction Training

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：