检索结果-南通市图书馆

pLoc_Deep-mEuk: Predict Subcellular Localization of Eukaryotic Proteins by Deep Learning

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Natural Science 2020年第6期12卷 400-428页

作者： Yutao Shao kuo-chen Chou Computer Science Jingdezhen Ceramic Institute Jingdezhen China Gordon Life Science Institute Boston MA USA

Recently, the life of worldwide human beings has been endangering by the spreading of pneu- monia-causing virus, such as Coronavirus, COVID-19, and H1N1. To develop effective drugs against Coronavirus, knowledge of protein subcellular localization is prerequisite. In 2019, a predictor called “pLoc_bal-mEuk” was developed for identifying the subcellular localization of eukaryotic proteins. Its predicted results are significantly better than its counterparts, particularly for those proteins that may simultaneously occur or move between two or more subcellular location site

关键词： Coronavirus Multi-Label System Eukaryotic Proteins Deep Learning Five-Steps Rule PseAAC

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

融合上下文和注意力的海洋涡旋小目标检测

中国图象图形学报 2023年第11期28卷 3509-3519页

作者：杜艳玲吴天宇陈括陈刚宋巍上海海洋大学信息学院上海200136 自然资源部东海信息中心上海200136 国家海洋信息中心天津300171

目的海洋涡旋精准检测是揭示海洋涡旋演变规律及其与其他海洋现象相互作用的基础。然而,海洋涡旋在其活跃海域呈现小尺度目标、密集分布的特点,导致显著的检测精度低问题。传统方法受限于人工设计参数缺乏泛化能力,而深度学习模型的高... 详细信息

目的海洋涡旋精准检测是揭示海洋涡旋演变规律及其与其他海洋现象相互作用的基础。然而,海洋涡旋在其活跃海域呈现小尺度目标、密集分布的特点,导致显著的检测精度低问题。传统方法受限于人工设计参数缺乏泛化能力,而深度学习模型的高采样率在检测小目标过程中底层细节和轮廓等信息损失严重,使得目标检测轮廓与目标真实轮廓相差甚远。针对海洋涡旋小目标特点导致检测精度低,高采样率深度模型检测轮廓不精确的问题,提出一种改进的U-Net网络。方法该模型基于渐进式采样结构,为获取上下文信息提升不同极性海洋涡旋目标的检测精度,增加上下文特征融合模块;为增加该模块对海洋涡旋小目标的关注,在特征融合前对最底层特征嵌入残差注意力模块,使模型可以更多关注海洋涡旋的轮廓信息。最后引入数据扩充方法缓解模型存在的过拟合问题。结果本文以南大西洋的卫星海表面高度数据集开展实验,结果表明,本文模型检测准确率达到了93.24%,同时在海洋涡旋的检测数量上与真实结果更加接近,验证了模型在小目标检测方面的性能更加优秀。结论本文提出的海洋涡旋小目标检测模型,在检测海洋涡旋的性能与海洋涡旋目标轮廓精准度方面均显著优于全卷积神经网络(fully convolutional network,FCN)等深度学习模型。

关键词：海洋涡旋小目标检测语义分割注意力机制特征融合

Pyogenic liver abscess caused by Klebsiella pneumoniae:analysis of the clinical characteristics and outcomes of 84 patients

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Chinese Medical Journal 2007年第2期120卷 136-139页

作者： CHAN Khee-siang YU Wen-liang TSAI Chi-lun chenG kuo-chen HOU Ching-cheng LEE Meng-chih TAN Che-kim Department of Intensive Care Medicine Chi Mei Medical Center Tainan Taiwan 710 China Institute of Medicine Chung Shan Medical University Taichung Taiwan 400 China

Background The increased incidence of pyogenic liver abscess caused by Klebsiella pneumoniae （***） was reported in the recent literature. This study was conducted retrospectively to investigate the clinical characteristics and outcomes of these patients. Methods Microbiological and medical databases of a medical center were searched from January 2000 to June 2003. Eighty-four patients with liver abscess caused by K. pneumoniae were analyzed. Results In the 84 patients, 52 men and 32 women aged （58.2±13.3） years on average, 64.4% had concomitant diabetes mellitus and 23.8% had biliary disease. The most common clinical symptoms were fever （98.8%）, chills （69.0%） and abdominal pain （58.3%）. 85.7% of the 84 patients received catheter drainage for the abscess. The length of hospital stay was （17.4 ±8.7） days. The mortality rate was 7.1%. Older age and presence of biliary disease were associated with mortality. Conclusions The low mortality of our patients was probably related to the high proportion of patients who received catheter drainage. Older age and presence of biliary disease were associated with the mortality.

关键词： Klebsiella pneumoniae liver abscess biliary tract disease

pLoc_Deep-mGpos: Predict Subcellular Localization of Gram Positive Bacteria Proteins by Deep Learning

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Journal of Biomedical Science and Engineering 2020年第5期13卷 55-65页

作者： Zhe Lu kuo-chen Chou Computer Science Jingdezhen Ceramic Institute Jingdezhen China Gordon Life Science Institute Boston MA USA

The recent worldwide spreading of pneumonia-causing virus, such as Coronavirus, COVID-19, and H1N1, has been endangering the life of human beings all around the world. In order to really understand the biological process within a cell level and provide useful clues to develop antiviral drugs, information of Gram positive bacteria protein subcellular localization is vitally important. In view of this, a CNN based protein subcellular localization predictor called “pLoc_Deep-mGpos” was developed. The predictor is particularly useful in dealing with the multi-sites systems in which some proteins may simultaneously occur in two or more different organelles that are the current focus of pharmaceutical industry. The global absolute true rate achieved by the new predictor is over 99% and its local accuracy is around 92% - 99%. Both are transcending other existing state-of-the-art predictors significantly. To maximize the convenience for most experimental scientists, a user-friendly web-server for the new predictor has been established at http://***/pLoc_Deep-mGpos/, which will become a very powerful tool for developing effective drugs to fight pandemic coronavirus and save the mankind of this planet.

关键词： Pandemic Coronavirus Multi-Label System Gram Positive Proteins Learning at Deeper Level Five-Steps Rule PseAAC

iATC_Deep-mISF: A Multi-Label Classifier for Predicting the Classes of Anatomical Therapeutic Chemicals by Deep Learning

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Advances in Bioscience and Biotechnology 2020年第5期11卷 153-159页

作者： Zhe Lu kuo-chen Chou Computer Science Jingdezhen Ceramic Institute Jingdezhen China Gordon Life Science Institute Boston MA 02478 USA

The recent worldwide spreading of pneumonia-causing virus, such as Coronavirus, COVID-19, and H1N1, has been endangering the life of human beings all around the world. To provide useful clues for developing antiviral drugs, information of anatomical therapeutic chemicals is vitally important. In view of this, a CNN based predictor called “iATC_Deep-mISF” has been developed. The predictor is particularly useful in dealing with the multi-label systems in which some chemicals may occur in two or more different classes. To maximize the convenience for most experimental scientists, a user-friendly web-server for the new predictor has been established at http://***/iATC_Deep-mISF/, which will become a very powerful tool for developing effective drugs to fight pandemic coronavirus and save the mankind of this planet.

关键词： Pandemic Coronavirus Multi-Label System Anatomical Therapeutic Chemicals Learning at Deeper Level Five-Steps Rule

pLoc_Deep-mAnimal: A Novel Deep CNN-BLSTM Network to Predict Subcellular Localization of Animal Proteins

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Natural Science 2020年第5期12卷 281-291页

作者： Yu-Tao Shao kuo-chen Chou Computer Science Jingdezhen Ceramic Institute Jingdezhen China Gordon Life Science Institute Boston MA USA

Current coronavirus pandemic has endangered mankind life. The reported cases are increasing exponentially. Information of animal protein subcellular localization can provide useful clues to develop antiviral drugs. To cope with such a catastrophe, a CNN based animal protein subcellular localization predictor called “pLoc_Deep-mAnimal” was developed. The predictor is particularly useful in dealing with the multi-sites systems in which some proteins may simultaneously occur in two or more different organelles that are the current focus of pharmaceutical industry. The global absolute true rate achieved by the new predictor is over 92% and its local accuracy is over 95%. Both have substantially exceeded the other existing state-of-the-art predictors. To maximize the convenience for most experimental scientists, a user-friendly web-server for the new predictor has been established at http://***/pLoc_Deep-mAnimal/, which will become a very useful tool for fighting pandemic coronavirus and save the mankind of this planet.

关键词： Pandemic Coronavirus Multi-Label System Animal Proteins Learning at Deeper Level Five Steps Rule PseAAC

Cell-PLoc 2.0: an improved package of web-servers for predicting subcellular localization of proteins in various organisms

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Natural Science 2010年第10期2卷 1090-1103页

作者： kuo-chen Chou Hong-Bin Shen 不详

Cell-PLoc 2.0 is a package of web-servers evolved from Cell-PLoc (Chou, K.C. & Shen, H.B., Nature Protocols, 2008, 2:153-162) by a top-down approach to improve the power for predicting subcellular localization of proteins in various organisms. It contains six predictors: Euk-mPLoc 2.0, Hum-mPLoc 2.0, Plant-mPLoc, Gpos-mPLoc, Gneg-mPLoc, and Virus-mPLoc, specialized for eukaryotic, human, plant, Gram- positive bacterial, Gram-negative bacterial, and virus proteins, respectively. Compared with Cell-PLoc, the predictors in the Cell-PLoc 2.0 have the following advantageous features: (1) they all have the capacity to deal with the multiplex proteins that can simultaneiously exist, or move between, two or more subcellular location sites;(2) no accession number is needed for the input of a query protein even if using the “high- level” GO (gene ontology) prediction engine;(3) the functional domain information and sequential evolution information are fused into the “ab initio” sequence-based prediction engine to enhance its accuracy. In this protocol, a step- to-step guide is provided for how to use the web server predictors in the Cell-PLoc 2.0 package, which is freely accessible to the public at http://***/bioinf/Cell-PLoc-2/.

关键词： Euk-mPLoc 2.0 Hum-mPLoc 2.0 Plant-mPLoc Gpos-mPLoc Gneg-mPLoc Virus-mPLoc Higher-level GO approach Ab-initio approach Functional domain Sequential evolution

长江口枯季盐度锋对深水航道及横沙东滩圈围工程的响应特征

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

水动力学研究与进展（A辑） 2022年第1期37卷 115-124页

作者：武云龙陈括匡翠萍王洁同济大学土木工程学院上海200092 上海勘测设计研究院有限公司上海200000

盐度锋作为长江口重要物理现象,对潮流、物质输移及沉降过程都有着重要影响。该文应用MIKE21软件建立了长江口二维水动力及盐度输运模型,探究深水航道及横沙东滩圈围工程对长江口枯季南北槽及北港盐度锋的影响,得出以下主要结论:南北槽... 详细信息

盐度锋作为长江口重要物理现象,对潮流、物质输移及沉降过程都有着重要影响。该文应用MIKE21软件建立了长江口二维水动力及盐度输运模型,探究深水航道及横沙东滩圈围工程对长江口枯季南北槽及北港盐度锋的影响,得出以下主要结论:南北槽盐度锋均呈双锋面结构,且主锋面(盐度梯度最大)均位于第一锋面处;但北港盐度锋呈单锋面结构。深水航道工程单独作用时,南北槽主锋面强度降低并向上游移动,南槽第二锋面基本消失,北槽第二锋面略有增强;北港锋面强度升高且向上游移动。横沙东滩圈围工程单独作用时,盐度锋的变化与深水航道工程单独作用时整体类似,且南北槽及北港主锋面变化程度更为显著,但南北槽第二锋面变化微弱。两工程共同作用时,南北槽盐度锋主要受深水航道工程控制,横沙东滩圈围工程会削弱南北槽主锋面强度;北港盐度锋主要受横沙东滩圈围工程控制,深水航道工程会削弱北港锋面强度。

关键词：盐度锋长江口数值模拟河口工程

REVIEW : Recent advances in developing web-servers for predicting protein attributes

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Natural Science 2009年第2期1卷 63-92页

作者： kuo-chen Chou Hong-Bin Shen 不详

Recent advance in large-scale genome se-quencing has generated a huge volume of pro-tein sequences. In order to timely utilize the in-formation hidden in these newly discovered sequences, it is highly desired to develop com- putational methods for efficiently identifying their various attributes because the information thus obtained will be very useful for both basic research and drug development. Particularly, it would be even more useful and welcome if a user-friendly web-server could be provided for each of these methods. In this minireview, a sy- stematic introduction is presented to highlight the development of these web-servers by our group during the last three years.

关键词： Cell-PLoc Signal-CF Signal-3L MemType-2L EzyPred HIVcleave GPCR-CA ProtIdent QuatIdent FoldRate