检索结果-南通市图书馆

Disease prediction by network information gain on a single sample basis

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Fundamental Research 2025年第1期5卷 215-227页

作者： Jinling Yan Peiluan Li Ying Li Rong Gao Cheng Bi Luonan Chen School of Mathematics and Statistics Henan University of Science and TechnologyLuoyang 471023China Key Laboratory of Information Fusion Technology of Ministry of Education School of AutomationNorthwestern Polytechnical UniversityXi'an 710072China Longmen Laboratory Luoyang 471003China Key Laboratory of Systems Biology Center for Excellence in Molecular Cell ScienceShanghai Institute of Biochemistry and Cell BiologyChinese Academy of SciencesShanghai 200031China Key Laboratory of Systems Health science of Zhejiang Province Hangzhou Institute for Advanced StudyUniversity of Chinese Academy of SciencesChinese Academy of SciencesHangzhou 310024China Guangdong institute of Intelligence science and Technology Zhuhai 519031China School of Life science and Technology ShanghaiTech UniversityShanghai 201210China

There are critical transition phenomena during the progression of many *** critical transitions are usually accompanied by catastrophic disease deterioration,and their prediction is of significant importance for disease prevention and ***,predicting disease deterioration solely based on a single sample is a difficult *** this study,we presented the network information gain(NIG)method,for predicting the critical transitions or disease state based on network flow entropy from omics data of each *** can not only efficiently predict disease deteriorations but also detect their dynamic network biomarkers on an individual basis and further identify potential therapeutic *** numerical simulation demonstrates the effectiveness of ***,our method was validated by successfully predicting disease deteriorations and identifying their potential therapeutic targets from four real omics datasets,i.e.,an influenza dataset and three cancer datasets.

关键词： Tipping point Network information gain Dynamic network biomarker Disease prediction Network flow entropy Drug target

Unsupervised Meteorological Downscaling Based on Dual Learning and Subgrid-scale Auxiliary Information

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 Atmospheric sciences 2025年第1期42卷 53-66页

作者： Jing HU Jialing mu Xiaomeng HUANG Xi WU Department of Computer science Chengdu University of Information TechnologyChengdu 610225China Department of Earth System science Ministry of Education Key Laboratory for Earth System ModelingInstitute for Global Change StudiesTsinghua UniversityBeijing 100084China

Climate downscaling is used to transform large-scale meteorological data into small-scale data with enhanced detail,which finds wide applications in climate modeling,numerical weather forecasting,and renewable *** deeplearning-based downscaling methods effectively capture the complex nonlinear mapping between meteorological data of varying scales,the supervised deep-learning-based downscaling methods suffer from insufficient high-resolution data in practice,and unsupervised methods struggle with accurately inferring small-scale specifics from limited large-scale inputs due to small-scale *** article presents DualDS,a dual-learning framework utilizing a Generative Adversarial Network–based neural network and subgrid-scale auxiliary information for climate *** a learning method is unified in a two-stream framework through up-and downsamplers,where the downsampler is used to simulate the information loss process during the upscaling,and the upsampler is used to reconstruct lost details and correct errors incurred during the *** dual learning strategy can eliminate the dependence on high-resolution ground truth data in the training process and refine the downscaling results by constraining the mapping *** findings demonstrate that DualDS is comparable to several state-of-the-art deep learning downscaling approaches,both qualitatively and ***,for a single surface-temperature data downscaling task,our method is comparable with other unsupervised algorithms with the same dataset,and we can achieve a 0.469 dB higher peak signal-to-noise ratio,0.017 higher structural similarity,0.08 lower RMSE,and the best correlation *** summary,this paper presents a novel approach to addressing small-scale uncertainty issues in unsupervised downscaling processes.

关键词： downscaling unsupervised deep learning dual learning auxiliary information

Fractal autoencoder with redundancy regularization for unsupervised feature selection

在线全文

学校读者我要写书评

暂无评论

science China(Information sciences) 2025年第2期68卷 89-102页

作者： Meiting SUN Fangyu LI Honggui HAN School of Information science and Technology Beijing University of Technology Beijing Key Laboratory of Computational Intelligence and Intelligent System Engineering Research Center of Digital Community Ministry of Education Beijing institute of Artificial Intelligence

Feature selection is a crucial step in data preprocessing because feature selection reduces the dimensionality of data by eliminating irrelevant and redundant features. Since manual labeling is expensive, unsupervised feature selection has received increasing attention in recent years. However, existing unsupervised feature selection methods tend to prioritize selecting highly correlated features over exploring feature diversity. Thus, a regularized fractal autoencoder(RFAE) method is proposed to select informative features in an unsupervised way. Specifically, the fractal autoencoder network extends autoencoders to construct a correspondence neural network and a selection neural network. The correspondence neural network exploits interfeature correlations and the selection neural network selects the informative features. A redundancy regularization strategy consists of a redundancy elimination regularization term based on the dependency between features and a sparse regularization term based on the group lasso. The redundancy regularization strategy eliminates feature subset redundancy and enhances network generalization ability. Extensive experimental results on six publicly available datasets show that the proposed RFAE outperforms the compared methods regarding clustering accuracy and classification accuracy. Moreover, the proposed RFAE achieves acceptable computation efficiency.

关键词： unsupervised feature selection fractal autoencoder correspondence neural network selection neural network redundancy regularization strategy

同方期刊数据库

PAMPHLET:PAM Prediction HomoLogous-Enhancement Toolkit for precise PAM prediction in CRISPR-Cas systems

在线全文

学校读者我要写书评

暂无评论

Journal of Genetics and Genomics 2025年第2期52卷 258-268页

作者： Chen Qi Xuechun Shen Baitao Li Chuan Liu Lei Huang Hongxia Lan Donglong Chen Yuan Jiang Dan Wang Guangdong Provincial Key Laboratory of Interdisciplinary Research and Application for data science BNU-HKBU United International CollegeZhuhaiGuangdong 519087China School of Biology and Biological Engineering South China University of TechnologyGuangzhouGuangdong 510006China BGI Research HangzhouZhejiang 310030China BGI Research ShenzhenGuangdong 518083China College of Life sciences University of Chinese Academy of SciencesBeijing 100049China Laboratory of Integrative Biomedicine Department of BiologyFaculty of ScienceUniversity of CopenhagenCopenhagenDenmark Qingdao-Europe Advanced institute for Life sciences BGI ResearchQingdaoShandong 266555China School of Life science Hangzhou Institute for Advanced StudyUniversity of Chinese Academy of SciencesHangzhouZhejiang 310024China STOmics Americas Ltd. 2904 Orchard PkwySan Jose CA 95134USA

CRISPR-Cas technology has revolutionized our ability to understand and engineer organisms,evolving from a singular Cas9 model to a diverse CRISPR toolbox.A critical bottleneck in developing new Cas proteins is identifying protospacer adjacent motif(PAM)*** to the limitations of experimental methods,bioinformatics approaches have become ***,existing PAM prediction programs are limited by the small number of spacers in CRISPR-Cas systems,resulting in low *** address this,we develop PAMPHLET,a pipeline that uses homology searches to identify additional spacers,significantly increasing the number of spacers up to *** is validated on 20 CRISPR-Cas systems and successfully predicts PAM sequences for 18 *** predictions are further validated using the DocMF platform,which characterizes protein-DNA recognition patterns via next-generation *** high consistency between PAMPHLET predictions and DocMF results for Cas proteins demonstrates the potential of PAMPHLET to enhance PAM sequence prediction accuracy,expedite the discovery process,and accelerate the development of CRISPR tools.

关键词： CRISPR-Cas Protospacer adjacentmotif Genome editing PAM prediction Computational framework

Semiparametric Additive Hazards Model with Doubly Truncated data

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Acta Mathematica Sinica,English Series 2025年第2期41卷 619-639页

作者： Yijin Zhang Liuquan Sun institute of Applied Mathematics Academy of Mathematics and Systems ScienceChinese Academy of SciencesBeijing 100190P.R.China University of Chinese Academy of sciences Beijing 100049P.R.China

Doubly truncated data arise when the survival times of interest are observed only if they fall within certain random *** this paper,we consider a semiparametric additive hazards model with doubly truncated data,and propose a weighted estimating equation approach to estimate the regression coefficients,where the weights are estimated both parametrically and *** asymptotic properties of the resulting estimators are *** studies demonstrate that the proposed estimators perform well in a finite *** application to Parkinson's disease data is provided.

关键词： Additive hazards model double truncation estimating equations inverse weighting survival analysis

New measurement of ^(63)Cu(γ,n)^(62)Cu cross-section using quasi-monoenergeticγ-ray beam

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Nuclear science and Techniques 2025年第2期36卷 131-140页

作者： Zhi-Cai Li Zi-Rui Hao Qian-Kun Sun Yu-Long Shen Long-Xiang Liu Hang-Hua Xu Yue Zhang Pu Jiao Meng-Die Zhou Yu-Xuan Yang Sheng Jin Kai-Jie Chen Zhen-Wei Wang Shan Ye Xin-Xiang Li Chun-Wang Ma Hong-Wei Wang Gong-Tao Fan Wen Luo School of Nuclear science and Technology University of South ChinaHengyang 421001China Shanghai Advanced Research institute Chinese Academy of SciencesShanghai 201210China Shanghai institute of Applied Physics Chinese Academy of SciencesShanghai 201800China University of Chinese Academy of science Beijing 100049China School of Physics Henan Normal UniversityXinxiang 453007China China institute of Atomic Energy Beijing 102413China institute of Nuclear science and Technology Henan Academy of SciencesZhengzhou 450046China

We present new data on the^(63)Cu(γ,n)cross-section studied using a quasi-monochromatic and energy-tunableγbeam produced at the Shanghai Laser Electron Gamma Source to resolve the long-standing discrepancy between existing measurements and evaluations of this *** an unfolding iteration method,^(63)Cu(γ,n)data were obtained with an uncertainty of less than 4%,and the inconsistencies between the available experimental data were ***γ-ray strength function of^(63)Cu(γ,n)was successfully extracted as an experimental *** further calculated the cross-section of the radiative neutron capture reaction^(62)Cu(n,γ)using the TALYS *** calculation method enables the extraction of(n,γ)cross-sections for unstable nuclides.

关键词： ^(63)Cu(γ n)reaction Cross-section data Quasi-monochromaticbeam Radiative neutron capture reaction

Atmospheric CO_(2) Removal Efficiency through Enhanced Silicate Weathering in Croplands:A Review with Emphasis on the Contribution of Fungi

在线全文

学校读者我要写书评

暂无评论

Journal of Earth science 2025年第1期36卷 197-211页

作者： Zi-Bo Li Gaojun Li Jonathan M.Adams Dong-Xing Guan Liang Zhao Rongjun Bian Qing Hu Xiancai Lu Junfeng Ji Jun Chen State Key Laboratory of Palaeobiology and Stratigraphy Nanjing Institute of Geology and PalaeontologyChinese Academy of SciencesNanjing 210008China Key Laboratory of Surficial Geochemistry Ministry of EducationSchool of Earth Sciences and Engineering and Frontiers Science Center for Critical Earth Material CyclingNanjing UniversityNanjing 210023China School of Geography and Ocean science Nanjing UniversityNanjing 210023China institute of Soil and Water Resources and Environmental science College of Environmental and Resource SciencesZhejiang UniversityHangzhou 310058China institute of Resource Ecosystem and Environment of AgricultureNanjing Agricultural UniversityNanjing 210095China Xiong'an institute of Innovation Chinese Academy of SciencesXiong'an 071700China

Enhanced silicate weathering(ESW)is a geoengineering method aimed at accelerating carbon dioxide(CO_(2))removal(CDR)from atmosphere by increasing the weathering flux of silicate rocks and *** has emerged as a promising strategy for *** studies underscore ESW’s substantial potential for CDR and its diverse benefits for crops when applied to ***,the well-known significant discrepancies in silicate weathering rates between laboratory and field conditions introduce uncertainty in CDR through *** compiling data from recent literature,we calculated and compared CDR efficiency(t CO_(2)t^(-1)_(silicate)ha^(-1)y^(-1))observed in mesocosm experiments and field *** findings indicate that CDR efficiencies in field trials are comparable to or exceeding that observed in mesocosm experiments by 1-3 orders of magnitude,particularly evident with wollastonite *** hierarchy of CDR efficiency among silicates suitable for ESW is ranked as follows:olivine≥wollastonite>basalt>albite≥*** suggest the potential role of biota,especially fungi,in contributing to higher CDR efficiencies observed in field trials compared to mesocosm *** further emphasize introducing fungi known for their effectiveness in silicate weathering could potentially enhance CDR efficiency through ESW in *** before implementing fungal-facilitated ESW,three key questions need addressing:(i)How does the community of introduced fungi evolve over time?(ii)What is the long-term trajectory of CDR efficiency following fungal introduction?and(iii)Could fungal introduction lead to organic matter oxidation,resulting in elevated CO_(2)emissions?These investigations are crucial for optimizing the efficiency and sustainability of fungal-facilitated ESW strategy.

关键词： enhanced weathering carbon dioxide removal efficiency fungi weathering rate altered surface layers

A Helmet Detection Algorithm Based on Transformers with Deformable Attention Module

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Electronics 2025年第1期34卷 229-241页

作者： Songle Chen Hongbo Sun Yuxin Wu Lei Shang Xiukai Ruan Engineering Research Center of Post Big data Technology and Application of Jiangsu Province Nanjing University of Posts and Telecommunications State Key Lab for Novel Software Technology Nanjing University institute of Intelligent Locks Wenzhou University

Wearing a helmet is one of the effective measures to protect workers' safety. To address the challenges of severe occlusion, multi-scale, and small target issues in helmet detection, this paper proposes a helmet detection algorithm based on deformable attention transformers. The main contributions of this paper are as follows. A compact end-to-end network architecture for safety helmet detection based on transformers is proposed. It cancels the computationally intensive transformer encoder module in the existing detection transformer(DETR) and uses the transformer decoder module directly on the output of feature extraction for query decoding, which effectively improves the efficiency of helmet detection. A novel feature extraction network named Swin transformer with deformable attention module(DSwin transformer) is proposed. By sparse cross-window attention, it enhances the contextual awareness of multi-scale features extracted by Swin transformer, and keeps high computational efficiency simultaneously. The proposed method generates the query reference points and query embeddings based on the joint prediction probabilities, and selects an appropriate number of decoding feature maps and sparse sampling points for query decoding, which further enhance the inference capability and processing speed. On the benchmark safety-helmet-wearing-dataset(SHWD), the proposed method achieves the average detection accuracy mAP@0.5 of 95.4% with 133.35G floating-point operations per second(FLOPs) and 20 frames per second(FPS), the state-of-the-art method for safety helmet detection.

关键词： Head Accuracy Network architecture Benchmark testing Transformers Feature extraction Safety Decoding Computational efficiency Detection algorithms

Mixture of Bacillus Amyloliquefaciens and Bacillus Pumilus Modulates Community Structures of Rice Rhizosphere Soil to Suppress Rice Seedling Blight

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Rice science 2025年第1期32卷 118-130,I0067-I0070页

作者： JIANG Nan QIU Jiehua TIAN Dagang SHI Huanbin LIU Zhiquan WEN Hui XIE Shuwei CHEN Huizhe WU Meng KOU Yanjun State Key Laboratory of Rice Biology and Breeding China National Rice Research InstituteHangzhou 311400China Biotechnology Research institute Fujian Academy of Agricultural SciencesFuzhou 350003China State Key Laboratory of Soil and Sustainable Agriculture the Institute of Soil ScienceChinese Academy of SciencesNanjing 210008China

Rice seedling blight,caused by various fungi,including Fusarium oxysporum,poses a severe threat to rice *** awareness grows regarding the environmental and safety hazards associated with the application of fungicides for managing rice seedling blight,there has been a shift in focus towards biological control *** this study,we isolated biocontrol bacteria from paddy fields that significantly inhibited the growth of *** in vitro and identified the strains as Bacillus amyloliquefaciens T40 and Bacillus pumilus ***,our findings indicated that the combined application of these Bacillus strains in soil was more effective in reducing the incidence of rice seedling blight than their individual *** of 16S and internal transcribed spacer rRNA gene sequencing data revealed that the mixture of the T40 and T208 strains exhibited the lowest average clustering coefficients,which were negatively correlated with the biomass of ***-inoculated rice ***,this mixture led to higher stochastic assembly(average|βNTI|munity structures,enhances microbial network stability,and boosts the resistance against rice seedling *** study supports the development and utilization of biological resources for crop protection.

关键词： application strategy disease control disease resistance microbial community structure microbial community assembly process Oryza sativa