检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Jalaboi, Raluca Winther, Ole Galimzianova, Alfiia Department of Applied Mathematics and Computer Science The Technical University of Denmark Richard Petersens Plads Building 324 Kongens LyngbyDK-2800 Denmark Medable A/S Silkegade 8 st Copenhagen CDK-1113 Denmark Bioinformatics Centre Department of Biology University of Copenhagen Copenhagen Denmark Center for Genomic Medicine Rigshospitalet Copenhagen University Hospital Copenhagen Denmark

Image quality is a crucial factor in the effectiveness and efficiency of teledermatological consultations. However, up to 50% of images sent by patients have quality issues, thus increasing the time to diagnosis and treatment. An automated, easily deployable, explainable method for assessing image quality is necessary to improve the current teledermatological consultation flow. We introduce ImageQX, a convolutional neural network for image quality assessment with a learning mechanism for identifying the most common poor image quality explanations: bad framing, bad lighting, blur, low resolution, and distance issues. ImageQX was trained on 26,635 photographs and validated on 9,874 photographs, each annotated with image quality labels and poor image quality explanations by up to 12 board-certified dermatologists. The photographic images were taken between 2017 and 2019 using a mobile skin disease tracking application accessible worldwide. Our method achieves expert-level performance for both image quality assessment and poor image quality explanation. For image quality assessment, ImageQX obtains a macro F1-score of 0.73 ± 0.01, which places it within standard deviation of the pairwise inter-rater F1-score of 0.77 ± 0.07. For poor image quality explanations, our method obtains F1-scores of between 0.37 ± 0.01 and 0.70 ± 0.01, similar to the inter-rater pairwise F1-score of between 0.24 ± 0.15 and 0.83 ± 0.06. Moreover, with a size of only 15 MB, ImageQX is easily deployable on mobile devices. With an image quality detection performance similar to that of dermatologists, incorporating ImageQX into the teledermatology flow can enable a better, faster flow for remote consultations. © 2022, CC BY-NC-ND.

关键词： Image quality

来源：评论

学校读者我要写书评

暂无评论

The modeling and mathematical analysis of the fractional-order of Cholera disease: Dynamical and Simulation

引用

Partial Differential Equations in applied mathematics 2024年 12卷

作者： Yaseen, Rasha M. Ali, Nidal F. Mohsen, Ahmed A. Khan, Aziz Abdeljawad, Thabet Department of biomedical Eng. Al-Khawarzmi College of Engineering University of Baghdad Baghdad Iraq Department of Medical Instrumentation Techniques Engineering Electrical Engineering Technical College Middle Technical University Baghdad Iraq Department of Mathematics College of Education for Pure Science (Ibn Al-Haitham) University of Baghdad Baghdad Iraq Department of Mathematics Open Education College Iraq Department of Mathematics and Sciences Prince Sultan University P.O. Box 66833 Riyadh 11586 Saudi Arabia Department of Mathematics and Applied Mathematics Sefako Makgatho Health Sciences Universitu Medusa 0204 South Africa Center for Applied Mathematics and Bioinformatics (CAMB) Gulf University for Science and Technology Hawally 32093 Kuwait

In this study, a cholera model with asymptomatic carriers was examined. A Holling type-II functional response function was used to describe disease transmission. For analyzing the dynamical behavior of cholera disease, a fractional-order model was developed. First, the positivity and boundedness of the system's solutions were established. The local stability of the equilibrium points was also analyzed. Second, a Lyapunov function was used to construct the global asymptotic stability of the system for both endemic and disease-free equilibrium points. Finally, numerical simulations and sensitivity analysis were carried out using matlab software to demonstrate the accuracy and validate the obtained results. © 2024 The Authors

关键词： Cholera model Fractional-order Sensitive analysis Stability analysis

来源：评论

学校读者我要写书评

暂无评论

Relaxation rates of gene expression kinetics reveal the feedback signs of autoregulatory gene networks

arXiv

引用

arXiv 2018年

作者： Jia, Chen Qian, Hong Chen, Min Zhang, Michael Q. Department of Mathematical Sciences University of Texas at Dallas RichardsonTX75080 United States Department of Applied Mathematics University of Washington SeattleWA98195 United States Department of Biological Sciences Center for Systems Biology University of Texas at Dallas RichardsonTX75080 United States MOE Key Lab Division of Bioinformatics CSSB TNLIST Tsinghua University Beijing100084 China

The transient response to a stimulus and subsequent recovery to a steady state are the fundamental characteristics of a living organism. Here we study the relaxation kinetics of autoregulatory gene networks based on the chemical master equation model of single-cell stochastic gene expression with nonlinear feedback regulation. We report a novel relation between the rate of relaxation, characterized by the spectral gap of the Markov model, and the feedback sign of the underlying gene circuit. When a network has no feedback, the relaxation rate is exactly the decaying rate of the protein. We further show that positive feedback always slows down the relaxation kinetics while negative feedback always speeds it up. Numerical simulations demonstrate that this relation provides a possible method to infer the feedback topology of autoregulatory gene networks by using time-series data of gene expression. Copyright © 2018, The Authors. All rights reserved.

关键词： Eigenvalues and eigenfunctions

来源：评论

学校读者我要写书评

暂无评论

DERMATOLOGICAL DIAGNOSIS EXPLAINABILITY BENCHMARK FOR CONVOLUTIONAL NEURAL NETWORKS

arXiv

引用

arXiv 2023年

作者： Jalaboi, Raluca Winther, Ole Galimzianova, Alfiia Department of Applied Mathematics and Computer Science The Technical University of Denmark Richard Petersens Plads Building 324 Kongens LyngbyDK-2800 Denmark Medable A/S Havnegade 25 3. Copenhagen CDK-1058 Denmark Bioinformatics Centre Department of Biology University of Copenhagen Copenhagen Denmark Center for Genomic Medicine Rigshospitalet Copenhagen University Hospital Copenhagen Denmark

In recent years, large strides have been taken in developing machine learning methods for various dermatological applications, supported in part by the widespread success of deep learning. To date, diagnosing diseases from images is one of the most explored applications of deep learning within dermatology. Convolutional neural networks (ConvNets) are the most commonly used deep learning method in medical imaging due to their training efficiency and accuracy, although they are often described as black boxes because of their limited explainability. One popular way to obtain insight into a ConvNet's decision mechanism is gradient class activation maps (Grad-CAM). A quantitative evaluation of the Grad-CAM explainability has been recently made possible by the release of DermXDB, a skin disease diagnosis explainability dataset which enables benchmarking the explainability performance of ConvNet architectures. In this paper, we perform a literature review to identify the most common ConvNet architectures used for this task, and compare their Grad-CAM explainability performance with the explanation maps provided by DermXDB. We identified 11 architectures: DenseNet121, EfficientNet-B0, InceptionV3, InceptionResNetV2, MobileNet, MobileNetV2, NASNetMobile, ResNet50, ResNet50V2, VGG16, and Xception. We pre-trained all architectures on an clinical skin disease dataset, and then fine-tuned them on a subset of DermXDB. Validation results on the DermXDB holdout subset show an explainability F1 score of between 0.35-0.46, with Xception the highest explainability performance, while InceptionResNetV2, ResNet50, and VGG16 displaying the lowest. NASNetMobile reports the highest characteristic-level explainability sensitivity, despite it's mediocre diagnosis performance. These results highlight the importance of choosing the right architecture for the desired application and target market, underline need for additional explainability datasets, and further confirm the need for explainabil

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Proceedings of the EuBIC-MS 2020 Developers’ Meeting

引用

EuPA Open Proteomics 2020年 24卷 1-6页

作者： Christopher Ashwood Wout Bittremieux Eric W. Deutsch Nadezhda T. Doncheva Viktoria Dorfer Ralf Gabriels Vladimir Gorshkov Surya Gupta Andrew R. Jones Lukas Käll Dominik Kopczynski Lydie Lane Ludwig Lautenbacher Marc Legeay Marie Locard-Paulet Bart Mesuere Yasset Perez-Riverol Eugen Netz Sander Willems European Bioinformatics Community for Mass Spectrometry (info@***) Denmark Department of Cellular and Integrative Physiology University of Nebraska Medical Center Omaha USA Department of Computer Science University of Antwerp Antwerp Belgium Institute for Systems Biology Seattle WA 98109 USA Novo Nordisk Foundation Center for Protein Research University of Copenhagen Denmark Bioinformatics Research Group University of Applied Sciences Upper Austria Hagenberg Austria VIB-UGent Center for Medical Biotechnology VIB Ghent Belgium Department of Biochemistry and Molecular Biology University of Southern Denmark Denmark Institute of Systems Molecular and Integrative Biology University of Liverpool UK Science for Life Laboratory KTH - Royal Institute of Technology Solna Stockholm Sweden Leibniz-Institut für Analytische Wissenschaften - ISAS - e.V. Dortmund Germany SIB-Swiss Institute of Bioinformatics and Department of Microbiology and Molecular Medicine Faculty of Medicine Geneva University Geneva Switzerland Technical University of Munich Chair for Proteomics and Bioanalytics Freising Germany European Molecular Biology Laboratory European Bioinformatics Institute (EMBL-EBI) Wellcome Trust Genome Campus Hinxton Cambridge CB10 1SD UK Applied Bioinformatics Dept. of Computer Science University of Tübingen Tübingen Germany Skaggs School of Pharmacy and Pharmaceutical Sciences University of California San Diego La Jolla CA 92093 USA Center for non-coding RNA in Technology and Health Department of Veterinary and Animal Sciences University of Copenhagen Denmark Department of Biomolecular Medicine Ghent University Ghent Belgium Department of Applied Mathematics Computer Science and Statistics Ghent University Ghent Belgium Biomolecular Interactions Max Planck Institute for Developmental Biology Tübingen Germany

The 2020 European bioinformatics Community for Mass Spectrometry (EuBIC-MS) Developers’ meeting was held from January 13 th to January 17 th 2020 in Nyborg, Denmark. Among the participants were scientists as well as developers working in the field of computational mass spectrometry (MS) and proteomics. The 4-day program was split between introductory keynote lectures and parallel hackathon sessions. During the latter, the participants developed bioinformatics tools and resources addressing outstanding needs in the community. The hackathons allowed less experienced participants to learn from more advanced computational MS experts, and to actively contribute to highly relevant research projects. We successfully produced several new tools that will be useful to the proteomics community by improving data analysis as well as facilitating future research. All keynote recordings are available on https://***/10.5281/zenodo.3890181 .

关键词： Computational mass spectrometry Mass spectrometry Proteomics bioinformatics Spectrum clustering Phosphoproteomics XIC extraction Proteomics graph networks Predicted spectra Metaproteomics Functional annotations Benchmark development

来源：评论

学校读者我要写书评

暂无评论

***: Definition and modeling of probability distributions in the JuliaStats ecosystem

arXiv

引用

arXiv 2019年

作者： Besançon, Mathieu Papamarkou, Theodore Anthoff, David Arslan, Alex Byrne, Simon Lin, Dahua Pearson, John Zuse Institute Berlin Department of Applied Mathematics Industrial Engineering Polytechnique Montréal MontréalQC Canada École Centrale de Lille Villeneuve d'Ascq France INOCS INRIA Lille CRISTAL Villeneuve d'Ascq France Department of Mathematics The University of Manchester Department of Mathematics University of Tennessee and Computational Sciences & Engineering Division Oak Ridge National Laboratory Energy and Resources Group University of California at Berkeley Beacon Biosignals Inc California Institute of Technology The Chinese University of Hong Kong Department of Biostatistics and Bioinformatics Duke University Medical Center DurhamNC United States

Random variables and their distributions are a central part in many areas of statistical methods. The *** package provides Julia users and developers tools for working with probability distributions, leveraging Julia features for their intuitive and flexible manipulation, while remaining highly efficient through zero-cost abstractions. Copyright © 2019, The Authors. All rights reserved.

关键词： Probability distributions

来源：评论

学校读者我要写书评

暂无评论

An Explainable Deep Neural Network Model Based on Multi-Granularity Co-Attention to Improve Prediction of Drug-Target Binding Affinity

SSRN

引用

SSRN 2024年

作者： Lin, Yanmei Cao, Aiqing Deng, Lei Liao, Mingzhi Zhang, Ru Zhang, Hao Peng, Yuzhong Guangxi Key Lab of Human-machine Interaction and Intelligent Decision Nanning Normal University Nanning530001 China Guangxi Academy of Sciences Nanning530007 China School of Computer Science and Engineering Central South University Changsha410083 China Center of Bioinformatics College of Life Sciences Northwest A&F University Shaanxi Yangling712100 China Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen518000 China Center for Applied Mathematics of Guangxi Nanning Normal University Nanning530100 China

The prediction of drug-target interactions is pivotal in modern new drug development and drug repositioning. Nonetheless, current methods for predicting drug-target interactions often lose essential molecular structure information during the modeling process, leading to low prediction accuracy. This work proposes rMolGIN, a novel graph neural network with residual connectivity for molecular feature learning. rMolGIN not only takes into account the differences in chemical bonding properties and atomic neighborhood interactions, but also captures global and local structural information of drug molecules. Furthermore, we propose a novel drug-target affinity model based on rMolGIN and deep neural networks, coupled with a multi-granularity co-attention mechanism called HMCoDTA to capture comprehensive structural insights from both drugs and proteins. The proposed innovative model allows for comprehensive insight into the structural relationships between drugs and proteins, facilitating a more accurate prediction of binding affinities. To validate the effectiveness of our proposed methods, we conducted extensive experiments on three benchmark datasets of drug-target binding affinity, comparing HMCoDTA against 19 state-of-the-art models. Notably, the results show that HMCoDTA outperforms existing methods, demonstrating the effectiveness and advantages of our model in predicting drug-target binding affinity. © 2024, The Authors. All rights reserved.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Interlayer antisynchronization in degree-biased duplex networks

引用

Physical Review E 2023年第3期107卷 034313-034313页

作者： Sayantan Nag Chowdhury Sarbendu Rakshit Chittaranjan Hens Dibakar Ghosh Department of Environmental Science and Policy University of California Davis California 95616 USA Technology Innovation Hub (TIH) IDEAS (Institute of Data Engineering Analytics and Science Foundation) Indian Statistical Institute 203 B. T. Road Kolkata 700108 India Department of Mechanical Engineering University of California Riverside California 92521 USA Center for Computational Natural Sciences and Bioinformatics International Institute of Information Technology Gachibowli Hyderabad 500032 India Physics and Applied Mathematics Unit Indian Statistical Institute 203 B. T. Road Kolkata 700108 India

With synchronization being one of nature's most ubiquitous collective behaviors, the field of network synchronization has experienced tremendous growth, leading to significant theoretical developments. However, most previous studies consider uniform connection weights and undirected networks with positive coupling. In the present article, we incorporate the asymmetry in a two-layer multiplex network by assigning the ratio of the adjacent nodes' degrees as the weights to the intralayer edges. Despite the presence of degree-biased weighting mechanism and attractive-repulsive coupling strengths, we are able to find the necessary conditions for intralayer synchronization and interlayer antisynchronization and test whether these two macroscopic states can withstand demultiplexing in a network. During the occurrence of these two states, we analytically calculate the oscillator's amplitude. In addition to deriving the local stability conditions for interlayer antisynchronization via the master stability function approach, we also construct a suitable Lyapunov function to determine a sufficient condition for global stability. We provide numerical evidence to show the necessity of negative interlayer coupling strength for the occurrence of antisynchronization, and such repulsive interlayer coupling coefficients cannot destroy intralayer synchronization.

关键词： Coupled oscillators Dynamics of networks Synchronization

来源：评论

学校读者我要写书评

暂无评论

Natural convection heat transport performance of nanofluids under the influence of inclined magnetic field

引用

Results in Physics 2024年 58卷

作者： Islam, Tarikul Fayz-Al-Asad, Md. Khatun, M.A. Parveen, N. Ahmad, Hijaz Askar, Sameh CMUP University of Porto Porto Portugal Department of Mathematics American International University –Bangladesh Khilkhet Kuratoli Dhaka-1229 Bangladesh Department of Mathematics Jagannath University Dhaka 1000 Bangladesh Department of Mathematics Bangladesh University of Engineering and Technology Dhaka-1000 Bangladesh Near East University Operational Research Center in Healthcare Nicosia PC: 99138 TRNC Mersin 10 Turkey Center for Applied Mathematics and Bioinformatics Gulf University for Science and Technology Mishref Kuwait Department of Computer Science and Mathematics Lebanese American University Beirut Lebanon Department of Mathematics and Informatics Azerbaijan University Jeyhun Hajibeyli street 71 AZ1007 Baku Azerbaijan Department of Statistics and Operations Research College of Science King Saud University P.O. Box 2455 Riyadh 11451 Saudi Arabia

Two-dimensional free convective temperature transportation and fluid flow within the semi-circular cavity occupied by nanofluid with influence of inclined MHD is studied numerically. While bottom wall is warmed by three distinct thermal conditions (uniform, parabolic, and sinusoidal), the upper circular wall is warmed at lower temperatures. A slopping magnetic field acts upon the enclosure whose strength is unchanging. The governing non-linear equations is resolved with the numerical scheme Galerkin type finite element technique. A strong agreement is found with the earlier work. The outcomes for the model parameters likely Rayleigh number, sloping angle of magnetic field, nanoparticles volume, size, shape, and Brownian effects, and Hartmann number are demonstrated through streamlines, isothermal lines, and mean Nusselt number. In addition, investigation is conducted the thermal features of various nanoparticles and the nanofluid produced from them. The outcomes reveal that thermal transfer rate is significantly enhanced by volume fraction nanoparticles and buoyancy-driven parameter Rayleigh number whilst reduces for higher Hartman number. The inclined angles of magnetic field and different thermal conditions have a positive influence on thermal transport. For Cu-H₂O nanofluids, thermal transport is enhanced by 10.98 % in a uniform thermal system, where it increases by 14.42 % in the parabolic thermal system and by 15.53 % in a sinusoidal thermal system for the only 5 % volume of nanoparticles. Moreover, nano-sized particles’ shape factor has a noteworthy role in thermal transport. It is found that heat transfer rate rises by 6.79 % for blade-shaped nanoparticles. Additionally, as considering Brownian effects of nanoparticles, the temperature transport rate is improved by 21.45 % for small-sized nanoparticles. © 2024 The Authors

关键词： Finite Element Method Inclined magnetic field Nanoparticles Natural convection Semi-circular cavity

来源：评论

学校读者我要写书评

暂无评论

Essential guidelines for computational method benchmarking

arXiv

引用

arXiv 2018年

作者： Weber, Lukas M. Saelens, Wouter Cannoodt, Robrecht Soneson, Charlotte Hapfelmeier, Alexander Gardner, Paul P. Boulesteix, Anne-Laure Saeys, Yvan Robinson, Mark D. Institute of Molecular Life Sciences University of Zurich Zurich Switzerland SIB Swiss Institute of Bioinformatics University of Zurich Zurich Switzerland Data Mining and Modelling for Biomedicine VIB Center for Inflammation Research Ghent Belgium Department of Applied Mathematics Computer Science and Statistics Ghent University Ghent Belgium Institute of Medical Informatics Statistics and Epidemiology Technical University of Munich Munich Germany Department of Biochemistry University of Otago Dunedin New Zealand Institute for Medical Information Processing Biometry and Epidemiology Ludwig-Maximilians-University Munich Germany Friedrich Miescher Institute for Biomedical Research SIB Swiss Institute of Bioinformatics Basel Switzerland

In computational biology and other sciences, researchers are frequently faced with a choice between several computational methods for performing data analyses. Benchmarking studies aim to rigorously compare the performance of different methods using well-characterized benchmark datasets, to determine the strengths of each method or to provide recommendations regarding suitable choices of methods for an analysis. However, benchmarking studies must be carefully designed and implemented to provide accurate, unbiased, and informative results. Here, we summarize key practical guidelines and recommendations for performing high-quality benchmarking analyses, based on our experiences in computational biology. Copyright © 2018, The Authors. All rights reserved.

关键词： Benchmarking

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：