检索结果-内蒙古大学图书馆

Proceedings of the 41st International Conference on Machine Learning

作者： Daniel Levine Syed Asad Rizvi Sacha Lévy Nazreen Pallikkavaliyaveetil David Zhang Xingyu Chen Sina Ghadermarzi Ruiming Wu Zihe Zheng Ivan Vrkic Anna Zhong Daphne Raskin Insu Han Antonio Henrique De Oliveira Fonseca Josue Ortega Caro Amin Karbasi Rahul M. Dhodapkar David Van Dijk Department of Computer Science Yale University New Haven CT School of Engineering Applied Science University of Pennsylvania Philadelphia PA School of Computer and Communication Sciences Swiss Federal Institute of Technology Lausanne Lausanne Switzerland Department of Computer Science Yale University New Haven CT and Department of Neuroscience Yale School of Medicine New Haven CT Department of Computer Science Yale University New Haven CT and Department of Neuroscience Yale School of Medicine New Haven CT and Wu Tsai Institute Yale University New Haven CT Google and Yale Institute for Foundations of Data Science New Haven CT and Department of Computer Science Yale University New Haven CT and Yale School of Engineering and Applied Science New Haven CT Roski Eye Institute University of Southern California Los Angeles CA and Department of Internal Medicine (Cardiology) Yale School of Medicine New Haven CT Department of Computer Science Yale University New Haven CT and Yale Institute for Foundations of Data Science New Haven CT and Wu Tsai Institute Yale University New Haven CT and Cardiovascular Research Center Yale School of Medicine New Haven CT and Interdepartmental Program in Computational Biology & Bioinformatics Yale University New Haven CT and Department of Internal Medicine (Cardiology) Yale School of Medicine New Haven CT

We introduce Cell2Sentence (C2S), a novel method to directly adapt large language models to a biological context, specifically single-cell transcriptomics. By transforming gene expression data into "cell sentences," C2S bridges the gap between natural language processing and biology. We demonstrate cell sentences enable the fine-tuning of language models for diverse tasks in biology, including cell generation, complex cell-type annotation, and direct data-driven text generation. Our experiments reveal that GPT-2, when fine-tuned with C2S, can generate biologically valid cells based on cell type inputs, and accurately predict cell types from cell sentences. This illustrates that language models, through C2S fine-tuning, can acquire a significant understanding of single-cell biology while maintaining robust text generation capabilities. C2S offers a flexible, accessible framework to integrate natural language processing with transcriptomics, utilizing existing models and libraries for a wide range of biological applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

On Performance Prediction of Big Data Transfer in High-performance Networks

On Performance Prediction of Big Data Transfer in High-perfo...

引用

IEEE International Conference on Communications (ICC)

作者： Wuji Liu Daqing Yun Chase Q. Wu Nageswara S.V. Rao Aiqin Hou Wei Shen Department of Computer Science New Jersey Institute of Technology Newark NJ USA Computer and Information Sciences Program Harrisburg University Harrisburg PA USA Computational Sciences and Engineering Division Oak Ridge National Laboratory Oak Ridge TN USA School of Information Science and Technology Northwest University Xi’an Shaanxi China School of Informatics Science and Technology Zhejiang Sci-Tech University Hangzhou Zhejiang China

ISBN: (数字)9781728150895

ISBN: (纸本)9781728150901

Big data generated by large-scale scientific and industrial applications need to be transferred between different geographical locations for remote storage, processing, and analysis. High-speed dedicated connections provisioned in High-performance Networks (HPNs) are increasingly utilized to carry out such big data transfer. HPN management highly relies on an important capability of performance (mainly throughput) prediction to reserve sufficient bandwidth and meanwhile avoid over-provisioning that may result in unnecessary resource waste. This capability is critical to improving the resource (mainly bandwidth) utilization of dedicated connections and meeting various user requests for data transfer. Conventional methods conduct performance prediction by fitting prior observed transfer history with predefined loss functions, without considering unobservable latent factors such as competing loads on end hosts. Such latent factors also have a significant impact on the application-level data transfer performance, which may result in an inaccurate prediction model. In this paper, we first investigate the impact of latent factors and propose a clustering-based method to eliminate their negative impact on performance prediction. We then develop a robust machine learning-based performance predictor by: i) incorporating the proposed latent factor elimination method into data preprocessing, and ii) adopting a customized domain guided loss function. Extensive experimental results show that our predictor achieves significantly higher prediction accuracy than several other state-of-the-art methods.

关键词： Data transfer Big Data Throughput Bandwidth Measurement Predictive models Protocols

来源：评论

学校读者我要写书评

暂无评论

Core collapse supernova gravitational wave emission for progenitors of 9.6, 15, and 25M⊙

引用

Physical Review D 2023年第4期107卷 043008-043008页

作者： Anthony Mezzacappa Pedro Marronetti Ryan E. Landfield Eric J. Lentz R. Daniel Murphy W. Raphael Hix J. Austin Harris Stephen W. Bruenn John M. Blondin O. E. Bronson Messer Jordi Casanova Luke L. Kronzer Department of Physics and Astronomy University of Tennessee 1408 Circle Drive Knoxville Tennessee 37996-1200 USA Physics Division National Science Foundation Alexandria Virginia 22314 USA National Center for Computational Sciences Oak Ridge National Laboratory P.O. Box 2008 Oak Ridge Tennessee 37831-6164 USA Physics Division Oak Ridge National Laboratory P.O. Box 2008 Oak Ridge Tennessee 37831-6354 USA Joint Institute for Nuclear Physics and its Applications Oak Ridge National Laboratory P.O. Box 2008 Oak Ridge Tennessee 37831-6374 USA Department of Physics Florida Atlantic University 777 Glades Road Boca Raton Florida 33431-0991 USA Department of Physics North Carolina State University Raleigh North Carolina 27695-8202 USA Physics Program Community College of Denver P.O. Box 173363 Denver Colorado 80217-3363 USA Department of Aerospace Engineering and Mechanics University of Alabama Box 870280 Tuscaloosa Alabama 35487-0280 USA

We present gravitational wave emission predictions based on three core collapse supernova simulations corresponding to three different progenitor masses. The masses span a large range, between 9.6 and 25M⊙, are all initially nonrotating, and are of two metallicities: zero and solar. We compute both the temporal evolution of the gravitational wave strains for both the plus and the cross polarizations, as well as their spectral decomposition and characteristic strains. The temporal evolution of our zero metallicity 9.6M⊙ progenitor model is distinct from the temporal evolution of our solar metallicity 15M⊙ progenitor model and our zero metallicity 25M⊙ progenitor model. In the former case, the high-frequency gravitational wave emission is largely confined to a brief time period ∼75 ms after bounce, whereas in the latter two cases high-frequency emission does not commence until ∼125 ms after bounce or later. The excitation mechanisms of the high-frequency emission in all three cases correspond to proto-neutron star convection and accretion onto the proto-neutron star from the convective gain layer above it, with the former playing the dominant role for most of the evolution. The low-frequency emission in all three models exhibits very similar behavior. At frequencies below ∼250 Hz, gravitational waves are emitted by neutrino-driven convection and the standing accretion shock instability (SASI). This emission extends throughout the simulations when a gain region is present. In all three models, explosion is observed at ∼125, ∼500, and ∼250 ms after bounce in the 9.6, 15, and 25M⊙ progenitor models, respectively. At these times, the low-frequency gravitational wave emission is joined by very low-frequency emission, below ∼10 Hz. These very low-frequency episodes are the result of explosion and begin at the above designated explosion times in each of our models. Our characteristic strains tell us that, in principle, all three gravitational wave signals would be detec

关键词： Gravitation Gravitational waves Novae & supernovae Transient & explosive astronomical phenomena

来源：评论

学校读者我要写书评

暂无评论

Phage therapy

NATURE REVIEWS METHODS PRIMERS

引用

NATURE REVIEWS METHODS PRIMERS 2025年第1期5卷 1页

作者： [Anonymous] Human Microbiome Research Program Department of Bacteriology and Immunology Faculty of Medicine University of Helsinki Helsinki Finland European Society of Clinical Microbiology and Infectious Diseases (ESCMID) Study Group for Non-traditional Antibacterial Therapy (ESGNTA) Basel Switzerland Institute of Biomedical and Oral Research (IBOR) Faculty of Dental Medicine Hebrew University of Jerusaleum Jerusalem Israel The Israeli Phage Center (IPTC) of the Hebrew University and Hadassah Medical Center Jerusalem Israel Department of Clinical Microbiology and Infectious Diseases Hadassah–Hebrew University Medical Center Jerusalem Jerusalem Israel Laboratory of Gene Technology Department of Biosystems KU Leuven Leuven Belgium Leicester Centre for Phage Research Department of Genetics and Genome Biology University of Leicester Leicester UK Center for Evolutionary Hologenomics Globe Institute University of Copenhagen Copenhagen Denmark Centre of Excellence for Omics-Driven Computational Biodiscovery (COMBio) AIMST University Bedong Kedah Malaysia Laboratory of Phage Molecular Biology Institute of Immunology and Experimental Therapy Wrocław Poland Wrocław University of Science and Technology Faculty of Medicine Wrocław Poland Department of Biological Sciences University of Pittsburgh Pittsburgh PA USA Laboratory for Molecular and Cellular Technology Queen Astrid Military Hospital Brussels Belgium Department of Biological and Environmental Science Nanoscience Center University of Jyväskylä Jyväskylä Finland Chemical Engineering Department Loughborough University Loughborough UK

Bacteriophage (phages) are viruses that exclusively use bacterial cells for propagation, killing the bacterial host in the process. In phage therapy, phages are used to reduce bacterial numbers, thereby curing bacterial infections. Although this principle is conceptually straightforward, its practical application faces several hurdles. In this Primer, the practical aspects of phage therapy are outlined. We introduce the microbiological methods used to prepare and characterize phages and elucidate their interactions with bacteria. The discussion covers how the information in complete phage genome sequences is used, along with how RNA sequencing can enhance our understanding of phage biology. Selection parameters for therapeutic phages for clinical applications and key elements in industrial-scale phage production are provided. A summary of clinical trials both past and present, phage administration and dosing issues is analysed, as well as limitations associated with phage therapy and mitigation strategies. Finally, we speculate on the future of phage therapy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Uncovering the HOXA9 Translational Regulatory Complex That Promotes AML Leukemic Stem Cells

引用

Blood 2024年 144卷 4106-4106页

作者： Xueqin Xie Florisela Herrejon Chavez Ilyes Baali Eren L. Chu Chiara Evans Xuejing Yang Wei Wei Hanzhi Luo Sun Mi Park Kathryn Chang Aspen Pierson Grace Han Emily Batchelor Quaid D. Morris Ly Vu Diu T.T. Nguyen Michael G. Kharas Molecular Pharmacology Program Memorial Sloan Kettering Cancer Center New York NY Memorial Sloan Kettering Cancer Center NY Weill Cornell Graduate School of Medical Sciences NY Memorial Sloan Kettering Cancer Center New York Molecular Pharmacology Program Center for Cell Engineering Center for Stem Cell Biology Center for Experimental Therapeutics Center for Hematologic Malignancies Memorial Sloan Kettering Cancer Center New York City NY Memorial Sloan Kettering Cancer Center ny Computational and Systems Biology Program Memorial Sloan Kettering Cancer Center New York Memorial Sloan-Kettering Cancer Center Vancouver Canada The University of British Columbia Vancouver Canada Simon Fraser University Vancouver Canada Center for Hemato-Oncology Barts Cancer Institute Queen Mary University of London London United Kingdom

HOXA9 is a master transcription factor of hematopoiesis and essential for maintaining self-renewal of leukemia stem cells (LSCs). Although mechanisms associated with its transcriptional regulation are extensively studied, how Hoxa9 mRNA translation is controlled remain poorly understood. We have previously identified the RNA binding protein (RBP) MUSASHI-2 (MSI2) as a central regulator of myeloid LSCs by controlling translation of crucial transcription factors including Hoxa9 (Park et al. JCI, 2015; Nguyen et al. Nature Comm, 2020) . However, the mechanisms by which HOXA9 translation is modulated and the role of MSI2 remain unknown. To characterize the HOXA9 3'UTR mRNA regulon, we used it as a bait to perform an RNA-pull down followed by mass spectrometry (MS) with control or MSI2 depleted cells. To determine the direct MSI2's protein interactors on HOXA9 , we also performed MSI2 co-immunoprecipitation (co-IP) MS in control or MSI2 deficient AML cells. We identified 10 RBPs that directly bind to MSI2 and are dependent on MSI2 for their binding to the HOXA9 -3'UTR mRNA. Among these, we focused on SYNCRIP, a known MSI2 interactor ( Vu et al. Nat Gen , 2017 ), HNRNPC and MOV10, of which binding ability on HOXA 9 3'UTR was most reduced and enhanced, respectively, upon MSI2 loss. Reciprocal co-IP confirmed the interactions between these RBPs with MSI2. We then reasoned that if these RBPs are in the same regulatory complex with MSI2, they might phenocopy MSI2 loss of function in LSCs. To understand how each selected factor impacts LSC function and gene control, we first assessed MSI2's global regulation by performing integrative omic studies including MSI2-HyperTRIBE, RNA-seq and proteomics in MLL-AF9 murine LSCs that have acutely deleted (68hrs) of Msi2. We found that MSI2 binding promotes translation of 264 genes while suppresses 8 genes; and only 10 genes affected at mRNA level. These data found that MSI2 mediates translation of the self-renewal program in LSCs. We the

关键词：

来源：评论

学校读者我要写书评

暂无评论

A hybrid semi-Lagrangian cut cell method for advection-diffusion problems with robin boundary conditions in moving domains

arXiv

引用

arXiv 2021年

作者： Barrett, Aaron Fogelson, Aaron L. Griffith, Boyce E. Department of Mathematics University of Utah Salt Lake CityUT United States Departments of Mathematics and Bioengineering University of Utah Salt Lake CityUT United States Departments of Mathematics Applied Physical Sciences and Biomedical Engineering University of North Carolina Chapel HillNC United States Carolina Center for Interdisciplinary Applied Mathematics University of North Carolina Chapel HillNC United States Computational Medicine Program University of North Carolina Chapel HillNC United States McAllister Heart Institute University of North Carolina Chapel HillNC United States

We present a new discretization approach to advection-diffusion problems with Robin boundary conditions on complex, time-dependent domains. The method is based on second order cut cell finite volume methods introduced by Bochkov et al. [8] to discretize the Laplace operator and Robin boundary condition. To overcome the small cell problem, we use a splitting scheme along with a semi-Lagrangian method to treat advection. We demonstrate second order accuracy in the L1, L2, and L∞norms for both analytic test problems and numerical convergence studies. We also demonstrate the ability of the scheme to convert one chemical species to another across a moving boundary. © 2021, CC BY-SA.

关键词： Advection

来源：评论

学校读者我要写书评

暂无评论

Position: Bayesian deep learning is needed in the age of large-scale AI 24

Position: Bayesian deep learning is needed in the age of lar...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Theodore Papamarkou Maria Skoularidou Konstantina Palla Laurence Aitchison Julyan Arbel David Dunson Maurizio Filippone Vincent Fortuin Philipp Hennig José Miguel Hernández-Lobato Aliaksandr Hubin Alexander Immer Theofanis Karaletsos Mohammad Emtiyaz Khan Agustinus Kristiadi Yingzhen Li Stephan Mandt Christopher Nemeth Michael A. Osborne Tim G. J. Rudner David Rügamer Yee Whye Teh Max Welling Andrew Gordon Wilson Ruqi Zhang Department of Mathematics The University of Manchester Manchester UK Eric and Wendy Schmidt Center Broad Institute of MIT and Harvard Cambridge Spotify London UK Computational Neuroscience Unit University of Bristol Bristol UK Centre Inria de l'Université Grenoble Alpes Grenoble France Department of Statistical Science Duke University Statistics Program KAUST Saudi Arabia Helmholtz AI Munich Germany and Department of Computer Science Technical University of Munich Munich Germany and Munich Center for Machine Learning Munich Germany Tübingen AI Center University of Tübingen Tübingen Germany Department of Engineering University of Cambridge Cambridge UK Department of Mathematics University of Oslo Oslo Norway and Bioinformatics and Applied Statistics Norwegian University of Life Sciences Ås Norway Department of Computer Science ETH Zurich Switzerland Chan Zuckerberg Initiative California Center for Advanced Intelligence Project RIKEN Tokyo Japan Vector Institute Toronto Canada Department of Computing Imperial College London London UK Department of Computer Science UC Irvine Irvine Department of Mathematics and Statistics Lancaster University Lancaster UK Department of Engineering Science University of Oxford Oxford UK Center for Data Science New York University New York Munich Center for Machine Learning Munich Germany and Department of Statistics LMU Munich Munich Germany DeepMind London UK and Department of Statistics University of Oxford Oxford UK Informatics Institute University of Amsterdam Amsterdam Netherlands Courant Institute of Mathematical Sciences and Center for Data Science Computer Science Department New York University New York Department of Computer Science Purdue University West Lafayette

In the current landscape of deep learning research, there is a predominant emphasis on achieving high predictive accuracy in supervised tasks involving large image and language datasets. However, a broader perspective reveals a multitude of overlooked metrics, tasks, and data types, such as uncertainty, active and continual learning, and scientific data, that demand attention. Bayesian deep learning (BDL) constitutes a promising avenue, offering advantages across these diverse settings. This paper posits that BDL can elevate the capabilities of deep learning. It revisits the strengths of BDL, acknowledges existing challenges, and highlights some exciting research avenues aimed at addressing these obstacles. Looking ahead, the discussion focuses on possible ways to combine large-scale foundation models with BDL to unlock their full potential.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Author Correction: Supervised learning of high-confidence phenotypic subpopulations from single-cell data

引用

Nature Machine Intelligence 2023年 676页

作者： Tao Ren Ling-Yun Wu Canping Chen Susan Liu Shunyi Du Zheng Xia Alexey V. Danilov Xiwei Wu Xiangnan Guan Mara H. Sherman Lisa M. Coussens Paul T. Spellman Andrew C. Adey Gordon B. Mills Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing China School of Mathematical Sciences University of Chinese Academy of Sciences Beijing China Computational Biology Program Oregon Health & Science University Portland OR USA Department of Biomedical Engineering Oregon Health & Science University Portland OR USA Knight Cancer Institute Oregon Health & Science University Portland OR USA City of Hope National Medical Center Duarte CA USA Department of Oncology Biomarker Development Genentech Inc South San Francisco CA USA Department of Cell Developmental & Cancer Biology Oregon Health & Science University Portland OR USA Cancer Biology & Genetics Program Memorial Sloan Kettering Cancer Center New York NY USA Department of Molecular and Medical Genetics Oregon Health & Science University Portland OR USA Division of Oncological Sciences Knight Cancer Institute Oregon Health & Science University Portland OR USA

来源：评论

学校读者我要写书评

暂无评论

Deep learning for drug repurposing: methods, databases, and applications

arXiv

引用

arXiv 2022年

作者： Pan, Xiaoqin Lin, Xuan Cao, Dongsheng Zeng, Xiangxiang Yu, Philip S. He, Lifang Nussinov, Ruth Cheng, Feixiong School of Computer Science and Engineering Hunan University China School of Computer Science Xiangtan University China Xiangya School of Pharmaceutical Sciences Central South University China Department of Computer Science University of Illinois at Chicago United States Department of Computer Science and Engineering Lehigh University United States Computational Structural Biology Section Basic Science Program Frederick National Laboratory for Cancer Research National Cancer Institute at Frederick FrederickMD21702 United States Department of Human Molecular Genetics and Biochemistry Sackler School of Medicine Tel Aviv University Tel Aviv69978 Israel Genomic Medicine Institute Lerner Research Institute Cleveland Clinic ClevelandOH44195 United States Department of Molecular Medicine Cleveland Clinic Lerner College of Medicine Case Western Reserve University ClevelandOH44195 United States Case Comprehensive Cancer Center Case Western Reserve University School of Medicine ClevelandOH44106 United States

Drug development is time-consuming and expensive. Repurposing existing drugs for new therapies is an attractive solution that accelerates drug development at reduced experimental costs, specifically for Coronavirus Disease 2019 (COVID-19), an infectious disease caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). However, comprehensively obtaining and productively integrating available knowledge and big biomedical data to effectively advance deep learning models is still challenging for drug repurposing in other complex diseases. In this review, we introduce guidelines on how to utilize deep learning methodologies and tools for drug repurposing. We first summarized the commonly used bioinformatics and pharmacogenomics databases for drug repurposing. Next, we discuss recently developed sequence-based and graph-based representation approaches as well as state-of-the-art deep learning-based methods. Finally, we present applications of drug repurposing to fight the COVID-19 pandemic, and outline its future challenges. © 2022, CC BY-NC-SA.

关键词： Coronavirus

来源：评论

学校读者我要写书评

暂无评论

Correction: Profiling chromatin accessibility in pediatric acute lymphoblastic leukemia identifies subtype-specific chromatin landscapes and gene regulatory networks

引用

Leukemia 2024年第8期38卷 1867页

作者： Jonathan D Diedrich Qian Dong Daniel C Ferguson Brennan P Bergeron Robert J Autry Maoxiang Qian Wenjian Yang Colton Smith James B Papizan Jon P Connelly Kohei Hagiwara Kristine R Crews Shondra M Pruett-Miller Ching-Hon Pui Jun J Yang Mary V Relling William E Evans Daniel Savic Hematological Malignancies Program and Center for Precision Medicine in Leukemia St. Jude Children's Research Hospital Memphis TN USA. Department of Pharmaceutical Sciences St. Jude Children's Research Hospital Memphis TN USA. Graduate School of Biomedical Sciences St. Jude Children's Research Hospital Memphis TN USA. Integrated Biomedical Sciences Program University of Tennessee Health Science Center Memphis TN USA. Department of Cell and Molecular biology and Center for Advanced Genome Engineering St. Jude Children's Research Hospital Memphis TN USA. Department of Computational Biology St. Jude Children's Research Hospital Memphis TN USA. Department of Oncology St. Jude Children's Research Hospital Memphis TN USA. Department of Pathology St. Jude Children's Research Hospital Memphis TN USA. Hematological Malignancies Program and Center for Precision Medicine in Leukemia St. Jude Children's Research Hospital Memphis TN USA. daniel.savic@***. Department of Pharmaceutical Sciences St. Jude Children's Research Hospital Memphis TN USA. daniel.savic@***. Integrated Biomedical Sciences Program University of Tennessee Health Science Center Memphis TN USA. daniel.savic@***.

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：