检索结果-内蒙古大学图书馆

32nd IEEE International Symposium on Computer-Based Medical Systems (IEEE CBMS)

作者： Schwertner, M. A. Rigo, S. J. Araujo, D. A. Silva, A. B. Eskofier, B. Univ Vale Rio Sinos UNISINOS Appl Comp Grad Program Sao Leopoldo Brazil FAU Erlangen Nurnberg Dept Comp Sci Machine Learning & Data Analyt Lab Erlangen Germany

ISBN: (纸本)9781728122861

This paper presents an approach for natural language question answering over a knowledge base generated by a medical texts information extraction process. The primary objective is to present a solution to help practitioners in oncology healthcare clinical environment with an intuitive method to access stored data. We identify health professional's needs in terms of information and interface with EHR systems. After that, we demonstrate a proposal to allow the integration of information extraction from clinical notes, knowledge base generation, and natural language question answering. The primary contributions are the identification of a solution to health professionals needs regarding usability in information access, and the demonstration of advantages obtained in representing health contents in a knowledge base.

关键词： Information Extraction Question Answering Clinical systems Oncology EHR

来源：评论

学校读者我要写书评

暂无评论

Helical structure motifs made searchable for functional peptide design

引用

NATURE COMMUNICATIONS 2022年第1期13卷 102-102页

作者： Tsai, Cheng-Yu Salawu, Emmanuel Oluwatobi Li, Hongchun Lin, Guan-Yu Kuo, Ting-Yu Voon, Liyin Sharma, Adarsh Hu, Kai-Di Cheng, Yi-Yun Sahoo, Sobha Stuart, Lutimba Chen, Chih-Wei Chang, Yuan-Yu Lu, Yu-Lin Ke, Simai Ortiz, Christopher Llynard D. Fang, Bai-Shan Wu, Chen-Chi Lan, Chung-Yu Fu, Hua-Wen Yang, Lee-Wei Natl Tsing Hua Univ Inst Bioinformat & Struct Biol Hsinchu 300044 Taiwan Natl Taiwan Univ Grad Inst Med Genom & Prote Coll Med Taipei 100025 Taiwan Natl Taiwan Univ Hosp Dept Otolaryngol Taipei 100225 Taiwan Acad Sinica Inst Informat Sci Bioinformat Program Taipei 115201 Taiwan Amazon Web Serv AWS Machine Learning Solut Lab Herndon VA USA Chinese Acad Sci Shenzhen Inst Adv Technol Res Ctr Comp Aided Drug Discovery Shenzhen 518055 Peoples R China Xiamen Univ Coll Chem & Chem Engn Xiamen 361005 Peoples R China Univ Pittsburgh Sch Med Dept Computat & Syst Biol Pittsburgh PA 15213 USA Natl Tsing Hua Univ Inst Mol & Cellular Biol Hsinchu 300044 Taiwan Praexisio Taiwan Inc New Taipei 221425 Taiwan Acad Sinica Inst Biol Chem Chem Biol & Mol Biophys Program Taipei 115201 Taiwan Natl Tsing Hua Univ Dept Chem Hsinchu 300044 Taiwan Xiamen Univ Key Lab Synthet Biotechnol Xiamen City Key Lab Chem Biol Fujian Prov Xiamen 361005 Peoples R China Natl Taiwan Univ Hosp Dept Med Res Hsin Chu Branch Hsinchu 302058 Taiwan Natl Tsing Hua Univ Dept Life Sci Hsinchu 300044 Taiwan Natl Ctr Theoret Sci Div Phys Taipei 106319 Taiwan Natl Tsing Hua Univ PhD Program Biomed Artificial Intelligence Hsinchu 300044 Taiwan

The systematic design of functional peptides has technological and therapeutic applications. However, there is a need for pattern-based search engines that help locate desired functional motifs in primary sequences regardless of their evolutionary conservation. Existing databases such as The Protein Secondary Structure database (PSS) no longer serves the community, while the Dictionary of Protein Secondary Structure (DSSP) annotates the secondary structures when tertiary structures of proteins are provided. Here, we extract 1.7 million helices from the PDB and compile them into a database (Therapeutic Peptide Design database;TP-DB) that allows queries of compounded patterns to facilitate the identification of sequence motifs of helical structures. We show how TP-DB helps us identify a known purification-tag-specific antibody that can be repurposed into a diagnostic kit for Helicobacter pylori. We also show how the database can be used to design a new antimicrobial peptide that shows better Candida albicans clearance and lower hemolysis than its template homologs. Finally, we demonstrate how TP-DB can suggest point mutations in helical peptide blockers to prevent a targeted tumorigenic protein-protein interaction. TP-DB is made available at http://***/design/.

关键词： Protein databases Protein design Protein function predictions Sequence annotation Peptides

来源：评论

学校读者我要写书评

暂无评论

learning the protein language: Evolution, structure, and function

引用

CELL SYSTEMS 2021年第6期12卷 654-+页

作者： Bepler, Tristan Berger, Bonnie New York Struct Biol Ctr Simons Machine Learning Ctr New York NY 10027 USA MIT Comp Sci & Artificial Intelligence Lab 77 Massachusetts Ave Cambridge MA 02139 USA MIT Computat & Syst Biol Program 77 Massachusetts Ave Cambridge MA 02139 USA MIT Dept Math Cambridge MA 02139 USA

Language models have recently emerged as a powerful machine-learning approach for distilling information from massive protein sequence databases. From readily available sequence data alone, these models discover evolutionary, structural, and functional organization across protein space. Using language models, we can encode amino-acid sequences into distributed vector representations that capture their structural and functional properties, as well as evaluate the evolutionary fitness of sequence variants. We discuss recent advances in protein language modeling and their applications to downstream protein property prediction problems. We then consider how these models can be enriched with prior biological knowledge and introduce an approach for encoding protein structural knowledge into the learned representations. The knowledge distilled by these models allows us to improve downstream function prediction through transfer learning. Deep protein language models are revolutionizing protein biology. They suggest new ways to approach protein and therapeutic design. However, further developments are needed to encode strong biological priors into protein language models and to increase their accessibility to the broader community.

关键词： proteins protein sequences natural language processing language models deep neural networks inductive bias transfer learning contact prediction transmembrane region prediction

来源：评论

学校读者我要写书评

暂无评论

Lyra: An Efficient and Expressive Subquadratic Architecture for Modeling Biological Sequences

arXiv

引用

arXiv 2025年

作者： Ramesh, Krithik Siddiqui, Sameed M. Gu, Albert Mitzenmacher, Michael D. Sabeti, Pardis C. Broad Institute of MIT and Harvard CambridgeMA02142 United States Massachusetts Institute of Technology CambridgeMA02139 United States Computational and Systems Biology Program Massachusetts Institute of Technology CambridgeMA02139 United States Machine Learning Department Carnegie Mellon University PittsburgPA15213 United States School of Engineering and Applied Sciences Harvard University CambridgeMA02138 United States Department of Organismic and Evolutionary Biology Harvard University CambridgeMA02138 United States Department of Immunology and Infectious Diseases Harvard T.H. Chan School of Public Health Harvard University BostonMA02115 United States Howard Hughes Medical Institute Chevy ChaseMD20815 United States

Deep learning architectures such as convolutional neural networks and Transformers have revolutionized biological sequence modeling, with recent advances driven by scaling up foundation and task-specific models. The computational resources and large datasets required, however, limit their applicability in biological contexts. We introduce Lyra, a subquadratic architecture for sequence modeling, grounded in the biological framework of epistasis for understanding sequence-to-function relationships. Mathematically, we demonstrate that state space models efficiently capture global epistatic interactions and combine them with projected gated convolutions for modeling local relationships. We demonstrate that Lyra is performant across over 100 wide-ranging biological tasks, achieving state-of-the-art (SOTA) performance in many key areas, including protein fitness landscape prediction, biophysical property prediction (e.g. disordered protein region functions) peptide engineering applications (e.g. antibody binding, cell-penetrating peptide prediction), RNA structure analysis, RNA function prediction, and CRISPR guide design. It achieves this with orders-of-magnitude improvements in inference speed and reduction in parameters (up to 120,000-fold in our tests) compared to recent biology foundation models. Using Lyra, we were able to train and run every task in this study on two or fewer GPUs in under two hours, democratizing access to biological sequence modeling at SOTA performance, with potential applications to many fields. © 2025, CC BY-NC-ND.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

An engineered protein-phosphorylation toggle network with implications for endogenous network discovery

引用

SCIENCE 2021年第6550期373卷 0780-0780页

作者： Mishra, Deepak Bepler, Tristan Teague, Brian Berger, Bonnie Broach, Jim Weiss, Ron MIT Dept Biol Engn 77 Massachusetts Ave Cambridge MA 02139 USA MIT Synthet Biol Ctr 77 Massachusetts Ave Cambridge MA 02139 USA MIT Comp Sci & Artificial Intelligence Lab 77 Massachusetts Ave Cambridge MA 02139 USA MIT Computat & Syst Biol Grad Program 77 Massachusetts Ave Cambridge MA 02139 USA New York Struct Biol Ctr Simons Machine Learning Ctr New York NY USA Univ Wisconsin Dept Biol Stout WI USA MIT Dept Math Cambridge MA 02139 USA Penn State Coll Med Dept Biochem & Mol Biol Hershey PA USA MIT Dept Elect Engn & Comp Sci Cambridge MA 02139 USA

Synthetic biological networks comprising fast, reversible reactions could enable engineering of new cellular behaviors that are not possible with slower regulation. Here, we created a bistable toggle switch in Saccharomyces cerevisiae using a cross-repression topology comprising 11 protein-protein phosphorylation elements. The toggle is ultrasensitive, can be induced to switch states in seconds, and exhibits long-term bistability. Motivated by our toggle's architecture and size, we developed a computational framework to search endogenous protein pathways for other large and similar bistable networks. Our framework helped us to identify and experimentally verify five formerly unreported endogenous networks that exhibit bistability. Building synthetic protein-protein networks will enable bioengineers to design fast sensing and processing systems, allow sophisticated regulation of cellular processes, and aid discovery of endogenous networks with particular functions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Importance of Wearable Health Monitoring Systems Using IoMT;Requirements, Advantages, Disadvantages and Challenges

Importance of Wearable Health Monitoring Systems Using IoMT;...

引用

International Symposium on Computational Intelligence and Informatics

作者： Fahime Khozeimeh Mohamad Roshanzamir Afshin Shoeibi Mohammad Tayarani Darbandy Roohallah Alizadehsani Hamid Alinejad-Rokny Davood Ahmadian Abbas Khosravi Saeid Nahavandi Institute for Intelligent Systems Research and Innovation (IISRI) Deakin University Victoria Australia Department of Computer Engineering Fasa University Fasa Iran Internship in Health Data Analytics Program AI-enabled Processes (AIP) Research Centre Macquarie University Sydney Australia School of Architecture Islamic Azad University Taft Taft Iran BioMedical Machine Learning Lab The Graduate School of Biomedical Engineering UNSW Sydney Sydney NSW Australia Faculty of Mathematics Statistics and Computer Sciences University of Tabriz Tabriz Iran

ISBN: (纸本)9798350398830

Providing better quality of service is one of the most important goals in medical/healthcare systems. The services provided should have features such as low latency, appropriate geographic distribution, and real-time interaction. Internet of Medical Things (IoMT) technology is one of the solutions to achieve high quality of services with these features. The wearable health monitoring systems which have become popular in the last decade are one of the foundations of achievement to these features. In this paper, the importance of wearable devices under IoMT technology is investigated. There are several reasons for using wearable devices under IoMT technology, such as reducing healthcare costs and long waiting times. Therefore, anyone working on wearable devices needs to have a general understanding of how they are designed and function. In fact, the integration of new devices to monitor and alert patients about their physical health is a promising option for improving health care systems around the world. Overcrowding in medical centers will be prevented by upgrading the facilities for the virtual presence of patients. It can also ensure real-time monitoring and reduce operating costs. In addition, it can accelerate treatment of patients and reduce the cost of investment and increase its coverage.

关键词： Costs Medical devices Wearable computers Quality of service Organizations Real-time systems Security

来源：评论

学校读者我要写书评

暂无评论

Cross-population coupling of neural activity based on Gaussian process current source densities

引用

PLOS COMPUTATIONAL BIOLOGY 2021年第11期17卷 e1009601-e1009601页

作者： Klein, Natalie Siegle, Joshua H. Teichert, Tobias Kass, Robert E. Carnegie Mellon Univ Dept Stat & Data Sci Pittsburgh PA 15213 USA Carnegie Mellon Univ Machine Learning Dept Pittsburgh PA 15213 USA Allen Inst MindScope Program Washington DC USA Univ Pittsburgh Dept Psychiat Pittsburgh PA USA Carnegie Mellon Univ Neurosci Inst Pittsburgh PA 15213 USA Los Alamos Natl Lab Stat Sci Grp Los Alamos NM 87544 USA

Author summaryTo better understand information processing in the brain, it is important to identify situations in which neural activity is coordinated across populations of neurons, including those in distinct layers of the cortex. Bulk population activity results in voltage changes across extracellular electrodes, but in raw form such voltage recordings can be hard to analyze and interpret. In this paper, we develop a novel framework for locating the sources of currents that produce the measured voltages, and decomposing those currents into interpretable components. We use this flexible framework to develop statistical methods of analysis, and we show that our methodology can be more effective than existing techniques for current source localization. We apply the method to extracellular recordings in two contexts: primate auditory cortex in response to tone stimuli, and mouse visual cortex in response to visual stimuli. In both cases, we get results that are useful for understanding cross-population activity while being difficult or impossible to obtain using the raw voltage signals. We thereby demonstrate the broad utility of our approach for identifying coordinated neural activity based on extracellular voltage recordings. Because local field potentials (LFPs) arise from multiple sources in different spatial locations, they do not easily reveal coordinated activity across neural populations on a trial-to-trial basis. As we show here, however, once disparate source signals are decoupled, their trial-to-trial fluctuations become more accessible, and cross-population correlations become more apparent. To decouple sources we introduce a general framework for estimation of current source densities (CSDs). In this framework, the set of LFPs result from noise being added to the transform of the CSD by a biophysical forward model, while the CSD is considered to be the sum of a zero-mean, stationary, spatiotemporal Gaussian process, having fast and slow components, and a

关键词： Covariance Graphs Auditory cortex Bandpass filters Vision Electrode recording Visual cortex White noise

来源：评论

学校读者我要写书评

暂无评论

Minimally instrumented SHERLOCK (miSHERLOCK) for CRISPR-based point-of-care diagnosis of SARS-CoV-2 and emerging variants

引用

SCIENCE ADVANCES 2021年第32期7卷 2944-2944页

作者： de Puig, Helena Lee, Rose A. Najjar, Devora Tan, Xiao Soekensen, Luis R. Angenent-Mari, Nicolaas M. Donghia, Nina M. Weckman, Nicole E. Ory, Audrey Ng, Carlos F. Nguyen, Peter Q. Mao, Angelo S. Ferrante, Thomas C. Lansberry, Geoffrey Sallum, Hani Niemi, James Collins, James J. Harvard Univ Wyss Inst Biol Inspired Engn Boston MA 02115 USA MIT Dept Biol Engn Inst Med Engn & Sci 77 Massachusetts Ave Cambridge MA 02139 USA Broad Inst MIT & Harvard Infect Dis & Microbiome Program Cambridge MA 02142 USA Boston Childrens Hosp Dept Pediat Div Infect Dis Boston MA 02115 USA Beth Israel Deaconess Med Ctr Dept Med Div Infect Dis Boston MA 02215 USA Harvard Med Sch Boston MA 02115 USA MIT Media Lab Cambridge MA 02139 USA Massachusetts Gen Hosp Div Gastroenterol Boston MA 02114 USA MIT Abdul Latif Jameel Clin Machine Learning Hlth 77 Massachusetts Ave Cambridge MA 02139 USA Harvard Univ Coll Arts & Sci Cambridge MA 02138 USA MIT Synthet Biol Ctr 77 Massachusetts Ave Cambridge MA 02139 USA MIT Harvard MIT Program Hlth Sci & Technol 77 Massachusetts Ave Cambridge MA 02139 USA

The COVID-19 pandemic highlights the need for diagnostics that can be rapidly adapted and deployed in a variety of settings. Several SARS-CoV-2 variants have shown worrisome effects on vaccine and treatment efficacy, but no current point-of-care (POC) testing modality allows their specific identification. We have developed miSHERLOCK, a low-cost, CRISPR-based POC diagnostic platform that takes unprocessed patient saliva;extracts, purifies, and concentrates viral RNA;performs amplification and detection reactions;and provides fluorescent visual output with only three user actions and 1 hour from sample input to answer out. miSHERLOCK achieves highly sensitive multiplexed detection of SARS-CoV-2 and mutations associated with variants B.1.1.7, B.1.351, and P.1. Our modular system enables easy exchange of assays to address diverse user needs and can be rapidly reconfigured to detect different viruses and variants of concern. An adjunctive smartphone application enables output quantification, automated interpretation, and the possibility of remote, distributed result reporting.

关键词： Coronavirus

来源：评论

学校读者我要写书评

暂无评论

DARPA's Role in machine learning

引用

AI MAGAZINE 2020年第2期41卷 36-48页

作者： Alspector, Joshua Dietterich, Thomas G. Bell Labs 600 Mt Ave Murray Hill NJ 07974 USA BELLCORE Piscataway NJ 08854 USA Univ Colorado Colorado Springs CO 80907 USA DARPA DL Program Arlington VA USA Inst Def Anal Alexandria VA 22311 USA DARPA Arlington VA 22203 USA Oregon State Univ Comp Sci Corvallis OR 97331 USA Int Machine Learning Soc Montreal PQ Canada Assoc Adv Artificial Intelligence Menlo Pk CA USA DARPA Informat Sci & Technol Study Grp Steering Comm Arlington VA USA

machine learning methods provide a way for artificial intelligence systems to learn from experience. This article describes four threads of machine learning research supported and guided by the Defense Advanced Research Projects Agency - probabilistic modeling for speech recognition, probabilistic relational models, the integration of multiple machine learning approaches into a task-specific system, and neural network technology. These threads illustrate the Defense Advanced Research Projects Agency way of creating timely advances in a field.

关键词： machine learning Relational model DARPA Neural network

来源：评论

学校读者我要写书评

暂无评论

Bridging the gap: Towards an expanded toolkit for AI-driven decision-making in the public sector

引用

GOVERNMENT INFORMATION QUARTERLY 2024年第4期41卷

作者： Fischer-Abaigar, Unai Kern, Christoph Barda, Noam Kreuter, Frauke Ludwig Maximilians Univ Munchen Dept Stat Ludwigstr 33 D-80539 Munich Germany Ludwig Maximilians Univ Munchen Munich Ctr Machine Learning Geschwister Scholl Pl 1 Munich Germany Univ Maryland Joint Program Survey Methodol 1218 LeFrak Hall 7251 Preinkert Dr College Pk MD 20742 USA Ben Gurion Univ Negev Dept Software & Informat Syst Engn 1 Ben Gurion Ave IL-8410501 Beer Sheva Israel Ben Gurion Univ Negev Dept Epidemiol Biostat & Community Hlth Sci 1 Ben Gurion Ave IL-8410501 Beer Sheva Israel

AI-driven decision-making systems are becoming instrumental in the public sector, with applications spanning areas like criminal justice, social welfare, financial fraud detection, and public health. While these systems offer great potential benefits to institutional decision-making processes, such as improved efficiency and reliability, these systems face the challenge of aligning machine learning (ML) models with the complex realities of public sector decision-making. In this paper, we examine five key challenges where misalignment can occur, including distribution shifts, label bias, the influence of past decision-making on the data side, as well as competing objectives and human-in-the-loop on the model output side. Our findings suggest that standard ML methods often rely on assumptions that do not fully account for these complexities, potentially leading to unreliable and harmful predictions. To address this, we propose a shift in modeling efforts from focusing solely on predictive accuracy to improving decision-making outcomes. We offer guidance for selecting appropriate modeling frameworks, including counterfactual prediction and policy learning, by considering how the model estimand connects to the decision-maker's utility. Additionally, we outline technical methods that address specific challenges within each modeling approach. Finally, we argue for the importance of external input from domain experts and stakeholders to ensure that model assumptions and design choices align with real-world policy objectives, taking a step towards harmonizing AI and public sector objectives.

关键词： Automated decision-making Reliable artificial intelligence Public policy Causal machine learning

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：