检索结果-内蒙古大学图书馆

Assessing the Potential of GPT-4 to Annotate Medical Notes Across Different Languages and Countries: A Model Evaluation Study

学校读者我要写书评

暂无评论

SSRN

SSRN 2024年

作者： Saad Menezes, Maria Clara Hoffman, Alexander F. Tan, Amelia L.M. Nalbandyan, Mariné Omenn, Gilbert S. Mazzotti, Diego R. Hernández-Arango, Alejandro Visweswaran, Shyam Venkatesh, Shruthi Mandl, Kenneth D. Bourgeois, Florence T. Lee, James W.K. Makmur, Andrew Hanauer, David A. Semanik, Michael G. Kerivan, Lauren T. Hill, Terra Forero, Julian Restrepo Castro, Carlos Andrés C.R. Vigna, Matteo Ceriana, Piero Abu-El-rub, Noor Avillach, Paul Bellazzi, Riccardo Callaci, Thomas Gutiérrez-Sacristán, Alba Malovini, Alberto Mathew, Jomol P. Morris, Michele Murthy, Venkatesh Parimbelli, Enea Patel, Lav P. Sáez, Carlos Samayamuthu, Malarkodi Jebathilagam Thompson, Jeffrey A. Tibollo, Valentina Xia, Zongqi Kohane, Isaac S. Harvard Medical School Department of Biomedical Informatics 10 Shattuck Street BostonMA02115 United States School of Medicine and Public Health University of Wisconsin-Madison Office of Informatics and Information Technology 750 Highland Ave MadisonWI53705 United States University of Michigan Department of Computational Medicine & Bioinformatics Internal Medicine Human Genetics Environmental Health 100 Washtenaw Avenue Ann ArborMI48109 United States University of Kansas Medical Center Division of Medical Informatics Division of Pulmonary Critical Care and Sleep Medicine Department of Internal Medicine 3901 Rainbow Blvd Kansas CityKS66160 United States University of Antioquia Hospital Alma Máter de Antioquia Department of Internal Medicine Calle 64 N°51 D - 154 Medellín Colombia University of Pittsburgh Department of Biomedical Informatics 5607 Baum Blvd PittsburghPA15206 United States University of Pittsburgh Department of Neurology 3501 5th Avenue PittsburghPA15206 United States Boston Children's Hospital Computational Health Informatics Program 300 Longwood Avenue BostonMA02115 United States Boston Children's Hospital Department of Pediatrics 300 Longwood Avenue BostonMA02115 United States National University Health System Department of Surgery 1E Kent Ridge Rd Singapore119228 Singapore National University Health System Department of Diagnostic Imaging 1E Kent Ridge Rd Singapore119228 Singapore University of Michigan Department of Learning Health Sciences NCRC 100 2800 Plymouth Road Ann ArborMI48109 United States University of Kansas Medical Center Department of Surgery 3901 Rainbow Blvd Kansas CityKS66160 United States Istituti Clinici Scientifici Maugeri IRCCS Respiratory rehabilitation unit Via Maugeri 10 Pavia27100 Italy University of Kansas Medical Center 3901 Rainbow Blvd Kansas CityKS66160 United States University of Pavia Department of Electrical Computer and Biomedical Engineering via Ferrata 5 Pavia2710

Background: Physicians invest hours creating patient notes, which are rich in information but difficult for computers to analyze due to their unstructured format. GPT-4 reshaped our ability to process text, yet it is unknown how well this model can handle medical notes. This project aims to compare GPT-4’s ability to annotate medical notes against experienced physicians across three different languages at multiple institutions and countries. Methods: This study included eight sites from four countries - the United States, Colombia, Singapore, and Italy. Each site contributed seven de-identified notes (admission, progress, or consult) from hospitalized patients. GPT-4 assessed each note by answering 14 questions, including demographic information, clinical judgments, data quality, and patients’ eligibility for a hypothetical study enrollment. For validation, two physicians from each site independently evaluated GPT-4's responses. Findings: Overall, 56 medical notes, written in English, Italian, and Spanish, were analyzed. A total of 784 responses from GPT-4 were generated. Both physicians agreed with GPT-4’s response 79% of the time (622/784, 95%CI 76-82%). Only one of the two physicians agreed with GPT-4’s response 10% of the time (82/784, 95%CI 8-13%). Neither physician agreed with GPT-4’s response 10% of the time (80/784, 95%CI 8-13%). Both physicians agreed with GPT-4 more often in notes written in Spanish and Italian than in English, with agreement rates of 88% (86/98, 95%CI 79-93%), 84% (82/98, 95%CI 75-90%), and 77% (454/588, 95%CI 74-80%), respectively. Hallucinations were rare (10/784, 95%CI 0-2%). GPT-4 correctly selected patients for a hypothetical study enrollment based on three criteria 90% of the time (95%CI 81-98%). Interpretation: The findings indicate that GPT-4 annotations demonstrated a high agreement rate with physicians across all languages. We also demonstrate GPT-4's potential to assist in patient selection for studies. Funding: None. Declarati

关键词： Medical computing

AGlobal benchmark of algorithms for segmentinglate gadolinium-enhanced cardiac magnetic resonance imaging

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Xiong, Zhaohan Xia, Qing Hu, Zhiqiang Huang, Ning Bian, Cheng Zheng, Yefeng Vesal, Sulaiman Ravikumar, Nishant Maier, Andreas Yang, Xin Heng, Pheng-Ann Ni, Dong Li, Caizi Tong, Qianqian Si, Weixin Puybareau, Elodie Khoudli, Younes Géraud, Thierry Chen, Chen Bai, Wenjia Rueckert, Daniel Xu, Lingchao Zhuang, Xiahai Luo, Xinzhe Jia, Shuman Sermesant, Maxime Liu, Yashu Wang, Kuanquan Borra, Davide Masci, Alessandro Corsi, Cristiana De Vente, Coen Veta, Mitko Karim, Rashed Preetha, Chandrakanth Jayachandran Engelhardt, Sandy Qiao, Menyun Wang, Yuanyuan Tao, Qian Nuñez-Garcia, Marta Camara, Oscar Savioli, Nicolo Lamata, Pablo Zhao, Jichao Auckland Bioengineering Institute University of Auckland Auckland New Zealand State Key Lab of Virtual Reality Technology and Systems Beihang University Beijing China School of Electronics Engineering and Computer Science Peking University Beijing China SenseTime Inc Shenzhen China Tencent Jarvis Laboratory Shenzhen China Pattern Recognition Lab Friedrich-Alexander-Universität Erlangen-Nürnberg Erlangen Germany Department of Computer Science and Engineering Chinese University of Hong Kong Hong Kong National-Regional Key Technology Engineering Laboratory for Medical Ultrasound School of Biomedical Engineering Shenzhen University Shenzhen China School of Computer Science Wuhan University Wuhan China Shenzhen Key Laboratory of Virtual Reality and Human Interaction Technology Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen China Epita Research and Development Laboratory Paris France Department of Computing Imperial College London London United Kingdom School of Naval Architecture Shanghai Jiao Tong University Ocean & Civil Engineering Shanghai China School of Data Science Fudan University Shanghai China Epione Research Group Universite Cote d'Azur Inria Sophia Antipolis France Harbin Institute of Technology School of Computer Science and Technology Harbin China Department of Electric University of Bologna Electronic and Information Engineering Cesena Italy Department of Biomedical Engineering Eindhoven University of Technology Eindhoven Netherlands School of Biomedical Engineering and Imaging Sciences Kings College London London United Kingdom Faculty of Electrical Engineering and Information Technology University of Magdeburg Magdeburg Germany Heidelberg University Hospital Germany Biomedical Engineering Center Fudan University Shanghai China Department of Radiology Leiden University Medical Center Leiden Netherlands Department of Information and Communication Technologies Universitat Pompeu Fabra Barcelona Spain D

Segmentation of cardiac images, particularly late gadolinium-enhanced magnetic resonance imaging (LGE-MRI)widely used for visualizing diseased cardiacstructures, is a crucial first step for clinical diagnosis and treatment. However, direct segmentation ofLGE-MRIsischallenging due to *** most clinical studies have relied on manual and labor-intensive approaches, automatic methods are of high interest, particularly optimized machine learning *** address this, we organized the "2018 Left Atrium Segmentation Challenge" using 154 3D LGE-MRIs, currently the world's largest cardiac LGE-MRI dataset, and associated labels of the left atriumsegmented by three medical experts,ultimately attractingthe participation of27 international teams. In this paper, extensive analysis of the submitted algorithms using technical and biological metrics was performed by undergoing subgroup analysis and conducting hyper-parameter analysis,offeringan overall picture ofthe major design choices of convolutional neural networks(CNNs) and practical considerations for achieving state-of-the-art left atrium segmentation. Results show the top methodachieved a dice score of 93.2%and a mean surface to a surface distance of 0.7mm, significantly outperforming prior state-of-the-art. Particularly, our analysisdemonstrated that double, sequentially usedCNNs, in which a first CNN is used for automatic region-of-interestlocalization and a subsequent CNN is used for refinedregional segmentation, achieved far superiorresults than traditional methods and pipelinescontaining *** findings from this study can potentially be extended to other imaging datasets and modalities, having an impact on the wider medical imaging *** large-scale benchmarking study makes a significant step towards much-improved segmentation methods for cardiac LGE-MRIs, and will serveas animportant benchmark for evaluating and comparing the future works in the field. Copyright © 2020, Th

关键词： Magnetic resonance imaging

HMIC: Hierarchical Medical Image Classification, A Deep Learning Approach

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Kowsari, Kamran Sali, Rasoul Ehsan, Lubaina Adorno, William Ali, Asad Moore, Sean Amadi, Beatrice Kelly, Paul Syed, Sana Brown, Donald Department of Systems and Information Engineering University of Virginia CharlottesvilleVA22904 United States CA90095 United States Sensing Systems for Health Lab University of Virginia CharlottesvilleVA22911 United States Department of Pediatrics School of Medicine University of Virginia CharlottesvilleVA22903 United States Department of Paediatrics and Child Health Aga Khan University Karachi74800 Pakistan Tropical Gastroenterology and Nutrition Group University of Zambia School of Medicine Lusak32379 Zambia Blizard Institute Barts and The London School of Medicine Queen Mary University of London LondonE1 4NS United Kingdom School of Data Science University of Virginia CharlottesvilleVA22904 United States

Image classification is central to the big data revolution in medicine. Improved information processing methods for diagnosis and classification of digital medical images have shown to be successful via deep learning approaches. As this field is explored, there are limitations to the performance of traditional supervised classifiers. This paper outlines an approach that is different from the current medical image classification tasks that view the issue as multi-class classification. We performed a hierarchical classification using our Hierarchical Medical Image classification (HMIC) approach. HMIC uses stacks of deep learning models to give particular comprehension at each level of the clinical picture hierarchy. For testing our performance, we use biopsy of the small bowel images that contain three categories in the parent level (Celiac Disease, Environmental Enteropathy, and histologically normal controls). For the child level, Celiac Disease Severity is classified into 4 classes (I, IIIa, IIIb, and IIIC). Copyright © 2020, The Authors. All rights reserved.

关键词： Medical imaging

学校读者我要写书评

暂无评论

INTRODUCTION

Bulletin of the American Meteorological Society 2024年第8期105卷 S1-S11页

作者： Boyer, T. Blunden, J. Dunn, R.J.H. NOAA/NESDIS National Centers for Environmental Information Silver Spring Maryland NOAA/NESDIS National Centers for Environmental Information Asheville North Carolina Met Office Hadley Centre Exeter United Kingdom European Centre for Medium-Range Weather Forecasts Reading United Kingdom University of Maryland College Park Maryland Scripps Institution of Oceanography University of California San Diego La Jolla California NOAA/NWS National Centers for Environmental Prediction Climate Prediction Center College Park Maryland Brandenburg University of Technology (BTU) Cottbus-Senftenberg Germany Servicio Meteorológico Nacional Buenos Aires Argentina NOAA/OAR Physical Sciences Laboratory Boulder Colorado European Centre for Medium-Range Weather Forecasts Bonn Germany Center for Geophysical Research and School of Physics University of Costa Rica San José Costa Rica Department of Meteorology and National Centre for Earth Observation University of Reading Reading United Kingdom Centro Nacional de Monitoramento e Alertas de Desastres Naturais CEMADEN São Paulo Brazil Université Grenoble Alpes Institut des Géosciences de l’Environnement IRD CNRS Grenoble INP Grenoble France Hampton University Hampton Virginia Seychelles Meteorological Authority Mahe Seychelles Section for Glaciers Ice and Snow Norwegian Water Resources and Energy Directorate Oslo Norway National Research Institute for Agriculture Food and Environment (INRAE) CARRTEL Université Savoie Mont Blanc Thonon les Bains France Graduate School of Agriculture Osaka Metropolitan University Sakai Japan Science Faculty Universidad Nacional de Colombia Bogotá Colombia University of Bremen Bremen Germany NOAA Global Monitoring Laboratory Boulder Colorado Servicio Nacional de Meteorología e Hidrología del Perú Lima Perú Centro de Investigaciones sobre Desertificación – Spanish National Research Council (CSIC-UV-GVA) Valencia Spain Hydro-Climate Extremes Lab (H-CEL) Ghent University Ghent Belgium Department o

In 2023, La Niña conditions that generally prevailed in the eastern Pacific Ocean from mid-2020 into early 2023 gave way to a strong El Niño by October. Atmospheric concentrations of Earth’s major greenhouse gases—carbon dioxide, methane, and nitrous oxide—all increased to record-high levels. The annual global average carbon dioxide concentration in the atmosphere rose to 419.3±0.1 ppm, which is 50% greater than the pre-industrial level. The growth from 2022 to 2023 was 2.8 ppm, the fourth highest in the record since the 1960s. The combined short-term effects of El Niño and the long-term effects of increasing levels of heat-trapping gases in the atmosphere contributed to new records for many essential climate variables reported here. The annual global temperature across land and oceans was the highest in records dating as far back as 1850, with the last seven months (June–December) having each been record warm. Over land, the globally averaged temperature was also record high. Dozens of countries reported record or near-record warmth for the year, including China and continental Europe as a whole (warmest on record), India and Russia (second warmest), and Canada (third warmest). Intense and widespread heatwaves were reported around the world. In Vietnam, an all-time national maximum temperature record of 44.2°C was observed at Tuong Duong on 7 May, surpassing the previous record of 43.4°C at Huong Khe on 20 April 2019. In Brazil, the air temperature reached 44.8°C in Araçuaí in Minas Gerais on 20 November, potentially a new national record and 12.8°C above normal. The effect of rising temperatures was apparent in the cryosphere, where snow cover extent by June 2023 was the smallest in the 56-year record for North America and seventh smallest for the Northern Hemisphere overall. Heatwaves contributed to the greatest average mass balance loss for Alpine glaciers around the world since the start of the record in 1970. Due to rapid volume loss beginning in 2021, St. A

关键词：

Spatiotemporal Knowledge Distillation for Efficient Estimation of Aerial Video Saliency

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Li, Jia Fu, Kui Zhao, Shengwei Ge, Shiming State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing100191 China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing100191 China Institute of Information Engineering Chinese Academy of Sciences Beijing100095 China School of Cyber Security at University of Chinese Academy of Sciences Beijing100095 China

—The performance of video saliency estimation techniques has achieved significant advances along with the rapid development of Convolutional Neural Networks (CNNs). However, devices like cameras and drones may have limited computational capability and storage space so that the direct deployment of complex deep saliency models becomes infeasible. To address this problem, this paper proposes a dynamic saliency estimation approach for aerial videos via spatiotemporal knowledge distillation. In this approach, five components are involved, including two teachers, two students and the desired spatiotemporal model. The knowledge of spatial and temporal saliency is first separately transferred from the two complex and redundant teachers to their simple and compact students, and the input scenes are also degraded from high-resolution to low-resolution to remove the probable data redundancy so as to greatly speed up the feature extraction process. After that, the desired spatiotemporal model is further trained by distilling and encoding the spatial and temporal saliency knowledge of two students into a unified network. In this manner, the inter-model redundancy can be further removed for the effective estimation of dynamic saliency on aerial videos. Experimental results show that the proposed approach outperforms ten state-of-the-art models in estimating visual saliency on aerial videos, while its speed reaches up to 28,738 FPS on the GPU platform. Copyright © 2019, The Authors. All rights reserved.

关键词： Students

The XRISM/Resolve View of the Fe K Region of Cyg X-3

学校读者我要写书评

暂无评论

Astrophysical Journal Letters 2024年第2期977卷 L34-L34页

作者： Audard, Marc Awaki, Hisamitsu Ballhausen, Ralf Bamba, Aya Behar, Ehud Boissay-Malaquin, Rozenn Brenneman, Laura Brown, Gregory V. Corrales, Lia Costantini, Elisa Cumbee, Renata Trigo, María Díaz Done, Chris Dotani, Tadayasu Ebisawa, Ken Eckart, Megan E. Eckert, Dominique Eguchi, Satoshi Enoto, Teruaki Ezoe, Yuichiro Foster, Adam Fujimoto, Ryuichi Fujita, Yutaka Fukazawa, Yasushi Fukushima, Kotaro Furuzawa, Akihiro Gallo, Luigi García, Javier A. Gu, Liyi Guainazzi, Matteo Hagino, Kouichi Hamaguchi, Kenji Hatsukade, Isamu Hayashi, Katsuhiro Hayashi, Takayuki Hell, Natalie Hodges-Kluck, Edmund Hornschemeier, Ann Ichinohe, Yuto Ishida, Manabu Ishikawa, Kumi Ishisaki, Yoshitaka Kaastra, Jelle Kallman, Timothy Kara, Erin Katsuda, Satoru Kanemaru, Yoshiaki Kelley, Richard Kilbourne, Caroline Kitamoto, Shunji Kobayashi, Shogo Kohmura, Takayoshi Kubota, Aya Leutenegger, Maurice Loewenstein, Michael Maeda, Yoshitomo Markevitch, Maxim Matsumoto, Hironori Matsushita, Kyoko McCammon, Dan McNamara, Brian Mernier, François Miller, Eric D. Miller, Jon M. Mitsuishi, Ikuyuki Mizumoto, Misaki Mizuno, Tsunefumi Mori, Koji Mukai, Koji Murakami, Hiroshi Mushotzky, Richard Nakajima, Hiroshi Nakazawa, Kazuhiro Ness, Jan-Uwe Nobukawa, Kumiko Nobukawa, Masayoshi Noda, Hirofumi Odaka, Hirokazu Ogawa, Shoji Ogorzalek, Anna Okajima, Takashi Ota, Naomi Paltani, Stephane Petre, Robert Plucinsky, Paul Porter, Frederick S. Pottschmidt, Katja Sato, Kosuke Sato, Toshiki Sawada, Makoto Seta, Hiromi Shidatsu, Megumi Simionescu, Aurora Smith, Randall Suzuki, Hiromasa Szymkowiak, Andrew Takahashi, Hiromitsu Takeo, Mai Tamagawa, Toru Tamura, Keisuke Tanaka, Takaaki Tanimoto, Atsushi Tashiro, Makoto Terada, Yukikatsu Terashima, Yuichi Tsuboi, Yohko Tsujimoto, Masahiro Tsunemi, Hiroshi Tsuru, Takeshi Uchida, Hiroyuki Uchida, Nagomi Uchida, Yuusuke Uchiyama, Hideki Ueda, Yoshihiro Uno, Shinichiro Vink, Jacco Watanabe, Shin Williams, Brian J. Yamada, Satoshi Yamada, Shinya Yamaguchi, Hiroya Yamaoka, Kazutaka Yamasaki, Noriko Yamauchi, Makoto Yamauchi, Shig Department of Astronomy University of Geneva Versoix CH-1290 Switzerland Department of Physics Ehime University Ehime 790-8577 Japan Department of Astronomy University of Maryland College Park 20742 MD United States NASA Goddard Space Flight Center Greenbelt 20771 MD United States Center for Research and Exploration in Space Science and Technology NASA GSFC (CRESST II) Greenbelt 20771 MD United States Department of Physics University of Tokyo Tokyo 113-0033 Japan Department of Physics Technion Technion City Haifa 3200003 Israel Center for Space Sciences and Technology University of Maryland Baltimore County (UMBC) Baltimore 21250 MD United States Center for Astrophysics-Harvard-Smithsonian 02138 MA United States Lawrence Livermore National Laboratory 94550 CA United States Department of Astronomy University of Michigan 48109 MI United States SRON Netherlands Institute for Space Research Leiden Netherlands ESO Karl-Schwarzschild-Strasse 2 Garching bei München 85748 Germany Centre for Extragalactic Astronomy Department of Physics University of Durham South Road Durham DH1 3LE United Kingdom Institute of Space and Astronautical Science (ISAS) Japan Aerospace Exploration Agency (JAXA) Kanagawa 252-5210 Japan Department of Economics Kumamoto Gakuen University Kumamoto 862-8680 Japan Department of Physics Kyoto University Kyoto 606-8502 Japan Department of Physics Tokyo Metropolitan University Tokyo 192-0397 Japan Department of Physics Hiroshima University Hiroshima 739-8526 Japan Department of Physics Fujita Health University Aichi 470-1192 Japan Department of Astronomy and Physics Saint Mary's University B3H 3C3 NS Canada California Institute of Technology Pasadena 91125 CA United States European Space Agency (ESA) European Space Research and Technology Centre (ESTEC) Noordwijk 2200AG Netherlands Faculty of Engineering University of Miyazaki 1-1 Gakuen-Kibanadai-Nishi Miyazaki Miyazaki 889-2192 Japan RIKEN Nishina Ce

The X-ray binary system Cygnus X-3 (4U 2030+40, V1521 Cyg) is luminous but enigmatic owing to the high intervening absorption. High-resolution X-ray spectroscopy uniquely probes the dynamics of the photoionized gas in the system. In this Letter, we report on an observation of Cyg X-3 with the XRISM/Resolve spectrometer, which provides unprecedented spectral resolution and sensitivity in the 2-10 keV band. We detect multiple kinematic and ionization components in absorption and emission whose superposition leads to complex line profiles, including strong P Cygni profiles on resonance lines. The prominent Fe XXV Hea and Fe XXVI Lya emission complexes are clearly resolved into their characteristic fine-structure transitions. Self-consistent photoionization modeling allows us to disentangle the absorption and emission components and measure the Doppler velocity of these components as a function of binary orbital phase. We find a significantly higher velocity amplitude for the emission lines than for the absorption lines. The absorption lines generally appear blueshifted by ∼-500-600 km s^-1. We show that the wind decomposes naturally into a relatively smooth and large-scale component, perhaps associated with the background wind itself, plus a turbulent, denser structure located close to the compact object in its orbit. © 2024. The Author(s). Published by the American Astronomical Society.

关键词： High mass x-ray binary stars High resolution spectroscopy

Proteomics Standards Initiative's ProForma 2.0: Unifying the Encoding of Proteoforms and Peptidoforms

学校读者我要写书评

暂无评论

arXiv 2021年

作者： LeDuc, Richard D. Deutsch, Eric W. Binz, Pierre-Alain Fellers, Ryan T. Cesnik, Anthony J. Klein, Joshua A. Van Den Bossche, Tim Gabriels, Ralf Yalavarthi, Arshika Perez-Riverol, Yasset Carver, Jeremy Bittremieux, Wout Kawano, Shin Pullman, Benjamin Bandeira, Nuno Kelleher, Neil L. Thomas, Paul M. Vizcaíno, Juan Antonio National Resource for Translational and Developmental Proteomics Northwestern University EvanstonIL60611 United States Institute for Systems Biology SeattleWA98109 United States Clinical Chemistry Service Lausanne University Hospital Lausanne1011 Switzerland Department of Genetics Stanford University StanfordCA94305 United States Chan Zuckerberg Biohub 499 Illinois St San FranciscoCA94158 United States SciLifeLab School of Engineering Sciences in Chemistry Biotechnology and Health KTH-Royal Institute of Technology Stockholm 113 51 SolnaSE-171 21 Sweden Program for Bioinformatics Boston University BostonMA02215 United States VIB-UGent Center for Medical Biotechnology VIB Technologiepark 75-FSVM II Ghent9052 Belgium Department of Biomolecular Medicine Faculty of Medicine and Health Sciences Ghent University Ghent9000 Belgium Cambridge HinxtonCB10 1SD United Kingdom La Jolla CA92093 United States La Jolla CA92093 United States La Jolla CA92093 United States Toyama University of International Studies Toyama Higashikuromaki 6 5-1 Toyama930-1292 Japan Database Center for Life Science Joint Support-Center for Data Science Research Research Organization of Information and Systems Chiba Kashiwa277-0871 Japan

It is important for the proteomics community to have a standardized manner to represent all possible variations of a protein or peptide primary sequence, including natural, chemicallyinduced and artifactualmodifications. The Human Proteome Organization (HUPO) Proteomics Standards Initiative (PSI) in collaboration with several members of the Consortium for Top-Down Proteomics (CTDP) has developed a standard notation called ProForma 2.0, which is a substantial extension of the original ProForma notation developed by the CTDP. ProForma 2.0 aims to unify the representation of proteoforms and peptidoforms. ProForma 2.0 supports use cases needed for bottom-up and middle-/top-down proteomics approaches and allows the encoding of highly modified proteins and peptides using a humanand machine-readable string. ProForma 2.0 can be used to represent protein modifications in a specified or ambiguous location, designated by mass shifts, chemical formulas, or controlled vocabulary terms, including cross-links (natural and chemical), and atomic isotopes. Notational conventions are based on public controlled vocabularies and ontologies. The most up-to-date full specification document and information about software implementations are available at http://***/proforma. © 2021, CC0.

关键词： Mass spectrometry

On large-scale dynamic topic modeling with nonnegative CP Tensor Decomposition

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Ahn, Miju Eikmeier, Nicole Haddock, Jamie Kassab, Lara Kryshchenko, Alona Leonard, Kathryn Needell, Deanna Madushani, R.W.M.A. Sizikova, Elena Wang, Chuntian Department of Engineering Management Information and Systems Southern Methodist University DallasTX75205 United States Department of Computer Science Grinnell College GrinnellIA50112 United States Department of Mathematics University of California Los AngelesCA90095-1555 United States Department of Mathematics Colorado State University Fort CollinsCO80523 United States Department of Mathematics California State University Channel Islands CamarilloCA93012 United States Department of Computer Science Occidental College Los AngelesCA90041 United States Section of Infectious Diseases Boston Medical Center MA02118 United States Center for Data Science New York University New YorkNY10011 United States Department of Mathematics University of Alabama TuscaloosaAL35487 United States

There is currently an unprecedented demand for large-scale temporal data analysis due to the explosive growth of data. Dynamic topic modeling has been widely used in social and data sciences with the goal of learning latent topics that emerge, evolve, and fade over time. Previous work on dynamic topic modeling primarily employ the method of nonnegative matrix factorization (NMF), where slices of the data tensor are each factorized into the product of lower-dimensional nonnegative matrices. With this approach, however, information contained in the temporal dimension of the data is often neglected or underutilized. To overcome this issue, we propose instead adopting the method of nonnegative CANDECOMP/PARAPAC (CP) tensor decomposition (NNCPD), where the data tensor is directly decomposed into a minimal sum of outer products of nonnegative vectors, thereby preserving the temporal information. The viability of NNCPD is demonstrated through application to both synthetic and real data, where significantly improved results are obtained compared to those of typical NMF-based methods. The advantages of NNCPD over such approaches are studied and discussed. To the best of our knowledge, this is the first time that NNCPD has been utilized for the purpose of dynamic topic modeling, and our findings will be transformative for both applications and further developments. Copyright © 2020, The Authors. All rights reserved.

关键词： Tensors

Mutual clustering on comparative texts via heterogeneous information networks

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Cao, Jianping Wang, Senzhang Wen, Danyan Peng, Zhaohui Yu, Philip S. Wang, Fei-yue Research Center for Military Computational Experiments and Parallel Systems Technology National University of Defense Technology Changsha410073 China Ministry of Industry and Information Technology Nanjing211106 China School of Economics & Management Nanjing University of Science and Technology Nanjing210094 China School of Computer Science and Technology Shandong University Qingdao China Department of Computer Science University of Illinois at Chicago Chicago60607 United States Institute for Data Science Tsinghua University Beijing100084 China Beijing China Qingdao Academy of Intelligent Industries Qingdao266000 China Institute of Systems Engineering Macau University of Science and Technology Macau999078 China

Currently, many intelligence systems contain the texts from multi-sources, e.g., bulletin board system (BBS) posts, tweets and news. These texts can be "comparative" since they may be semantically correlated and thus provide us with different perspectives toward the same topics or events. To better organize the multi-sourced texts and obtain more comprehensive knowledge, we propose to study the novel problem of Mutual Clustering on Comparative Texts (MCCT), which aims to cluster the comparative texts simultaneously and collaboratively. The MCCT problem is difficult to address because 1) comparative texts usually present different data formats and structures and thus they are hard to organize, and 2) there lacks an effective method to connect the semantically correlated comparative texts to facilitate clustering them in an unified way. To this aim, in this paper we propose a Heterogeneous information Network-based Text clustering framework HINT. HINT first models multi-sourced texts (e.g. news and tweets) as heterogeneous information networks by introducing the shared "anchor texts" to connect the comparative texts. Next, two similarity matrices based on HINT as well as a transition matrix for cross-text-source knowledge transfer are constructed. Comparative texts clustering are then conducted by utilizing the constructed matrices. Finally, a mutual clustering algorithm is also proposed to further unify the separate clustering results of the comparative texts by introducing a clustering consistency constraint. We conduct extensive experimental on three tweets-news datasets, and the results demonstrate the effectiveness and robustness of the proposed method in addressing the MCCT problem. Copyright © 2019, The Authors. All rights reserved.

关键词： Clustering algorithms