检索结果-内蒙古大学图书馆

Perspectives of Earth and Space Scientists 2024年第1期5卷

作者： Sophie Goliber Jason Coenen Heather Fair Angela R. Szesciorka Kirstin Schulz David J. Harning Benjamin Fernando Stanislav Saas Ksenofontov Astrid Pacini Marisol Juarez Rivera Radiance Calmer John A. Conroy Eva Lisa Doting Marie Bergelin Devon Dunmire Maria Luisa Sánchez Montes Alexandra M. Ravelo Anne Sledd Taylor R. Stinchcomb Emily J. Tibbett Mariama C. Dryák-Vallies The State University of New York at Buffalo Buffalo NY USA Department of Earth and Atmospheric Sciences University of Nebraska-Lincoln Lincoln NE USA Department of Plant and Microbial Biology University of Minnesota Saint Paul MN USA Marine Mammal Institute Hatfield Marine Science Center Oregon State University Newport OR USA Oden Institute for Computational Engineering and Sciences The University of Texas at Austin Austin TX USA Institute of Arctic and Alpine Research University of Colorado Boulder Boulder CO USA Johns Hopkins University Baltimore MD USA ARCTICenter University of Northern Iowa Cedar Falls IA USA Applied Physics Laboratory Polar Science Center University of Washington Seattle WA USA University of New Mexico Albuquerque NM USA Cooperative Institute for Research in Environmental Sciences University of Colorado Boulder CO USA Ocean Sciences Department University of California Santa Cruz Santa Cruz CA USA Department of Earth and Environmental Science University of Pennsylvania Philadelphia PA USA Berkeley Geochronology Center Berkeley CA USA Department of Earth and Environmental Sciences KU Leuven Heverlee Belgium International Arctic Research Center University of Alaska Fairbanks Fairbanks AK USA National Oceanic and Atmospheric Administration Physical Sciences Laboratory Boulder CO USA Wildlife Conservation Society Arctic-Beringia Program Fairbanks AK USA University of Massachusetts Amherst Amherst MA USA Polar Science Early Career Community Office University of Colorado Boulder Boulder CO USA

In 2023, the first Polar Postdoc Leadership Workshop convened to discuss present and future polar science issues and to develop leadership skills. The workshop discussions fostered a collective commitment to inclusive leadership within the polar science community among all participants. Here, we outline challenges encountered by underrepresented groups in polar sciences, while also noting that progress has been made to improve inclusivity in the field. Further, we highlight the inclusive leadership principles identified by workshop participants to bring to the polar community as we transition into leadership roles. Finally, insights and practical knowledge we gained from the workshop are shared, aiming to inform the community of our commitment to inclusive leadership and encourage the polar community to join us in pursuing action toward our shared vision for a more welcoming polar science future. As a small community of postdoctoral researchers, we outline the leadership skills envisioned for an inclusive future in polar sciences Our vision is to increase the success of underrepresented individuals as leaders by creating a welcoming and supportive career environment Group norms and leadership skills focused on emotional intelligence are critical to equity and inclusion in polar sciences

关键词：

来源：评论

学校读者我要写书评

暂无评论

Pretreatment Chemometrics in Holistic Biogas Life Cycle Assessment: Framing Case Study with Carica papaya

引用

Waste and Biomass Valorization 2018年 1-14页

作者： Jensen, Cory D. Olugbemide, A.D. Akpa, F.A.O. Oladipo, Ajayi College of Engineering and Computational Sciences Colorado School of Mines GoldenCO United States Division of Liberal Arts and International Studies Joint Policy Program with the University of Colorado Colorado School of Mines GoldenCO United States Auchi Polytechnic AuchiEdo State Nigeria Department of Basic Sciences Auchi Polytechnic AuchiEdo State Nigeria Department of Science Laboratory Technology Auchi Polytechnic AuchiEdo State Nigeria Department of Agricultural and Bio-Environmental Engineering Auchi Polytechnic AuchiEdo State Nigeria

This research explores synergistic pre-treatment parameters and chemometrics as applicable to systems level biogas related research frameworks (such as the sustainable development goals) for anaerobic digestion biomass processes-policy. Specifically, the hypothesis that simple feedstock pretreatment-digestion methods can be applied to rapidly evaluate biochemical-biogas potential of anaerobically digested Carica papaya petioles was tested. Pretreatment parameters explored include hydration, i.e. 1:4, 1:6, 1:8 and 1:10 substrate mass to water weight ratios and hydrochloric acid pretreatment chemistry, i.e. 1%—0.3 M, 3%—0.7 M, 5%—1.0 M, in batch digestions experiments with non-inoculated C. papaya petioles. Biomass feedstock was obtained from Edo State, Nigeria. Digestions were performed at ambient temperature, i.e. 27 °C, for 3 weeks. Pretreated C. papaya petiole samples were analyzed with Fourier transform infrared spectroscopy to characterize spectra with characteristic absorbance ratios indicative of physicochemical changes in biomass that include;cross-linked lignin ratio, the lateral order index, and hydrogen bond intensity. Cumulative gaseous yields from C. papaya petiole digestions were fit to the modified Gompertz form and optimized with non-linear regression in Matlab® to derive mathematical parameters, i.e. daily maximum production rate of biogas, a lag phase prior to biogas production, and biogas potential. An optimum C. papaya petiole pretreatment digestion scenario, i.e. 1:4 substrate-to-water ratio and 3%, i.e. 0.7 M, HCl pretreatment resulted in a 150% increase in yield, (10.9 mL gas/g VS) compared to non-pretreated C. papaya petiole digestion. Analysis with the modified Gompertz form also suggests rapid biogas potential assessment can be performed in a few days-time, i.e. approximately 10 days with distinct visual characterization of individual digestion performance. It was concluded that the applied digestion procedures with the use of C. papaya peti

关键词： Anaerobic digestion

来源：评论

学校读者我要写书评

暂无评论

Integrating yeast chemical genomics and mammalian cell pathway analysis

引用

中国药理学报（英文版） 2019年第9期40卷 1245-1255页

作者： Fu-lai Zhou Sheena C Li Yue Zhu Wan-jing Guo Li-jun Shao Justin Nelson Scott Simpkins De-hua Yang Qing Liu Yoko Yashiroda Jin-biao Xu Yao-yue Fan Jian-min Yue Minoru Yoshida Tian Xia Chad L Myers Charles Boone Ming-wei Wang The National Center for Drug Screening and the CAS Key Laboratory of Receptor Research Shanghai Institute of Materia MedicaChinese Academy of Sciences(CAS)Shanghai 201203China University of Chinese Academy of Sciences Beijing 100049China RIKEN Center for Sustainable Resource Science WakoSaitama 3510198Japan Bioinformatics and Computational Biology Program University of Minnesota-Twin CitiesMinneapolisMinnesota 55455USA The National Center for Drug Screening and the CAS Key Laboratory of Receptor Research Shanghai Institute of Materia MedicaChinese Academy of Sciences(CAS)Shanghai 201203China The State Key Laboratory of Drug Research Shanghai Institute of Materia MedicaChinese Academy of SciencesShanghai 201203China RIKEN Center for Sustainable Resource Science WakoSaitama 3510198Japan Department of Biology The University of TokyoBunkyo-kuTokyo 1138657Japan Collaborative Research for Innovative Microbiology The University of TokyoBunkyo-kuTokyo 1138657Japan Department of Electronics and Information Engineering Huazhong University of Science and TechnologyWuhan 430074China RIKEN Center for Sustainable Resource Science WakoSaitama 3510198Japan Donnelly Centre and Department of Molecular Genetics University of TorontoOntario M5S 3E1Canada

Chemical genomics has been applied extensively to evaluate small molecules that modulate biological processes in Saccharomyces ***,we use yeast as a surrogate system for studying compounds that are active against metazoan ***-scale chemical-genetic profiling of thousands of synthetic and natural compounds from the Chinese National Compound Library identified those with high-confidence bioprocess target *** discover compounds that have the potential to function like therapeutic agents with known targets,we also analyzed a reference library of approved *** uncharacterized compounds with chemical-genetic profiles resembling existing drugs that modulate autophagy and Wnt/β-catenin signal transduction were further examined in mammalian cells,and new modulators with specific modes of action were *** analysis exploits yeast as a general platform for predicting compound bioactivity in mammalian cells.

关键词： yeast chemical genomics tubulin cytoskeleton assembly autophagy Wnt/β-catenin signaling pathway

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 25 M☉

arXiv

引用

arXiv 2022年

作者： Mezzacappa, Anthony Marronetti, Pedro Landfield, Ryan E. Lentz, Eric J. Hix, W. Raphael Harris, J. Austin Bruenn, Stephen W. Blondin, John M. Messer, O.E. Bronson Casanova, Jordi Kronzer, Luke L. Department of Physics and Astronomy University of Tennessee 1408 Circle Drive KnoxvilleTN37996-1200 United States Physics Division National Science Foundation AlexandriaVA22314 United States National Center for Computational Sciences Oak Ridge National Laboratory P.O. Box 2008 Oak RidgeTN37831-6164 United States Physics Division Oak Ridge National Laboratory P.O. Box 2008 Oak RidgeTN37831-6354 United States Joint Institute for Nuclear Physics and its Applications Oak Ridge National Laboratory P.O. Box 2008 Oak RidgeTN37831-6374 United States Department of Physics Florida Atlantic University 777 Glades Road Boca RatonFL33431-0991 United States Department of Physics North Carolina State University RaleighNC27695-8202 United States Physics Program Community College of Denver P.O. Box 173363 DenverCO80217-3363 United States Department of Aerospace Engineering and Mechanics University of Alabama Box 870280 TuscaloosaAL35487-0280 United States

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 25 M☉ , are all initially non-rotating, 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, 9.6 M☉ progenitor model is distinct from the temporal evolution of our Solar metallicity, 15 M☉ progenitor model and our zero metallicity, 25 M☉ 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. Nonetheless, the physical origin of the high-frequency emission in all three cases corresponds to convection in the proto-neutron star of both Schwarzschild and Ledoux type, and convective overshoot. 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 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 25 M☉ 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 detectable by current-generation detectors for a supernova at a distance of 10 kpc. However, our 9.6 M☉ progeni

关键词： Strain

来源：评论

学校读者我要写书评

暂无评论

Mapping the interaction surface between Ca_Vβ and actin and its role in calcium channel clearance

引用

Nature Communications 2025年第1期16卷 1-21页

作者： Castilla, Francisco Lugo, Victor Miranda-Laferte, Erick Jordan, Nadine Huesgen, Pitter F. Santiago-Schübel, Beatrix Alfonso-Prieto, Mercedes Hidalgo, Patricia Institute of Biological Information Processing (IBI-1)—Molecular and Cellular Physiology Forschungszentrum Jülich Jülich Germany Graduate Program Faculty of Mathematics and Natural Sciences Heinrich-Heine University Düsseldorf Germany Central Institute of Engineering Electronics and Analytics (ZEA-3) Forschungszentrum Jülich Jülich Germany Institute of Biological Information Processing (IBI-7)—Structural Biochemistry Forschungszentrum Jülich Jülich Germany Institute of Neuroscience and Medicine (INM-9)—Computational Biomedicine Forschungszentrum Jülich Jülich Germany Cécile and Vogt Institute for Brain Research Medical Faculty Heinrich-Heine University Düsseldorf Germany Institute of Biochemistry Heinrich-Heine University Düsseldorf Germany Biologics Analytical Research and Development AbbVie Deutschland GmbH & Co. KG Ludwigshafen Germany Institute of Biology II University of Freiburg Freiburg Germany

Defective ion channel turnover and clearance of damaged proteins are associated with aging and neurodegeneration. The L-type CaV1.2 voltage-gated calcium channel mediates depolarization-induced calcium signals in hear...

Defective ion channel turnover and clearance of damaged proteins are associated with aging and neurodegeneration. The L-type Ca_V1.2 voltage-gated calcium channel mediates depolarization-induced calcium signals in heart and brain. Here, we determined the interaction surface between actin and two calcium channel subunits, Ca_Vβ₂ and Ca_Vβ₄, using cross-linking mass spectrometry and protein-protein docking, and uncovered a role in replenishing conduction-defective Ca_V1.2 channels. computational and in vitro mutagenesis identified hotspots in Ca_Vβ that decreased the affinity for actin but not for Ca_V1.2. When coexpressed with Ca_V1.2, none of the tested actin-association-deficient Ca_Vβ mutants altered the single-channel properties or the total number of channels at the cell surface. However, coexpression with the Ca_Vβ₂ hotspot mutant downregulated current amplitudes, and with a concomitant reduction in the number of functionally available channels, indicating that current inhibition resulted from a build-up of conduction silent channels. Our findings established Ca_Vβ₂–actin interaction as a key player for clearing the plasma membrane of corrupted Ca_V1.2 proteins to ensure the maintenance of a functional pool of channels and proper calcium signal transduction. The Ca_Vβ–actin molecular model introduces a potentially druggable protein-protein interface to intervene Ca_V-mediated signaling processes. © The Author(s) 2025.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Adversarial Training for Privacy-Preserving Deep Learning Model Distribution

Adversarial Training for Privacy-Preserving Deep Learning Mo...

引用

IEEE International Conference on Big Data

作者： Mohammed Alawad Shang Gao Xiao-Cheng Wu Eric B. Durbin Linda Coyle Lynne Penberthy Georgia Tourassi Oak Ridge National Laboratory Computational Sciences and Engineering DivisionHealth Data Sciences Institute Oak Ridge TN USA Louisiana Tumor Registry Louisiana State University Health Sciences Center New Orleans LA USA Kentucky Cancer Registry University of Kentucky Lexington KY USA Information Management Services Inc Calverton MD USA Surveillance Research Program Division of Cancer Control and Population Sciences National Cancer Institute Bethesda MD USA

ISBN: (数字)9781728108582

ISBN: (纸本)9781728108599

Collaboration among cancer registries is essential to develop accurate, robust, and generalizable deep learning models for automated information extraction from cancer pathology reports. Sharing data presents a serious privacy issue, especially in biomedical research and healthcare delivery domains. Distributing pretrained deep learning (DL) models has been proposed to avoid critical data sharing. However, there is growing recognition that collaboration among clinical institutes through DL model distribution exposes new security and privacy vulnerabilities. These vulnerabilities increase in natural language processing (NLP) applications, in which the dataset vocabulary with word vector representations needs to be associated with the other model parameters. In this paper, we propose a novel privacy-preserving DL model distribution across cancer registries for information extraction from cancer pathology reports with privacy and confidentiality considerations. The proposed approach exploits the adversarial training framework to distinguish private features from shared features among different datasets. It only shares registry-invariant model parameters, without sharing raw data nor registry-specific model parameters among cancer registries. Thus, it protects both the data and the trained model simultaneously. We compare our proposed approach to single-registry models, and a model trained on centrally hosted data from different cancer registries. The results show that the proposed approach significantly outperforms the single-registry models and achieves statistically indistinguishable micro and macro F1-score as compared to the centralized model.

关键词： Cancer Data models Pathology Training Machine learning Privacy Convolution

来源：评论

学校读者我要写书评

暂无评论

Benchmarking Emergency Department Triage Prediction Models with Machine Learning and Large Public Electronic Health Records

arXiv

引用

arXiv 2021年

作者： Xie, Feng Zhou, Jun Lee, Jin Wee Tan, Mingrui Li, Siqi Rajnthern, Logasan S.O. Chee, Marcel Lucas Chakraborty, Bibhas Wong, An-Kwok Ian Dagan, Alon Ong, Marcus Eng Hock Gao, Fei Liu, Nan Centre for Quantitative Medicine and Programme in Health Services and Systems Research Duke-NUS Medical School Singapore Singapore Singapore Singapore School of Electrical and Electronic Engineering Nanyang Technological University Singapore Singapore Faculty of Medicine Nursing and Health Sciences Monash University VIC Australia Department of Statistics and Data Science National University of Singapore Singapore Singapore Department of Biostatistics and Bioinformatics Duke University DurhamNC United States Division of Pulmonary Allergy and Critical Care Medicine Duke University DurhamNC United States Department of Emergency Medicine Beth Israel Deaconess Medical Center Harvard Medical School BostonMA United States MIT Critical Data Laboratory for Computational Physiology Institute for Medical Engineering and Science Massachusetts Institute of Technology CambridgeMA United States Department of Emergency Medicine Singapore General Hospital Singapore Singapore SingHealth AI Health Program Singapore Health Services Singapore Singapore Institute of Data Science National University of Singapore Singapore Singapore

The demand for emergency department (ED) services is increasing across the globe, particularly during the current COVID-19 pandemic. Clinical triage and risk assessment have become increasingly challenging due to the shortage of medical resources and the strain on hospital infrastructure caused by the pandemic. As a result of the widespread use of electronic health records (EHRs), we now have access to a vast amount of clinical data, which allows us to develop predictive models and decision support systems to address these challenges. To date, however, there are no widely accepted benchmark ED triage prediction models based on large-scale public EHR data. An open-source benchmarking platform would streamline research workflows by eliminating cumbersome data preprocessing, and facilitate comparisons among different studies and methodologies. In this paper, based on the Medical Information Mart for Intensive Care IV Emergency Department (MIMIC-IV-ED) database, we developed a publicly available benchmark suite for ED triage predictive models and created a benchmark dataset that contains over 400,000 ED visits from 2011 to 2019. We introduced three ED-based outcomes (hospitalization, critical outcomes, and 72-hour ED reattendance) and implemented a variety of popular methodologies, ranging from machine learning methods to clinical scoring systems. We evaluated and compared the performance of these methods against benchmark tasks. Our codes are open-source, allowing anyone with MIMIC-IV-ED data access to perform the same steps in data processing, benchmark model building, and experiments. This study provides future researchers with insights, suggestions, and protocols for managing raw data and developing risk triaging tools for emergency care. © 2021, CC BY.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Phenotate: crowdsourcing phenotype annotations as exercises in undergraduate classes (vol 12, pg 631, 2020)

引用

GENETICS IN MEDICINE 2020年第8期22卷 1427-1427页

作者： Chang, Willie H. Mashouri, Pouria Lozano, Alexander X. Johnstone, Brittney Husic, Mia Olry, Annie Maiella, Sylvie Balci, Tugce B. Sawyer, Sarah L. Robinson, Peter N. Rath, Ana Brudno, Michael Centre for Computational Medicine The Hospital For Sick Children Toronto ON Canada Department of Computer Science Princeton University Princeton NJ USA Faculty of Medicine University of Toronto Toronto ON Canada Department of Materials Science & Engineering Stanford University Stanford CA USA Sunnybrook Health Sciences Centre Toronto ON Canada Orphanet Institut national de la santé et de la recherche médicale Paris France Medical Genetics Program of Southwestern Ontario London Health Sciences Centre London ON Canada Department of Genetics Children’s Hospital of Eastern Ontario and Children’s Hospital of Eastern Ontario Research Institute University of Ottawa Ottawa ON Canada The Jackson Laboratory for Genomic Medicine Farmington CT USA Institute for Systems Genomics University of Connecticut Farmington CT USA Department of Computer Science University of Toronto Toronto ON Canada Genetics and Genome Biology Program The Hospital for Sick Children Toronto ON Canada University Health Network Toronto ON Canada

Purposecomputational documentation of genetic disorders is highly reliant on structured data for differential diagnosis, pathogenic variant identification, and patient matchmaking. However, most information on rare diseases (RDs) exists in freeform text, such as academic literature. To increase availability of structured RD data, we developed a crowdsourcing approach for collecting phenotype information using student *** developed Phenotate, a web application for crowdsourcing disease phenotype annotations through assignments for undergraduate genetics students. Using student-collected data, we generated composite annotations for each disease through a machine learning approach. These annotations were compared with those from clinical practitioners and gold standard curated *** Phenotate in five undergraduate genetics courses, we collected annotations for 22 diseases. Student-sourced annotations showed strong similarity to gold standards, with F-measures ranging from 0.584 to 0.868. Furthermore, clinicians used Phenotate annotations to identify diseases with comparable accuracy to other annotation sources and gold standards. For six disorders, no gold standards were available, allowing us to create some of the first structured annotations for them, while students demonstrated ability to research *** enables crowdsourcing RD phenotypic annotations through educational assignments. Presented as an intuitive web-based tool, it offers pedagogical benefits and augments the computable RD knowledgebase.

关键词： rare diseases phenotype crowdsourcing medical education machine learning

来源：评论

学校读者我要写书评

暂无评论

Tequila: A platform for rapid development of quantum algorithms

arXiv

引用

arXiv 2020年

作者： Kottmann, Jakob S. Alperin-Lea, Sumner Tamayo-Mendoza, Teresa Cervera-Lierta, Alba Lavigne, Cyrille Yen, Tzu-Ching Verteletskyi, Vladyslav Schleich, Philipp Anand, Abhinav Degroote, Matthias Chaney, Skylar Kesibi, Maha Curnow, Naomi Grace Solo, Brandon Tsilimigkounakis, Georgios Zendejas-Morales, Claudia Izmaylov, Artur F. Aspuru-Guzik, Alán Chemical Physics Theory Group Department of Chemistry University of Toronto Canada Department of Computer Science University of Toronto Canada Department of Chemistry and Chemical Biology Harvard University United States Center for Computational Engineering Science RWTH Aachen University Aachen Germany Department of Physics Williams College WilliamstownMA United States University of Cambridge United Kingdom Quantum Open Source Foundation QC Mentorship Program Department of Physical and Environmental Sciences University of Toronto Scarborough Canada Vector Institute for Artificial Intelligence Toronto Canada Lebovic Fellow Toronto Canada

Variational quantum algorithms are currently the most promising class of algorithms for deployment on near-term quantum computers. In contrast to classical algorithms, there are almost no standardized methods in quantum algorithmic development yet, and the field continues to evolve rapidly. As in classical computing, heuristics play a crucial role in the development of new quantum algorithms, resulting in a high demand for flexible and reliable ways to implement, test, and share new ideas. Inspired by this demand, we introduce tequila, a development package for quantum algorithms in python, designed for fast and flexible implementation, prototyping and deployment of novel quantum algorithms in electronic structure and other fields. tequila operates with abstract expectation values which can be combined, transformed, differentiated, and optimized. On evaluation, the abstract data structures are compiled to run on state of the art quantum simulators or interfaces. Copyright © 2020, The Authors. All rights reserved.

关键词： Quantum theory

来源：评论

学校读者我要写书评

暂无评论

Ten quick tips for deep learning in biology

arXiv

引用

arXiv 2021年

作者： Lee, Benjamin D. Gitter, Anthony Greene, Casey S. Raschka, Sebastian Maguire, Finlay Titus, Alexander J. Kessler, Michael D. Lee, Alexandra J. Chevrette, Marc G. Stewart, Paul Allen Britto-Borges, Thiago Cofer, Evan M. Yu, Kun-Hsing Carmona, Juan Jose Fertig, Elana J. Kalinin, Alexandr A. Signal, Beth Lengerich, Benjamin J. Triche, Timothy J. Boca, Simina M. In-Q-Tel Labs School of Engineering and Applied Sciences Harvard University Department of Genetics Harvard Medical School United States Department of Biostatistics and Medical Informatics University of Wisconsin-Madison MadisonWI United States Morgridge Institute for Research MadisonWI United States Department of Systems Pharmacology and Translational Therapeutics Perelman School of Medicine University of Pennsylvania PhiladelphiaPA United States Department of Biochemistry and Molecular Genetics University of Colorado School of Medicine AuroraCO United States Center for Health AI University of Colorado School of Medicine AuroraCO United States Department of Statistics University of Wisconsin Madison United States Faculty of Computer Science Dalhousie University Canada University of New Hampshire Bioeconomy.XYZ United States Department of Oncology Johns Hopkins University United States Institute for Genome Sciences University of Maryland School of Medicine United States Genomics and Computational Biology Graduate Program University of Pennsylvania United States Department of Systems Pharmacology and Translational Therapeutics University of Pennsylvania United States Wisconsin Institute for Discovery Department of Plant Pathology University of Wisconsin-Madison United States Department of Biostatistics and Bioinformatics Moffitt Cancer Center TampaFL United States Section of Bioinformatics and Systems Cardiology Klaus Tschira Institute for Integrative Computational Cardiology University Hospital Heidelberg Germany University Hospital Heidelberg Germany Lewis-Sigler Institute for Integrative Genomics Princeton University PrincetonNJ United States Graduate Program in Quantitative and Computational Biology Princeton University PrincetonNJ United States Department of Biomedical Informatics Harvard Medical School United States Department of Pathology Brigham and Women's Hospital United States Philips Healthcare CambridgeMA United States Philips Research

Machine learning is a modern approach to problem-solving and task automation. In particular, machine learning is concerned with the development and applications of algorithms that can recognize patterns in data and use them for predictive modeling. Artificial neural networks are a particular class of machine learning algorithms and models that evolved into what is now described as deep learning. Given the computational advances made in the last decade, deep learning can now be applied to massive data sets and in innumerable contexts. Therefore, deep learning has become its own subfield of machine learning. In the context of biological research, it has been increasingly used to derive novel insights from high-dimensional biological data. To make the biological applications of deep learning more accessible to scientists who have some experience with machine learning, we solicited input from a community of researchers with varied biological and deep learning interests. These individuals collaboratively contributed to this manuscript's writing using the GitHub version control platform and the Manubot manuscript generation toolset. The goal was to articulate a practical, accessible, and concise set of guidelines and suggestions to follow when using deep learning. In the course of our discussions, several themes became clear: the importance of understanding and applying machine learning fundamentals as a baseline for utilizing deep learning, the necessity for extensive model comparisons with careful evaluation, and the need for critical thought in interpreting results generated by deep learning, among others. © 2021, CC BY.

关键词： Learning algorithms

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：