检索结果-内蒙古大学图书馆

Exploration of Dark Chemical Genomics Space via Portal Learning: Applied to Targeting the Undruggable Genome and COVID-19 Anti-Infective Polypharmacology

Research Square

引用

Research Square 2021年

作者： Cai, Tian Xie, Li Chen, Muge Liu, Yang He, Di Zhang, Shuo Mura, Cameron Bourne, Philip E. Xie, Lei Ph.D. Program in Computer Science The Graduate Center The City University of New York New York10016 United States Department of Computer Science Hunter College The City University of New York New York10065 United States Master Program in Computer Science Courant Institute of Mathematical Sciences New York University United States School of Data Science Department of Biomedical Engineering University of Virginia VA22903 United States Helen and Robert Appel Alzheimer’s Disease Research Institute Feil Family Brain & Mind Research Institute Weill Cornell Medicine Cornell University New York10021 United States

Advances in biomedicine are largely fueled by exploring uncharted territories of human biology. Machine learning can both enable and accelerate discovery, but faces a fundamental hurdle when applied to unseen data with distributions that differ from previously observed ones—a common dilemma in scientific inquiry. We have developed a new deep learning framework, called Portal Learning, to explore dark chemical and biological space. Three key, novel components of our approach include: (i) end-to-end, step-wise transfer learning, in recognition of biology’s sequence-structure-function paradigm, (ii) out-of-cluster meta-learning, and (iii) stress model selection. Portal Learning provides a practical solution to the out-of-distribution (OOD) problem in statistical machine learning. Here, we have implemented Portal Learning to predict chemical-protein interactions on a genome-wide scale. Systematic studies demonstrate that Portal Learning can effectively assign ligands to unexplored gene families (unknown functions), versus existing state-of-the-art methods. Compared with AlphaFold2-based protein-ligand docking, Portal Learning significantly improved the performance by 79% in PR-AUC and 27% in ROC-AUC, respectively. The superior performance of Portal Learning allowed us to target previously "undruggable" proteins and design novel polypharmacological agents for disrupting interactions between SARS-CoV-2 and human proteins. Portal Learning is general-purpose and can be further applied to other areas of scientific inquiry. © 2021, CC BY.

关键词： Coronavirus

来源：评论

学校读者我要写书评

暂无评论

Information system model for maize research to anticipate the impact of climate change on Indonesian food security

引用

AIP Conference Proceedings 2023年第1期2594卷

作者： A. S. Perbangsa F. A. Munawwar M. B. Pabendon B. Pardamean Information Systems Department School of Information Systems Bina Nusantara University Jakarta 11480 Indonesia Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta 11480 Indonesia Indonesia Cereals Research Institute Maros South Sulawesi 90514 Indonesia Computer Science Department BINUS Graduate Program Master of Computer Science Bina Nusantara University Jakarta 11480 Indonesia

As a rich country in genetic resources, Indonesia has the potential for strengthening food security. Maize is one of the commodities that greatly affect food security in Indonesia. Maize is also widely used as animal feed. The high demand for maize requires efforts to increase the productivity of sustainable cultivation. Various research efforts that have been carried out require the support of a comprehensive information system. This study aimed to build a research model for maize genetic resource information systems that can help search for superior varieties. The data collection method used was collecting genotype, phenotype, climate data and interviewing the maize breeders or researchers. As for the design of the model, this study used the Object-Oriented Analysis & Design (OOAD) method with notation from Unified Modelling Language (UML). The result of this research was a web-based model of information systems for maize research.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Exploration of dark chemical genomics space via portal learning: Applied to targeting the undruggable genome and COVID-19 anti-infective polypharmacology

arXiv

引用

arXiv 2021年

Advances in biomedicine are largely fueled by exploring uncharted territories of human biology. Machine learning can both enable and accelerate discovery, but faces a fundamental hurdle when applied to unseen data with distributions that differ from previously observed ones—a common dilemma in scientific inquiry. We have developed a new deep learning framework, called Portal Learning, to explore dark chemical and biological space. Three key, novel components of our approach include: (i) end-to-end, step-wise transfer learning, in recognition of biology’s sequence-structure-function paradigm, (ii) out-of-cluster meta-learning, and (iii) stress model selection. Portal Learning provides a practical solution to the out-of-distribution (OOD) problem in statistical machine learning. Here, we have implemented Portal Learning to predict chemical-protein interactions on a genome-wide scale. Systematic studies demonstrate that Portal Learning can effectively assign ligands to unexplored gene families (unknown functions), versus existing state-of-the-art methods, thereby allowing us to target previously "undruggable" proteins and design novel polypharmacological agents for disrupting interactions between SARS-CoV-2 and human proteins. Portal Learning is general-purpose and can be further applied to other areas of scientific *** Codes 68T07 © 2021, CC BY.

关键词： Genes

来源：评论

学校读者我要写书评

暂无评论

The 230 GHz Variability of Numerical Models of Sagittarius A* II. The Physical Origins of the Variability

arXiv

引用

arXiv 2024年

作者： Chan, Ho-Sang Chan, Chi-Kwan JILA University of Colorado National Institute of Standards and Technology 440 UCB BoulderCO80309-0440 United States Department of Astrophysical and Planetary Sciences University of Colorado 391 UCB BoulderCO80309 United States Steward Observatory Department of Astronomy University of Arizona 933 N. Cherry Avenue TucsonAZ85721 United States Data Science Institute University of Arizona 1230 N. Cherry Avenue TucsonAZ85721 United States Program in Applied Mathematics University of Arizona 617 North Santa Rita TucsonAZ85721 United States

We explored in Chan et al. (2024) how the ion-electron temperature ratio affects certain numerical models of Sagittarius A* (Sgr A*). Specifically, we studied these effects in magnetic-dominated regions in magnetic-arrested disk (MAD), focusing on the 3-hour variability at 230 GHz — M∆T. In this study, we investigate how variations in electron temperature prescription parameter, RLow, influence M∆T by analyzing a series of general-relativistic raytracing (GRRT) snapshots. In certain black hole models with a spin a > 0, we discover that increasing RLow renders the photon ring more optically thick, obscuring the varying accretion flows that contribute to the variability. However, as RLow increases further, MAD flux eruptions become more pronounced, compensating for the decrease in M∆T. For models with a spin a Low also increases the optical thickness of the fluid, voids within the optically thick gas fail to cover the entire photon ring. Similarly, flux eruptions are more prominent as RLow increases further, contributing to the observed rise in M∆T against RLow. For black holes with a ≈ 0, although the effect of increasing optical depth is still present, their 230 GHz light curves and hence M∆T are insensitive to the changes in RLow. Furthermore, we find that the variability of the 230 GHz light curves at RLow = 1 correlates with fluctuations in the internal energy of the gas near the black hole, indicating that unusual gas heating may be the source of significant M∆T seen in simulations. Our findings highlight potential approaches for refining M∆T to better align with observations when modelling Sgr A* or other low-luminosity active galactic nuclei. © 2024, CC BY.

关键词： Photons

来源：评论

学校读者我要写书评

暂无评论

Assessing high-order effects in feature importance via predictability decomposition

arXiv

引用

arXiv 2024年

作者： Ontivero-Ortega, Marlis Faes, Luca Cortes, Jesus M. Marinazzo, Daniele Stramaglia, Sebastiano Dipartimento Interateneo di Fisica Università degli Studi di Bari Aldo Moro Bari Italy INFN Sezione di Bari Bari70126 Italy Dipartimento di Ingegneria Università di Palermo Palermo90128 Italy Faculty of Technical Sciences University of Novi Sad Serbia Biocruces-Bizkaia Health Research Institute Barakaldo Spain Biomedical Research Doctorate Program University of the Basque Country Leioa Spain Department of Cell Biology and Histology University of the Basque Country Leioa Spain IKERBASQUE Basque Foundation for Science Bilbao Spain Department of Data Analysis Ghent University Ghent Belgium

Building on recent advances in describing redundancy and synergy in multivariate interactions among random variables, we propose a novel approach to quantify cooperative effects in feature importance, a key technique in explainable artificial intelligence. Specifically, we introduce an adaptive version of the widely used metric Leave One Covariate Out (LOCO), designed to disentangle high-order effects involving a particular input feature in regression problems. LOCO measures the reduction in prediction error when the feature of interest is added to the set of features used in regression. Unlike the standard approach that computes LOCO using all available features, our method identifies the subsets of features that maximize and minimize LOCO. This results in a decomposition of LOCO into a two-body component and higher-order components (redundant and synergistic), while also identifying the features that contribute to these high-order effects in conjunction with the driving feature. We demonstrate the effectiveness of the proposed method in a benchmark data-set related to wine quality and to proton/pion discrimination using simulated detector measurements generated by GEANT. © 2024, CC BY.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Controversy Score Calculation for News Articles

Controversy Score Calculation for News Articles

引用

First International Conference on Transdisciplinary AI (TransAI)

作者： Paul Kim Ziyu Fan Lance Fernando Jacques Sham Crystal Sun Yixin Sun Brian Wright Xi Yang Nicholas Ross Diane Myung-kyung Woodbridge Data Science Program University of San Francisco

ISBN: (纸本)9781728141282

From the 2016 election continuing to the present, a strong focus has developed on the US news media landscape. From issues such as fake news to ideological wars between news sources, helping readers become more discerning news consumers remains a priority for technologists and journalists alike. This paper is a summary of our contribution to the continuing discussion of public empowerment towards making more informed news consumption decisions. In this paper we introduce NewsPhi, a news-feed application designed to provide topic-based contextual information on a changing corpus of daily news. NewsPhi's main contribution is a "controversy score" of news topics - a score that summarizes how controversial a certain news topic is according to the larger media environment. We find that this approach to building products for news readers is both unique and in line with ongoing bias and opinion formation research in the social sciences. Rather than seeking to correct or standardize news opinions, NewsPhi provides important contextual information to inform readers of existing opinions on existing and new topics while also lightly encouraging further exploration.

关键词： Natural language processing Unsupervised learning Information science Information retrieval news Information sciences Unsupervised learning Natural Language Processing information retrieval building products Journalists Reader Device Component Technician

来源：评论

学校读者我要写书评

暂无评论

data Mining for Predicting Customer Satisfaction Using Clustering Techniques

Data Mining for Predicting Customer Satisfaction Using Clust...

引用

International Conference on Information Management and Technology (ICIMTech)

作者： Kartika Purwandari Join W. C. Sigalingging Muhammad Fhadli Shinta Nur Arizky Bens Pardamean Bioinformatics & Data Science Research Center Bina Nusantara University Jakarta Indonesia National Central University Taoyuan Taiwan BINUS Graduate Program – Master of Computer Science Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9781728170718

ISBN: (纸本)9781728170725

Managing customer satisfaction has become an important business trend, including restaurants business. This study aims to determine the application of the K-means, Spectral Clustering (SC), and Agglomerative Clustering (AC) method for measuring customer satisfaction on a family restaurant in Taiwan. We contribute the data collection process and application of data mining in a family restaurant. The clustering analysis based on agglomerative clustering approach performs as well as the K-means approach to cluster the same characteristics of the customers. At last, this study shows the measurement result of customer satisfaction and provides improvement suggestion to the restaurant concerned.

关键词： data mining Customer satisfaction Principal component analysis Computer science Reliability data visualization

来源：评论

学校读者我要写书评

暂无评论

Citizen science in environmental and ecological sciences

NATURE REVIEWS METHODS PRIMERS

引用

NATURE REVIEWS METHODS PRIMERS 2022年第1期2卷 1-20页

作者： Morneau, Dominique Novel Data Ecosystems for Sustainability Research Group Advancing Systems Analysis Program International Institute for Applied Systems Analysis (IIASA) Laxenburg Austria Centre d’écologie et des sciences de la conservation Muséum national d’Histoire naturelle Paris France Faculté de droit Université de Namur Namur Belgium Citizen Science Lab Leiden University Leiden Netherlands Department of Mechanical Engineering University of Bath Bath UK Nordic Foundation for Development and Ecology (NORDECO) Copenhagen Denmark Department of Biology Brandeis University Waltham MA USA Ornamental Plant Pathology Department of Plant Pathology Puyallup Research and Extension Center Washington State University Puyallup WA USA Environmental and Sustainability Participatory Information Systems Group Institute of Marine Sciences (ICM-CSIC) Barcelona Spain Electron Microscopy Science Technology Platform The Francis Crick Institute London UK Departamento de Biologia Marina Facultad Ciencias del Mar Universidad Católica del Norte Coquimbo Chile Millennium Nucleus Ecology and Sustainable Management of Oceanic Island (ESMOI) Coquimbo Chile Centro de Estudios Avanzados en Zonas Áridas (CEAZA) Coquimbo Chile Department of Geography University College London (UCL) London UK

This PrimeView highlights the utility of citizen science across a range of ecological and environmental science research.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Secure decentralized decisions to enhance coordination in consolidated hospital systems

引用

IISE Transactions on Healthcare Systems Engineering 2020年第2期10卷 99-112页

作者： Badré, Adrien Mohebbi, Shima Soltanisehat, Leili Data Science and Analytics Program University of Oklahoma Norman OK United States School of Industrial and Systems Engineering and Data Science and Analytics Program University of Oklahoma Norman OK United States School of Industrial and Systems Engineering University of Oklahoma Norman OK United States

Shared decision making has become a crucial solution to build a consolidated healthcare system. While there is some research in the healthcare literature discussing the advantages and disadvantages of shared decision making, its efficiency has not been addressed quantitatively. In this paper, we propose a Decentralized Patients Assignment System (DPAS) as a universal decentralized decision making architecture. It utilizes the blockchain technology, machine learning, and integer programing to enhance coordination among healthcare providers and patients in consolidated hospital systems. To test the efficiency of the proposed DPAS, a prototype system is developed using an Agent-based model and Ethereum and is compared to the current practice of central referral systems in consolidated hospital systems. The agent-based model consists of four agents including patients, physicians, hospitals, and miners interacting within a decentralized system. The proposed system highlights the importance of interoperability and consensus among healthcare agents in the decision making process. The results demonstrate the DPAS efficiency in decreasing computational time and rejection rates for patients transfer. © 2019, © 2019 “IISE”.

关键词： Blockchain architecture intelligent agents optimization patients referral predictive analytics smart contracts

来源：评论

学校读者我要写书评

暂无评论

Antioxidant and Antidiabetic Activities of Melastoma Malabathricum Leaves Extracts

引用

Hunan Daxue Xuebao/Journal of Hunan University Natural sciences 2022年第7期49卷 144-153页

作者： Idris, Muddatstsir Purnomo, Adi Setyo Martak, Fahimah Fatmawati, Sri Department of Chemistry Faculty of Science and Data Analytics Institut Teknologi Sepuluh Nopember Jalan Arif Rahman Hakim Sukolilo Surabaya East Java60111 Indonesia Program of Pharmacy Study Faculty of Mathematics and Natural Sciences University of Lambung Mangkurat A. Yani KM. 35.8 Banjarbaru South Kalimantan70714 Indonesia Agri-Food and Biotechnology Research Center Institut Teknologi Sepuluh Nopember Jalan Arif Rahman Hakim Sukolilo Surabaya East Java60111 Indonesia

Currently, no effective medication is available to treat diabetes despite this disease is a serious health problem. As part of our project to explore Indonesian medicinal plants for antidiabetic agents, this study aimed to investigate the total phenolic and flavonoid contents, antioxidant and antidiabetic properties of Melastoma malabathricum leaves extracts. Spectrophotometric methods were used to determine the total phenolic and flavonoid contents. Antioxidant activity was performed using DPPH, ABTS, and FRAP methods. The in vitro antidiabetic test was conducted through an inhibitory evaluation of α-glucosidase and α-amylase, while STZ-induced diabetic rats were used for in vivo study. The highest value of total phenolic (183.71 ± 0.11 mg GAE/g Extract) was recorded in the methanolic extract and flavonoid (24.10 ± 0.04 mg QE/g Extract) contents were recorded in the EtOAc extract. The methanolic extract has the highest DPPH and ABTS activities with IC50 values of 8.58 ± 0.03 and 4.59 ± 0.03 μg/mL, respectively. It also showed the highest FRAP activity with a 51.15 ± 0.10 µM Fe2+/g. In vitro antidiabetic testing of the methanolic extract of leaves against α-glucosidase and α-amylase was reported for the first time. This novel result showed that the methanolic extract inhibited α-glucosidase and α-amylase with IC50 values of 75.25±1.60 and 52.38±1.32 μg/mL, respectively. A dose of 200 mg/Kg body weight of the methanolic extract reduced rats’ blood glucose rate and serum blood glucose by 51.01% and 37.82%, respectively, after 15 days of treatments. These findings suggested that the methanolic extract of M. malabathricum leaves can be used as a potential source of antioxidant and antidiabetic agents. © 2022 Hunan University. All rights reserved.

关键词： Antioxidants

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：