检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Huang, Yepeng Su, Xiaorui Ullanat, Varun Liang, Ivy Clegg, Lindsay Olabode, Damilola Ho, Nicholas John, Bino Gibbs, Megan Zitnik, Marinka Department of Biomedical Informatics Harvard Medical School BostonMA United States Program in Biological and Biomedical Sciences Harvard Medical School BostonMA United States Harvard College CambridgeMA United States Clinical Pharmacology and Quantitative Pharmacology Clinical Pharmacology & Safety Sciences R&D AstraZeneca GaithersburgMD United States Clinical Pharmacology and Quantitative Pharmacology Clinical Pharmacology & Safety Sciences R&D AstraZeneca WalthamMA United States Program in Computational Biology Carnegie Mellon University PittsburghPA United States Imaging and Data Analytics Clinical Pharmacology & Safety Sciences R&D AstraZeneca WalthamMA United States Kempner Institute for the Study of Natural and Artificial Intelligence Harvard University AllstonMA United States Broad Institute of MIT and Harvard CambridgeMA United States Harvard Data Science Initiative CambridgeMA United States

Predicting clinical outcomes from preclinical data is essential for identifying safe and effective drug combinations, reducing late-stage clinical failures, and accelerating the development of precision therapies. Current models rely on structural or target-based features to identify high-efficacy, low-toxicity drug combinations. However, these approaches fail to incorporate the multimodal data necessary for accurate, clinically-relevant predictions. Here, we introduce MADRIGAL, a multimodal AI model that learns from structural, pathway, cell viability, and transcriptomic data to predict drug combination effects across 953 clinical outcomes and 21,842 compounds, including combinations of approved drugs and novel compounds in development. MADRIGAL uses a transformer bottleneck module to unify preclinical drug data modalities while handling missing data during training and inference—a major challenge in multimodal learning. It outperforms single-modality methods and state-of-the-art models in predicting adverse drug interactions. MADRIGAL performs virtual screening of anticancer drug combinations and supports polypharmacy management for type II diabetes and metabolic dysfunction-associated steatohepatitis (MASH). It identifies transporter-mediated drug interactions. MADRIGAL predicts resmetirom, the first and only FDA-approved drug for MASH, among therapies with the most favorable safety profile. It supports personalized cancer therapy by integrating genomic profiles from cancer patients. Using primary acute myeloid leukemia samples and patient-derived xenograft models, it predicts the efficacy of personalized drug combinations. Integrating MADRIGAL with a large language model allows users to describe clinical outcomes in natural language, improving safety assessment by identifying potential adverse interactions and toxicity risks. MADRIGAL provides a multimodal approach for designing combination therapies with improved predictive accuracy and clinical relevance. Copy

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Predicting Oil and Gas Pipe Wall Thickness Using Machine Learning

Predicting Oil and Gas Pipe Wall Thickness Using Machine Lea...

引用

2021 International Conference on data analytics for Business and Industry, ICDABI 2021

作者： Mohammed, Abdulrahim Hewahi, Nabil College of Science University of Bahrain Big Data Science and Analytics Program Sakhir Bahrain College of Information Technology University of Bahrain Department of Computer Science Sakhir Bahrain

ISBN: (纸本)9781665416566

Pipeline networks are crucial for process industries transportation and business operation. These vital elements, however, are highly exposed to material degradation due to corrosion that seriously impedes operational profitability, reliability, and safety. Industries usually monitor pipeline corrosion rate by gauging pipe wall thickness. Predicting pipe wall thickness helps industries to identify locations with high corrosion rate at an early stage and take necessary actions. The aim of this research is to predict pipe wall thickness at different locations using different machine learning algorithms including Support Vector Machine (SVM), Random Forest (RF), k-Nearest Neighbor (KNN), fully connected Artificial Neural Network (ANN), and Long Short-Term Memory (LSTM). The data processed and analyzed in this study included six different process variables as well as pipe wall thickness at three different locations in a downstream oil and gas industry. The study findings demonstrated that LSTM with test Root Mean Squared Errors (RMSEs) of 0.019 mm, 0.015 mm, and 0.017 mm for the three selected locations, outperformed the other methods applied and successfully identified the pipe wall thickness pattern. © 2021 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Tweets Sentiment Analysis during COVID-19 Pandemic

Tweets Sentiment Analysis during COVID-19 Pandemic

引用

2020 International Conference on data analytics for Business and Industry: Way Towards a Sustainable Economy, ICDABI 2020

作者： Alanezi, Maha A. Hewahi, Nabil M. University of Bahrain Big Data Science Analytics Master Program Collage of Science Sakhir Bahrain University of Bahrain Collage of Information Technology Department of Computer Science Sakhir Bahrain

ISBN: (纸本)9781728196756

The aim of this paper is to investigate the impact of social distance on people during COVID-19 pandemic using twitter sentiment analysis through a comparison between the k-means clustering and Mini-Batch k-means clustering approaches. To find the most common frequent words, two datasets have been investigated (WHO and Bahrain ministry of health datasets) to be as data preparation and exploration. Another two datasets (English and Arabic datasets) are used in the clustering of k-means. In this paper, a comparison between k-means and Mini-Batch k-means is performed to find a pattern. The word frequency shows that there are several words related to the pandemic. The sentiment analysis result show that in USA, Australia, Nigeria, Canada, and England, most tweets are neutral. However, the majority of tweets are positive tweets from both Italy and India. In addition, the k-means cluster in the English dataset reveals several cluster trends where COVID-19 pandemic procedures are addressed in cluster 1, and health workers are encouraged in cluster 3. © 2020 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Prediction of Stock Price and Direction Using Neural Networks: datasets Hybrid Modeling Approach

Prediction of Stock Price and Direction Using Neural Network...

引用

2020 International Conference on data analytics for Business and Industry: Way Towards a Sustainable Economy, ICDABI 2020

作者： Aradi, Mohamed Al Hewahi, Nabil Univestity of Bahain Sakhir Big Data Science Analytics Master Program Collage of Science Bahrain Univestity of Bahain Collage of Information Technology Department of Computer Science Sakhir Bahrain

ISBN: (纸本)9781728196756

Stock prices prediction is one of the most daunting tasks to achieve for day traders, investors, and data scientists. They are complex functions of a wide array of contributing factors that affects the movement dynamics. Politics, social outlook, the company's sales performance, and socio-economic factors all have an influence of how the stock is perceived globally and thus affecting the price movement based on the supply/demand balance. In this work a Framework is proposed to predict the price and movement direction by using multiple datasets that includes news sentiment, social sentiment, company earnings announcement, and technical indicators. A case study was applied on the Apple Inc. stock using Long short-term Memory Neural Networks (LSTM) and Deep Neural Networks (DNN). Results showed superiority of the LSTM model in both predicting stock value [75.4 MSE, +-2.52 PE] and the direction with [70.1% classification accuracy] over the DNN model which suffered from prediction lag and dependency on trend indicators achieving [53.1%] in predicting the direction of the stock. © 2020 IEEE.

关键词： Fruits

来源：评论

学校读者我要写书评

暂无评论

Random Forest vs. SVM vs. KNN in classifying Smartphone and Smartwatch sensor data using CRISP-DM

Random Forest vs. SVM vs. KNN in classifying Smartphone and ...

引用

2020 International Conference on data analytics for Business and Industry: Way Towards a Sustainable Economy, ICDABI 2020

作者： Saleh, Sadiq Jaffer Ali, Sayed Qasim Zeki, Ahmed M. University of Bahrain Big Data Science Analytics Master Program Bahrain University of Bahrain College of Information Technology Deptartment of Information Systems Bahrain

ISBN: (纸本)9781728196756

Nowadays IoT sensors become one of the major sources of data, starting from home automation going to daily devices. Focusing on handsets that have the most significant contribution factor on data blooming and booming. The problem at hand is data mining methods comparison, for selecting the best method that serves sensor data. Methodology used was CRISP-DM. This paper found Random Forest data mining method to work best under the described circumstances. © 2020 IEEE.

关键词： data mining

来源：评论

学校读者我要写书评

暂无评论

Macrophages direct location-dependent recall of B cell memory to vaccination

引用

Cell 2025年

作者： Dhenni, Rama Hoppé, Alexandra Carey Reynaldi, Arnold Kyaw, Wunna Handoko, Nathalie Tricia Grootveld, Abigail K. Keith, Yuki Honda Bhattacharyya, Nayan Deger Ahel, Holly I. Telfser, Aiden Josiah McCorkindale, Andrew N. Yazar, Seyhan Bui, Christina H.T. Smith, James T. Khoo, Weng Hua Boyd, Mollie Obeid, Solange Milner, Brad Starr, Mitchell Brilot, Fabienne Milogiannakis, Vanessa Akerman, Anouschka Aggarwal, Anupriya Davenport, Miles P. Deenick, Elissa K. Chaffer, Christine L. Croucher, Peter I. Brink, Robert Goldstein, Leonard D. Cromer, Deborah Turville, Stuart G. Kelleher, Anthony D. Venturi, Vanessa Munier, C. Mee Ling Phan, Tri Giang Precision Immunology Program Garvan Institute of Medical Research Sydney NSW Australia St. Vincent's Healthcare Clinical Campus School of Clinical Medicine Faculty of Medicine and Health UNSW Sydney Kensington Sydney NSW Australia Immunovirology and Pathogenesis Program Kirby Institute UNSW Sydney Sydney NSW Australia Infection Analytics Program Kirby Institute UNSW Sydney Sydney NSW Australia Data Science Platform Garvan Institute of Medical Research Sydney 2010 NSW Australia St. Vincent's Hospital Sydney Sydney NSW Australia Cancer Plasticity and Dormancy Program The Kinghorn Cancer Centre Garvan Institute of Medical Research Sydney 2010 NSW Australia St. Vincent's Centre for Applied Medical Research Sydney NSW Australia Immune Biotherapies Program Garvan Institute of Medical Research Sydney 2010 NSW Australia Brain Autoimmunity Group Kids Neuroscience Centre The Children's Hospital at Westmead Faculty of Medicine and Health School of Medical Sciences Sydney NSW Australia School of Medical Science Faculty of Medicine and Health University of Sydney Sydney NSW Australia

Vaccines generate long-lived plasma cells and memory B cells (Bmems) that may re-enter secondary germinal centers (GCs) to further mutate their B cell receptor upon boosting and re-exposure to antigen. We show in mouse models that lymph nodes draining the site of primary vaccination harbor a subset of Bmems that reside in the subcapsular niche, generate larger recall responses, and are more likely to re-enter GCs compared with circulating Bmems in non-draining lymph nodes. This location-dependent recall of Bmems into the GC in the draining lymph node was dependent on CD169⁺ subcapsular sinus macrophages (SSMs) in the subcapsular niche. In human participants, boosting of the BNT162b2 vaccine in the same arm generated more rapid secretion of broadly neutralizing antibodies, GC participation, and clonal expansion of SARS-CoV-2-specific B cells than boosting of the opposite arm. These data reveal an unappreciated role for primed draining lymph node SSMs in Bmem cell fate determination. © 2025 The Author(s)

关键词： affinity maturation broadly neutralizing antibodies germinal center immune imprinting memory original antigenic sin plasma cells SARS-CoV-2 subcapsular sinus macrophage vaccine

来源：评论

学校读者我要写书评

暂无评论

Applying Parallel Processing to Improve the Computation Speed of K-Nearest Neighbor Algorithm

Applying Parallel Processing to Improve the Computation Spee...

引用

2020 International Conference on data analytics for Business and Industry: Way Towards a Sustainable Economy, ICDABI 2020

作者： Alanezi, Maha A. Alqaddoumi, Abdulla University of Bahrain Collage of Science Big Data Science and Analytics Master Program Sakhir Bahrain University of Bahrain Collage of Information Technology Department of Information System Sakhir Bahrain

ISBN: (纸本)9781728196756

K-Nearest Neighbor (KNN) is a widely used algorithm to gain an accurate and efficient classification. One of the drawbacks of the algorithm is the time required to calculate the distance for each point. In this paper, the aim is to speed up the KNN algorithm with the implementation of multi threads and multiprocessors to reduce the time to execute the algorithm. There are two medical datasets used to apply the KNN algorithm for the comparison of the sequential and parallel performance. The datasets utilized are Heart Test and Breast Cancer Wisconsin (Diagnostic) data Sets. The multiprocessing is used to parallelize the computation of the distance of KNN. The parallel KNN outperforms the sequential version with the speedup increase, leading to reduction in time for both the processes and threads. © 2020 IEEE.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Comparing Naïve Bayes, Decision Tree and Logistic Regression Methods in Fraudulent Credit Card Transactions

Comparing Naïve Bayes, Decision Tree and Logistic Regressio...

引用

2020 International Conference on data analytics for Business and Industry: Way Towards a Sustainable Economy, ICDABI 2020

作者： Alanezi, Maha A. Homeed, Mawra T. Mohamed, Zahra S. Zeki, Ahmed M. University of Bahrain Big Data Science Analytics Master Program Collage of Science Sakhir Bahrain University of Bahrain Collage of Information Technology Department of Information System Sakhir Bahrain

ISBN: (纸本)9781728196756

data mining is utilized to explore banks' data to unravel any hidden scams and detect potential frauds. The aim of this paper is to compare between the Naïve Bayes, Decision Tree and Logistic Regression in fraudulent credit card transactions. Cross-Industry Standard Process for data Mining (CRISP-DM) is followed to achieve the aim of this research. In terms of accuracy, the best classification model was Logistic Regression with 94.6% accuracy, compared with the Decision Tree and Naïve Bayes that showed accuracy of 89.1% and 90.9% respectively. Other measures were also calculated like time needed to build the model among others. © 2020 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Characterization and Classification of Purity of Limestone in Madura Island for Industrial Application 1

Characterization and Classification of Purity of Limestone i...

引用

1st International Symposium on Physics and Applications, ISPA 2020

作者： Munawaroh, F. Muharrami, L.K. Triwikantoro Arifin, Z. Natural Science Education Study Program Universitas Trunojoyo Madura Bangkalan Indonesia Department of Physics Faculty of Science and Data Analytics Institut Teknologi Sepuluh Nopember Surabaya Indonesia

The characterization and classification of purity of limestone at Madura Island was investigated. Sampling was taken from nine quarries from different areas. The chemical analysis was carried out by X-ray fluorescence (XRF);the crystalline phase was characterized by X-ray diffraction (XRD). Analysis of purity classification based on XRF and XRD results according to British Geological Survey. Limestone has different purity, there are very high, medium, low and impure purity. The sample has a very high purity from Pamekasan (P.1) with CaO content of 99.06 wt% and 100% calcite. The samples are medium purity from Bangkalan (B.1, B.3), Pamekasan (P.2), Sumenep (S.1, and S.3) with CaO content of 91.61- 93.67 wt%. The samples are low purity from S.2 with CaO content 85.79 wt% and 100% dolomite. And the sample has impurities from P.3 and B.2 with CaO content 82.3 wt% and 84.7 wt%. Limestone with very high and medium purity which is processed into PCC can be applied in many industries as filler in rubber, paper making, plastic, paint, food, pharmaceutical, ceramic, adhesives, sealants, agriculture, and animal feed. © Published under licence by IOP Publishing Ltd.

关键词： Limestone

来源：评论

学校读者我要写书评

暂无评论

The exposome and pancreatic cancer, lifestyle and environmental risk factors for PDAC

引用

Seminars in Cancer Biology 2025年 113卷 100-129页

作者： Peduzzi, Giulia Archibugi, Livia Farinella, Riccardo de Leon Pisani, Ruggero Ponz Vodickova, Ludmila Vodicka, Pavel Kraja, Bledar Sainz, Juan Bars-Cortina, David Daniel, Neil Silvestri, Roberto Uysal-Onganer, Pinar Landi, Stefano Dulińska-Litewka, Joanna Comandatore, Annalisa Campa, Daniele Hughes, David J. Rizzato, Cosmeri Department of Biology University of Pisa Pisa Italy Pancreato-Biliary Endoscopy and Endosonography Division Pancreas Translational and Clinical Research Center IRCCS Ospedale San Raffaele Milan Italy Biomedical Center Martin Bioinformatic Center Comenius University in Bratislava Jessenius Faculty of Medicine in Martin Slovakia Faculty of Medicine and Biomedical Center in Pilsen Charles University Pilsen Czech Republic University Clinic of Gastrohepatology University Hospital Center Mother Teresa Tirana Albania Department of Biochemistry and Molecular Biology University of Granada Granada Spain Centro de Investigación Biomédica en Red de Epidemiología y Salud Pública (CIBERESP) Madrid 28029 Spain GENYO. Centre for Genomics and Oncological Research. Genomic Oncology department Granada Spain Instituto de Investigación Biosanitaria Ibs.Granada Granada Spain Institut Català d'Oncologia (ICO) IDIBELL Unit of Biomarkers and Susceptibility (UBS) Oncology Data Analytics Program (ODAP) Catalan Institute of Oncology (ICO) L′Hospitalet del Llobregat Barcelona Spain Institut Català d'Oncologia (ICO) IDIBELL ONCOBELL Program Bellvitge Biomedical Research Institute (IDIBELL) L′Hospitalet de Llobregat Barcelona Spain Molecular Epidemiology of Cancer Group UCD Conway Institute School of Biomolecular and Biomedical Science University College Dublin Dublin Ireland Cancer Mechanisms and Biomarkers Research Group School of Life Sciences University of Westminster London United Kingdom Chair of Medical Biochemistry Medical College Jagiellonian University Krakow Poland General Surgery Unit Department of Translational Research and New Technologies in Medicine and Surgery University of Pisa Italy

Pancreatic cancer (PC), particularly pancreatic ductal adenocarcinoma (PDAC), is a significant global health issue with high mortality rates. PDAC, though only 3 % of cancer diagnoses, causes 7 % of cancer deaths due to its severity and asymptomatic early stages. Risk factors include lifestyle choices, environmental exposures, and genetic predispositions. Conditions like new-onset type 2 diabetes and chronic pancreatitis also contribute significantly. Modifiable risk factors include smoking, alcohol consumption, non-alcoholic fatty pancreatic disease (NAFPD), and obesity. Smoking and heavy alcohol consumption increase PC risk, while NAFPD and obesity, particularly central adiposity, contribute through chronic inflammation and insulin resistance. Refined sugar and sugar-sweetened beverages (SSBs) are also linked to increased PC risk, especially among younger individuals. Hormonal treatments and medications like statins, aspirin, and metformin have mixed results on PC risk, with some showing protective effects. The gut microbiome influences PC through the gut-pancreas axis, with disruptions leading to inflammation and carcinogenesis. Exposure to toxic substances, including heavy metals and chemicals, is associated with increased PC risk. Glycome changes, such as abnormal glycosylation patterns, are significant in PDAC development and offer potential for early diagnosis. Interactions between environmental and genetic factors are crucial in PDAC susceptibility. Genome-wide association studies (GWAS) have identified several single nucleotide polymorphisms (SNPs) linked to PDAC, but gene-environment interactions remain largely unexplored. Future research should focus on polygenic risk scores (PRS) and large-scale studies to better understand these interactions and their impact on PDAC risk. © 2025 The Authors

关键词： Exposome Pancreatic Cancer Risk factors

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：