检索结果-内蒙古大学图书馆

Advancements in Ligand-Based Virtual Screening through the Synergistic Integration of Graph Neural Networks and Expert-Crafted Descriptors

引用

Journal of Chemical Information and Modeling 2025年第10期65卷 2025 May 14页

作者： Liu, Yunchao Moretti, Rocco Wang, Yu Dong, Ha Yan, Bailu Bodenheimer, Bobby Derr, Tyler Meiler, Jens Department of Computer Science Vanderbilt University 2201 West End Ave Nashville 37235 TN United States Department of Chemistry Center for Structural Biology Vanderbilt University 2201 West End Ave Nashville 37235 TN United States School of Computer and Data Sciences University of Oregon 1585 East 13th Avenue Eugene 97403 OR United States Department of Neural Science Amherst College 220 South Pleasant Street Amherst 01002 MA United States Department of Biostatistics Vanderbilt University 2201 West End Ave Nashville 37235 TN United States Department of Computer Science Electrical Engineering and Computer Engineering Vanderbilt University 2201 West End Ave Nashville 37235 TN United States Department of Computer Science Data Science Institute Vanderbilt University 2201 West End Ave Nashville 37235 TN United States Institute of Drug Discovery Leipzig University Medical School Härtelstraße 16-18 Leipzig 04103 Germany Center for Scalable Data Analytics and Artificial Intelligence (ScaDS.AI) Humboldtstraße 25 Leipzig 04105 Germany

The fusion of traditional chemical descriptors with graph neural networks (GNNs) offers a compelling strategy for enhancing ligand-based virtual screening methodologies. A comprehensive evaluation revealed that the benefits derived from this integrative strategy vary significantly among different GNNs. Specifically, while GCN and SchNet demonstrate pronounced improvements by incorporating descriptors, SphereNet exhibits only marginal enhancement. Intriguingly, despite SphereNet’s modest gain, all three models-GCN, SchNet, and SphereNet-achieve comparable performance levels when leveraging this combination strategy. This observation underscores a pivotal insight: sophisticated GNN architectures may be substituted with simpler counterparts without sacrificing efficacy, provided that they are augmented with descriptors. Furthermore, our analysis reveals a set of expert-crafted descriptors’ robustness in scaffold-split scenarios, frequently outperforming the combined GNN-descriptor models. Given the critical importance of scaffold splitting in accurately mimicking real-world drug discovery contexts, this finding accentuates an imperative for GNN researchers to innovate models that can adeptly navigate and predict within such frameworks. Our work not only validates the potential of integrating descriptors with GNNs in advancing ligand-based virtual screening but also illuminates pathways for future enhancements in model development and application. Our implementation can be found at https://***/meilerlab/gnn-descriptor. © 2025 The Authors. Published by American Chemical Society.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Fair and explainable Myocardial Infarction (MI) prediction: Novel strategies for feature selection and class imbalance correction

引用

computers in Biology and Medicine 2025年 184卷 109413-109413页

作者： Akter, Simon Bin Akter, Sumya Tuli, Moon Das Eisenberg, David Lotvola, Aaron Islam, Humayera Fernandez, Jorge Fresneda Hüttemann, Maik Pias, Tanmoy Sarkar Martin Tuchman School of Management New Jersey Institute of Technology Newark NJ07102 United States Greenlife Medical College & Hospital Dhaka Bangladesh Department of Computer Science Virginia Tech College of Engineering BlacksburgVA United States Institute for Data Science and Informatics University of Missouri Columbia United States Department of Biochemistry Microbiology and Immunology Wayne State University School of Medicine DetroitMI United States Department of Information Management and Business Analytics Montclair State University Feliciano School of Business NJ United States Department of Oncology Wayne State University School of Medicine DetroitMI United States Center for Molecular Medicine and Genetics Wayne State University School of Medicine DetroitMI United States

The rising incidences of myocardial infarction (MI), often affecting individuals without traditional risk factors, highlight the urgent need for improved early detection using personal health data. However, health surveys and electronic health records (EHRs) frequently suffer from class imbalances, leading to prediction biases and differences between specificity and sensitivity, which hinder reliable model development despite the valuable insights contained in these datasets. To address this, we have introduced a novel approach to enhance MI risk prediction using self-reported attributes from the Behavioral Risk Factor Surveillance System (BRFSS) and the National Health Interview Survey (NHIS) dataset. Our approach incorporates three innovative techniques: the Dual-Path Artificial Neural Network (DP-ANN) to mitigate biased decision making across imbalanced datasets, the Triple Criteria Selection (TCS) for unbiased feature selection, and Minority Weighted Sampling (MWS) to tackle challenges of uncontrolled minority class sampling. These methods collectively enhance MI prediction and feature relevance. The DP-ANN model has achieved balanced performance, with an average specificity of 80%, sensitivity of 82%, and AUC–ROC of 89.5%, improving imbalance variance by approximately 14.96% compared to prior studies. By outperforming other models across four heavily imbalanced datasets, our approach demonstrates robustness and generalizability. Additionally, SHapley Additive exPlanations (SHAP) analysis has revealed key predictors and risk factors for MI, such as coronary heart disease and bronchitis in females, and stroke among individuals aged 35–54. In conclusion, our study provides a robust model for healthcare professionals to assess MI risk through targeted factors, promoting early detection and potentially improving patient outcomes. © 2024

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Using PlanetScope-derived time-series elevation models and orthophotos to track glacier 3D dynamics in mid-latitude mountain regions

引用

Mapping sciences and Remote Sensing 2025年第1期62卷

作者： Shengxi Gui Rongjun Qin a Geospatial Data Analytics Lab The Ohio State University Columbus OH USAb Department of Civil Environmental and Geodetic Engineering The Ohio State University Columbus OH USA a Geospatial Data Analytics Lab The Ohio State University Columbus OH USAb Department of Civil Environmental and Geodetic Engineering The Ohio State University Columbus OH USAc Department of Electrical and Computer Engineering The Ohio State University Columbus OH USAd Translational Data Analytics Institute The Ohio State University Columbus OH USA

ABSTRACTAssessing glacier surface height changes provides crucial insights into glacier mass loss and the impact of climate variability. Remote sensing images play a vital role in providing data points for monitoring. Oftentimes, the glacier height change observation is sparse with notable time intervals, yet it is unclear whether these sparse observations are within seasonal variations. Thus, data with high-temporal resolution are necessary to 1) establish sufficiently dense observations to achieve enhanced conclusions; 2) derive higher-level data, such as motion velocity, to assess the level of global warming and climate change. PlanetScope satellite constellations can provide global daily/weekly observations with a 4 m ground sample distance (GSD). In this work, we report a study on monitoring fast dynamic glaciers in mid-latitude mountain regions in America and Asia using the derived time-series 3D elevation models from PlanetScope. The study includes three sites: La Perouse Glacier (North America), Viedma Glacier (South America), and Skamri Glacier (Central Asia). Based on PlanetScope data, we derived near bi-monthly 4-m resolution 3D elevation models for the year of 2019–2023 using satellite stereo photogrammetry, to track the ice flow in 3D. The results can be used to decorrelate the factors from seasonable variation: the Viedma Glacier is observed thinner over time with a slower flow rate; although through a single and short-term observation, the thinning rate of La Perouse Glacier is shown accelerating, we did not observe evidence that La Perouse Glacier and Skamri Glacier have obvious thinning other than its seasonable variations within a few years of time frames (since the PlanetScope images were available). By focusing on the local surface motion variations, our study shows that the glacier velocity varies with regional climate, geography, and hydrology, with a notable 45-day lag response between climate factors and flow speed in Viedma and Skamri Glacie

关键词： Glacier dynamics 3D reconstruction satellite stereo matching glacier surface motion PlanetScope

来源：评论

学校读者我要写书评

暂无评论

Visualizing functional network connectivity differences using an explainable machine-learning method

引用

Physiological Measurement 2025年第4期46卷 2025 Apr 17页

作者： Sendi, Mohammad S E Itkyal, Vaibhavi S Edwards-Swart, Sabrina J Chun, Ji Ye Mathalon, Daniel H Ford, Judith M Preda, Adrian van Erp, Theo G M Pearlson, Godfrey D Turner, Jessica A Calhoun, Vince D Wallace H. Coulter Department of Biomedical Engineering Georgia Institute of Technology Emory University AtlantaGA United States Department of Electrical and Computer Engineering Georgia Institute of Technology AtlantaGA United States McLean Hospital Harvard Medical School BostonMA United States Tri-institutional Center for Translational Research in Neuroimaging and Data Science Georgia State University Georgia Institute of Technology Emory University AtlantaGA United States Department of Neuroscience Emory University AtlantaGA United States Department of Computer Science Georgia State University AtlantaGA United States Department of Psychiatry Weill Institute of Neurosciences University of California San FranciscoCA United States Mental Health Service Veterans Affairs San Francisco Healthcare System San FranciscoCA United States Department of Psychiatry and Human Behavior University of California IrvineCA United States Department of Psychiatry School of Medicine Yale University New HavenCT United States Department of Psychiatry and Behavioral Health College of Medicine The Ohio State University ColumbusOH United States

Objective. Functional network connectivity (FNC) estimated from resting-state functional magnetic resonance imaging showed great information about the neural mechanism in different brain disorders. But previous research has mainly focused on standard statistical learning approaches to find FNC features separating patients from control. While machine learning models can improve classification accuracy, they often lack interpretability, making it difficult to understand how they arrive at their decisions. Approach. Explainable machine learning helps address this issue by identifying which features contribute most to the model’s predictions. In this study, we introduce a novel framework leveraging SHapley Additive exPlanations (SHAPs) to identify crucial FNC features distinguishing between two distinct population classes. Main results. Initially, we validate our approach using synthetic data. Subsequently, applying our framework, we ascertain FNC biomarkers distinguishing between, controls and schizophrenia (SZ) patients with accuracy of 81.04% as well as middle aged adults and old aged adults with accuracy 71.38%, respectively, employing random forest, XGBoost, and CATBoost models. Significance. Our analysis underscores the pivotal role of the cognitive control network (CCN), subcortical network (SCN), and somatomotor network in discerning individuals with SZ from controls. In addition, our platform found CCN and SCN as the most important networks separating young adults from older. © 2025 The Author(s). Published on behalf of institute of Physics and engineering in Medicine by IOP Publishing Ltd.

关键词： Explainable AI Functional Network Connectivity Machine Learning Neuroimaging

来源：评论

学校读者我要写书评

暂无评论

Domain decomposition and mortar mixed approach for nonlinear elliptic equations modeling flow in porous media

引用

Heliyon 2025年第4期11卷 e42724页

作者： Arshad, Muhammad Mehmood, Adil Salleh, Zabidin Akhtar, Sumaira Saleem Khan, Suliman Inc, Mustafa Department of Mathematics Abbottabad University of Science and Technology Abbottabad Pakistan Special Interest Group on Modelling and Data Analytics Faculty of Computer Science and Mathematics Universiti Malaysia Terengganu Kuala Nerus Terengganu 21030 Malaysia Department of Mathematics Women University Mardan Khyber Pakhtunkhwa Pakistan State Key Laboratory of Mechanics and Control for Aerospace Structures College of Aerospace Engineering Nanjing University of Aeronautics and Astronautics Nanjing 210016 China Department of Mathematıcs Firat University Elazig 23119 Türkiye Department of Mathematics Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Tamil Nadu Chennai 602105 India Department of Computer Engineering Biruni University Istanbul 34010 Türkiye

The equations describe the behavior of steady state flow in porous medium generally results in elliptic partial differential equations with coefficient represents the permeability of the medium. This article presents the extension of mortar mixed method for second order nonlinear elliptic equations that describes flow in porous media. The domain is decomposed into non-overlapping regions with each partitioned independently. The grids on subdomains are allowed to be non-matching across the subdomains internal boundaries. The fixed point argument (FPA) is employed to establish the existence and uniqueness of discrete problem, and optimal order error estimates are provided for approximations. The computational results are given to validate the theory. © 2025 The Author(s)

关键词： Darcy law Existence Mixed methods Mortar methods Nonlinear equations Numerical results

来源：评论

学校读者我要写书评

暂无评论

HAM: Hybrid Associations Models for Sequential Recommendation (Extended abstract) 39

HAM: Hybrid Associations Models for Sequential Recommendatio...

引用

39th IEEE International Conference on data engineering, ICDE 2023

作者： Peng, Bo Ren, Zhiyun Parthasarathy, Srinivasan Ning, Xia The Ohio State University Department of Computer Science and Engineering United States The Ohio State University Department of Biomedical Informatics United States The Ohio State University Translational Data Analytics Institute Department of Computer Science and Engineering United States The Ohio State University Translational Data Analytics Institute Department of Biomedical Informatics Department of Computer Science and Engineering United States

ISBN: (纸本)9798350322279

Sequential recommendation aims to identify and recommend the next few items of users' interest. It becomes an effective tool to help users select their favorite items from a variety of options. A key challenge in sequential recommendation is to learn the patterns and dynamics, which are most pertinent to inform future interactions of users. With the prosperity of deep learning, many deep models, particularly based on recurrent neural networks [1] and with attention mechanisms [2] , [3] , have been developed for sequential recommendation purposes. However, our analysis demonstrates that, these deep models, particularly those with attention mechanisms, may not always learn meaningful attention weights from the extremely sparse recommendation data, and thus, could degrade the recommendation performance. Therefore, in this study, instead of deep models, we develop novel, effective and efficient hybrid associations models (HAM) to better learn from the sparse and limited recommendation data. This study has been published in IEEE Transactions on Knowledge and data engineering. Please refer to the full manuscript [4] for more details. © 2023 IEEE.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

A two-stage deep learning-based hybrid model for daily wind speed forecasting

引用

Heliyon 2025年第1期11卷 e41026页

作者： Band, Shahab S. Ameri, Rasoul Qasem, Sultan Noman Mehdizadeh, Saeid Gupta, Brij B. Pai, Hao-Ting Shahmirzadi, Danyal Salwana, Ely Mosavi, Amir Future Technology Research Center National Yunlin University of Science and Technology Douliu Taiwan Department of Information Management International Graduate School of Artificial Intelligence National Yunlin University of Science and Technology Douliu Taiwan Computer Science Department College of Computer and Information Sciences Imam Mohammad Ibn Saud Islamic University (IMSIU) Riyadh 11432 Saudi Arabia Computer Science Department Faculty of Applied Science Taiz University Taiz 6803 Yemen Water Engineering Department Urmia University Urmia Iran Department of Computer Science and Information Engineering Asia University Taichung 413 Taiwan Symbiosis Centre for Information Technology (SCIT) Symbiosis International University Pune India Center for Interdisciplinary Research University of Petroleum and Energy Studies (UPES) Dehradun India Department of Big Data Business Analytics National Pingtung University Pingtung Taiwan of Engineering Science and Technology National Yunlin University of Science and Technology 123 University Road Yunlin Douliou 64002 Taiwan Institute of Visual Informatics Universiti Kebangsaan Malaysia Selangor Bangi 43600 Malaysia John von Neumann Faculty of Informatics Obuda University Budapest Hungary Ludovika University of Public Service Budapest Hungary

Global adoption of wind energy continues to increase, while improving the efficiency of turbine settings requires reliable wind speed (WS) models. The latest models rely on artificial intelligence (AI) optimizations which constructs tests on a range of novel hybrid models to examine the reliability. Gradient Boosting (GB), Random Forest (RF), and Long Short-Term Memory (LSTM) are used in new combinations for data pre-processing. A Time Varying Filter-based Empirical Mode Decomposition (TVFEMD) model is coupled with the GB and LSTM standalone models, to create TVFEMD-GB and TVFEMD-LSTM hybrids, which are run in competition with each other. Eventually, a preferred hybrid form is established, simultaneous hybridization of TVFEMD with GB and LSTM. This study is the first to hybridize these fundamental systems, and create a TVFEMD-GB-LSTM model that can forecast WS. This study finds that the novel hybrid models exhibit superior performance to standalone GB and LSTM models, opening the pathway to alternative WS prediction techniques. © 2024 The Authors

关键词： Artificial intelligence Big data data science Forecasting Gradient boosting Long short-term memory Machine learning Wind speed

来源：评论

学校读者我要写书评

暂无评论

Exploring Policy and Regulations of Clinical AI systems: View from Patients with Chronic Diseases

引用

Health Policy and Technology 2025年

作者： Bijun Wang Onur Asan Turki Alelyani Department of Business Analytics Data Science Florida Polytechnic University Lakeland FL USA Systems Engineering Stevens Institute of Technology Hoboken NJ USA College of Computer Science and Information Systems Najran University Najran Saudi Arabia

Background Artificial Intelligence (AI) has become a transformative force in healthcare, offering opportunities to enhance patient care, improve efficiency, and reduce costs. However, patients' perspectives, which greatly influence the acceptance and implementation of AI technologies, remain under-researched. Objective This study explores patients with chronic conditions’ perspectives on clinical AI systems, focusing on their concerns, government involvement, accountability for potential AI error, and preferences between AI and doctor recommendations. These insights are crucial for tailoring AI technologies to meet patients' needs and expectations and better engage patients in adopting new technologies. Method This study conducted an online open-ended survey with valid responses from 140 patients with chronic conditions, exploring four aspects of clinical AI perspectives. The data was systematically coded and analyzed using an inductive thematic analysis approach to identify emergent themes. Result The majority of participants expressed concerns about the implementation of AI in healthcare (92.86%), with the top worries including lack of human touch (22.86%), potential AI bias and fairness (16.43%), and over-dependence on AI (16.43%). Regarding responsibility for potential treatment damages, 37.14% of participants believed that physicians should bear the responsibility, 16.43% considered AI developers accountable, and 1.42% viewed the government as the responsible party. Furthermore, 44.57% suggested that responsibility should be shared among stakeholders. In terms of government role, 51.43% saw regulation and monitoring as key responsibilities, while 8.57% perceived no government role in AI healthcare. Finally, around 80% of patients preferred treatment recommendations from care providers over AI. Conclusion The findings suggest patients are looking for a balanced approach between technology and human involvement, with clear accountability and proper regulation. Th

关键词：

来源：评论

学校读者我要写书评

暂无评论

AI/ML-Based Automatic Modulation Recognition: Recent Trends and Future Possibilities

arXiv

引用

arXiv 2025年

作者： Jafarigol, Elaheh Alaghband, Behnoud Gilanpour, Azadeh Hosseinipoor, Saeid Mirmozafari, Mirhamed Data Science and Analytics Institute University of Oklahoma 202 W. Boyd St. Room 409 NormanOK73019 United States Electrical and Computer Science Department University of New Mexico Farris Engineering Center 1901 RedondoMSC01 1130 AlbuquerqueNM87131 United States Labcorp Drug Development 3301 Kinsman Blvd MadisonWI53704 United States Samsung Research America San FranciscoCA94111 United States Maxwave LLC 2616 Dublin Way WaunakeeWI53597 United States

We present a review of high-performance automatic modulation recognition (AMR) models proposed in the literature to classify various Radio Frequency (RF) modulation schemes. We replicated these models and compared their performance in terms of accuracy across a range of signal-to-noise ratios. To ensure a fair comparison, we used the same dataset (RadioML-2016A), the same hardware, and a consistent definition of test accuracy as the evaluation metric, thereby providing a benchmark for future AMR studies. The hyperparameters were selected based on the authors’ suggestions in the associated references to achieve results as close as possible to the originals. The replicated models are publicly accessible for further analysis of AMR models. We also present the test accuracies of the selected models versus their number of parameters, indicating their complexities. Building on this comparative analysis, we identify strategies to enhance these models’ performance. Finally, we present potential opportunities for improvement, whether through novel architectures, data processing techniques, or training strategies, to further advance the capabilities of AMR models. © 2025, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A deep reinforcement learning approach for wind speed forecasting

引用

engineering Applications of Computational Fluid Mechanics 2025年第1期19卷

作者： Band, Shahab S. Lin, Ting Jia Qasem, Sultan Noman Ameri, Rasoul Shahmirzadi, Danyal Aslam, Muhammad Shamrooz Pai, Hao-Ting Salwana, Ely Mousavi, Amir International Graduate School of AI National Yunlin University of Science and Technology Douliu Taiwan Department of Information Management International Graduate School of Artificial Intelligence National Yunlin University of Science and Technology Douliu Taiwan Computer Science Department College of Computer and Information Sciences Imam Mohammad Ibn Saud Islamic University (IMSIU) Riyadh Saudi Arabia Computer Science Department Faculty of Applied Science Taiz University Taiz Yemen Department of Information Management National Yunlin University of Science and Technology Douliu Taiwan Graduate School of Engineering Science and Technology National Yunlin University of Science and Technology Douliu Taiwan Artificial Intelligence Research Institute China University of Mining and Technology Xuzhou China Department of Big Data Business Analytics National Pingtung University Pingtung Taiwan Institute of Visual Informatics Universiti Kebangsaan Malaysia Selangor Bangi Malaysia Institute of the Information Society Ludovika University of Public Service Budapest Hungary John Von Neumann Faculty of Informatics Obuda University Budapest Hungary Department of Information and Computing Systems Abylkas Saginov Karaganda Technical University Karaganda Kazakhstan

The conventional wind forecasting methods often struggle to handle the non-stationary and inconsistent wind patterns. This paper presents a hybrid method of Empirical Wavelet Transf... 详细信息

The conventional wind forecasting methods often struggle to handle the non-stationary and inconsistent wind patterns. This paper presents a hybrid method of Empirical Wavelet Transform (EWT) and Deep Reinforcement Learning (DRL) for wind speed modeling to overcome the forecasting challenges. The EWT method transforms the original wind speed series into several independent modes and a residual series. In addition, the DRL method is utilised to optimise the weights associated with three distinct supervised deep learning models, i.e., Long Short-Term Memory (LSTM), Convolutional Neural Networks with LSTM (CNN-LSTM), and CNN with Gated Recurrent Units (CNN-GRU). The performance of the proposed EWT-DRL is evaluated against deep learning models, including LSTM, CNN-LSTM, CNN-GRU, and their coupling with EWT. The combination of EWT and the DRL (EWT-DRL) method achieves a Mean Absolute Error (MAE) of 0.151, a Mean Squared Error (MSE) of 0.060, a Root Mean Squared Error (RMSE) of 0.192, and a correlation coefficient (R) of 0.9913. These results indicate the effectiveness of EWT-DRL in improving accuracy for wind speed modeling. © 2025 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group.

关键词： artificial intelligence deep reinforcement learning empirical wavelet transform long short-term memory machine learning Renewable energy wind speed forecasting

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：