检索结果-内蒙古大学图书馆

Predicting Drug Effects from High-Dimensional, Asymmetric Drug datasets by Using Graph Neural Networks: A Comprehensive Analysis of Multitarget Drug Effect Prediction

Predicting Drug Effects from High-Dimensional, Asymmetric Dr...

引用

International Conference on Machine learning and Applications (ICMLA)

作者： Avishek Bose Guojing Cong Learning Systems Group Data and AI Systems Section Computer Science and Mathematics Division Oak Ridge National Laboratory Oak Ridge TN USA

ISBN: (数字)9798350374889

ISBN: (纸本)9798350374896

Graph neural networks (GNNs) have emerged as one of the most effective ML techniques for drug effect prediction from drug molecular graphs. Despite having immense potential, GNN models lack performance when using datasets that contain high-dimensional, asymmetrically co-occurrent drug effects as targets with complex correlations between them. Training individual learning models for each drug effect and incorporating every prediction result for a wide spectrum of drug effects are impractical. Therefore, an opportunity exists to address this challenge as multitarget prediction problems and predict all drug effects at a time. We developed standard and hybrid GNNs to perform two separate tasks: multiregression for continuous values and multilabel classification for categorical values contained in our datasets. Because multilabel classification makes the target data even more sparse and introduces asymmetric label co-occurrence, learning these models becomes difficult and heavily impacts the GNN's performance. To address these challenges, we propose a new data oversampling technique to improve multilabel classification performances on all the given imbalanced molecular graph datasets. Using the technique, we improve the data imbalance ratio of the drug effects while protecting the datasets' integrity. Finally, we evaluate the multilabel classification performance of the best-performing hybrid GNN model on all the oversampled datasets obtained from the proposed oversampling technique. In all the evaluation metrics (i.e., precision, recall, and F1 score), this model significantly outperforms other ML models, including GNN models when they are trained on the original datasets or oversampled datasets with MLSMOTE, which is a well-known oversampling technique.

关键词： Drugs Training Measurement Correlation Multi label classification Machine learning Predictive models Graph neural networks data models Standards

来源：评论

学校读者我要写书评

暂无评论

Transferable Graph Neural Fingerprint Models for Quick Response to Future Bio-Threats 22

Transferable Graph Neural Fingerprint Models for Quick Respo...

引用

22nd IEEE International Conference on Machine learning and Applications, ICMLA 2023

作者： Chen, Wei Ren, Yihui Kagawa, Ai Carbone, Matthew R. Chen, Samuel Yen-Chi Qu, Xiaohui Yoo, Shinjae Clyde, Austin Ramanathan, Arvind Stevens, Rick L. Van Dam, Hubertus J. J. Lu, Deyu Center for Functional Nanomaterials Brookhaven National Laboratory UptonNY United States Computational Science Initiative Brookhaven National Laboratory UptonNY United States Argonne National Laboratory Data Science and Learning Division LemontIL United States Condensed Matter Physics & Materials Science Brookhaven National Laboratory UptonNY United States

ISBN: (纸本)9798350345346

Fast screening of drug molecules based on the ligand binding affinity is an important step in the drug discovery pipeline. Graph neural fingerprint is a promising method for developing molecular docking surrogates with high throughput and great fidelity. In this study, we built a COVID-19 drug docking dataset of about 300,000 drug candidates on 23 coronavirus protein targets. With this dataset, we trained graph neural fin-gerprint docking models for high-throughput virtual COVID-19 drug screening. The graph neural fingerprint models yield high prediction accuracy on docking scores with the mean squared error lower than 0.21 kcal/mol for most of the docking targets, showing significant improvement over conventional circular fin-gerprint methods. To make the neural fingerprints transferable for unknown targets, we also propose a transferable graph neural fingerprint method trained on multiple targets. With comparable accuracy to target-specific graph neural fingerprint models, the training and data efficiency of the transferable model is several times higher. We highlight that the impact of this study extends beyond COVID-19 dataset, as our approach for fast virtual ligand screening can be easily adapted and integrated into a general machine learning-accelerated pipeline to battle future bio-threats. © 2023 IEEE.

关键词： Bioinformatics Graph Neural Networks Transfer learning

来源：评论

学校读者我要写书评

暂无评论

WRATH: Workload Resilience Across Task Hierarchies in Task-based Parallel Programming Frameworks

arXiv

引用

arXiv 2025年

作者： Zhou, Sicheng Li, Zhuozhao Hayot-Sasson, Valérie Pan, Haochen Gonthier, Maxime Pauloski, J. Gregory Chard, Ryan Chard, Kyle Foster, Ian Department of Computer Science Southern University of Science and Technology Guangdong China Department of Computer Science University of Chicago ChicagoIL United States Data Science and Learning Division Argonne National Laboratory LemontIL United States

Failures in Task-based Parallel Programming (TBPP) can severely degrade performance and result in incomplete or incorrect outcomes. Existing failure-handling approaches, including reactive, proactive, and resilient methods such as retry and checkpointing mechanisms, often apply uniform retry mechanisms regardless of the root cause of failures, failing to account for the unique characteristics of TBPP frameworks such as heterogeneous resource availability and task-level failures. To address these limitations, we propose WRATH, a novel systematic approach that categorizes failures based on the unique layered structure of TBPP frameworks and defines specific responses to address failures at different layers. WRATH combines a distributed monitoring system and a resilient module to collaboratively address different types of failures in real time. The monitoring system captures execution and resource information, reports failures, and profiles tasks across different layers of TBPP frameworks. The resilient module then categorizes failures and responds with appropriate actions, such as hierarchically retrying failed tasks on suitable resources. Evaluations demonstrate that WRATH significantly improves TBPP robustness, tripling the task success rate and maintaining an application success rate of over 90% for resolvable failures. Additionally, WRATH can reduce the time to failure by 20%-50%, allowing tasks that are destined to fail to be identified and fail more quickly. © 2025, CC BY.

关键词： Parallel programming

来源：评论

学校读者我要写书评

暂无评论

Experiences on Developing an on-Demand Entanglement Service Coexisting with Classical Traffic over a Q-LAN Testbed

Experiences on Developing an on-Demand Entanglement Service ...

引用

Quantum Computing and Engineering (QCE), IEEE International Conference on

作者： Md Shariful Islam Joaquin Chung Raj Kettimuthu Anirudh Ramesh Prem Kumar Data Science and Learning Division Argonne National Laboratory Lemont IL Dept. of Electrical and Computer Eng. Northwestern University Evanston IL USA

ISBN: (数字)9798331541378

ISBN: (纸本)9798331541385

Near-term quantum networks will require a framework for requesting the distribution of entanglement between remote parties. Centralized controllers that provide an interface to users, while orchestrating the functionalities of quantum devices and systems in the network have been proposed to achieve this goal. In this paper, we report our experiences on developing an on-demand entanglement service coexisting with classical traffic over a quantum local area network (Q-LAN) testbed. Our Q-LAN testbed is located at Argonne National Laboratory campus, and it is composed of deployed fiber optics links interconnect commercial quantum and classical networking equipment. We utilize an empirical model to determine the configuration parameters of a commercial entangled photon source (EPS), given the requested coincidence-to-accidental ratio (CAR) and knowledge of the power levels of classical traffic on the network. We delineate our approach towards building an orchestrator based on this model and report our results attained up to this point. Future research aims to extend remote entanglement capabilities, improve timing synchronization, and enhance communications across multiple nodes, further advancing the practical deployment of quantum network technologies.

关键词： Optical fibers Knowledge engineering Quantum entanglement Buildings Optical fiber LAN Quantum networks Synchronization Automobiles Photonics

来源：评论

学校读者我要写书评

暂无评论

Predicting Drug Effects from High-Dimensional, Asymmetric Drug datasets by Using Graph Neural Networks: A Comprehensive Analysis of Multitarget Drug Effect Prediction

arXiv

引用

arXiv 2024年

作者： Bose, Avishek Cong, Guojing Learning Systems Group Data and AI Systems Section Computer Science and Mathematics Division Oak Ridge National Laboratory Oak RidgeTN United States

Graph neural networks (GNNs) have emerged as one of the most effective ML techniques for drug effect prediction from drug molecular graphs. Despite having immense potential, GNN models lack performance when using datasets that contain high-dimensional, asymmetrically co-occurrent drug effects as targets with complex correlations between them. Training individual learning models for each drug effect and incorporating every prediction result for a wide spectrum of drug effects are impractical. Therefore, an opportunity exists to address this challenge as multitarget prediction problems and predict all drug effects at a time. We developed standard and hybrid GNNs to perform two separate tasks: multiregression for continuous values and multilabel classification for categorical values contained in our datasets. Because multilabel classification makes the target data even more sparse and introduces asymmetric label co-occurrence, learning these models becomes difficult and heavily impacts the GNN’s performance. To address these challenges, we propose a new data oversampling technique to improve multilabel classification performances on all the given imbalanced molecular graph datasets. Using the technique, we improve the data imbalance ratio of the drug effects while protecting the datasets’ integrity. Finally, we evaluate the multilabel classification performance of the best-performing hybrid GNN model on all the oversampled datasets obtained from the proposed oversampling technique. In all the evaluation metrics (i.e., precision, recall, and F1 score), this model significantly outperforms other ML models, including GNN models when they are trained on the original datasets or oversampled datasets with MLSMOTE, which is a well-known oversampling technique. Copyright © 2024, The Authors. All rights reserved.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Trillion Parameter AI Serving Infrastructure for Scientific Discovery: A Survey and Vision 23

Trillion Parameter AI Serving Infrastructure for Scientific ...

引用

Proceedings of the IEEE/ACM 10th International Conference on Big data Computing, Applications and Technologies

作者： Nathaniel C Hudson J. Gregory Pauloski Matt Baughman Alok Kamatar Mansi Sakarvadia Logan Ward Ryan Chard André Bauer Maksim Levental Wenyi Wang Will Engler Owen Price Skelly Ben Blaiszik Rick Stevens Kyle Chard Ian Foster Department of Computer Science University of Chicago Chicago Illinois United States Data Science and Learning Division Argonne National Laboratory Lemont Illinois US Data Science and Learning Division Argonne National Laboratory Lemont Illinois United States Globus University of Chicago Chicago Illinois United States Globus The University of Chicago Chicago Illinois United States Department of Computer Science University of Chicago Chicago Illinois USA

ISBN: (纸本)9798400704734

Deep learning methods are transforming research, enabling new techniques, and ultimately leading to new discoveries. As the demand for more capable AI models continues to grow, we are now entering an era of Trillion Parameter Models (TPM), or models with more than a trillion parameters---such as Huawei's PanGu-Σ. We describe a vision for the ecosystem of TPM users and providers that caters to the specific needs of the scientific community. We then outline the significant technical challenges and open problems in system design for serving TPMs to enable scientific research and discovery. Specifically, we describe the requirements of a comprehensive software stack and interfaces to support the diverse and flexible requirements of researchers.

关键词： artificial intelligence grid computing deep learning applications systems design survey

来源：评论

学校读者我要写书评

暂无评论

Investigation of Red Fox Algorithm for Solving Task Assignment Problem in Heterogeneous Unmanned Aerial Vehicle Swarm

Investigation of Red Fox Algorithm for Solving Task Assignme...

引用

Artificial Intelligence For Internet of Things (AIIoT), International Conference on

作者： K. Manaswitha Titus Issac Salaja Silas J Sebastian Terance Division of Data Science and Cyber Security Karunya Institute of Technology and Sciences Coimbatore India Division of Computer Science and Engineering Karunya Institute of Technology and Sciences Coimbatore India Division of Artificial Intelligence and Machine Learning Karunya Institute of Technology and Sciences Coimbatore India

ISBN: (数字)9798350372120

ISBN: (纸本)9798350372137

In recent years, there have been significant advancements in Unmanned Aerial Vehicles (UAVs), leading to their integration into everyday life. UAVs are constrained by limited energy, communication, and localization. The various challenges in UAV research include localization, routing, navigation, and task assignment. Recently, UAV swarms have been employed across a wide range of applications. This study focuses on solving task assignment problems within UAV swarms, considering the unique multi-objective resource constraints of UAVs. The work explores the feasibility of adopting the Red Fox Algorithm to address the task assignment problem in UAV swarms. The investigation examines two primary input parameters: Task Energy Demand and distance. The evaluation includes energy utilization and shortest distance as performance metrics. Notably, the proposed approach outperforms the Particle Swarm Optimization Algorithm (PSO), resulting in a 17.47% lower energy utilization while maintaining a 17.83% reduction in the shortest distance travelled. By leveraging the Red Fox Algorithm, the work aims to enhance the efficiency and effectiveness of task allocation in UAV swarms, contributing to their broader adoption across various applications.

关键词： Location awareness Measurement Navigation Autonomous aerial vehicles Routing Resource management Internet of Things

来源：评论

学校读者我要写书评

暂无评论

Distributed Model Exploration with EMEWS

Distributed Model Exploration with EMEWS

引用

Simulation Winter Conference

作者： Nicholson Collier Justin M. Wozniak Arindam Fadikar Abby Stevens Jonathan Ozik Decision and Infrastructure Sciences Division Argonne National Laboratory Lemont IL USA Consortium for Advanced Science and Engineering University of Chicago Chicago IL USA Data Science and Learning Division Argonne National Laboratory Lemont IL USA

ISBN: (数字)9798331534202

ISBN: (纸本)9798331534219

As high-performance computing resources have become increasingly available, new modes of applying and experimenting with simulation and other computational tools have become possible. This tutorial presents recent advancements to the Extreme-scale Model Exploration with Swift (EMEWS) framework. EMEWS is a high-performance computing (HPC) model exploration (ME) framework, developed for large-scale analyses (e.g., calibration, optimization) of computational models. We focus on three new use-inspired EMEWS capabilities, improved accessibility through binary installation, a new decoupled architecture (EMEWS DB) and task API for distributing workflows on heterogeneous compute resources, and improved EMEWS project creation capabilities. We present a complete worked example where EMEWS DB is used to connect a Python Bayesian optimization algorithm to worker pools running both locally and on remote compute resources. The example, including an R version, and additional details on EMEWS are made available on a public website.

关键词： Analytical models Computational modeling High performance computing Tutorials Computer architecture Calibration Bayes methods Optimization

来源：评论

学校读者我要写书评

暂无评论

Balancing Federated learning Trade-Offs for Heterogeneous Environments

Balancing Federated Learning Trade-Offs for Heterogeneous En...

引用

IEEE Annual Conference on Pervasive Computing and Communications Workshops (PerCom)

作者： Matt Baughman Nathaniel Hudson Ian Foster Kyle Chard Department of Computer Science University of Chicago Chicago IL United States Data Science & Learning Division Argonne National Laboratory Lemont IL United States

Federated learning (FL) is an enabling technology for supporting distributed machine learning across several de-vices on decentralized data. A critical challenge when FL in practice is the system resource heterogeneity of worker devices that train the ML model locally. FL workflows can be run across diverse computing devices, from sensors to High Performance Computing (HPC) clusters; however, these resource disparities may result in some devices being too burdened by the task of training and thus struggle to perform robust training when compared to more high-power devices (or clusters). Techniques can be applied to reduce the cost of training on low-power devices, such as reducing the number of epochs to perform during training. However, such techniques may also negatively harm the performance of the locally-trained model, introducing a resource-model performance trade-off. In this work, we perform robust experimentation with the aim of balancing this resource-model performance trade-off in FL. Our results provide intuition for how training hyper-parameters can be tuned to improve this trade-off in FL.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Advancing AI/ML at the Advanced Photon Source

引用

Synchrotron Radiation News 2022年第4期35卷 28-35页

作者： Benmore, Chris Bicer, Tekin Chan, Maria K. Y. Di, Zichao Gürsoy, Dog˘a Hwang, Inhui Kuklev, Nikita Lin, Dergan Liu, Zhengchun Lobach, Ihar Qiao, Zhi Rebuffi, Luca Sharma, Hemant Shi, Xianbo Sun, Chengjun Yao, Yudong Zhou, Tao Sandy, Alec Miceli, Antonino Sun, Yine Schwarz, Nicholas Cherukara, Mathew J. X-ray Science Division Advanced Photon Source Argonne National Laboratory Lemont IL United States Data Science and Learning Division Argonne National Laboratory Lemont IL United States Center for Nanoscale Materials Argonne National Laboratory Lemont IL United States Mathematics and Computer Science Argonne National Laboratory Lemont IL United States Accelerator Science Division Advanced Photon Source Argonne National Laboratory Lemont IL United States

Click to increase image sizeClick to decrease image size

关键词：

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：