检索结果-内蒙古大学图书馆

Atom-based machine learning for estimating nucleophilicity and electrophilicity with applications to retrosynthesis and chemical stability

引用

CHEMICAL SCIENCE 2025年第13期16卷 5676-5687页

作者： ree, Nicolai Wollschlaeger, Jan M. Goeller, Andreas H. Jensen, Jan H. Univ Copenhagen Dept Chem Univ Pk 5 DK-2100 Copenhagen O Denmark Bayer AG R&D Pharmaceut Machine Learning Res D-13353 Berlin Germany Bayer AG Pharmaceut R&D Computat Mol Design D-42096 Wuppertal Germany

Nucleophilicity and electrophilicity are important properties for evaluating the reactivity and selectivity of chemical reactions. It allows the ranking of nucleophiles and electrophiles on reactivity scales, enabling a better understanding and prediction of reaction outcomes. Building upon our recent work (N. ree, A. H. G & ouml;ller and J. H. Jensen, Automated quantum chemistry for estimating nucleophilicity and electrophilicity with applications to retrosynthesis and covalent inhibitors, digit. discov., 2024, 3, 347-354), we introduce an atom-based machine learning (ML) approach for predicting methyl cation affinities (MCAs) and methyl anion affinities (MAAs) to estimate nucleophilicity and electrophilicity, respectively. The ML models are trained and validated on QM-derived data from around 50 000 neutral drug-like molecules, achieving Pearson correlation coefficients of 0.97 for MCA and 0.95 for MAA on the held-out test sets. In addition, we demonstrate the ML approach on two different applications: first, as a general tool for filtering retrosynthetic routes based on chemical selectivity predictions, and second, as a tool for assessing the chemical stability of esters and carbamates towards hydrolysis reactions. The code is freely available on GitHub under the MIT open source license and as a web application at https://***.

关键词： Hydrolysis

来源：评论

学校读者我要写书评

暂无评论

unidINO: Assay-independent feature extraction for fluorescence microscopy images

引用

COMPUTATIONAL ANd STrUCTUrAL BIOTECHNOLOGY JOUrNAL 2025年 27卷 928-936页

作者： Morelli, Flavio M. Kim, Vladislav Hecker, Franziska Geibel, Sven Zapata, Paula A. Marin Bayer AG R&D Machine Learning Res Pharmaceut Div Berlin Germany Free Univ Berlin Dept Math & Comp Sci Berlin Germany Bielefeld Univ Proteome & Metabolome Res Bielefeld Germany Bayer AG Crop Sci Div R&D Hit Discovery Monheim Germany

High-content imaging (HCI) enables the characterization of cellular states through the extraction of quantitative features from fluorescence microscopy images. despite the widespread availability of HCI data, the development of generalizable feature extraction models remains challenging due to the heterogeneity of microscopy images, as experiments often differ in channel count, cell type, and assay conditions. To address these challenges, we introduce unidINO, a generalist feature extraction model capable of handling images with an arbitrary number of channels. We train unidINO on a dataset of over 900,000 single-channel images from diverse experimental contexts and concatenate single-channel features to generate embeddings for multi-channel images. Our extensive validation across varied datasets demonstrates that unidINO outperforms traditional computer vision methods and transfer learning from natural images, while also providing interpretability through channel attribution. unidINO offers an out-of-the-box, computationally efficient solution for feature extraction in fluorescence microscopy, with the potential to significantly accelerate the analysis of HCI datasets.

关键词： High-content imaging Fluorescence microscopy Morphological profiling Self-supervised learning representation learning deep learning Computer vision

来源：评论

学校读者我要写书评

暂无评论

HeartMAE: Advancing Cardiac MrI Analysis through Optical Flow Guided Masked Autoencoding 4

HeartMAE: Advancing Cardiac MRI Analysis through Optical Flo...

引用

4th machine learning for Health Symposium, ML4H 2024

作者： Kim, Vladislav Schneider, Lisa Kalaie, Soodeh O'regan, declan Bender, Christian Machine Learning Research Pharmaceuticals R&D Bayer AG Germany MRC Laboratory of Medical Sciences Imperial College London United Kingdom Translational Sciences Pharmaceuticals R&D Bayer AG Germany

Cardiac MrI is a powerful diagnostic tool, but traditional analysis relies on complex segmentation-based workflows that may provide only a partial picture of cardiovascular health. To address these limitations, we introduce HeartMAE, a novel framework that uses masked autoencoding (MAE) to learn features directly from cardiac MrIs, without any labels. By incorporating optical flow during training, HeartMAE is guided towards cardiac regions, which significantly improves its downstream performance. A multitask model, built on a shared HeartMAE embedding layer, accurately predicts key cardiac health indicators, extracardiac features and major cardiovascular conditions. Moreover, HeartMAE features may be used as embeddings for clustering to enable patient stratification. requiring only MrI data, HeartMAE is highly scalable and adaptable to larger datasets, paving the way for foundation models in cardiac imaging. © 2024 V. Kim, L. Schneider, S. Kalaie, d. O'regan & C. Bender.

关键词： Heart

来源：评论

学校读者我要写书评

暂无评论

discriminative Frontal Face Synthesis by Using Attention and Metric learning

引用

JOUrNAL OF SIGNAL PrOCESSING SYSTEMS FOr SIGNAL IMAGE ANd VIdEO TECHNOLOGY 2024年第12期96卷 809-820页

作者： Cevikalp, Hakan Turgut, Kaya Topal, Cihan Eskisehir Osmagazi Univ Elect & Elect Engn Machine Learning & Comp Vis Lab Eskisehir Turkiye Huawei Turkey R&D Ctr AIE Dept Istanbul Turkiye Istanbul Tech Univ Dept AI & Data Engn Istanbul Turkiye

This paper introduces a novel approach for obtaining distinctive frontal facial representations from collections of multiple facial images. The primary objective is to ensure that the profound features extracted through a deep Convolutional Neural Network (CNN) from these learned facial representations exhibit notable separability within the feature space. The acquisition of frontal facial representations capable of effectively representing entire sets of images holds significant value as it considerably reduces the number of image samples requiring processing. This acceleration proves especially advantageous during the classification testing phase. The proposed method combines three fundamental components: attention mechanisms, adversarial methodologies, and metric learning strategies. We adopt a U-Net architecture enhanced by attention modules for the facial aggregation network that generates frontal faces that approximate multiple face images within image sets. Furthermore, we employ both a discriminator network and a pre-trained facial classification network to successfully achieve the goals of adversarial and metric learning. The experimental studies on different face recognition datasets demonstrate that using only attention mechanisms and metric learning strategy is sufficient to synthesize discriminative frontal face images yielding high classification accuracies.

关键词： Frontal face synthesis Attention module Face recognition Image sets deep learning

来源：评论

学校读者我要写书评

暂无评论

deep Uniformly distributed Centers on a Hypersphere for Open Set recognition 15

Deep Uniformly Distributed Centers on a Hypersphere for Open...

引用

15th Asian Conference on machine learning (ACML)

作者： Cevikalp, Hakan Yavuz, Hasan Serhan Saribas, Hasan Eskisehir Osmangazi Univ Machine Learning & Comp Vis Lab Eskisehir Turkiye Huawei Turkey R&D Ctr Istanbul Turkiye

This study introduces a new approach for open set recognition, wherein we propose a novel method utilizing uniformly distributed centers on a hypersphere. Each class in the proposed method is represented by a center, and these centers and features of the deep learning architecture are jointly learned from the training data in an end-to-end fashion. We ensure that the centers lie on the boundary of a hypersphere whose center is positioned at the origin. The class-specific samples are compelled by the proposed loss function to be closer to their respective centers. In open set recognition scenarios, an additional loss term is employed to separate the background samples from the known class centers. The assignment of test samples to classes is based on the Euclidean distances calculated from the learned class centers. Experimental results show that the proposed method yields the state-of-the-art accuracies on open set recognition datasets.

关键词： Open set recognition classification deep learning uniformly distributed centers

来源：评论

学校读者我要写书评

暂无评论

diffPerf: Toward Performance differentiation and Optimization With SdN Implementation

引用

IEEE TrANSACTIONS ON NETWOrK ANd SErVICE MANAGEMENT 2024年第1期21卷 1012-1031页

作者： Aljoby, Walid A. Wang, Xin divakaran, dinil Mon Fu, Tom Z. J. Ma, richard T. B. Harras, Khaled A. Carnegie Mellon Univ Qatar Dept Comp Sci Doha Qatar Natl Univ Singapore Dept Comp Sci Singapore 119077 Singapore Trustwave Cyber Secur R&D Dept Singapore Singapore Alluxio Inc Machine Learning Dept Singapore Singapore

The continuous growth of Internet traffic, especially video content, presents challenges for access providers (APs) who must upgrade their infrastructure to meet increasing demands. Ensuring a high-quality experience (QoE) for end-users and finding ways to monetize network resources are key concerns. Guaranteeing QoE is complex, as it depends not only on link capacity but also on competing traffic flows and shared network data plane buffers. To address these challenges, we propose diffPerf, an in-network, online, and dynamic allocation system. diffPerf operates at both macroscopic and microscopic levels. At the macroscopic level, it elastically allocates bandwidth to performance-centric service classes defined by APs to accommodate different performance requirements. At the microscopic level, diffPerf employs a lightweight data-driven algorithm to statistically differentiate and isolate traffic flows within each class, improving their performance. We implemented diffPerf prototypes using SdN-based technology, one with Opendaylight and OpenFlow hardware switches, and the other with programmable Intel Tofino switches. Our evaluation focused on on-demand video streaming. The results demonstrate that diffPerf offers APs a range of allocation choices while ensuring strong performance isolation. Additionally, diffPerf improves fairness and enhances overall user-perceived QoE within each class. Notably, diffPerf conserves bandwidth and delivers a QoE improvement approximately $4.6\times $ higher than TCP BBr, the most popular congestion control mechanism on the Internet.

关键词： In-network optimization intelligent networks software-defined networks bandwidth allocation quality of experience video streaming buffer size TCP flows

来源：评论

学校读者我要写书评

暂无评论

PILOT: equivariant diffusion for pocket-conditioned de novo ligand generation with multi-objective guidance via importance sampling

引用

CHEMICAL SCIENCE 2024年第36期15卷 14954-14967页

作者： Cremer, Julian Le, Tuan Noe, Frank Clevert, djork-Arne Schuett, Kristof T. Pfizer Worldwide R&D Machine Learning & Computat Sci Berlin Germany Free Univ Berlin Dept Math & Comp Sci Berlin Germany Univ Pompeu Fabra Computat Sci Lab PRBB Barcelona Spain Microsoft Microsoft Res AI Sci 4 Berlin Germany

The generation of ligands that both are tailored to a given protein pocket and exhibit a range of desired chemical properties is a major challenge in structure-based drug design. Here, we propose an in silico approach for the de novo generation of 3d ligand structures using the equivariant diffusion model PILOT, combining pocket conditioning with a large-scale pre-training and property guidance. Its multi-objective trajectory-based importance sampling strategy is designed to direct the model towards molecules that not only exhibit desired characteristics such as increased binding affinity for a given protein pocket but also maintains high synthetic accessibility. This ensures the practicality of sampled molecules, thus maximizing their potential for the drug discovery pipeline. PILOT significantly outperforms existing methods across various metrics on the common benchmark dataset Crossdocked2020. Moreover, we employ PILOT to generate novel ligands for unseen protein pockets from the Kinodata-3d dataset, which encompasses a substantial portion of the human kinome. The generated structures exhibit predicted IC50 values indicative of potent biological activity, which highlights the potential of PILOT as a powerful tool for structure-based drug design.

关键词： Ligands

来源：评论

学校读者我要写书评

暂无评论

deep neural network-based tools for hotel marketing activities of online travel agents

引用

Multimedia Tools and Applications 2025年 1-24页

作者： Keles, Ali Keles, Ayturk Keles, Mustafa Berk Mutlu, Behçet Department of Computer Education and Instructional Technology Faculty of Education Agri Ibrahim Cecen University Agri04100 Turkey Machine Learning Engineer *** Istanbul Turkey Director of Technology R&D Center *** Istanbul Turkey Department of Computer Engineering Gebze Technical University Kocaeli Turkey

Vacationers always want to choose the hotel that best meets their needs and expectations. For this, they typically use online travel agents (OTAs). OTAs must analyze millions of images from thousands of hotels quickly and classify them accurately to best meet demands. This is a highly complex and challenging task. OTAs also have to choose a default image to represent best way each hotel in order to best market hotels to vacationers and encourage click behavior. This is another challenge to overcome. The biggest problem in classifying millions of images from different areas of hotels is that these areas often have similar objects and environments. For this reason, fewer categories have been used in deep learning (dL) studies conducted so far. In this study, two deep neural networks (dNN) have been developed to accomplish these challenging tasks. The first network is the "hotel image classification network" (HICNet), which classifies images of different areas of hotels into 11 categories. In a multi-class classification task that includes closely related categories such as bar, food, and lobby, the HICNet network achieved very good results, reaching an average of 79% precision, sensitivity, and F1-score. The second network is the "hotel default image network" (HdINet), which enables the determination of a default image for each hotel on the OTA page. HdINet can accurately identify the default image of hotels with an average of 92% precision, sensitivity, and F1-score. These networks have been integrated into the OTA system named *** and are currently in active use. © The Author(s) 2025.

关键词： Hotels

来源：评论

学校读者我要写书评

暂无评论

remote telepresence over large distances via robot avatars: Case studies 1

Remote telepresence over large distances via robot avatars: ...

引用

1st IEEE Conference on Telepresence, Telepresence 2024

作者： Elobaid, Mohamed dafarra, Stefano ranjbari, Ehsan romualdi, Giulio Chaki, Tomohiro Kawakami, Tomohiro Yoshiike, Takahide Pucci, daniele Honda R&d Frontier Robotics Innovative Research Excellence Saitama Japan Artificial and Mechanical Intelligence Ami Italian Insititute of Technology Genoa Italy The University of Manchester Machine Learning and Optimisation Manchester United Kingdom

ISBN: (纸本)9798331528249

This paper discusses the necessary considerations and adjustments that allow a recently proposed avatar system architecture to be used with different robotic avatar morphologies (both wheeled and legged robots with various types of hands and kinematic structures) for the purpose of enabling remote (intercontinental) telepresence under communication bandwidth restrictions. The case studies reported involve robots using both position and torque control modes, independently of their software middleware. © 2024 IEEE.

关键词： Middleware

来源：评论

学校读者我要写书评

暂无评论

Multi-channel capsule network ensemble for plant disease detection

引用

SN APPLIEd SCIENCES 2021年第7期3卷 707页

作者： Peker, Musa Ozveri R&D Ctr Dept Artificial Intelligence Machine Learning Bursa Turkey

This study presents a new deep learning approach based on capsule networks and ensemble learning for the detection of plant diseases. The developed method is called as multi-channel capsule network ensemble. The main innovation behind the proposed method is the use of multi-channel capsule networks, individually trained on images applied different preprocessing techniques and then combined together. In this way, the final ensemble can better detect plant diseases by making use of different attributes of the data. Our experiments carried out using a well-known data set and various state-of-the-art classification methods demonstrate that our classification approach can provide competitive advantages in terms of classification *** HighlightsAn ensemble of capsule networks has been developed for the automated detection of plant diseases with high *** accuracy has been achieved with ensemble learning compared to a single modelWith the proposed method, better results have been obtained compared to state-of-the-art classification methods in the literature

关键词： Multi-channel capsule network ensemble Plant disease detection Capsule networks Ensemble learning

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：