检索结果-内蒙古大学图书馆

arXiv 2020年

作者： Polyanskii, Nikita Vorobyev, Ilya Institute for Communications Engineering Technical University of Munich Munich80333 Germany Center for Computational and Data-Intensive Science and Engineering Skolkovo Institute of Science and Technology Moscow121205 Russia Advanced Combinatorics and Complex Networks Lab Moscow Institute of Physics and Technology Dolgoprudny141701 Russia

We study the duplication with transposition distance between strings of length n over a q-ary alphabet and their roots. In other words, we investigate the number of duplication operations of the form x = (abcd) → y = (abcbd), where x and y are strings and a, b, c and d are their substrings, needed to get a q-ary string of length n starting from the set of strings without duplications. For exact duplication, we prove that the maximal distance between a string of length at most n and its root has the asymptotic order n/ log n. For approximate duplication, where a β-fraction of symbols may be duplicated incorrectly, we show that the maximal distance has a sharp transition from the order n/ log n to log n at β = (q - 1)/q. The motivation for this problem comes from genomics, where such duplications represent a special kind of mutation and the distance between a given biological sequence and its root is the smallest number of transposition mutations required to generate the sequence. Copyright © 2020, The Authors. All rights reserved.

关键词： DNA sequences

来源：评论

学校读者我要写书评

暂无评论

Hyena architecture enables fast and efficient protein language modeling

iMetaOmics

引用

iMetaOmics 2024年第1期2卷

作者： Yiming Zhang Bian Bian Manabu Okumura Department of Information and Communications Engineering School of Engineering Institute of Science Tokyo Yokohama Japan Department of Computational Biology and Medical Sciences Graduate School of Frontier Sciences The University of Tokyo Kashiwa Japan Artificial Intelligence Research Center National Institute of Advanced Industrial Science and Technology (AIST) Tokyo Japan Department of Data Science School of Frontier Engineering Kitasato University Sagamihara Japan

The emergence of self-supervised deep language models has revolutionized natural language processing tasks and has recently extended its applications to biological sequence analysis. Traditional language models, primarily based on Transformer architectures, demonstrate substantial effectiveness in various applications. However, these models are inherently constrained by the attention mechanism's quadratic computational complexity, , which limits their efficiency and leads to high computational costs. To address these limitations, we introduce ProtHyena, a novel approach that leverages the Hyena operator in protein language modeling. This innovative methodology alternates between subquadratic long convolutions and element-wise gating operations, which circumvents the constraints imposed by attention mechanisms and reduces computational complexity to subquadratic levels. This enables faster and more memory-efficient modeling of protein sequences. ProtHyena can achieve state-of-the-art results and comparable performance in 8 downstream tasks, including protein engineering (protein fluorescence and stability prediction), protein property prediction (neuropeptide cleavage, signal peptide, solubility, disorder, gene function prediction), protein structure prediction, with only 1.6 M parameters. The architecture of ProtHyena represents a highly efficient solution for protein language modeling, offering a promising avenue for fast and efficient analysis of protein sequences. Novel Architecture: ProtHyena applies Hyena architecture for protein language modeling, outperforming traditional attention-based models with lower computational costs and fewer parameters. State-of-the-Art Performance: Achieves leading results across classification and regression tasks, excelling with diverse protein sequences. Efficiency: Optimized for faster training and lower memory usage, enabling scalable modeling of long protein sequences.

关键词： Hyena architecture protein language model protein pre-training

来源：评论

学校读者我要写书评

暂无评论

Real-Time TCAD: a new paradigm for TCAD in the artificial intelligence era

Real-Time TCAD: a new paradigm for TCAD in the artificial in...

引用

International Conference on Simulation of Semiconductor Processes and Devices (SISPAD)

作者： Sanghoon Myung Jinwoo Kim Yongwoo Jeon Wonik Jang In Huh Jaemin Kim Songyi Han Kang-hyun Baek Jisu Ryu Yoon-Suk Kim Jiseong Doh Jae-ho Kim Changwook Jeong Dae Sin Kim Computational Science and Engineering Team Data and Information Technology Center Device Solution Business Samsung Electronics Co. Ltd Korea

ISBN: (数字)9784863487635

ISBN: (纸本)9781728173542

This paper presents a novel approach to enable real-time device simulation and optimization. State-of-the-art algorithms which can describe semiconductor domain are adopted to train deep learning models whose input and output are process condition and doping profile / electrical characteristic, respectively. Our framework enables to update automatically deep learning models by estimating the uncertainty of the model prediction. Our Real-Time TCAD framework is validated on 130nm processes for display driver integration circuit (DDI), and 1) prediction time was 530,000 times faster than conventional TCAD, and time spent for process optimization was reduced by 300,000 times compared to human expert, 2) the model achieved average accuracy of 99% compared to TCAD simulation results, and thus, 3) process development time for DDI was reduced by 8 weeks.

关键词： Deep learning Uncertainty Predictive models Real-time systems Semiconductor process modeling Integrated circuit modeling Optimization

来源：评论

学校读者我要写书评

暂无评论

Accurately predicting anticancer peptide using an ensemble of heterogeneously trained classifiers

引用

Informatics in Medicine Unlocked 2023年 42卷

作者： Azim, Sayed Mehedi Sabab, Noor Hossain Nuri Noshadi, Iman Alinejad-Rokny, Hamid Sharma, Alok Shatabda, Swakkhar Dehzangi, Iman Center for Computational and Integrative Biology Rutgers University Camden 08102 NJ United States Department of Computer Science and Engineering United International University Plot 2 United City Madani Avenue BaddaDhaka 1212 Bangladesh Department of Bioengineering University of California Riverside 92507 CA United States BioMedical Machine Learning Lab The Graduate School of Biomedical Engineering The University of New South Wales (UNSW Sydney) Sydney NSW 2052 Australia UNSW Data Science Hub UNSW Sydney Sydney NSW 2052 Australia Health Data Analytics Program AI-enabled Processes Research Centre Macquarie University Sydney 2109 Australia Institute for Integrated and Intelligent Systems Griffith University Brisbane Australia Laboratory for Medical Science Mathematics RIKEN Center for Integrative Medical Sciences Yokohama 230-0045 Japan Department of Computer Science Rutgers University Camden 08102 NJ United States

The use of therapeutic peptides for the treatment of cancer has received tremendous attention in recent years. Anticancer peptides (ACPs) are considered new anticancer drugs which have several advantages over chemistry-based drugs including high specificity, strong tumor penetration capacity, and low toxicity level for normal cells. Due to the rise of experimentally verified bioactive peptides, several in silico approaches became imperative for the investigation of the characteristics of ACPs. In this paper, we proposed a new machine learning tool named iACP-RF that uses a combination of several sequence-based features and an ensemble of three heterogeneously trained Random Forest classifiers to accurately predict anticancer peptides. Experimental results show that our proposed model achieves an accuracy of 75.9% which outperforms other state-of-the-art methods by a significant margin. We also achieve 0.52, 75.6%, and 76.2% in terms of Matthews Correlation Coefficient (MCC), Sensitivity, and Specificity, respectively. iACP-RF as a standalone tool and its source code are publicly available at: https://***/MLBC-lab/iACP-RF. © 2023 The Authors

关键词： Anticancer peptides Ensemble learning Feature extraction Heterogeneous classifiers Machine learning Random Forest

来源：评论

学校读者我要写书评

暂无评论

End-to-end AI Framework for Interpretable Prediction of Molecular and Crystal Properties

arXiv

引用

arXiv 2022年

作者： Park, Hyun Zhu, Ruijie Huerta, E.A. Chaudhuri, Santanu Tajkhorshid, Emad Cooper, Donny Theoretical and Computational Biophysics Group Beckman Institute for Advanced Science and Technology University of Illinois at Urbana-Champaign UrbanaIL61801 United States Department of Materials Science and Engineering Northwestern University EvanstonIL60208 United States Data Science and Learning Division Argonne National Laboratory LemontIL60439 United States Department of Computer Science The University of Chicago ChicagoIL60637 United States Department of Physics University of Illinois at Urbana-Champaign UrbanaIL61801 United States Multiscale Materials and Manufacturing Lab University of Illinois Chicago ChicagoIL60607 United States Department of Biochemistry University of Illinois at Urbana-Champaign UrbanaIL61801 United States Center for Biophysics and Quantitative Biology University of Illinois at Urbana-Champaign UrbanaIL61801 United States Computational Science and Engineering Data Science and AI Department TotalEnergies EP Research & Technology USA LLC HoustonTX77002 United States

We introduce an end-to-end computational framework that allows for hyperparameter optimization using the DeepHyper library, accelerated model training, and interpretable AI inference. The framework is based on state-of-the-art AI models including CGCNN, PhysNet, SchNet, MPNN, MPNN-transformer, and TorchMD-NET. We employ these AI models along with the benchmark QM9, hMOF, and MD17 datasets to showcase how the models can predict user-specified material properties within modern computing environments. We demonstrate transferable applications in the modeling of small molecules, inorganic crystals and nanoporous metal organic frameworks with a unified, standalone framework. We have deployed and tested this framework in the ThetaGPU supercomputer at the Argonne Leadership Computing Facility, and in the Delta supercomputer at the National center for Supercomputing Applications to provide researchers with modern tools to conduct accelerated AI-driven discovery in leadership-class computing environments. We release these digital assets as open source scientific software in GitLab, and ready-to-use Jupyter notebooks in Google Colab. Copyright © 2022, The Authors. All rights reserved.

关键词： Organometallics

来源：评论

学校读者我要写书评

暂无评论

Image-guided patient-specific optimization of catheter placement for convection-enhanced nanoparticle delivery in recurrent glioblastoma

引用

Computers in Biology and Medicine 2024年 179卷 108889-108889页

作者： Wu, Chengyue Hormuth, David A. Christenson, Chase D. Woodall, Ryan T. Abdelmalik, Michael R.A. Phillips, William T. Hughes, Thomas J.R. Brenner, Andrew J. Yankeelov, Thomas E. Oden Institute for Computational Engineering and Sciences The University of Texas at Austin AustinTX78712 United States Department of Biomedical Engineering The University of Texas at Austin AustinTX78712 United States Department of Aerospace Engineering and Engineering Mechanics The University of Texas at Austin AustinTX78712 United States Department of Diagnostic Medicine The University of Texas at Austin AustinTX78712 United States Department of Oncology The University of Texas at Austin AustinTX78712 United States Livestrong Cancer Institutes The University of Texas at Austin AustinTX78712 United States Department of Imaging Physics The University of Texas MD Anderson Cancer Center HoustonTX77030 United States Department of Breast Imaging The University of Texas MD Anderson Cancer Center HoustonTX77030 United States Department of Biostatistics The University of Texas MD Anderson Cancer Center HoustonTX77030 United States Institute for Data Science in Oncology The University of Texas MD Anderson Cancer Center HoustonTX77030 United States Division of Mathematical Oncology Beckman Research Institute City of Hope National Medical Center 1500 East Duarte Rd DuarteCA91010 United States Department of Mechanical Engineering Eindhoven University of Technology Eindhoven Netherlands Department of Radiology UT Health San Antonio San AntonioTX78229 United States Mays Cancer Center UT Health San Antonio San AntonioTX78229 United States

Background: Proper catheter placement for convection-enhanced delivery (CED) is required to maximize tumor coverage and minimize exposure to healthy tissue. We developed an image-based model to patient-specifically optimize the catheter placement for rhenium-186 (186Re)-nanoliposomes (RNL) delivery to treat recurrent glioblastoma (rGBM). Methods: The model consists of the 1) fluid fields generated via catheter infusion, 2) dynamic transport of RNL, and 3) transforming RNL concentration to the SPECT signal. Patient-specific tissue geometries were assigned from pre-delivery MRIs. Model parameters were personalized with either 1) individual-based calibration with longitudinal SPECT images, or 2) population-based assignment via leave-one-out cross-validation. The concordance correlation coefficient (CCC) was used to quantify the agreement between the predicted and measured SPECT signals. The model was then used to simulate RNL distributions from a range of catheter placements, resulting in a ratio of the cumulative RNL dose outside versus inside the tumor, the "off-target ratio" (OTR). Optimal catheter placement) was identified by minimizing OTR. Results: Fifteen patients with rGBM from a Phase I/II clinical trial (NCT01906385) were recruited to the study. Our model, with either individual-calibrated or population-assigned parameters, achieved high accuracy (CCC > 0.80) for predicting RNL distributions up to 24 h after delivery. The optimal catheter placements identified using this model achieved a median (range) of 34.56 % (14.70 %–61.12 %) reduction on OTR at the 24 h post-delivery in comparison to the original placements. Conclusions: Our image-guided model achieved high accuracy for predicting patient-specific RNL distributions and indicates value for optimizing catheter placement for CED of radiolabeled liposomes. © 2024 Elsevier Ltd

关键词： Nanoparticles

来源：评论

学校读者我要写书评

暂无评论

Tempered enthusiasm by interviewed experts for synthetic data and ELSI checklists for AI in medicine

引用

AI and ethics 2025年第3期5卷 3241-3254页

作者： Laura Y Cabrera Jennifer Wagner Sara Gerke Daniel Susser Department of Engineering Science and Mechanics Pennsylvania State University W-316 Millennium Science Complex University Park PA 16802 USA. Department of Philosophy Pennsylvania State University University Park PA 16802 USA. Huck Institutes of the Life Sciences Pennsylvania State University University Park PA 16802 USA. Rock Ethics Institute Pennsylvania State University University Park PA 16802 USA. Bioethics Program Pennsylvania State University University Park PA 16802 USA. School of Engineering Design and Innovation Pennsylvania State University University Park PA 16802 USA. Department of Anthropology Pennsylvania State University University Park PA 16802 USA. Department of Biomedical Engineering Pennsylvania State University University Park PA 16802 USA. Institute for Computational and Data Sciences Pennsylvania State University University Park PA 16802 USA. College of Law and European Union Center University of Illinois Urbana-Champaign Champaign IL 61820 USA. Department of Information Science Cornell University Ithaca NY 14853 USA.

Synthetic data are increasingly being used in data-driven fields. While synthetic data is a promising tool in medicine, it raises new ethical, legal, and social implications (ELSI) challenges. There is a recognized need for well-designed approaches and standards for documenting and communicating relevant information about artificial intelligence (AI) research datasets and models, including consideration of the many ELSI challenges. This study investigates the ethical dimensions of synthetic data and explores the utility and challenges of ELSI-focused computational checklists for biomedical AI via semi-structure interviews with subject matter experts. Our results suggest that AI experts have tempered views about the promises and challenges of both synthetic data and ELSI-focused computational checklists. Experts discussed a number of ELSI issues covered by previous literature on the topic, such as issues of bias and privacy, yet other less discussed ELSI issues, such as social justice implications and issues of trust were also raised. When discussing ELSI-focused computational checklists our participants highlighted the challenges connected to developing and implementing them.

关键词： Artificial intelligence computational checklists ELSI Synthetic data

来源：评论

学校读者我要写书评

暂无评论

The Artificial Intelligence Ontology: LLM-assisted construction of AI concept hierarchies

arXiv

引用

arXiv 2024年

作者： Joachimiak, Marcin P. Miller, Mark A. Caufield, J. Harry Ly, Ryan Harris, Nomi L. Tritt, Andrew Mungall, Christopher J. Bouchard, Kristofer E. Biosystems Data Science Department Environmental Genomics and Systems Biology Division Lawrence Berkeley National Laboratory 1 Cyclotron Road BerkeleyCA94720 United States Scientific Data Division Lawrence Berkeley National Laboratory 1 Cyclotron Road BerkeleyCA94720 United States Applied Mathematics and Computational Research Division Lawrence Berkeley National Laboratory 1 Cyclotron Road BerkeleyCA94720 United States Biological Systems & Engineering Division Lawrence Berkeley National Laboratory 1 Cyclotron Road BerkeleyCA94720 United States Helen Wills Neuroscience Institute UC Berkeley BerkeleyCA94720 United States Redwood Center for Theoretical Neuroscience UC Berkeley BerkeleyCA94720 United States

The Artificial Intelligence Ontology (AIO) is a systematization of artificial intelligence (AI) concepts, methodologies, and their interrelations. Developed via manual curation, with the additional assistance of large language models (LLMs), AIO aims to address the rapidly evolving landscape of AI by providing a comprehensive framework that encompasses both technical and ethical aspects of AI technologies. The primary audience for AIO includes AI researchers, developers, and educators seeking standardized terminology and concepts within the AI domain. The ontology is structured around six top-level branches: Networks, Layers, Functions, LLMs, Preprocessing, and Bias, each designed to support the modular composition of AI methods and facilitate a deeper understanding of deep learning architectures and ethical considerations in AI. AIO's development utilized the Ontology Development Kit (ODK) for its creation and maintenance, with its content being dynamically updated through AI-driven curation support. This approach not only ensures the ontology's relevance amidst the fast-paced advancements in AI but also significantly enhances its utility for researchers, developers, and educators by simplifying the integration of new AI concepts and methodologies. The ontology's utility is demonstrated through the annotation of AI methods data in a catalog of AI research publications and the integration into the BioPortal ontology resource, highlighting it potential for cross-disciplinary research. The AIO ontology is open source and is available on GitHub (https://***/berkeleybop/artificial-intelligence-ontology) and BioPortal (https://***/ontologies/AIO). © 2024, CC BY.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Active Brownian motion in two dimensions under stochastic resetting

引用

Physical Review E 2020年第5期102卷 052129-052129页

作者： Vijay Kumar Onkar Sadekar Urna Basu Centre for Computational and Data-Intensive Science and Engineering Skolkovo Institute of Science and Technology Nobelya Ulitsa 3 Moscow 121205 Russia Indian Institute of Science Education and Research Homi Bhabha Road Pashan Pune 411008 India Raman Research Institute C. V. Raman Avenue Bengaluru 560080 India

We study the position distribution of an active Brownian particle (ABP) in the presence of stochastic resetting in two spatial dimensions. We consider three different resetting protocols: (1) where both position and orientation of the particle are reset, (2) where only the position is reset, and (3) where only the orientation is reset with a certain rate r. We show that in the first two cases, the ABP reaches a stationary state. Using a renewal approach, we calculate exactly the stationary marginal position distributions in the limiting cases when the resetting rate r is much larger or much smaller than the rotational diffusion constant DR of the ABP. We find that, in some cases, for a large resetting rate, the position distribution diverges near the resetting point; the nature of the divergence depends on the specific protocol. For the orientation resetting, there is no stationary state, but the motion changes from a ballistic one at short times to a diffusive one at late times. We characterize the short-time non-Gaussian marginal position distributions using a perturbative approach.

关键词： Fluctuations & noise Nonequilibrium statistical mechanics Stochastic processes

来源：评论

学校读者我要写书评

暂无评论

A Likelihood Approach to Nonparametric Estimation of a Singular Distribution Using Deep Generative Models

arXiv

引用

arXiv 2021年

作者： Chae, Minwoo Kim, Dongha Kim, Yongdai Lin, Lizhen Department of Industrial and Management Engineering Pohang University of Science and Technology Gyeongbuk Pohang37673 Korea Republic of School of Mathematics Statistics and Data Science Data Science Center Sungshin Women’s University Seoul02844 Korea Republic of Department of Statistics Seoul National University Seoul08826 Korea Republic of Department of Applied and Computational Mathematics and Statistics University of Notre Dame South BendIN46556 United States

We investigate statistical properties of a likelihood approach to nonparametric estimation of a singular distribution using deep generative models. More specifically, a deep generative model is used to model high-dimensional data that are assumed to concentrate around some low-dimensional structure. Estimating the distribution supported on this low-dimensional structure, such as a low-dimensional manifold, is challenging due to its singularity with respect to the Lebesgue measure in the ambient space. In the considered model, a usual likelihood approach can fail to estimate the target distribution consistently due to the singularity. We prove that a novel and effective solution exists by perturbing the data with an instance noise, which leads to consistent estimation of the underlying distribution with desirable convergence rates. We also characterize the class of distributions that can be efficiently estimated via deep generative models. This class is sufficiently general to contain various structured distributions such as product distributions, classically smooth distributions and distributions supported on a low-dimensional manifold. Our analysis provides some insights on how deep generative models can avoid the curse of dimensionality for nonparametric distribution estimation. We conduct a thorough simulation study and real data analysis to empirically demonstrate that the proposed data perturbation technique improves the estimation performance *** Codes 62G05 (Primary), 62G20 (Secondary) © 2021, CC BY-NC-SA.

关键词： Perturbation techniques

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：