检索结果-内蒙古大学图书馆

OUGENE： a disease associated over-expressed and under-expressed gene database

学校读者我要写书评

暂无评论

Science Bulletin 2016年第10期61卷 752-754页

作者： Xiaoyong Pan Hong-Bin Shen Section for Animal Genetics Bioinformatics and Breeding Center for Non-Coding RNA in Technology and Health University of Copenhagen 1870 Frederiksberg Denmark Department of Disease Systems Biology Novo NordiskFoundation Center for Protein Research University ofCopenhagen 1870 Frederiksberg Denmark Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University and Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai 200240 China

Gene over-expression or under-expression is closely associated with human diseases, which contributes to phenotypic variations and diversity. To our best knowledge, there is no single open specific resource available to provide the association information between gene over- or under-expression and various diseases. In this study, we presented a comprehensive disease-associated over- and under-expressed gene database （OUGene） based on our proposed text mining pipeline and several open curated databases. It contains total 41,269 unique associa- tions between 7,238 over- or under-expressed genes and 1,480 diseases, which are supported by 81,974 evidence sentences from 56,442 articles. The OUGene is compre- hensive and covers most important therapeutic areas. Meanwhile a new scoring system is designed to rank the associations based on benchmarking against hand-curated data. OUGene provides an easy-of-use web interface for researchers to analyze these data and visualize the associ- ated networks, which can give insights to the complex relationships between over- and under-expressed genes and diseases at a system level. It is available at ***. ***/bioinf/OUGene/.

关键词： Text mining Gene over- and under-expression Disease Database

The Effect of Aggregating Subtype Performances Depends Strongly on the Performance Measure Used

学校读者我要写书评

暂无评论

The Effect of Aggregating Subtype Performances Depends Stron...

International Conference on pattern recognition

作者： David M.J. Tax Herman M.J. Sontrop Marcel J.T Reinders Perry D. Moerland Pattern Recognition Laboratory Delft University of Technology Delft CD The Netherlands Molecular Diagnostics Department Philips Research Eindhoven AE The Netherlands Delft Bioinformatics Lab. Delft University of Technology Delft CD The Netherlands Department of Clinical Epidemiology Academic Medical Center Amsterdam AZ The Netherlands

ISBN: (纸本)9781479952106

For some classification tasks the data can be partitioned into disjoint subsets based on some attribute, for example a disease subtype. It then seems logical to train a classifier with the same classes as the original classification problem for each subtype separately, such that the performance per subtype is optimized. Unfortunately, the influence of the subtype performances on the aggregated overall performance depends strongly on the performance measure used and can be very counterintuitive. We show that for some performance measures (e.g., classification accuracy, precision, recall, Fi) the aggregated performance is a simple linear combination of subtype performances. In these cases, improving the performance of a subtype-specific classifier implies that the overall performance improves. However, for other performance measures (e.g., balanced accuracy rate, area under the ROC curve) and also for performance measures in survival analysis (concordance index), additional cross terms appear in the aggregation of the subtype performances. These cross terms are heavily dependent on both the overall class imbalance and the subtype class imbalances. For these measures, improving subtype performances may actually result in a decrease of the overall performance.

关键词： Nickel Accuracy Indexes Breast cancer Silicon Biomedical measurement Approximation methods

iPINNs: Incremental learning for Physics-informed neural networks

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Dekhovich, Aleksandr Sluiter, Marcel H.F. Tax, David M.J. Bessa, Miguel A. Department of Materials Science and Engineering Delft University of Technology Mekelweg 2 Delft2628 CD Netherlands Pattern Recognition and Bioinformatics Laboratory Delft University of Technology Van Mourik Broekmanweg 6 Delft2628 XE Netherlands School of Engineering Brown University 184 Hope St. ProvidenceRI02912 United States

Physics-informed neural networks (PINNs) have recently become a powerful tool for solving partial differential equations (PDEs). However, finding a set of neural network parameters that lead to fulfilling a PDE can be challenging and non-unique due to the complexity of the loss landscape that needs to be traversed. Although a variety of multi-task learning and transfer learning approaches have been proposed to overcome these issues, there is no incremental training procedure for PINNs that can effectively mitigate such training challenges. We propose incremental PINNs (iPINNs) that can learn multiple tasks (equations) sequentially without additional parameters for new tasks and improve performance for every equation in the sequence. Our approach learns multiple PDEs starting from the simplest one by creating its own subnetwork for each PDE and allowing each subnetwork to overlap with previously learned subnetworks. We demonstrate that previous subnetworks are a good initialization for a new equation if PDEs share similarities. We also show that iPINNs achieve lower prediction error than regular PINNs for two different scenarios: (1) learning a family of equations (e.g., 1-D convection PDE);and (2) learning PDEs resulting from a combination of processes (e.g., 1-D reaction-diffusion PDE). The ability to learn all problems with a single network together with learning more complex PDEs with better generalization than regular PINNs will open new avenues in this field. © 2023, CC BY.

关键词： Complex networks

Cooperative data-driven modeling

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Dekhovich, Aleksandr Turan, O. Taylan Yi, Jiaxiang Bessa, Miguel A. Department of Material Science and Engineering Delft University of Technology Mekelweg 2 Delft2628 CD Netherlands Pattern Recognition and Bioinformatics Laboratory Delft University of Technology Van Mourik Broekmanweg 6 Delft2628 XE Netherlands School of Engineering Brown University 184 Hope St. ProvidenceRI02912 United States

Data-driven modeling in mechanics is evolving rapidly based on recent machine learning advances, especially on artificial neural networks. As the field matures, new data and models created by different groups become available, opening possibilities for cooperative modeling. However, artificial neural networks suffer from catastrophic forgetting, i.e. they forget how to perform an old task when trained on a new one. This hinders cooperation because adapting an existing model for a new task affects the performance on a previous task trained by someone else. The authors developed a continual learning method1 that addresses this issue, applying it here for the first time to solid mechanics. In particular, the method is applied to recurrent neural networks to predict history-dependent plasticity behavior, although it can be used on any other architecture (feedforward, convolutional, etc.) and to predict other phenomena. This work intends to spawn future developments on continual learning that will foster cooperative strategies among the mechanics community to solve increasingly challenging problems. We show that the chosen continual learning strategy can sequentially learn several constitutive laws without forgetting them, using less data to achieve the same error as standard (non-cooperative) training of one law per model. © 2022, CC BY.

关键词： Recurrent neural networks

Neural network relief: a pruning algorithm based on neural activity

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Dekhovich, Aleksandr Tax, David M.J. Sluiter, Marcel H.F. Bessa, Miguel A. Department of Materials Science and Engineering Delft University of Technology Mekelweg 2 Delft2628 CD Netherlands Pattern Recognition and Bioinformatics Laboratory Delft University of Technology Van Mourik Broekmanweg 6 Delft2628 XE Netherlands School of Engineering Brown University 184 Hope St. ProvidenceRI02912 United States

Current deep neural networks (DNNs) are overparameterized and use most of their neuronal connections during inference for each task. The human brain, however, developed specialized regions for different tasks and performs inference with a small fraction of its neuronal connections. We propose an iterative pruning strategy introducing a simple importance-score metric that deactivates unimportant connections, tackling overparameterization in DNNs and modulating the firing patterns. The aim is to find the smallest number of connections that is still capable of solving a given task with comparable accuracy, i.e. a simpler subnetwork. We achieve comparable performance for LeNet architectures on MNIST, and significantly higher parameter compression than state-of-the-art algorithms for VGG and ResNet architectures on CIFAR-10/100 and Tiny-ImageNet.∗ Our approach also performs well for the two different optimizers considered – Adam and SGD. The algorithm is not designed to minimize FLOPs when considering current hardware and software implementations, although it performs reasonably when compared to the state of the art. © 2021, CC BY.

关键词： Deep neural networks

ROSE: Robust Selective Fine-tuning for Pre-trained Language Models

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Jiang, Lan Zhou, Hao Lin, Yankai Li, Peng Zhou, Jie Jiang, Rui Ministry of Education Key Laboratory of Bioinformatics Center for Synthetic and Systems Biology Department of Automation BNRist Tsinghua University China Pattern Recognition Center WeChat AI Tencent Inc. China Gaoling School of Artificial Intelligence Renmin University of China Beijing China Beijing Key Laboratory of Big Data Management and Analysis Methods Beijing China Tsinghua University China

Even though the large-scale language models have achieved excellent performances, they suffer from various adversarial attacks. A large body of defense methods has been proposed. However, they are still limited due to redundant attack search spaces and the inability to defend against various types of attacks. In this work, we present a novel fine-tuning approach called RObust SEletive fine-tuning (ROSE) to address this issue. ROSE conducts selective updates when adapting pretrained models to downstream tasks, filtering out invaluable and unrobust updates of parameters. Specifically, we propose two strategies: the first-order and second-order ROSE for selecting target robust parameters. The experimental results show that ROSE achieves significant improvements in adversarial robustness on various downstream NLP tasks, and the ensemble method even surpasses both variants above. Furthermore, ROSE can be easily incorporated into existing fine-tuning methods to improve their adversarial robustness further. The empirical analysis confirms that ROSE eliminates unrobust spurious updates during fine-tuning, leading to solutions corresponding to flatter and wider optima than the conventional method. Code is available at https://***/jiangllan/ROSE. © 2022, CC BY.

关键词： Computational linguistics

Predicting functional impact of single amino acid polymorphisms by integrating sequence and structural features

学校读者我要写书评

暂无评论

Predicting functional impact of single amino acid polymorphi...

IEEE International Conference on Systems Biology

作者： Mingjun Wang Hong-Bin Shen Tatsuya Akutsu Jiangning Song State Engineering Laboratory for Industrial Enzymes Tianjin Institute of Industrial Biotechnology Chinese Academy of Sciences (CAS) Tianjin China Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai China Bioinformatics Center Institute for Chemical Research Kyoto University Uji Kyoto Japan Department of Biochemistry and Molecular Biology Faculty of Medicine Monash University Melbourne VIC Australia

Single amino acid polymorphisms (SAPs) are the most abundant form of known genetic variations associated with human diseases. It is of great interest to study the sequence-structure-function relationship underlying SAPs. In this work, we collected the human variant data from three databases and divided them into three categories, i.e. cancer somatic mutations (CSM), Mendelian disease-related variant (SVD) and neutral polymorphisms (SVP). We built support vector machine (SVM) classifiers to predict these three classes of SAPs, using the optimal features selected by a random forest algorithm. Consequently, 280 sequence-derived and structural features were initially extracted from the curated datasets from which 18 optimal candidate features were further selected by random forest. Furthermore, we performed a stepwise feature selection to select characteristic sequence and structural features that are important for predicting each SAPs class. As a result, our predictors achieved a prediction accuracy (ACC) of 84.97, 96.93, 86.98 and 88.24%, for the three classes, CSM, SVD and SVP, respectively. Performance comparison with other previously developed tools such as SIFT, SNAP and Polyphen2 indicates that our method provides a favorable performance with higher Sensitivity scores and Matthew's correlation coefficients (MCC). These results indicate that the prediction performance of SAPs classifiers can be effectively improved by feature selection. Moreover, division of SAPs into three respective categories and construction of accurate SVM-based classifiers for each class provides a practically useful way for investigating the difference between Mendelian disease-related variants and cancer somatic mutations.

关键词： Support vector machines Accuracy Proteins Feature extraction Humans Amino acids Databases

Dynamic vortical flow profile quantitatively characterizes mitral valvular-left ventricular hemodynamic coupling: In vivo analysis by dynamic 3D enstrophy mapping from 4D Flow MRI

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Elbaz, Mohammed S.M. Le, Trung Bao Garg, Pankaj Roest, Arno A.W. Lelieveldt, Boudewijn P.F. Plein, Sven Westenberg, Jos J.M. Sotiropoulos, Fotis van der Geest, Rob J. Department of Radiology Northwestern University ChicagoIL United States Department of Radiology Leiden University Medical Center Leiden Netherlands Department of Civil Engineering Stony Brook University Stony BrookNY United States University of Leeds Leeds United Kingdom Department of Pediatrics Division of Pediatric Cardiology Leiden University Medical Center Leiden Netherlands Pattern Recognition and Bioinformatics Group Faculty of Electrical Engineering Mathematics and Computer Science Delft University of Technology Delft Netherlands Computational Fluids Laboratory North Dakota State University United States

Vortical blood flow in the human left ventricular (LV) inflow initiates from the mitral valve (MV) and evolves within the LV during diastolic E-filling. Hence, vortical flow links MV and LV hemodynamics. This study sought to elucidate and quantitatively characterize the in vivo 3D dynamics of LV vortical flow over E-filling and relation to MV-LV hemodynamic coupling using 4D Flow MRI flow field. 34 healthy volunteers and 5 example patients underwent 4D Flow MRI. Vortical blood flow evolution was mapped in the LV over E-wave using enstrophy density. A new dimensionless profile PMV-LV was derived as a function of both MV vortex formation time (VFT) and LV volumetric enstrophy density. Results reveal that 3D vortical flow evolution in the healthy LV follows a bi-phasic behavior with a vortical growth phase followed by a vortical decay phase. In healthy LVs studied, the PMV-LV profile showed that the vortical growth and decay phases are characterized by a vortical growth time Tgrowth = 1.23 ± 0.25, growth rate α = 0.80 ± 0.17, decay time Tdecay = 0.96 ± 0.39 and decay rate β = -1.02 ± 0.49. Distinctly altered parameters were found in the pilot patients studied. The derived PMV-LV profile quantitatively characterizes MV-LV hemodynamic coupling by vortical flow dynamics. Results herein unravel new insights into cardiac physiology and could enable a novel standardized methodology to study MV-LV hemodynamic coupling and association to cardiac function in health and disease. Copyright © 2018, The Authors. All rights reserved.

关键词： Heart

Comparative cellular analysis of motor cortex in human, marmoset and mouse (vol 598, pg 111, 2021)

学校读者我要写书评

暂无评论

NATURE 2022年第7904期604卷 E8-E8页

作者： Bakken, Trygve E. Jorstad, Nikolas L. Hu, Qiwen Lake, Blue B. Tian, Wei Kalmbach, Brian E. Crow, Megan Hodge, Rebecca D. Krienen, Fenna M. Sorensen, Staci A. Eggermont, Jeroen Yao, Zizhen Aevermann, Brian D. Aldridge, Andrew I. Bartlett, Anna Bertagnolli, Darren Casper, Tamara Castanon, Rosa G. Crichton, Kirsten Daigle, Tanya L. Dalley, Rachel Dee, Nick Dembrow, Nikolai Diep, Dinh Ding, Song-Lin Dong, Weixiu Fang, Rongxin Fischer, Stephan Goldman, Melissa Goldy, Jeff Graybuck, Lucas T. Herb, Brian R. Hou, Xiaomeng Kancherla, Jayaram Kroll, Matthew Lathia, Kanan van Lew, Baldur Li, Yang Eric Liu, Christine S. Liu, Hanqing Lucero, Jacinta D. Mahurkar, Anup McMillen, Delissa Miller, Jeremy A. Moussa, Marmar Nery, Joseph R. Nicovich, Philip R. Niu, Sheng-Yong Orvis, Joshua Osteen, Julia K. Owen, Scott Palmer, Carter R. Pham, Thanh Plongthongkum, Nongluk Poirion, Olivier Reed, Nora M. Rimorin, Christine Rivkin, Angeline Romanow, William J. Sedeno-Cortes, Adriana E. Siletti, Kimberly Somasundaram, Saroja Sulc, Josef Tieu, Michael Torkelson, Amy Tung, Herman Wang, Xinxin Xie, Fangming Yanny, Anna Marie Zhang, Renee Ament, Seth A. Behrens, M. Margarita Bravo, Hector Corrada Chun, Jerold Dobin, Alexander Gillis, Jesse Hertzano, Ronna Hof, Patrick R. Hollt, Thomas Horwitz, Gregory D. Keene, C. Dirk Kharchenko, Peter V. Ko, Andrew L. Lelieveldt, Boudewijn P. Luo, Chongyuan Mukamel, Eran A. Pinto-Duarte, Antonio Preiss, Sebastian Regev, Aviv Ren, Bing Scheuermann, Richard H. Smith, Kimberly Spain, William J. White, Owen R. Koch, Christof Hawrylycz, Michael Tasic, Bosiljka Macosko, Evan Z. McCarroll, Steven A. Ting, Jonathan T. Zeng, Hongkui Zhang, Kun Feng, Guoping Ecker, Joseph R. Linnarsson, Sten Lein, Ed S. Allen Institute for Brain Science Seattle WA USA Department of Physiology and Biophysics University of Washington Seattle WA USA Department of Biomedical Informatics Harvard Medical School Boston MA USA Department of Bioengineering University of California San Diego La Jolla CA USA The Salk Institute for Biological Studies La Jolla CA USA Epilepsy Center of Excellence Department of Veterans Affairs Medical Center Seattle WA USA Stanley Institute for Cognitive Genomics Cold Spring Harbor Laboratory Cold Spring Harbor NY USA Department of Genetics Harvard Medical School Boston MA USA Broad Institute of MIT and Harvard Cambridge MA USA LKEB Department of Radiology Leiden University Medical Center Leiden The Netherlands Pattern Recognition and Bioinformatics group Delft University of Technology Delft The Netherlands J. Craig Venter Institute La Jolla CA USA Department of Pathology University of California San Diego CA USA Division of Vaccine Discovery La Jolla Institute for Immunology La Jolla CA USA Genomic Analysis Laboratory The Salk Institute for Biological Studies La Jolla CA USA Computer Science and Engineering Program University of California San Diego La Jolla CA USA Howard Hughes Medical Institute The Salk Institute for Biological Studies La Jolla CA USA Bioinformatics and Systems Biology Graduate Program University of California San Diego La Jolla CA USA Institute for Genomes Sciences University of Maryland School of Medicine Baltimore MD USA Center for Epigenomics Department of Cellular and Molecular Medicine University of California San Diego La Jolla CA USA Ludwig Institute for Cancer Research La Jolla CA USA Department of Computer Science University of Maryland College Park College Park MD USA Sanford Burnham Prebys Medical Discovery Institute La Jolla CA USA Biomedical Sciences Program School of Medicine University of California San Diego La Jolla CA USA University of Connecticut Storrs CT USA Department