检索结果-内蒙古大学图书馆

33rd IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2023

作者： MacDonald, Kincaid Bhaskar, Dhananjay Thampakkul, Guy Nguyen, Nhi Zhang, Joia Perlmutter, Michael Adelstein, Ian Krishnaswamy, Smita Yale University Department of Mathematics United States Pomona College Department of Mathematics United States University of Washington Department of Statistics United States Boise State University Department of Mathematics United States Yale University Department of Computer Science United States Yale University Applied Mathematics Program United States Yale University Computational Biology and Bioinformatics Program United States

ISBN: (纸本)9798350324112

We consider the problem of embedding point cloud data sampled from an underlying manifold with an associated flow or velocity. Such data arises in many contexts where static snapshots of dynamic entities are measured, including in high-throughput biology such as single-cell transcriptomics. Existing embedding techniques either do not utilize velocity information or embed the coordinates and velocities independently, i.e., they either impose velocities on top of an existing point embedding or embed points within a prescribed vector field. Here we present FlowArtist, a neural network that embeds points while jointly learning a vector field around the points. The combination allows FlowArtist to better separate and visualize velocity-informed structures. Our results, on toy datasets and single-cell RNA velocity data, illustrate the value of utilizing coordinate and velocity information in tandem for embedding and visualizing high-dimensional data. © 2023 IEEE.

关键词： RNA

来源：评论

学校读者我要写书评

暂无评论

BRAINLM: A FOUNDATION MODEL FOR BRAIN ACTIVITY RECORDINGS 12

BRAINLM: A FOUNDATION MODEL FOR BRAIN ACTIVITY RECORDINGS

引用

12th International Conference on Learning Representations, ICLR 2024

作者： Caro, Josue Ortega de Fonseca, Antonio H. Rizvi, Syed A. Rosati, Matteo Averill, Christopher Cross, James L. Mittal, Prateek Zappala, Emanuele Dhodapkar, Rahul M. Abdallah, Chadi G. van Dijk, David Wu Tsai Institute United States Interdepartmental Neuroscience Program Yale University United States Baylor College of Medicine United States Department of Computer Science United States Yale School of Medicine United States University of Southern California United States Interdepartmental Program in Computational Biology & Bioinformatics United States Internal Medicine United States Cardiovascular Research Center Yale University United States Department of Mathematics and Statistics Idaho State University United States

We introduce the Brain Language Model (BrainLM), a foundation model for brain activity dynamics trained on 6,700 hours of fMRI recordings. Utilizing self-supervised masked-prediction training, BrainLM demonstrates proficiency in both fine-tuning and zero-shot inference tasks. Fine-tuning allows for the accurate prediction of clinical variables like age, anxiety, and PTSD as well as forecasting of future brain states. Critically, the model generalizes well to entirely new external cohorts not seen during training. In zero-shot inference mode, BrainLM can identify intrinsic functional networks directly from raw fMRI data without any network-based supervision during training. The model also generates interpretable latent representations that reveal relationships between brain activity patterns and cognitive states. Overall, BrainLM offers a versatile and interpretable framework for elucidating the complex spatiotemporal dynamics of human brain activity. It serves as a powerful "lens" through which massive repositories of fMRI data can be analyzed in new ways, enabling more effective interpretation and utilization at scale. The work demonstrates the potential of foundation models to advance computational neuroscience research. © 2024 12th International Conference on Learning Representations, ICLR 2024. All rights reserved.

关键词： Brain

来源：评论

学校读者我要写书评

暂无评论

APIR:Aggregating Universal Proteomics Database Search Algorithms for Peptide Identification with FDR Control

引用

Genomics, Proteomics & bioinformatics 2024年第2期22卷 171-187页

作者： Yiling Elaine Chen Xinzhou Ge Kyla Woyshner MeiLu McDermott Antigoni Manousopoulou Scott B.Ficarro Jarrod A.Marto Kexin Li Leo David Wang Jingyi Jessica Li Department of Statistics and Data Science University of CaliforniaLos AngelesCA 90095USA Department of Immuno-Oncology Beckman Research InstituteCity of Hope National Medical CenterDuarteCA 91010USA Department of Quantitative and Computational Biology University of Southern CaliforniaLos AngelesCA 90089USA Department of Cancer Biology and Blais Proteomics Center Dana-Farber Cancer InstituteDepartment of PathologyBrigham and Women’s Hospital and Harvard Medical SchoolBostonMA 02215USA Department of Pediatrics City of Hope National Medical CenterDuarteCA 91010USA Bioinformatics Interdepartmental Program University of CaliforniaLos AngelesCA 90095USA Department of Human Genetics University of CaliforniaLos AngelesCA 90095USA Department of Computational Medicine University of CaliforniaLos AngelesCA 90095USA Department of Biostatistics University of CaliforniaLos AngelesCA 90095USA

Advances in mass spectrometry(MS)have enabled high-throughput analysis of proteomes in biological *** state-of-the-art MS data analysis relies on database search algorithms to quantify proteins by identifying peptide–spectrum matches(PSMs),which convert mass spectra to peptide *** database search algorithms use distinct search strategies and thus may identify unique ***,no existing approaches can aggregate all user-specified database search algorithms with a guaranteed increase in the number of identified peptides and a control on the false discovery rate(FDR).To fill in this gap,we proposed a statistical framework,Aggregation of Peptide Identification Results(APIR),that is universally compatible with all database search ***,under an FDR threshold,APIR is guaranteed to identify at least as many,if not more,peptides as individual database search algorithms *** of APIR on a complex proteomics standard dataset showed that APIR outpowers individual database search algorithms and empirically controls the *** data studies showed that APIR can identify disease-related proteins and post-translational modifications missed by some individual database search *** APIR framework is easily extendable to aggregating discoveries made by multiple algorithms in other high-throughput biomedical data analysis,e.g.,differential gene expression analysis on RNA sequencing *** APIR R package is available at https://***/yiling0210/APIR.

关键词： Shotgun proteomics Peptide–spectrum match Peptide identification Aggregation of lists FDR control

来源：评论

学校读者我要写书评

暂无评论

Predicting dynamic cellular protein-RNA interactions by deep learning using in vivo RNA structures

引用

细胞研究（英文版） 2021年第5期31卷 495-516页

作者： Lei Sun Kui Xu Wenze Huang Yucheng T.Yang Pan Li Lei Tang Tuanlin Xiong Qiangfeng Cliff Zhang MOE Key Laboratory of Bioinformatics Beijing Advanced Innovation Center for Structural Biology and Frontier Research Center for Biological StructureCenter for Synthetic and Systems BiologySchool of Life SciencesTsinghua UniversityBeijing 100084China Tsinghua-Peking Center for Life Sciences Beijing 100084China Program in Computational Biology and Bioinformatics Yale UniversityNew HavenCT 06520USA Department of Molecular Biophysics and Biochemistry Yale UniversityNew HavenCT 06520USA

Interactions with RNA-binding proteins (RBPs) are integral to RNA function and cellular regulation,and dynamically reflect specific cellular ***,presently available tools for predicting RBP-RNA interactions employ RNA sequence and/or predicted RNA structures,and therefore do not capture their condition-dependent ***,after profiling transcriptome-wide in vivo RNA secondary structures in seven cell types,we developed PrismNet,a deep learning tool that integrates experimental in vivo RNA structure data and RBP binding data for matched cells to accurately predict dynamic RBP binding in various cellular *** results for 168 RBPs support its utility for both understanding CUP-seq results and largely extending such interaction data to accurately analyze additional cell ***,PrismNet employs an 'attention' strategy to computationally identify exact RBP-binding nucleotides,and we discovered enrichment among dynamic RBP-binding sites for structure-changing variants(riboSNitches),which can link genetic diseases with dysregulated RBP *** rich profiling data and deep learning-based prediction tool provide access to a previously inaccessible layer of cell-type-specific RBP-RNA interactions,with clear utility for understanding and treating human diseases.

关键词： bioinformatics Mechanisms of disease Molecular biology

来源：评论

学校读者我要写书评

暂无评论

Multiomics Reveals Induction of Neuroblastoma SK-N-BE(2)C Cell Death by Mitochondrial Division Inhibitor 1 through Multiple Effects

引用

Journal of Proteome Research 2024年第1期23卷 301-315页

作者： Wang, Wei-Hsuan Kao, Yi-Chun Hsieh, Chiao-Hui Tsai, Shin-Yu Cheung, Chantal Hoi Yin Huang, Hsuan-Cheng Juan, Hsueh-Fen Genome and Systems Biology Degree Program Academia Sinica and National Taiwan University Taipei 106 Taiwan Department of Life Science National Taiwan University Taipei 106 Taiwan Center for Computational and Systems Biology National Taiwan University Taipei 106 Taiwan Institute of Biomedical Informatics National Yang Ming Chiao Tung University Taipei 112 Taiwan Graduate Institute of Biomedical Electronics and Bioinformatics National Taiwan University Taipei 106 Taiwan Center for Advanced Computing and Imaging in Biomedicine National Taiwan University Taipei 106 Taiwan

Mitochondrial division inhibitor 1 (Mdivi-1) is a well-known synthetic compound aimed at inhibiting dynamin-related protein 1 (Drp1) to suppress mitochondrial fission, making it a valuable tool for studying mitochondrial dynamics. However, its specific effects beyond Drp1 inhibition remain to be confirmed. In this study, we employed integrative proteomics and phosphoproteomics to delve into the molecular responses induced by Mdivi-1 in SK-N-BE(2)C cells. A total of 3070 proteins and 1945 phosphorylation sites were identified, with 880 of them represented as phosphoproteins. Among these, 266 proteins and 97 phosphorylation sites were found to be sensitive to the Mdivi-1 treatment. Functional enrichment analysis unveiled their involvement in serine biosynthesis and extrinsic apoptotic signaling pathways. Through targeted metabolomics, we observed that Mdivi-1 enhanced intracellular serine biosynthesis while reducing the production of C24:1-ceramide. Within these regulated phosphoproteins, dynamic dephosphorylation of proteasome subunit alpha type 3 serine 250 (PSMA3-S250) occurred after Mdivi-1 treatment. Further site-directed mutagenesis experiments revealed that the dephosphorylation-deficient mutant PSMA3-S250A exhibited a decreased cell survival. This research confirms that Mdivi-1’s inhibition of mitochondrial division leads to various side effects, ultimately influencing cell survival, rather than solely targeting Drp1 inhibition. © 2023 American Chemical Society.

关键词： Mdivi-1 multiomics neuroblastoma phosphoproteome proteome targeted metabolome

来源：评论

学校读者我要写书评

暂无评论

Single-cell multi-ome regression models identify functional and disease-associated enhancers and enable chromatin potential analysis (vol 56, pg 627, 2024)

引用

NATURE GENETICS 2024年第6期56卷 1319-1319页

作者： Mitra, Sneha Malik, Rohan Wong, Wilfred Rahman, Afsana Hartemink, Alexander J. Pritykin, Yuri Dey, Kushal K. Leslie, Christina S. Computational and Systems Biology Program Memorial Sloan Kettering Cancer Center New York City NY USA Rye Country Day School Rye NY USA Tri-Institutional Training Program in Computational Biology and Medicine New York City NY USA Hunter College City University of New York New York City NY USA Department of Computer Science Duke University Durham NC USA Program in Computational Biology and Bioinformatics Duke University Durham NC USA Center for Genomic and Computational Biology Duke University Durham NC USA Department of Computer Science Princeton University Princeton NJ USA Lewis-Sigler Institute for Integrative Genomics Princeton University Princeton NJ USA

We present a gene-level regulatory model, single-cell ATAC + RNA linking (SCARlink), which predicts single-cell gene expression and links enhancers to target genes using multi-ome (scRNA-seq and scATAC–seq co-assay) sequencing data. The approach uses regularized Poisson regression on tile-level accessibility data to jointly model all regulatory effects at a gene locus, avoiding the limitations of pairwise gene–peak correlations and dependence on peak calling. SCARlink outperformed existing gene scoring methods for imputing gene expression from chromatin accessibility across high-coverage multi-ome datasets while giving comparable to improved performance on low-coverage datasets. Shapley value analysis on trained models identified cell-type-specific gene enhancers that are validated by promoter capture Hi-C and are 11× to 15× and 5× to 12× enriched in fine-mapped eQTLs and fine-mapped genome-wide association study (GWAS) variants, respectively. We further show that SCARlink-predicted and observed gene expression vectors provide a robust way to compute a chromatin potential vector field to enable developmental trajectory analysis.

关键词： Epigenetics Population genetics Software

来源：评论

学校读者我要写书评

暂无评论

Particle-based simulations reveal two positive feedback loops allow relocation and stabilization of the polarity site during yeast mating

引用

PLoS computational biology 2023年第10 October期19卷 e1011523-e1011523页

作者： Guan, Kaiyun Curtis, Erin R. Lew, Daniel J. Elston, Timothy C. Curriculum in Bioinformatics and Computational Biology University of North Carolina at Chapel Hill Chapel HillNC United States Department of Biology Massachusetts Institute of Technology CambridgeMA United States Department of Pharmacology and Computational Medicine Program University of North Carolina at Chapel Hill Chapel HillNC United States

Many cells adjust the direction of polarized growth or migration in response to external directional cues. The yeast Saccharomyces cerevisiae orient their cell fronts (also called polarity sites) up pheromone gradients in the course of mating. However, the initial polarity site is often not oriented towards the eventual mating partner, and cells relocate the polarity site in an indecisive manner before developing a stable orientation. During this reorientation phase, the polarity site displays erratic assembly-disassembly behavior and moves around the cell cortex. The mechanisms underlying this dynamic behavior remain poorly understood. Particle-based simulations of the core polarity circuit revealed that molecular-level fluctuations are unlikely to overcome the strong positive feedback required for polarization and generate relocating polarity sites. Surprisingly, inclusion of a second pathway that promotes polarity site orientation generated relocating polarity sites with properties similar to those observed experimentally. This pathway forms a second positive feedback loop involving the recruitment of receptors to the cell membrane and couples polarity establishment to gradient sensing. This second positive feedback loop also allows cells to stabilize their polarity site once the site is aligned with the pheromone gradient. © 2023 Guan et al.

关键词： Cells

来源：评论

学校读者我要写书评

暂无评论

Higher-Order Generalization Bounds: Learning Deep Probabilistic programs via PAC-Bayes Objectives

arXiv

引用

arXiv 2022年

作者： Warrell, Jonathan Gerstein, Mark Program in Computational Biology and Bioinformatics Department of Molecular Biophysics and Biochemistry Yale University New HavenCT06520 United States

Deep Probabilistic programming (DPP) allows powerful models based on recursive computation to be learned using efficient deep-learning optimization techniques. Additionally, DPP offers a unified perspective, where inference and learning algorithms are treated on a par with models as stochastic programs. Here, we offer a framework for representing and learning flexible PAC-Bayes bounds as stochastic programs using DPP-based methods. In particular, we show that DPP techniques may be leveraged to derive generalization bounds that draw on the compositionality of DPP representations. In turn, the bounds we introduce offer principled training objectives for higher-order probabilistic programs. We offer a definition of a higher-order generalization bound, which naturally encompasses single- and multi-task generalization perspectives (including transfer- and meta-learning) and a novel class of bound based on a learned measure of model complexity. Further, we show how modified forms of all higher-order bounds can be efficiently optimized as objectives for DPP training, using variational techniques. We test our framework using single- and multi-task generalization settings on synthetic and biological data, showing improved performance and generalization prediction using flexible DPP model representations and learned complexity measures. Copyright © 2022, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Bayesian Spectral Graph Denoising with Smoothness Prior

Bayesian Spectral Graph Denoising with Smoothness Prior

引用

Annual Conference on Information Sciences and Systems (CISS)

作者： Sam Leone Xingzhi Sun Michael Perlmutter Smita Krishnaswamy Program for Applied Mathematics Yale University Department of Computer Science Yale University Department of Mathematics Boise State University Department of Genetics Yale School of Medicine Wu Tsai Institute Yale University FAIR Meta AI Computational Biology and Bioinformatics Program Yale University

Here we consider the problem of denoising features associated to complex data, modeled as signals on a graph, via a smoothness prior. This is motivated in part by settings such as single-cell RNA where the data is very high-dimensional, but its structure can be captured via an affinity graph. This allows us to utilize ideas from graph signal processing. In particular, we present algorithms for the cases where the signal is perturbed by Gaussian noise, dropout, and uniformly distributed noise. The signals are assumed to follow a prior distribution defined in the frequency domain which favors signals which are smooth across the edges of the graph. By pairing this prior distribution with our three models of noise generation, we propose Maximum A Posteriori (M.A.P.) estimates of the true signal in the presence of noisy data and provide algorithms for computing the M.A.P. Finally, we demonstrate the algorithms’ ability to effectively restore signals from white noise on image data and from severe dropout in single-cell RNA sequence data.

关键词：

来源：评论

学校读者我要写书评

暂无评论

ProtSCAPE: Mapping the landscape of protein conformations in molecular dynamics

arXiv

引用

arXiv 2024年

作者： Viswanath, Siddharth Bhaskar, Dhananjay Johnson, David R. Rocha, João Felipe Castro, Egbert Grady, Jackson D. Grigas, Alex T. Perlmutter, Michael A. O’Hern, Corey S. Krishnaswamy, Smita Department of Computer Science Yale University United States Department of Genetics Yale University United States Program in Computing Boise State University United States Computational Biology and Bioinformatics Program Yale University United States Department of Mathematics Boise State University United States

Understanding the dynamic nature of protein structures is essential for comprehending their biological functions. While significant progress has been made in predicting static folded structures, modeling protein motions on microsecond to millisecond scales remains challenging. To address these challenges, we introduce a novel deep learning architecture, Protein Transformer with Scattering, Attention, and Positional Embedding (ProtSCAPE), which leverages the geometric scattering transform alongside transformer-based attention mechanisms to capture protein dynamics from molecular dynamics (MD) simulations. ProtSCAPE utilizes the multi-scale nature of the geometric scattering transform to extract features from protein structures conceptualized as graphs and integrates these features with dual attention structures that focus on residues and amino acid signals, generating latent representations of protein trajectories. Furthermore, ProtSCAPE incorporates a regression head to enforce temporally coherent latent representations. Importantly, we demonstrate that ProtSCAPE generalizes effectively from short to long trajectories and from wild-type to mutant proteins, surpassing traditional approaches by delivering more precise and interpretable upsampling of dynamics. © 2024, CC BY.

关键词： Molecular docking

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：