检索结果-内蒙古大学图书馆

SSRN 2025年

作者： Liu, Tianyu Zhang, Xiangyu Ying, Rex Zhao, Hongyu Interdepartmental Program in Computational Biology & Bioinformatics Yale University New HavenCT06511 United States Department of Biostatistics Yale University New HavenCT06511 United States Department of Computer Science Yale University New HavenCT06511 United States

Sequence-to-function models can predict gene expression from sequence data and be used to link genetic information with transcriptomics data to understand regulatory processes and their effects on complex phenotypes. The genomic language models are pre-trained with large-scale DNA sequences and can generate robust representations of these sequences by learning the genomic context. However, few studies can estimate the predictability of gene expression levels and bridge these two classes of models together to explore individualized gene expression prediction. In this manuscript, we propose UKBioBERT as a DNA language model pre-trained with genetic variants from UK BioBank. We demonstrate that UKBioBERT generates informative embeddings capable of identifying gene functions, and improving gene expression prediction in cell lines, thereby enhancing our understanding of gene expression predictability. Building upon these embeddings, we combine UKBioBERT with state-of-the-art sequence-to-function architectures, Enformer and Borzoi, to create UKBioFormer and UKBioZoi. These models exhibit better performance in predicting highly predictable gene expression levels and can be generalized across different cohorts. Furthermore, UKBioFormer effectively captures the relationship between genetic variants and expression variations, enabling in-silico mutation analyses. Collectively, our findings underscore the value of integrating genomic language models and sequence-to-function approaches for advancing functional genomics research. © 2025, The Authors. All rights reserved.

关键词： Genome

来源：评论

学校读者我要写书评

暂无评论

Learning Multi-cellular Representations of Single-Cell Transcriptomics Data Enables Characterization of Patient-Level Disease States 29th

Learning Multi-cellular Representations of Single-Cell Tran...

引用

29th International Conference on Research in Computational Molecular Biology, RECOMB 2025

作者： Liu, Tianyu De Brouwer, Edward Kuo, Tony Diamant, Nathaniel Missarova, Alsu Wang, Hanchen Hao, Minsheng Bravo, Hector Corrada Scalia, Gabriele Regev, Aviv Heimberg, Graham Research and Early Development Genentech South San FranciscoCA94080 United States Interdepartmental Program in Computational Biology and Bioinformatics Yale University New HavenCT06511 United States Roche Informatics F. Hoffmann-La Roche Ltd. Mississauga Canada Department of Computer Science Stanford University Palo AltoCA94035 United States

ISBN: (纸本)9783031902512

Single-cell RNA-seq (scRNA-seq) has become a prominent tool for studying human biology and disease. The availability of massive scRNA-seq datasets and advanced machine learning techniques has recently driven the development of single-cell foundation models that provide informative and versatile cell representations based on expression profiles. However, to understand disease states, we need to consider entire tissue ecosystems, simultaneously considering many different interacting cells. Here, we tackle this challenge by generating patient-level representations derived from multi-cellular expression context measured with scRNA-seq of tissues. We develop PaSCient, a novel model that employs a multi-level representation learning paradigm and provides importance scores at the individual cell and gene levels for fine-grained analysis across multiple cell types and gene programs characteristic of a given disease. We apply PaSCient to learn a disease model across a large-scale scRNA-seq atlas of 12.5 million cells from over 2,700 patients. Comprehensive and rigorous benchmarking demonstrates the superiority of PaSCient in disease classification and its multiple downstream applications, including dimensionality reduction, gene/cell type prioritization, and patient subgroup discovery. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Biomolecules

来源：评论

学校读者我要写书评

暂无评论

Synthetic Control Removes Spurious Discoveries from Double Dipping in Single-Cell and Spatial Transcriptomics Data Analyses 29th

Synthetic Control Removes Spurious Discoveries from Double ...

引用

29th International Conference on Research in Computational Molecular Biology, RECOMB 2025

作者： Song, Dongyuan Chen, Siqi Lee, Christy Li, Kexin Ge, Xinzhou Li, Jingyi Jessica Department of Genetics and Genome Sciences University of Connecticut Health Center FarmingtonCT06032 United States Interdepartmental Program of Bioinformatics University of California Los Angeles Los AngelesCA90095-7246 United States Department of Statistics and Data Science University of California Los Angeles Los AngelesCA90095-1554 United States Department of Statistics Oregon State University CorvallisOR97331-4606 United States

ISBN: (纸本)9783031902512

Double dipping is a common analytical pitfall in single-cell and spatial transcriptomics data analysis: after a clustering algorithm finds clusters as putative cell types or spatial domains, statistical tests are applied to the same data to identify differentially expressed (DE) genes as potential cell-type or spatial-domain markers. Because the genes that contribute to clustering are inherently likely to be identified as DE genes, double dipping can result in false-positive markers, especially when clusters are spurious, leading to ambiguously defined cell types or spatial domains. To address this challenge, we propose ClusterDE, a statistical method designed to identify post-clustering DE genes as reliable markers of cell types and spatial domains, while controlling the false discovery rate (FDR) regardless of clustering quality. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Biomolecules

来源：评论

学校读者我要写书评

暂无评论

MetNetAPI: A flexible method to access and manipulate biological network data from MetNet

引用

BMC Research Notes 2010年第1期3卷 1-9页

作者： Sucaet, Yves Wurtele, Eve Syrkin Department of Genetics Development and Cell Biology Iowa State University Ames IA 50011 United States Interdepartmental Program in Bioinformatics and Computational Biology Iowa State University Ames IA 50011 United States

Background. Convenient programmatic access to different biological databases allows automated integration of scientific knowledge. Many databases support a function to download files or data snapshots, or a webservice that offers "live" data. However, the functionality that a database offers cannot be represented in a static data download file, and webservices may consume considerable computational resources from the host server. Results. MetNetAPI is a versatile Application programming Interface (API) to the MetNetDB database. It abstracts, captures and retains operations away from a biological network repository and website. A range of database functions, previously only available online, can be immediately (and independently from the website) applied to a dataset of interest. Data is available in four layers: molecular entities, localized entities (linked to a specific organelle), interactions, and pathways. Navigation between these layers is intuitive (e.g. one can request the molecular entities in a pathway, as well as request in what pathways a specific entity participates). Data retrieval can be customized: Network objects allow the construction of new and integration of existing pathways and interactions, which can be uploaded back to our server. In contrast to webservices, the computational demand on the host server is limited to processing data-related queries only. Conclusions. An API provides several advantages to a systems biology software platform. MetNetAPI illustrates an interface with a central repository of data that represents the complex interrelationships of a metabolic and regulatory network. As an alternative to data-dumps and webservices, it allows access to a current and "live" database and exposes analytical functions to application developers. Yet it only requires limited resources on the server-side (thin server/fat client setup). The API is available for Java, *** and R programming environments and offers flexible query and bro

关键词： Application program Interface Molecular Entity Biological Database Command Line Interface Network Object

来源：评论

学校读者我要写书评

暂无评论

Doubly-stochastic normalization of the Gaussian kernel is robust to heteroskedastic noise

arXiv

引用

arXiv 2020年

作者： Landa, Boris Coifman, Ronald R. Kluger, Yuval Program in Applied Mathematics Yale University Interdepartmental Program in Computational Biology and Bioinformatics Yale University Department of Pathology Yale University School of Medicine

A fundamental step in many data-analysis techniques is the construction of an affinity matrix describing similarities between data points. When the data points reside in Euclidean space, a widespread approach is to from an affinity matrix by the Gaussian kernel with pairwise distances, and to follow with a certain normalization (e.g. the row-stochastic normalization or its symmetric variant). We demonstrate that the doubly-stochastic normalization of the Gaussian kernel with zero main diagonal (i.e. no self loops) is robust to heteroskedastic noise. That is, the doubly-stochastic normalization is advantageous in that it automatically accounts for observations with different noise variances. Specifically, we prove that in a suitable high-dimensional setting where heteroskedastic noise does not concentrate too much in any particular direction in space, the resulting (doubly-stochastic) noisy affinity matrix converges to its clean counterpart with rate m−1/2, where m is the ambient dimension. We demonstrate this result numerically, and show that in contrast, the popular row-stochastic and symmetric normalizations behave unfavourably under heteroskedastic noise. Furthermore, we provide a prototypical example of simulated single-cell RNA sequence data with strong intrinsic heteroskedasticity, where the advantage of the doubly-stochastic normalization for exploratory analysis is evident. Copyright © 2020, The Authors. All rights reserved.

关键词： Stochastic systems

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

An epigenetic clock for Xenopus tropicalis

引用

npj aging 2025年第1期11卷 38页

作者： Ronan Bennett Marco Morselli Kseniya Petrova Leonid Peshkin Matteo Pellegrini Bioinformatics Interdepartmental Program University of California Los Angeles Los Angeles CA USA. Department of Chemistry Life Sciences and Environmental Sustainability University of Parma Parma Italy. Department of Systems Biology Harvard Medical School Boston MA USA. Department of Systems Biology Harvard Medical School Boston MA USA. pesha@hms.harvard.edu. Department of Molecular Cell and Developmental Biology University of California Los Angeles Los Angeles CA USA. matteop@ucla.edu.

DNA methylation clocks have been widely used for accurate age prediction, but most studies have been carried out on mammals. Here we present an epigenetic clock for the aquatic frog Xenopus tropicalis, a widely used model organism in developmental biology and genomics. To construct the clock, we collected DNA methylation data from 192 frogs using targeted bisulfite sequencing at genomic regions containing CpG sites previously shown to have age-associated methylation in Xenopus. We found highly positively and negatively age-correlated CpGs are enriched in heterochromatic regions marked with H4K20me3 and H3K9me3. Positively age-correlated CpGs are enriched in bivalent chromatin and gene bodies with H3K36me3, and tend to be proximal to lowly expressed genes. These epigenetic features of aging are similar to those found in mammals, suggesting evolutionary conservation of epigenetic aging mechanisms. Our clock enables future aging biology experiments that leverage the unique properties of amphibians.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Hyperbolic procrustes analysis using riemannian geometry 21

Hyperbolic procrustes analysis using riemannian geometry

引用

Proceedings of the 35th International Conference on Neural Information Processing Systems

作者： Ya-Wei Eileen Lin Yuval Kluger Ronen Talmon Viterbi Faculty of Electrical and Computer Engineering Technion Program in Applied Mathematics Yale University and Interdepartmental Program in Computational Biology and Bioinformatics Yale University and Department of Pathology Yale University

ISBN: (纸本)9781713845393

Label-free alignment between datasets collected at different times, locations, or by different instruments is a fundamental scientific task. Hyperbolic spaces have recently provided a fruitful foundation for the development of informative representations of hierarchical data. Here, we take a purely geometric approach for label-free alignment of hierarchical datasets and introduce hyperbolic Procrustes analysis (HPA). HPA consists of new implementations of the three prototypical Procrustes analysis components: translation, scaling, and rotation, based on the Riemannian geometry of the Lorentz model of hyperbolic space. We analyze the proposed components, highlighting their useful properties for alignment. The efficacy of HPA, its theoretical properties, stability and computational efficiency are demonstrated in simulations. In addition, we showcase its performance on three batch correction tasks involving gene expression and mass cytometry data. Specifically, we demonstrate high-quality unsupervised batch effect removal from data acquired at different sites and with different technologies that outperforms recent methods for label-free alignment in hyperbolic spaces.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Hyperbolic Diffusion Procrustes Analysis for Intrinsic Representation of Hierarchical Data Sets

Hyperbolic Diffusion Procrustes Analysis for Intrinsic Repre...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Ya-Wei Eileen Lin Yuval Kluger Ronen Talmon Viterbi Faculty of Electrical and Computer Engineering Technion Interdepartmental Program in Computational Biology and Bioinformatics Yale University Applied Math Program Yale University Department of Pathology School of Medicine Yale University

In this paper, we present Hyperbolic Diffusion Procrustes Analysis (HDPA), a new method for informative representation of hierarchical datasets based on hyperbolic geometry, diffusion geometry, and Procrustes analysis. Our method jointly embeds multiple datasets in a product manifold of hyperbolic spaces, where the data's hidden common hierarchical structure is provably recovered. In addition, our method generates an intrinsic embedding that accommodates the joint representation of multiple datasets with different features, acquired by different equipment, at different sites, or under different environmental conditions. Experimental results demonstrate the efficacy of HDPA on three biomedical datasets comprising heterogeneous gene expression and mass cytometry data.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Use of Bayesian networks to dissect the complexity of genetic disease: application to the Genetic Analysis Workshop 17 simulated data

引用

BMC proceedings 2011年第9期5 Suppl 9卷 S37页

作者： Jia Kang Wei Zheng Lun Li Joon Sang Lee Xiting Yan Hongyu Zhao Interdepartmental Program in Computational Biology and Bioinformatics Yale University PO Box 208009 New Haven CT 06520-8114 USA. hongyu.zhao@yale.edu.

Complex diseases are often the downstream event of a number of risk factors, including both environmental and genetic variables. To better understand the mechanism of disease onset, it is of great interest to systematically investigate the crosstalk among various risk factors. Bayesian networks provide an intuitive graphical interface that captures not only the association but also the conditional independence and dependence structures among the variables, resulting in sparser relationships between risk factors and the disease phenotype than traditional correlation-based methods. In this paper, we apply a Bayesian network to dissect the complex regulatory relationships among disease traits and various risk factors for the Genetic Analysis Workshop 17 simulated data. We use the Bayesian network as a tool for the risk prediction of disease outcome.

关键词： Bayesian Network Disease Phenotype Area Under Curve Conditional Independence Risk Prediction Model

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：