检索结果-内蒙古大学图书馆

41st International Conference on Machine Learning, ICML 2024

作者： Levine, Daniel Rizvi, Syed Asad Lévy, Sacha Pallikkavaliyaveetil, Nazreen Zhang, David Chen, Xingyu Ghadermarzi, Sina Wu, Ruiming Zheng, Zihe Vrkic, Ivan Zhong, Anna Raskin, Daphne Han, Insu de Oliveira Fonseca, Antonio Henrique Caro, Josue Ortega Karbasi, Amin Dhodapkar, Rahul M. van Dijk, David Department of Computer Science Yale University New HavenCT United States School of Engineering Applied Science University of Pennsylvania PhiladelphiaPA United States School of Computer and Communication Sciences Swiss Federal Institute of Technology Lausanne Lausanne Switzerland Department of Neuroscience Yale School of Medicine New HavenCT United States Wu Tsai Institute Yale University New HavenCT United States Google United States Yale Institute for Foundations of Data Science New HavenCT United States Yale School of Engineering and Applied Science New HavenCT United States Roski Eye Institute University of Southern California Los AngelesCA United States Yale School of Medicine New HavenCT United States Cardiovascular Research Center Yale School of Medicine New HavenCT United States Interdepartmental Program in Computational Biology & Bioinformatics Yale University New HavenCT United States

We introduce Cell2Sentence (C2S), a novel method to directly adapt large language models to a biological context, specifically single-cell transcriptomics. By transforming gene expression data into"cell sentences," C2S bridges the gap between natural language processing and biology. We demonstrate cell sentences enable the finetuning of language models for diverse tasks in biology, including cell generation, complex cell-type annotation, and direct data-driven text generation. Our experiments reveal that GPT-2, when fine-tuned with C2S, can generate biologically valid cells based on cell type inputs, and accurately predict cell types from cell sentences. This illustrates that language models, through C2S finetuning, can acquire a significant understanding of single-cell biology while maintaining robust text generation capabilities. C2S offers a flexible, accessible framework to integrate natural language processing with transcriptomics, utilizing existing models and libraries for a wide range of biological applications. Copyright 2024 by the author(s)

关键词： Gene expression

来源：评论

学校读者我要写书评

暂无评论

Local two-sample testing over graphs and point-clouds by random-walk distributions

arXiv

引用

arXiv 2020年

作者： Landa, Boris Qu, Rihao Chang, Joseph Kluger, Yuval Program in Applied Mathematics Yale University Department of Pathology Yale University School of Medicine Department of Statistics and Data Science Yale University Interdepartmental Program in Computational Biology and Bioinformatics Yale University Department of Immunology Yale School of Medicine

Rejecting the null hypothesis in two-sample testing is a fundamental tool for scientific discovery. Yet, aside from concluding that two samples do not come from the same probability distribution, it is often of interest to characterize how the two distributions differ. Given samples from two densities f1and f0, we consider the task of localizing occurrences of the inequality f1> f0. To avoid the challenges associated with high-dimensional space, we propose a general hypothesis testing framework where hypotheses are formulated adaptively to the data by conditioning on the combined sample from the two densities. We then investigate a special case of this framework where the notion of locality is captured by a random walk on a weighted graph constructed over this combined sample. We derive a tractable testing procedure for this case employing a type of scan statistic, and provide non-asymptotic lower bounds on the power and accuracy of our test to detect whether f1> f0in a local sense. Furthermore, we characterize the test's consistency according to a certain problem-hardness parameter, and show that our test achieves the minimax detection rate for this parameter. We conduct numerical experiments to validate our method, and demonstrate our approach on two real-world applications: detecting and localizing arsenic well contamination across the United States, and analyzing two-sample single-cell RNA sequencing data from melanoma *** Codes 62G10 Copyright © 2020, The Authors. All rights reserved.

关键词： Random processes

来源：评论

学校读者我要写书评

暂无评论

Spectral Top-Down Recovery of Latent Tree Models

arXiv

引用

arXiv 2021年

作者： Aizenbud, Yariv Jaffe, Ariel Wang, Meng Hu, Amber Amsel, Noah Nadler, Boaz Chang, Joseph T. Kluger, Yuval Program in Applied Mathematics Yale University New HavenCT06511 United States Department of Computer Science Weizmann Institute of Science Rehovot76100 Israel Department of Statistics Yale University New HavenCT06520 United States Interdepartmental Program in Computational Biology and Bioinformatics Yale University New HavenCT06511 United States Department of Pathology Yale University New HavenCT06511 United States

Modeling the distribution of high dimensional data by a latent tree graphical model is a prevalent approach in multiple scientific domains. A common task is to infer the underlying tree structure, given only observations of its terminal nodes. Many algorithms for tree recovery are computationally intensive, which limits their applicability to trees of moderate size. For large trees, a common approach, termed divide-and-conquer, is to recover the tree structure in two steps. First, recover the structure separately of multiple, possibly random subsets of the terminal nodes. Second, merge the resulting subtrees to form a full tree. Here, we develop Spectral Top-Down Recovery (STDR), a deterministic divide-and-conquer approach to infer large latent tree models. Unlike previous methods, STDR partitions the terminal nodes in a non random way, based on the Fiedler vector of a suitable Laplacian matrix related to the observed nodes. We prove that under certain conditions, this partitioning is consistent with the tree structure. This, in turn, leads to a significantly simpler merging procedure of the small subtrees. We prove that STDR is statistically consistent and bound the number of samples required to accurately recover the tree with high probability. Using simulated data from several common tree models in phylogenetics, we demonstrate that STDR has a significant advantage in terms of runtime, with improved or similar accuracy. Copyright © 2021, The Authors. All rights reserved.

关键词： Recovery

来源：评论

学校读者我要写书评

暂无评论

A general kernel boosting framework integrating pathways for predictive modeling based on genomic data

arXiv

引用

arXiv 2020年

作者： Zeng, Li Yu, Zhaolong Zhang, Yiliang Zhao, Hongyu Department of Biostatistics Yale University New HavenCT06511 United States Interdepartmental Program in Computational Biology and Bioinformatics Yale University New HavenCT06511 United States Department of Genetics Yale School of Medicine New HavenCT06510 United States

Predictive modeling based on genomic data has gained popularity in biomedical research and clinical practice by allowing researchers and clinicians to identify biomarkers and tailor treatment decisions more efficiently. Analysis incorporating pathway information can boost discovery power and better connect new findings with biological mechanisms. In this article, we propose a general framework, Pathway-based Kernel Boosting (PKB), which incorporates clinical information and prior knowledge about pathways for prediction of binary, continuous and survival outcomes. We introduce appropriate loss functions and optimization procedures for different outcome types. Our prediction algorithm incorporates pathway knowledge by constructing kernel function spaces from the pathways and use them as base learners in the boosting procedure. Through extensive simulations and case studies in drug response and cancer survival datasets, we demonstrate that PKB can substantially outperform other competing methods, better identify biological pathways related to drug response and patient survival, and provide novel insights into cancer pathogenesis and treatment response. Copyright © 2020, The Authors. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

A linked data graph approach to integration of immunological data

A linked data graph approach to integration of immunological...

引用

IEEE International Conference on bioinformatics and Biomedicine

作者： Syed Ahmad Chan Bukhari Jeff Mandell Steven H. Kleinstein Kei-Hoi Cheung Division of Computer Science Mathematics and Science Lesley H. & William L. Collins College of Professional Studies St. John's University Interdepartmental Program in Computational Biology and Bioinformatics Yale University Department of Pathology Interdepartmental Program in Computational Biology and Bioinformatics Yale University Department of Emergency Medicine and Yale Center for Medical Informatics Computationa Biology and Bioinformaticcs Yale University

ISBN: (纸本)9781728118680

Systems biology involves the integration of multiple data types (across different data sources) to offer a more complete picture of the biological system being studied. While many existing biological databases are implemented using the traditional SQL (Structured Query Language) database technology, NoSQL database technologies have been explored as a more relationship-based, flexible and scalable method of data integration. In this paper, we describe how to use the Neo4J graph database to integrate a variety of types of data sets in the context of systems vaccinology. Specifically, we have converted into a common graph model diverse types of vaccine response measurement data from the NIH/NIAID ImmPort data repository, pathway data from Reactome, influenza virus strains from WHO, and taxonomic data from NCBI Taxon. While Neo4J provides a graph-based query language (Cypher) for data retrieval, we develop a web-based dashboard for users to easily browse and visualize data without the need to learn Cypher. In addition, we have prototyped a natural language query interface for users to interact with our system. In conclusion, we demonstrate the feasibility of using a graph-based database for storing and querying immunological data with complex biological relationships. Querying a graph database through such relationships has the potential to reveal novel relationships among heterogeneous biological data.

关键词： ontology knowledgebase graph database immunology influenza vaccine graphic library Knowledge Bases Influenza Vaccines Ontology Immunology data integration Passwords DNA Integration integration data types Data sources SQL

来源：评论

学校读者我要写书评

暂无评论

Worm Perturb-Seq: massively parallel whole-animal RNAi and RNA-seq

引用

Nature communications 2025年第1期16卷 4785页

作者： Hefei Zhang Xuhang Li Dongyuan Song Onur Yukselen Shivani Nanda Alper Kucukural Jingyi Jessica Li Manuel Garber Albertha J M Walhout Department of Systems Biology University of Massachusetts Chan Medical School Worcester MA USA. Bioinformatics Interdepartmental Ph.D. Program University of California Los Angeles CA USA. Department of Genetics and Genome Sciences University of Connecticut Health Center Farmington CT USA. Via Scientific Inc. Cambridge MA USA. Pathology Beth Israel Deaconess Medical Center Harvard Medical School Boston MA USA. Department of Genomics and Computational Biology University of Massachusetts Chan Medical School Worcester MA USA. Department of Statistics and Data Science Department of Biostatistics Department of Computational Medicine and Department of Human Genetics University of California Los Angeles CA USA. Department of Genomics and Computational Biology University of Massachusetts Chan Medical School Worcester MA USA. manuel.garber@umassmed.edu. Department of Systems Biology University of Massachusetts Chan Medical School Worcester MA USA. marian.walhout@umassmed.edu.

Transcriptomes provide highly informative molecular phenotypes that, combined with gene perturbation, can connect genotype to phenotype. An ultimate goal is to perturb every gene and measure transcriptome changes, however, this is challenging, especially in whole animals. Here, we present 'Worm Perturb-Seq (WPS)', a method that provides high-resolution RNA-sequencing profiles for hundreds of replicate perturbations at a time in living animals. WPS introduces multiple experimental advances combining strengths of Caenhorhabditis elegans genetics and multiplexed RNA-sequencing with a novel analytical framework, EmpirDE. EmpirDE leverages the unique power of large transcriptomic datasets and improves statistical rigor by using gene-specific empirical null distributions to identify DEGs. We apply WPS to 103 nuclear hormone receptors (NHRs) and find a striking 'pairwise modularity' in which pairs of NHRs regulate shared target genes. We envision the advances of WPS to be useful not only for C. elegans, but broadly for other models, including human cells.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Spectral neighbor joining for reconstruction of latent tree models

arXiv

引用

arXiv 2020年

作者： Jaffe, Ariel Amsel, Noah Nadler, Boaz Chang, Joseph T. Kluger, Yuval Program in Applied Mathematics Yale University New HavenCT06511 United States Department of Computer Science Weizmann Institute of Science Rehovot76100 Israel Department of Statistics Yale University New HavenCT06520 United States Interdepartmental Program in Computational Biology and Bioinformatics New HavenCT06511 Singapore Department of Pathology New HavenCT06511 United States

A key assumption in multiple scientific applications is that the distribution of observed data can be modeled by a latent tree graphical model. An important example is phylogenetics, where the tree models the evolutionary lineages of various organisms. Given a set of independent realizations of the random variables at the leaves of the tree, a common task is to infer the underlying tree topology. In this work we develop Spectral Neighbor Joining (SNJ), a novel method to recover latent tree graphical models. In contrast to distance based methods, SNJ is based on a spectral measure of similarity between all pairs of observed variables. We prove that SNJ is consistent, and derive a sufficient condition for correct tree recovery from an estimated similarity matrix. Combining this condition with a concentration of measure result on the similarity matrix, we bound the number of samples required to recover the tree with high probability. We illustrate via extensive simulations that SNJ requires fewer samples to accurately recover trees in regimes where the tree contains a large number of leaves or long edges. We provide theoretical support for this observation by analyzing the model of a perfect binary tree. Copyright © 2020, The Authors. All rights reserved.

关键词： Recovery

来源：评论

学校读者我要写书评

暂无评论

帕博利珠单抗治疗伴脑转移NSCLC患者的一项非随机、开放Ⅱ期试验的长期随访结果和生物标志物分析

引用

中国肺癌杂志 2021年第9期24卷 I0007-I0016页

作者： Sarah B GOLDBERG Kurt A SCHALPER Scott N GETTINGER Amit MAHAJAN Roy S HERBST Anne C CHANG Rogerio LILENBAUM Frederick H WILSON Sacit Bulent OMAY James B YU Lucia JILAVEANU Thuy TRAN Kira PAVLIK Elin ROWEN Heather GERRSH Annette KOMLO Richa GUPTA Hailey WYATT Matthew RIBEIRO Yuval KLUGER Geyu ZHOU Wei WEI Veronica L CHANG Harriet M KLUGER 董晓荣(翻译/校对) Department of Medicine(Medical Oncology) Yale School of MedicineNew HavenCTUSA Department of Pathology Yale School of MedicineNew HavenCTUSA Department of Radiology Yale School of MedicineNew HavenCTUSA Department of Neurosurgery Yale School of MedicineNew HavenCTUSA Department of Therapeutic Radiology Yale School of MedicineNew HavenCTUSA Interdepartmental Program in Computational Biology and Bioinformatics Yale School of MedicineNew HavenCTUSA Department of Biostatistics Yale School of Public HealthNew HavenCTUSA 华中科技大学同济医学院附属协和医院胸部肿瘤科

背景与目的我们开展了一项帕博利珠单抗用于伴未治疗脑转移的非小细胞肺癌(non-small cell lung cancer,NSCLC)或黑色素瘤患者的疗效和安全性的II期试验,旨在评估程序性死亡受体1(programmed cell death 1,PD-1)抑制剂在中枢神经系统(ce... 详细信息

背景与目的我们开展了一项帕博利珠单抗用于伴未治疗脑转移的非小细胞肺癌(non-small cell lung cancer,NSCLC)或黑色素瘤患者的疗效和安全性的II期试验,旨在评估程序性死亡受体1(programmed cell death 1,PD-1)抑制剂在中枢神经系统(central nervous system,CNS)中的疗效。中期结果已发表,现报道对NSCLC队列的更新分析结果。方法这是一项开放性、单中心、II期试验。纳入标准:年龄≥18岁,诊断为晚期NSCLC并伴有≥1个5 mm-20 mm脑转移病灶,既往从未治疗或之前放疗后进展,无神经系统症状,不需要激素治疗且美国东部肿瘤协作组(Eastern Cooperative Oncology Group,ECOG)<2分。患者每2周接受一次帕博利珠单抗(10 mg/kg)治疗。队列1为程序性死亡配体1(programmed cell death ligand 1,PD-L1)≥1%的患者,队列2为PD-L1<1%或未评估的患者。主要终点是脑转移患者缓解比例。所有经治患者均纳入疗效与安全性终点的分析。该研究已结束入组,并于***登记注册,注册号为NCT02085070。结果2014年3月31日-2018年5月21日,共42例患者接受治疗。中位随访时间为8.3个月(IQR:4.5个月-26.2个月)。队列1的37例患者中11例有脑转移缓解[29.7%(95%CI:15.9%-47.0%)]。队列2未观察到缓解。治疗相关的3级-4级不良事件(adverse events,AEs)包括2例肺炎、1例全身症状、1例结肠炎、1例肾上腺皮质功能不全、1例高血糖症和1例低钾血症。6例(14%)患者发生了治疗相关的严重不良事件,包括肺炎、急性肾损伤、低钾血症和肾上腺皮质功能不全。没有观察到治疗相关死亡病例。结论帕博利珠单抗治疗PD-L1≥1%的NSCLC伴脑转移患者有效,且对所有纳入的未经治疗的脑转移患者安全。需要进一步探索免疫治疗用于NSCLC合并CNS转移。

关键词：非小细胞肺癌脑转移免疫治疗帕博利珠单抗

来源：评论

学校读者我要写书评

暂无评论

Cell2Sentence: teaching large language models the language of biology 24

Cell2Sentence: teaching large language models the language o...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Daniel Levine Syed Asad Rizvi Sacha Lévy Nazreen Pallikkavaliyaveetil David Zhang Xingyu Chen Sina Ghadermarzi Ruiming Wu Zihe Zheng Ivan Vrkic Anna Zhong Daphne Raskin Insu Han Antonio Henrique De Oliveira Fonseca Josue Ortega Caro Amin Karbasi Rahul M. Dhodapkar David Van Dijk Department of Computer Science Yale University New Haven CT School of Engineering Applied Science University of Pennsylvania Philadelphia PA School of Computer and Communication Sciences Swiss Federal Institute of Technology Lausanne Lausanne Switzerland Department of Computer Science Yale University New Haven CT and Department of Neuroscience Yale School of Medicine New Haven CT Department of Computer Science Yale University New Haven CT and Department of Neuroscience Yale School of Medicine New Haven CT and Wu Tsai Institute Yale University New Haven CT Google and Yale Institute for Foundations of Data Science New Haven CT and Department of Computer Science Yale University New Haven CT and Yale School of Engineering and Applied Science New Haven CT Roski Eye Institute University of Southern California Los Angeles CA and Department of Internal Medicine (Cardiology) Yale School of Medicine New Haven CT Department of Computer Science Yale University New Haven CT and Yale Institute for Foundations of Data Science New Haven CT and Wu Tsai Institute Yale University New Haven CT and Cardiovascular Research Center Yale School of Medicine New Haven CT and Interdepartmental Program in Computational Biology & Bioinformatics Yale University New Haven CT and Department of Internal Medicine (Cardiology) Yale School of Medicine New Haven CT

We introduce Cell2Sentence (C2S), a novel method to directly adapt large language models to a biological context, specifically single-cell transcriptomics. By transforming gene expression data into "cell sentences," C2S bridges the gap between natural language processing and biology. We demonstrate cell sentences enable the fine-tuning of language models for diverse tasks in biology, including cell generation, complex cell-type annotation, and direct data-driven text generation. Our experiments reveal that GPT-2, when fine-tuned with C2S, can generate biologically valid cells based on cell type inputs, and accurately predict cell types from cell sentences. This illustrates that language models, through C2S fine-tuning, can acquire a significant understanding of single-cell biology while maintaining robust text generation capabilities. C2S offers a flexible, accessible framework to integrate natural language processing with transcriptomics, utilizing existing models and libraries for a wide range of biological applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Distinct adipose progenitor cells emerging with age drive active adipogenesis

引用

Science (New York, N.Y.) 2025年第6745期388卷 eadj0430页

作者： Wang, Guan Li, Gaoyan Song, Anying Zhao, Yutian Yu, Jiayu Wang, Yifan Dai, Wenting Salas, Martha Qin, Hanjun Medrano, Leonard Dow, Joan Li, Aimin Armstrong, Brian Fueger, Patrick T. Yu, Hua Zhu, Yi Shao, Mengle Wu, Xiwei Jiang, Lei Campisi, Judith Yang, Xia Wang, Qiong A. Department of Molecular and Cellular Endocrinology Arthur Riggs Diabetes and Metabolism Research Institute City of Hope Medical Center Duarte CA USA Department of Integrative Biology and Physiology University of California Los Angeles CA United States Light Microscopy Core City of Hope Medical Center Duarte CA USA The Integrative Genomics Core City of Hope Medical Center Duarte CA USA Division of Developmental and Translational Diabetes and Endocrinology Research City of Hope Medical Center Duarte CA USA Comprehensive Metabolic Phenotyping Core City of Hope Medical Center Duarte CA USA Pathology Core of Shared Resources City of Hope Medical Center Duarte CA USA Comprehensive Cancer Center Beckman Research Institute City of Hope Medical Center Duarte CA USA Children's Nutrition Research Center Department of Pediatrics Baylor College of Medicine Houston TX United States Key Laboratory of Immune Response and Immunotherapy Shanghai Institute of Immunity and Infection Chinese Academy of Sciences Shanghai China Buck Institute for Research on Aging Novato CA United States Bioinformatics Interdepartmental Program University of California Los Angeles CA United States Institute for Quantitative and Computational Biosciences University of California Los Angeles CA United States Molecular and Medical Pharmacology University of California Los Angeles CA United States

Starting at middle age, adults often suffer from visceral adiposity and associated adverse metabolic disorders. Lineage tracing in mice revealed that adipose progenitor cells (APCs) in visceral fat undergo extensive adipogenesis during middle age. Thus, despite the low turnover rate of adipocytes in young adults, adipogenesis is unlocked during middle age. Transplantations quantitatively showed that APCs in middle-aged mice exhibited high adipogenic capacity cell-autonomously. Single-cell RNA sequencing identified a distinct APC population, the committed preadipocyte, age-enriched (CP-A), emerging at this age. CP-As demonstrated elevated proliferation and adipogenesis activity. Pharmacological and genetic manipulations indicated that leukemia inhibitory factor receptor signaling was indispensable for CP-A adipogenesis and visceral fat expansion. These findings uncover a fundamental mechanism of age-dependent adipose remodeling, offering critical insights into age-related metabolic diseases.

关键词：

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：