Integrative clustering of cells and samples using multi-modal single-cell data

使用多模态单细胞数据对细胞和样本进行综合聚类

基本信息

批准号：
10215623
负责人：
Joshua D Campbell
金额：
$ 35.89万
依托单位：
BOSTON UNIVERSITY MEDICAL CAMPUS
依托单位国家：
美国
项目类别：
财政年份：
2019
资助国家：
美国
起止时间：
2019-08-01 至 2024-07-31
项目状态：
已结题

来源：
https://reporter.nih.gov/project-details/10215623
关键词：
Academic Medical Centers Address African Algorithms American Apache Atlases Bayesian Modeling Bioinformatics Biological Biological Process Biology Biometry Biopsy Boston Brain Catalogs Cells Cellular Assay Characteristics Chromatin Clinical Data Cloud Computing Complex Computational Biology Data Data Set Development Developmental Process Devices Disease Environment European Funding Gene Cluster Gene Expression Genomics Goals High Performance Computing Human Immunology Individual Lesion Letters Lung Lung nodule Malignant Neoplasms Malignant neoplasm of prostate Massachusetts Measurement Measures Messenger RNA Methods Microfluidics Modeling Molecular Molecular and Cellular Biology Nature Noise Normal Cell Nose Opiate Addiction Patients Procedures Process Proteins Protocols documentation Research Personnel Running Sampling Smoker Smoking Speed Subgroup Techniques Technology Tissues Visualization base cancer heterogeneity cell type cloud based cloud platform cluster computing combat complex biological systems computer science digital discrete data epigenetic marker experimental study genomic data high risk human tissue insight language processing large scale data lung development multimodal data multimodality multiple data types new technology novel premalignant protein biomarkers protein expression single cell analysis single cell technology single-cell RNA sequencing user-friendly web interface

项目摘要

Single-cell genomic technologies such as single-cell RNA-seq have emerged as powerful techniques to quantify molecular states of individual cells and can be used to elucidate the cellular building blocks of complex tissues and diseases. Given recent rapid advances in single-cell technologies, novel statistical and computational approaches are needed to efficiently analyze large-scale single-cell datasets with multiple data types such as gene and protein expression. Discrete Bayesian hierarchical models have been widely used for unsupervised modeling of discrete data types in fields such as Nature Language Processing (NLP). We have developed a Bayesian hierarchical model called Cellular Latent Dirichlet Allocation (Celda) to perform bi-clustering of genes into modules and cells into subpopulations. We will develop novel models that can perform clustering of cells into subpopulations using multi-modal genomic data or clustering of patients into subgroups using both single- cell data and patient-level characteristics. These novel methods will be made available in a scalable and interpretable cloud-based framework accessible to both computational and non-computational users. The aims of this study are to (1) develop novel models to perform integrative multi-modal and multi-level clustering with single-cell data, (2) develop an R package and cloud-based platform with a web interface for rapid inference and visualization of large-scale datasets, and (3) apply Celda models to single-cell datasets from a variety of biological settings including cancer, lung development, and immunology. Overall, these aims will be accomplished by an interdisciplinary team with strong expertise in computational biology and bioinformatics, biostatistics, computer science, and molecular and cellular biology.

单细胞基因组技术（例如单细胞RNA-seq）已成为量化的强大技术单个细胞的分子态，可用于阐明复杂组织的细胞构建块和疾病。鉴于单细胞技术的最新快速进步，新型统计和计算需要采用方法来有效地分析具有多种数据类型的大规模单细胞数据集基因和蛋白质表达。离散的贝叶斯分层模型已被广泛用于无监督在诸如自然语言处理（NLP）等领域中离散数据类型的建模。我们已经开发了贝叶斯分层模型称为细胞潜在迪里奇莱特分配（CELDA），以执行基因的双聚类进入模块和细胞分成亚群。我们将开发可以执行细胞聚类的新型模型使用多模式基因组数据或患者聚集到亚组中的亚组中的亚组细胞数据和患者级特征。这些新颖的方法将以可扩展性和可解释的基于云的框架可供计算和非计算用户访问。目的这项研究的是（1）开发新型模型，以执行综合多模式和多级聚类与单细胞数据，（2）开发一个带有Web接口的R包和云平台，用于快速推断和大规模数据集的可视化，（3）将CELDA模型应用于各种单细胞数据集生物环境，包括癌症，肺发育和免疫学。总的来说，这些目标将是由一个跨学科团队完成的，在计算生物学和生物信息学方面具有强大的专业知识，生物统计学，计算机科学以及分子和细胞生物学。

项目成果

期刊论文数量（6）

专著数量（0）

科研奖励数量（0）

会议论文数量（0）

专利数量（0）

Machine learning enables design automation of microfluidic flow-focusing droplet generation.

DOI：
10.1038/s41467-020-20284-z
发表时间：
2021-01-04
期刊：
Nature communications
影响因子：
16.6
作者：
Lashkaripour A;Rodriguez C;Mehdipour N;Mardian R;McIntyre D;Ortiz L;Campbell J;Densmore D
通讯作者：
Densmore D

Characterization and decontamination of background noise in droplet-based single-cell protein expression data with DecontPro.

使用 DecontPro 对基于液滴的单细胞蛋白质表达数据中的背景噪声进行表征和净化。