Developing tools for the unbiased analysis and visualization of scRNA-seq data

开发用于 scRNA-seq 数据公正分析和可视化的工具

• 批准号: 10279320
• 负责人: Eric J Deeds
• 金额: $ 29.67万
• 依托单位: UNIVERSITY OF CALIFORNIA LOS ANGELES
• 依托单位国家: 美国
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-09-01 至 2025-08-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10279320
• 关键词: Address; Adipose tissue; Algorithms; B-Cell Development; B-Cell Lymphomas; Benchmarking; Binomial Model; Biological; Biological Preservation; Biomedical Research; Candidate Disease Gene; Cells; Collaborations; Communities; Complex; Computational algorithm; Computer software; Data; Data Analyses; Data Set; Development; Diabetes Mellitus; Dimensions; Disease; Gene Expression; Gene Expression Regulation; Genes; Geometry; Goals; Homeostasis; Individual; Knowledge; Lead; Malignant Neoplasms; Measurement; Messenger RNA; Methods; Microscopy; Modeling; Neighborhoods; Noise; Pharmaceutical Preparations; Population; Process; Research Personnel; Resolution; Source; Statistical Models; Structure; Techniques; Testing; Three-Dimensional Image; Tissue-Specific Gene Expression; Tissues; Training; Translating; Variant; Visualization; Work; analysis pipeline; base; cell type; computerized tools; data complexity; data visualization; deep neural network; experimental study; feature selection; genome-wide; high dimensionality; imaging Segmentation; improved; innovation; insight; novel; novel strategies; single-cell RNA sequencing; tool; treatment response

ABSTRACT Single-cell RNA sequencing (scRNA-seq) provides genome-wide information about gene expression at the resolution of individual cells. The unprecedented scope of these data is revolutionizing our understanding of development and tissue homeostasis as well as diseases like cancer. A major issue with scRNA-seq, however, is the shear scale of the data, consisting of ~20,000 gene expression measurements in thousands to millions of cells. Effective computational approaches are clearly required to translate data of this size and complexity into actionable biological insights. For instance, scRNA-seq data are approximately 20,000-dimensional, and as a result all available analysis pipelines rely on multiple dimensionality reduction steps. This usually entails a combination of linear tools like PCA and non-linear techniques like t-SNE and UMAP. The data is generally reduced to between 10- and 100-D for data analysis (e.g. clustering into distinct cell types) and 2-D for visualization. The problem, however, is that dimensionality reduction can lead to loss of information. We recently showed that this loss of information is dramatic: for any given cell, over 95% of its neighbors are changed in the process of dimensionality reduction. This complete change in the structure of the data can introduce significant noise and bias into the analysis, and suggests the critical need for alternative approaches. The premise of this application is that reducing bias in scRNA-seq data analysis will maximize our ability to extract meaningful information from the data. In this proposal, we focus on developing new algorithms to address three specific steps in the typical analysis pipeline: (1) Dimensionality Reduction: Our hypothesis is that deep neural networks can be explicitly trained to maximize the amount of information that can be retained for both data analysis and visualization. (2) Feature Selection: Not all genes are equally informative for downstream analyses, so researchers generally choose a subset of genes based on variation in the population. We have shown that standard approaches to selecting genes convolve true biological variation with technical noise from the experiment. We hypothesize that statistical models based on our understanding of sources of technical noise can be used to select more informative genes. (3) Cell clustering: Clustering the data to determine cell types is critical, but cells with different identities often form complex, overlapping geometries in gene expression space that are difficult for existing algorithms to resolve. Our hypothesis is that new clustering tools, guided by prior knowledge and leveraging innovations in clustering from image segmentation, can overcome this problem. We will build these new tools and test them against existing benchmark datasets and novel data generated by our experimental collaborators. We will also integrate these tools into popular scRNA-seq analysis packages. Successful completion of the proposed work will allow the field to extract more biologically relevant information from the burgeoning set of scRNA-seq datasets.

抽象的 单细胞RNA测序（SCRNA-SEQ）提供了有关基因表达基因表达的基因表达的信息 单个细胞的分辨率。这些数据的前所未有的范围正在彻底改变我们对 发育和组织稳态以及癌症等疾病。但是，Scrna-Seq的一个主要问题 是数据的剪切量表，包括大约20,000个基因表达测量值，以数千至数百万美元的形式组成 细胞。显然需要有效的计算方法来翻译这种大小和复杂性的数据 进入可行的生物学见解。例如，SCRNA-SEQ数据约为20,000维，并且 结果，所有可用的分析管道都依赖于多个维度降低步骤。这通常需要一个 PCA等线性工具和T-SNE和UMAP等线性工具的组合。数据通常是 用于数据分析（例如，聚集到不同的单元格类型）和2-D的数据分析介于10到100-D之间 可视化。但是，问题是降低维度会导致信息丢失。我们 最近表明，信息丢失是巨大的：对于任何给定的单元，超过95％的邻居是 在降低维度的过程中发生了变化。数据结构的完全更改可以 将明显的噪音和偏见引入分析中，并提出对替代方法的关键需求。 该应用程序的前提是，减少SCRNA-SEQ数据分析中的偏差将最大化我们的能力 从数据中提取有意义的信息。在此提案中，我们专注于开发新算法 解决典型分析管道中的三个特定步骤：（1）降低维度：我们的假设是 可以明确训练深层神经网络，以最大程度地保留信息的量 用于数据分析和可视化。 （2）特征选择：并非所有基因都同样有用 下游分析，因此研究人员通常会根据基于差异的基因子集选择一部分基因 人口。我们已经表明，选择基因的标准方法使真实的生物学变异与 实验的技术噪音。我们根据我们对的理解来假设统计模型 技术噪声的来源可用于选择更多有用的基因。 （3）细胞聚类：聚类 确定细胞类型的数据至关重要，但是具有不同身份的细胞通常形成复杂的重叠 对于现有算法而言，基因表达空间中的几何形状很难解决。我们的假设是 新的聚类工具，以先验知识和利用创新为指导 细分，可以克服这个问题。我们将构建这些新工具，并根据现有 我们的实验合作者生成的基准数据集和新颖数据。我们还将整合这些 工具中流行的SCRNA-SEQ分析软件包。成功完成拟议的工作将允许 从迅速发展的SCRNA-SEQ数据集中提取更多具有生物学相关信息的字段。