A Spatially Resolved Molecular Atlas of Human Endothelium

人类内皮细胞的空间分辨分子图谱

• 批准号: 10411809
• 负责人: Long Cai
• 金额: $ 10万
• 依托单位: CALIFORNIA INSTITUTE OF TECHNOLOGY
• 依托单位国家: 美国
• 财政年份: 2018
• 资助国家: 美国
• 起止时间: 2018-09-20 至 2022-06-30
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10411809
• 关键词: Address; Algorithms; Area; Atlases; Biological; Biological Assay; Categories; Cells; Characteristics; Collaborations; Collection; Color; Communities; Computer Analysis; Computer software; Cytometry; Data; Data Set; Detection; Development; Dimensions; Disease; Endothelium; Genomics; Health; Human; Human BioMolecular Atlas Program; Image; Image Analysis; Immunofluorescence Immunologic; Individual; Investigation; Label; Libraries; Machine Learning; Mechanics; Methods; Modeling; Molecular; Nuclear; Positioning Attribute; Proteome; Proteomics; Research Personnel; Resolution; Semantics; Software Tools; Spottings; Technology; Tissue imaging; Tissues; Training; United States National Institutes of Health; Work; base; cell type; crowdsourcing; data modeling; deep learning; design; falls; genomic data; high dimensionality; human imaging; human tissue; human-in-the-loop; learning strategy; member; multiplexed imaging; next generation; open source; operation; preservation; single cell analysis; single molecule; terabyte; transcriptome; transcriptomics; two-dimensional

Project Abstract Recent advances in imaging and genomics are revolutionizing our understanding of human tissues. As these two technologies become more intertwined and high-throughput, there is an increasing need for scalable methods to interpret these data with single-cell resolution. In this Supplement, we seek to build on ongoing work to develop scalable and accurate algorithms for single-cell analysis of spatial genomics data. We propose to develop annotation software for annotating individual cells, their cell types, and functional tissue units in multiplexed imaging data. This software will be essential to produce training data to power the next generation of deep learning models for analyzing multiplexed imaging data.

项目摘要 成像和基因组学的最新进展正在彻底改变我们对人体组织的理解。正如这些 两种技术变得更加交织和高吞吐量，对可扩展性的需求越来越大 以单细胞分辨率解释这些数据的方法。在本补充文件中，我们力求在持续进行的基础上 致力于开发可扩展且准确的算法，用于空间基因组数据的单细胞分析。我们建议 开发注释软件，用于注释单个细胞、它们的细胞类型和功能组织单位 多路复用成像数据。该软件对于生成训练数据来为下一代提供动力至关重要 用于分析多重成像数据的深度学习模型。