Image Tools for Computational Cellular Barcoding and Automated Annotation

用于计算细胞条形码和自动注释的图像工具

• 批准号: 10367874
• 负责人: STEVEN M FINKBEINER
• 金额: $ 41.35万
• 依托单位: J. DAVID GLADSTONE INSTITUTES
• 依托单位国家: 美国
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-01-19 至 2025-12-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10367874
• 关键词: Address; Algorithms; Anatomy; Animal Model; Artificial Intelligence; Automated Annotation; Bar Codes; Basic Science; Bioinformatics; Biological; Biological Markers; Biomedical Research; Brain; Cell Separation; Cells; Cellular biology; Central Nervous System Diseases; Characteristics; Chemicals; Collection; Communities; Complex; Complex Mixtures; Computers; Computing Methodologies; Consumption; Cultured Cells; Data; Data Analyses; Data Science; Data Set; Detection; Foundations; Genomics; Goals; Gold; Human; Image; Imaging Device; Imaging technology; Immobilization; Individual; Intervention; Investigation; Label; Learning; Letters; Link; Machine Learning; Manuals; Measurement; Memory; Microscope; Microscopy; Modeling; Monitor; Morphology; Nerve Degeneration; Neurites; Neurons; Neurosciences; Nightmare; Ownership; Phenotype; Physiology; Proteomics; Quality Control; Readability; Reading; Research; Research Personnel; Research Project Grants; Resolution; Sampling; Slice; Stimulus; Techniques; Technology; Testing; Time; Tissues; To specify; United States National Library of Medicine; Validation; Variant; Work; algorithm development; base; biomedical informatics; cell behavior; cell motility; cell type; cellular imaging; computerized tools; cost; data curation; data repository; experimental study; fluorescence imaging; image processing; in silico; interest; large datasets; machine learning algorithm; meetings; next generation; repository; response; robotic microscopy; screening; synaptogenesis; tool

PROJECT SUMMARY With technological breakthroughs in high-throughput single-cell imaging and screening, we can precisely monitor native cell behavior in response to diverse stimuli. Improvements in resolution and new detection capacity further enrich the recording from each cell. Many image-processing steps that help to extract the full breadth of the recording can be automated to a throughput comparable to the imaging itself. However, because biological samples can be complex and nonhomogeneous, it is valuable to specify subsets of cells when addressing downstream biological questions. With the amount of data that can now be generated from high-throughput measurements, this subset-selection step is a significant bottleneck to obtaining a quantitative result about the biological sample. Currently, the gold standard to reliably filter through cell data is manual annotation by a technician. This approach is costly and time-consuming, creating a significant bottleneck to answering important biological questions. To overcome this bottleneck, we will develop tools to automate annotation with three unique approaches: chemical annotation, annotation amplification, and cellular barcoding. Chemical annotation will deliver a computer-readable cell label via an additional biomarker. Annotation amplification will use small, curated datasets to generate large ones. Cellular barcoding will identify pixel-based signatures to uniquely identify individual cells. Once annotation is addressed computationally, relevant cells can be classified in-line with the acquisition. We can then produce a large annotated dataset. Both the computational tools and data repository will be shared with the scientific community as a validation set for new models and as a foundation for algorithms that could be developed across research groups studying cells with fluorescence imaging. The goal of this work is to generate the technology and define the experimental-computational methods that automate the highly manual steps of cell curation through a strong interplay between wet-lab and machine-learning techniques. The technology we propose is relevant to a broad scope of high-throughput measurement applications, because it enables curating samples computationally rather than experimentally.

项目摘要 随着高通量单细胞成像和筛选技术的突破，我们可以精确地监测 天然细胞对不同刺激的反应。分辨率的提高和新的检测能力进一步提高 丰富每个细胞的记录。许多图像处理步骤有助于提取 记录可以自动化到与成像本身相当的吞吐量。然而，由于生物 样本可以是复杂的和非均匀的，在寻址时指定细胞的子集是有价值的。 下游生物问题。随着现在可以从高吞吐量 在测量中，该子集选择步骤是获得关于测量的定量结果的显著瓶颈。 生物样本目前，可靠地过滤单元格数据的黄金标准是由 技师这种方法既昂贵又耗时，给回答重要问题造成了严重的瓶颈。 生物问题。为了克服这个瓶颈，我们将开发工具来自动化注释， 方法：化学注释、注释扩增和细胞条形码化。化学注释将 通过另外的生物标志物递送计算机可读的细胞标记。注释放大将使用小的， 策展数据集以生成大型数据集。细胞条形码将识别基于像素的签名， 识别单个细胞。一旦通过计算解决注释问题，就可以对相关细胞进行在线分类 与收购。然后，我们可以生成一个大型的带注释的数据集。计算工具和数据 存储库将与科学界共享，作为新模型的验证集和 这些算法可以在研究荧光成像细胞的研究小组中开发出来。目标 这项工作的重点是生成技术，并定义自动化的实验计算方法。 通过湿实验室和机器学习技术之间的强大相互作用，高度手动的细胞策展步骤。 我们提出的技术与广泛的高通量测量应用相关，因为 它使得能够通过计算而不是通过实验来管理样本。