捕捉细胞异质性在细胞群体的表征以图像为基础的分析,使用对比学习
Robert van Dijk1, John Arevalo2, Mehrtash Babadi3
1CellVoyant Technologies, Bristol, United Kingdom.
PLoS computational biology
|November 11, 2024
概括
CytoSummaryNet通过聚合单细胞数据来增强基于图像的细胞概况,改进了行动预测的机制. 这种深度学习方法捕捉了细胞异质性,优于传统的平均化方法.
科学领域:
- 计算生物学是一种计算生物学.
- 细胞成像 细胞成像
- 机器学习是机器学习.
背景情况:
- 基于图像的细胞概况测量数千个单细胞特征,以比较扰乱的细胞群.
- 平均单细胞概况掩盖了关键的细胞异质性,限制了预测准确性.
研究的目的:
- 引入 CytoSummaryNet,一种基于深度集的新方法,用于改进单细胞特征数据的聚合.
- 通过捕捉细胞异质性来增强基于图像的细胞分析中的动作预测机制.
主要方法:
- CytoSummaryNet在多实例学习框架内采用自我监督的对比学习.
- 该方法聚合了单细胞概况,优先考虑信息细胞和减轻碎片或小线粒细胞等人工物.
主要成果:
- 与平均配置文件相比,CytoSummaryNet在平均平均精度方面提高了30-68%的行动预测机制.
- 解释性分析显示,该模型优先考虑大型,不拥挤的细胞,有效地处理细胞异质性.
结论:
- CytoSummaryNet为单细胞配置文件提供了一个简单的后处理方法,大大提高了检索性能.
- 该方法只需要随时可用的扰动标签用于培训,使其广泛适用于基于图像的分析数据集.
更多相关视频
09:21Author Spotlight: Generating Neuronal Phenotypic Profiles - A Protocol to Culture and Image Human Midbrain Dopaminergic Neurons
Published on: July 7, 2023
1.4K
09:48Discrimination and Characterization of Heterocellular Populations Using Quantitative Imaging Techniques
Published on: June 30, 2017
7.4K
相关概念视频
01:30Classification of Leukocytes
4.0K
Leukocytes are classified into two groups based on the presence or absence of cytoplasmic granules. Granular leukocytes, which contain granules, belong to the myeloid lineage and are divided into three subtypes: neutrophils, eosinophils, and basophils. These cells are roughly spherical and characterized by the granules in their cytoplasm.
Neutrophils are the most abundant type of granular leukocytes, comprising 50-70% of all leukocytes. They feature small, evenly distributed granules and a...
Neutrophils are the most abundant type of granular leukocytes, comprising 50-70% of all leukocytes. They feature small, evenly distributed granules and a...
4.0K
01:22iPS Cell Differentiation
2.9K
The ability of induced pluripotent stem cells or iPSCs to differentiate into most body cell types has stimulated repair and regenerative medicine research over the past few decades. iPSC-derived blood cells, hepatocytes, beta islet cells, cardiomyocytes, neurons, and other cell types can repair injuries or regenerate damaged tissue in diseases such as diabetes and neurodegenerative disorders.
2.9K