Learning unsupervised feature representations for single cell microscopy images with paired cell inpainting
Learning unsupervised feature representations for single cell microscopy images with paired cell inpainting
复制标题
DOI：
10.1371/journal.pcbi.1007348
复制
发表时间：
2019-09-01
影响因子：
4.3
通讯作者：
Moses, Alan M.
中科院分区：
文献类型：
--
作者：
Lu, Alex X.;Kraus, Oren Z.;Moses, Alan M.
细胞显微镜图像包含丰富的生物学见解。为了提取这些信息，研究人员使用特征，或测量图像中感兴趣的模式。在这里，我们引入卷积神经网络（CNN）来自动设计荧光显微镜的特征。我们使用一种自监督方法来学习显微镜图像中单细胞的特征表示，而不需要标记训练数据。我们在一个简单的任务上训练CNN，该任务利用显微镜图像的固有结构并控制细胞形态和成像的变化：给定图像中的一个细胞，CNN被要求预测来自同一图像的第二个不同细胞中的荧光模式。我们表明，我们的方法学习了描述酵母和人类显微镜数据集中单细胞中蛋白质表达模式的高质量特征。此外，通过在人类蛋白质全蛋白质组聚类分析中捕获高分辨率细胞成分，以及通过定量多定位蛋白质和单细胞变异性，我们证明了我们的特征对探索性生物学分析是有用的。我们认为，在多通道显微镜图像中，配对细胞染色是一种获得单细胞特征表示的通用方法。
Cellular microscopy images contain rich insights about biology. To extract this information, researchers use features, or measurements of the patterns of interest in the images. Here, we introduce a convolutional neural network (CNN) to automatically design features for fluorescence microscopy. We use a self-supervised method to learn feature representations of single cells in microscopy images without labelled training data. We train CNNs on a simple task that leverages the inherent structure of microscopy images and controls for variation in cell morphology and imaging: given one cell from an image, the CNN is asked to predict the fluorescence pattern in a second different cell from the same image. We show that our method learns high-quality features that describe protein expression patterns in single cells both yeast and human microscopy datasets. Moreover, we demonstrate that our features are useful for exploratory biological analysis, by capturing high-resolution cellular components in a proteome-wide cluster analysis of human proteins, and by quantifying multi-localized proteins and single-cell variability. We believe paired cell inpainting is a generalizable method to obtain feature representations of single cells in multichannel microscopy images.