Accurate Classification of Protein Subcellular Localization from High-Throughput Microscopy Images Using Deep Learning.
Accurate Classification of Protein Subcellular Localization from High-Throughput Microscopy Images Using Deep Learning.
复制标题
DOI：
10.1534/g3.116.033654
复制
发表时间：
2017-05-05
期刊：
影响因子：
--
通讯作者：
Parts L
中科院分区：
文献类型：
--
作者：
Pärnamaa T;Parts L
许多单细胞的高通量显微镜会产生难以直接分析的高维数据。一个重要的问题是自动检测荧光标记蛋白质所在的细胞区室，这对于有经验的人来说是一项相对简单的任务，但在计算机上很难自动化。在这里，我们训练了一个11层神经网络，该网络基于映射数千个酵母蛋白质的数据，实现了91%的每细胞定位分类准确率，以及99%的每蛋白质准确率。我们确认，低级别的网络功能对应于基本的图像特征，而更深层的本地化类。使用这个网络作为特征计算器，我们训练标准分类器，在只观察少量训练样本后将蛋白质分配到以前看不见的隔间。我们的结果是迄今为止最准确的亚细胞定位分类，并证明了深度学习对高通量显微镜的有用性。
High-throughput microscopy of many single cells generates high-dimensional data that are far from straightforward to analyze. One important problem is automatically detecting the cellular compartment where a fluorescently-tagged protein resides, a task relatively simple for an experienced human, but difficult to automate on a computer. Here, we train an 11-layer neural network on data from mapping thousands of yeast proteins, achieving per cell localization classification accuracy of 91%, and per protein accuracy of 99% on held-out images. We confirm that low-level network features correspond to basic image characteristics, while deeper layers separate localization classes. Using this network as a feature calculator, we train standard classifiers that assign proteins to previously unseen compartments after observing only a small number of training examples. Our results are the most accurate subcellular localization classifications to date, and demonstrate the usefulness of deep learning for high-throughput microscopy.