Google, Inc., Mountain View, CA 94043, USA.
Google, Inc., Mountain View, CA 94043, USA.
Cell. 2018 Apr 19;173(3):792-803.e19. doi: 10.1016/j.cell.2018.03.040. Epub 2018 Apr 12.
Microscopy is a central method in life sciences. Many popular methods, such as antibody labeling, are used to add physical fluorescent labels to specific cellular constituents. However, these approaches have significant drawbacks, including inconsistency; limitations in the number of simultaneous labels because of spectral overlap; and necessary perturbations of the experiment, such as fixing the cells, to generate the measurement. Here, we show that a computational machine-learning approach, which we call "in silico labeling" (ISL), reliably predicts some fluorescent labels from transmitted-light images of unlabeled fixed or live biological samples. ISL predicts a range of labels, such as those for nuclei, cell type (e.g., neural), and cell state (e.g., cell death). Because prediction happens in silico, the method is consistent, is not limited by spectral overlap, and does not disturb the experiment. ISL generates biological measurements that would otherwise be problematic or impossible to acquire.
显微镜是生命科学的一种核心方法。许多流行的方法，如抗体标记，被用于向特定的细胞成分添加物理荧光标记。然而，这些方法有显著的缺点，包括不一致性；由于光谱重叠，同时标记的数量有限；以及为了产生测量结果而对实验进行必要的干扰，例如固定细胞。在这里，我们展示了一种计算机器学习方法，我们称之为“虚拟标记”（ISL），它可以从未标记的固定或活生物样本的透射光图像中可靠地预测一些荧光标记。ISL 可以预测一系列的标记物，如细胞核、细胞类型（如神经）和细胞状态（如细胞死亡）。由于预测是在虚拟环境中进行的，所以该方法具有一致性，不受光谱重叠的限制，也不会干扰实验。ISL 生成的生物学测量结果是其他方法可能难以或无法获得的。
