In Silico Labeling: Predicting Fluorescent Labels in Unlabeled Images

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. [Display omitted] •Fluorescence microscopy images can be predicted from transmitted-light z stacks•7 fluorescent labels were validated across three labs, modalities, and cell types•New labels can be predicted using minimal additional training data In silico labeling, a machine-learning approach, reliably infers fluorescent measurements from transmitted-light images of unlabeled fixed or live biological samples.