You are here

Cell DOI:10.1016/j.cell.2018.03.040

In Silico Labeling: Predicting Fluorescent Labels in Unlabeled Images.

Publication TypeJournal Article
Year of Publication2018
AuthorsChristiansen, EM, Yang, SJ, D Ando, M, Javaherian, A, Skibinski, G, Lipnick, S, Mount, E, O'Neil, A, Shah, K, Lee, AK, Goyal, P, Fedus, W, Poplin, R, Esteva, A, Berndl, M, Rubin, LL, Nelson, P, Finkbeiner, S
Date Published2018 04 19
KeywordsAlgorithms, Animals, Cell Line, Tumor, Cell Survival, Cerebral Cortex, Fluorescent Dyes, Humans, Image Processing, Computer-Assisted, Induced Pluripotent Stem Cells, Machine Learning, Microscopy, Fluorescence, Motor Neurons, Neural Networks (Computer), Neurosciences, Rats, Software, Stem Cells

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.


Alternate JournalCell
PubMed ID29656897
PubMed Central IDPMC6309178
Grant ListR01 NS083390 / NS / NINDS NIH HHS / United States
RF1 AG056151 / AG / NIA NIH HHS / United States
RF1 AG058476 / AG / NIA NIH HHS / United States
R37 NS101996 / NS / NINDS NIH HHS / United States
U54 NS091046 / NS / NINDS NIH HHS / United States
C06 RR018928 / RR / NCRR NIH HHS / United States