Format

Send to

Choose Destination
Mol Syst Biol. 2017 Apr 18;13(4):924. doi: 10.15252/msb.20177551.

Automated analysis of high-content microscopy data with deep learning.

Kraus OZ1,2, Grys BT2,3, Ba J1, Chong Y4, Frey BJ1,2,5,6, Boone C7,3,5, Andrews BJ7,3,5.

Author information

1
Department of Electrical and Computer Engineering, University of Toronto, Toronto, ON, Canada.
2
Donnelly Centre for Cellular and Biomolecular Research, University of Toronto, Toronto, ON, Canada.
3
Department of Molecular Genetics, University of Toronto, Toronto, ON, Canada.
4
Cellular Pharmacology, Discovery Sciences, Janssen Pharmaceutical Companies, Johnson & Johnson, Beerse, Belgium.
5
Canadian Institute for Advanced Research, Program on Genetic Networks, Toronto, ON, Canada.
6
Canadian Institute for Advanced Research, Program on Learning in Machines & Brains, Toronto, ON, Canada.
7
Donnelly Centre for Cellular and Biomolecular Research, University of Toronto, Toronto, ON, Canada charlie.boone@utoronto.ca brenda.andrews@utoronto.ca.

Abstract

Existing computational pipelines for quantitative analysis of high-content microscopy data rely on traditional machine learning approaches that fail to accurately classify more than a single dataset without substantial tuning and training, requiring extensive analysis. Here, we demonstrate that the application of deep learning to biological image data can overcome the pitfalls associated with conventional machine learning classifiers. Using a deep convolutional neural network (DeepLoc) to analyze yeast cell images, we show improved performance over traditional approaches in the automated classification of protein subcellular localization. We also demonstrate the ability of DeepLoc to classify highly divergent image sets, including images of pheromone-arrested cells with abnormal cellular morphology, as well as images generated in different genetic backgrounds and in different laboratories. We offer an open-source implementation that enables updating DeepLoc on new microscopy datasets. This study highlights deep learning as an important tool for the expedited analysis of high-content microscopy data.

KEYWORDS:

Saccharomyces cerevisiae ; deep learning; high‐content screening; image analysis; machine learning

PMID:
28420678
PMCID:
PMC5408780
[Indexed for MEDLINE]
Free PMC Article

Supplemental Content

Full text links

Icon for HighWire Icon for PubMed Central
Loading ...
Support Center