Accurate Classification of Protein Subcellular Localization from High-Throughput Microscopy Images Using Deep Learning

By Tanel Pärnamaa, Leopold Parts. 2016

144 citations recorded by the source corpus.

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.

Subfields: Biophysics, Computer Vision and Pattern Recognition, Media Technology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biophysics

In Computer Vision and Pattern Recognition

In Media Technology

Citations in the corpus

Deep learning for computational biology (2016, positive): “Pa¨rnamaa and Parts used CNNs to classify pre-segmented image patches of individual yeast cells carrying a fluorescent protein to different subcellular localization patterns (Pa¨rnamaa & Parts, 2016).”
Applications of Deep Learning and Reinforcement Learning to Biological Data (2017, methodology): “cell nuclei. 3.2 Bioimaging DNN was used in detecting 12 different cellular compartments from microscopy images and was reported to have achieved classification accuracy of 87% compared to 75% for RF [136]. The mean performance of the detection was 83.24 5.18% using DNN and 69.85 6.33% using RF (Fig”
Machine learning and computer vision approaches for phenotypic profiling (2017, methodology): “Deep learning has also been used to classify protein localization in yeast and mechanisms of action in a publicly available drug screen (Kraus et al., 2016; Pärnamaa and Parts, 2016 Preprint ).”
Deep learning for cellular image analysis (2019, methodology): “Deep learning has also been used to classify spatial patterns in fluorescence images and to determine protein localization in large datasets from yeast 82–84 and humans 57 .”