Figure Open Access

Visualization of SARS-CoV-2 Infection Scenes by "Zero-Shot" Enhancements of Electron Microscopy Images

Drefs, Jakob; Salwig, Sebastian; Lücke, Jörg


JSON-LD (schema.org) Export

{
  "description": "<p>&quot;Zero-Shot&quot; enhancements of an electron microscopy image of SARS-CoV-2&nbsp; viruses&nbsp;in Vero cell cultures using&nbsp;probabilistic machine learning algorithms for denoising.&nbsp;&nbsp;The data available here&nbsp;were obtained and are discussed in&nbsp;the paper <em>Visualization of SARS-CoV-2 Infection Scenes by &quot;Zero-Shot&quot; Enhancements of Electron Microscopy Images </em>by <a href=\"https://www.biorxiv.org/content/10.1101/2021.02.25.432265v1\">Drefs et al. (2021)</a>.&nbsp;As input we used data made available by&nbsp;<a href=\"https://www.nature.com/articles/s41598-021-82852-7\">Laue et al. (2021)</a>&nbsp;who recorded images&nbsp;of ultrathin plastic sections using transmission electron microscopy (we downloaded the data from&nbsp;<a href=\"https://zenodo.org/record/3986580#.YDYT_ehKiUk\">this Zenodo repository</a>). The input image can be found in the H5 file&nbsp;<em>sars-cov2-em-noisy-input.h5.</em> Based on the data, we estimated pixel means and variances during the application of probabilistic machine learning algorithms for denoising. In the H5 files&nbsp;<em>sars-cov2-em-sssc-mean-reconstruction.h5</em> and&nbsp;<em>sars-cov2-em-sssc-variance-reconstruction.h5</em>&nbsp;the&nbsp;mean and variance of pixel estimations obtained with a Spike-and-Slab Sparse Coding (SSSC)&nbsp;model can be found&nbsp;(illustrated in&nbsp;Fig. 2 in the paper by Drefs et al. (2021)).&nbsp;In the H5 files&nbsp;<em>sars-cov2-em-gpmm-mean-reconstruction.h5</em> and&nbsp;<em>sars-cov2-em-gpmm-variance-reconstruction.h5</em>&nbsp;the mean and variance of pixel estimations obtained with a Gamma Poisson Mixture model&nbsp;(GPMM)&nbsp;can be found&nbsp;(illustrated in&nbsp;Fig. 3&nbsp;in the paper by Drefs et al. (2021)). The image &quot;<em>sars-cov2-em-sssc-variance-reconstruction-colorized.png&quot;&nbsp;</em>(illustrated in&nbsp;Fig.1 in the paper by Drefs et al. (2021))&nbsp;was obtained after contrast enhancement and colorization:&nbsp;structures that we manually identified as belonging to a cell were colored in blue, the remainder was colorized in yellow.</p>\n\n<p>The H5 files can be read and visualized in Python as follows:</p>\n\n<pre><code>import glob                                                                                 \nimport h5py                                                                                 \nimport matplotlib.pyplot as plt\nfor file in glob.glob(\"*.h5\"):\n    with h5py.File(file, \"r\") as f:\n        plt.figure()                                                                        \n        plt.imshow(f[\"data\"][...], cmap=\"gray\")\n        plt.title(file)\nplt.show()</code></pre>\n\n<p>&nbsp;</p>", 
  "license": "https://creativecommons.org/licenses/by/4.0/legalcode", 
  "creator": [
    {
      "affiliation": "Machine Learning Lab, School of Medicine and Health Science, University of Oldenburg, Germany", 
      "@type": "Person", 
      "name": "Drefs, Jakob"
    }, 
    {
      "affiliation": "Machine Learning Lab, School of Medicine and Health Science, University of Oldenburg, Germany", 
      "@type": "Person", 
      "name": "Salwig, Sebastian"
    }, 
    {
      "affiliation": "Machine Learning Lab, School of Medicine and Health Science, University of Oldenburg, Germany", 
      "@id": "https://orcid.org/0000-0001-9921-2529", 
      "@type": "Person", 
      "name": "L\u00fccke, J\u00f6rg"
    }
  ], 
  "url": "https://zenodo.org/record/4559517", 
  "datePublished": "2021-02-25", 
  "keywords": [
    "SARS-CoV", 
    "Coronaviridae", 
    "Virus Particle", 
    "Machine Learning", 
    "Unsupervised Learning", 
    "Probabilistic Generative Models", 
    "Transmission Electron Microscopy", 
    "Image Reconstruction", 
    "Image Denoising"
  ], 
  "@context": "https://schema.org/", 
  "identifier": "https://doi.org/10.5281/zenodo.4559517", 
  "@id": "https://doi.org/10.5281/zenodo.4559517", 
  "@type": "ImageObject", 
  "name": "Visualization of SARS-CoV-2 Infection Scenes by  \"Zero-Shot\" Enhancements of Electron Microscopy Images"
}
382
33
views
downloads
All versions This version
Views 382382
Downloads 3333
Data volume 62.6 MB62.6 MB
Unique views 362362
Unique downloads 1818

Share

Cite as