Figure Open Access

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

Drefs, Jakob; Salwig, Sebastian; Lücke, Jörg


MARC21 XML Export

<?xml version='1.0' encoding='UTF-8'?>
<record xmlns="http://www.loc.gov/MARC21/slim">
  <leader>00000nkm##2200000uu#4500</leader>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">SARS-CoV</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">Coronaviridae</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">Virus Particle</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">Machine Learning</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">Unsupervised Learning</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">Probabilistic Generative Models</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">Transmission Electron Microscopy</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">Image Reconstruction</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">Image Denoising</subfield>
  </datafield>
  <controlfield tag="005">20210302095306.0</controlfield>
  <datafield tag="500" ind1=" " ind2=" ">
    <subfield code="a">We would like to acknowledge funding by the German Ministry of Research and Education (BMBF) in the project 05M2020 (SPAplus) which enabled this research through a top-up fund for COVID-19 research; and we would like to acknowledge funding by the DFG project 352015383 (SFB 1330, B2) which provided source code to train generative models. Furthermore, we would like to acknowledge support in terms of computational resources by the Oldenburg High Performance Compute Cluster (CARL) and  by the North German Supercomputing Alliance under grant nim00006.</subfield>
  </datafield>
  <controlfield tag="001">4559517</controlfield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Machine Learning Lab, School of Medicine and Health Science, University of Oldenburg, Germany</subfield>
    <subfield code="a">Salwig, Sebastian</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Machine Learning Lab, School of Medicine and Health Science, University of Oldenburg, Germany</subfield>
    <subfield code="0">(orcid)0000-0001-9921-2529</subfield>
    <subfield code="a">Lücke, Jörg</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">2361200</subfield>
    <subfield code="z">md5:88feeb70a50b5156c37f923135a5edb3</subfield>
    <subfield code="u">https://zenodo.org/record/4559517/files/sars-cov2-em-gpmm-mean-reconstruction.h5</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">2361200</subfield>
    <subfield code="z">md5:d49489eccd04f2f59c87d8b72bd72377</subfield>
    <subfield code="u">https://zenodo.org/record/4559517/files/sars-cov2-em-gpmm-variance-reconstruction.h5</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">526304</subfield>
    <subfield code="z">md5:9acd027f1f66c016fcd2efbba37d3b72</subfield>
    <subfield code="u">https://zenodo.org/record/4559517/files/sars-cov2-em-noisy-input.h5</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">2361200</subfield>
    <subfield code="z">md5:237cde6de13ae1f1728aca1a11a9d9dd</subfield>
    <subfield code="u">https://zenodo.org/record/4559517/files/sars-cov2-em-sssc-mean-reconstruction.h5</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">392691</subfield>
    <subfield code="z">md5:8224f1878e3212262baac10b3554bc37</subfield>
    <subfield code="u">https://zenodo.org/record/4559517/files/sars-cov2-em-sssc-variance-reconstruction-colorized.png</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">2361200</subfield>
    <subfield code="z">md5:408e3d997fc2b34bd4957ac047fe328d</subfield>
    <subfield code="u">https://zenodo.org/record/4559517/files/sars-cov2-em-sssc-variance-reconstruction.h5</subfield>
  </datafield>
  <datafield tag="542" ind1=" " ind2=" ">
    <subfield code="l">open</subfield>
  </datafield>
  <datafield tag="260" ind1=" " ind2=" ">
    <subfield code="c">2021-02-25</subfield>
  </datafield>
  <datafield tag="909" ind1="C" ind2="O">
    <subfield code="p">user-covid-19</subfield>
    <subfield code="p">user-ai_ml</subfield>
    <subfield code="o">oai:zenodo.org:4559517</subfield>
  </datafield>
  <datafield tag="100" ind1=" " ind2=" ">
    <subfield code="u">Machine Learning Lab, School of Medicine and Health Science, University of Oldenburg, Germany</subfield>
    <subfield code="a">Drefs, Jakob</subfield>
  </datafield>
  <datafield tag="245" ind1=" " ind2=" ">
    <subfield code="a">Visualization of SARS-CoV-2 Infection Scenes by  "Zero-Shot" Enhancements of Electron Microscopy Images</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">user-ai_ml</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">user-covid-19</subfield>
  </datafield>
  <datafield tag="540" ind1=" " ind2=" ">
    <subfield code="u">https://creativecommons.org/licenses/by/4.0/legalcode</subfield>
    <subfield code="a">Creative Commons Attribution 4.0 International</subfield>
  </datafield>
  <datafield tag="650" ind1="1" ind2="7">
    <subfield code="a">cc-by</subfield>
    <subfield code="2">opendefinition.org</subfield>
  </datafield>
  <datafield tag="520" ind1=" " ind2=" ">
    <subfield code="a">&lt;p&gt;&amp;quot;Zero-Shot&amp;quot; enhancements of an electron microscopy image of SARS-CoV-2&amp;nbsp; viruses&amp;nbsp;in Vero cell cultures using&amp;nbsp;probabilistic machine learning algorithms for denoising.&amp;nbsp;&amp;nbsp;The data available here&amp;nbsp;were obtained and are discussed in&amp;nbsp;the paper &lt;em&gt;Visualization of SARS-CoV-2 Infection Scenes by &amp;quot;Zero-Shot&amp;quot; Enhancements of Electron Microscopy Images &lt;/em&gt;by &lt;a href="https://www.biorxiv.org/content/10.1101/2021.02.25.432265v1"&gt;Drefs et al. (2021)&lt;/a&gt;.&amp;nbsp;As input we used data made available by&amp;nbsp;&lt;a href="https://www.nature.com/articles/s41598-021-82852-7"&gt;Laue et al. (2021)&lt;/a&gt;&amp;nbsp;who recorded images&amp;nbsp;of ultrathin plastic sections using transmission electron microscopy (we downloaded the data from&amp;nbsp;&lt;a href="https://zenodo.org/record/3986580#.YDYT_ehKiUk"&gt;this Zenodo repository&lt;/a&gt;). The input image can be found in the H5 file&amp;nbsp;&lt;em&gt;sars-cov2-em-noisy-input.h5.&lt;/em&gt; Based on the data, we estimated pixel means and variances during the application of probabilistic machine learning algorithms for denoising. In the H5 files&amp;nbsp;&lt;em&gt;sars-cov2-em-sssc-mean-reconstruction.h5&lt;/em&gt; and&amp;nbsp;&lt;em&gt;sars-cov2-em-sssc-variance-reconstruction.h5&lt;/em&gt;&amp;nbsp;the&amp;nbsp;mean and variance of pixel estimations obtained with a Spike-and-Slab Sparse Coding (SSSC)&amp;nbsp;model can be found&amp;nbsp;(illustrated in&amp;nbsp;Fig. 2 in the paper by Drefs et al. (2021)).&amp;nbsp;In the H5 files&amp;nbsp;&lt;em&gt;sars-cov2-em-gpmm-mean-reconstruction.h5&lt;/em&gt; and&amp;nbsp;&lt;em&gt;sars-cov2-em-gpmm-variance-reconstruction.h5&lt;/em&gt;&amp;nbsp;the mean and variance of pixel estimations obtained with a Gamma Poisson Mixture model&amp;nbsp;(GPMM)&amp;nbsp;can be found&amp;nbsp;(illustrated in&amp;nbsp;Fig. 3&amp;nbsp;in the paper by Drefs et al. (2021)). The image &amp;quot;&lt;em&gt;sars-cov2-em-sssc-variance-reconstruction-colorized.png&amp;quot;&amp;nbsp;&lt;/em&gt;(illustrated in&amp;nbsp;Fig.1 in the paper by Drefs et al. (2021))&amp;nbsp;was obtained after contrast enhancement and colorization:&amp;nbsp;structures that we manually identified as belonging to a cell were colored in blue, the remainder was colorized in yellow.&lt;/p&gt;

&lt;p&gt;The H5 files can be read and visualized in Python as follows:&lt;/p&gt;

&lt;pre&gt;&lt;code&gt;import glob                                                                                 
import h5py                                                                                 
import matplotlib.pyplot as plt
for file in glob.glob("*.h5"):
    with h5py.File(file, "r") as f:
        plt.figure()                                                                        
        plt.imshow(f["data"][...], cmap="gray")
        plt.title(file)
plt.show()&lt;/code&gt;&lt;/pre&gt;

&lt;p&gt;&amp;nbsp;&lt;/p&gt;</subfield>
  </datafield>
  <datafield tag="773" ind1=" " ind2=" ">
    <subfield code="n">doi</subfield>
    <subfield code="i">isVersionOf</subfield>
    <subfield code="a">10.5281/zenodo.4559516</subfield>
  </datafield>
  <datafield tag="024" ind1=" " ind2=" ">
    <subfield code="a">10.5281/zenodo.4559517</subfield>
    <subfield code="2">doi</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">image</subfield>
    <subfield code="b">figure</subfield>
  </datafield>
</record>
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