Dataset Open Access

DeepSTARR manuscript data

de Almeida, Bernardo P


MARC21 XML Export

<?xml version='1.0' encoding='UTF-8'?>
<record xmlns="http://www.loc.gov/MARC21/slim">
  <leader>00000nmm##2200000uu#4500</leader>
  <controlfield tag="005">20210920134831.0</controlfield>
  <controlfield tag="001">5502060</controlfield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">2561720</subfield>
    <subfield code="z">md5:7e53a9351b2520a4713a5ffdb5f1566c</subfield>
    <subfield code="u">https://zenodo.org/record/5502060/files/DeepSTARR.model.h5</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">11615</subfield>
    <subfield code="z">md5:9b796f79441e53dc75dd79b911fff872</subfield>
    <subfield code="u">https://zenodo.org/record/5502060/files/DeepSTARR.model.json</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">4476205</subfield>
    <subfield code="z">md5:011690ca80cf967d56fefd0c1386419f</subfield>
    <subfield code="u">https://zenodo.org/record/5502060/files/Sequences_activity_Test.txt</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">43682499</subfield>
    <subfield code="z">md5:4e65afa021fd426c74dbf24c31b8bbf9</subfield>
    <subfield code="u">https://zenodo.org/record/5502060/files/Sequences_activity_Train.txt</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">4409299</subfield>
    <subfield code="z">md5:5f30e863b2239e4f9ade6e7b81b3ff3c</subfield>
    <subfield code="u">https://zenodo.org/record/5502060/files/Sequences_activity_Val.txt</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">12025132</subfield>
    <subfield code="z">md5:c2d831a6e2cfb9345fa5e52de76bb453</subfield>
    <subfield code="u">https://zenodo.org/record/5502060/files/Sequences_Test.fa</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">116924268</subfield>
    <subfield code="z">md5:fe474a31c23db2daf7dc4d1fc49a8e5a</subfield>
    <subfield code="u">https://zenodo.org/record/5502060/files/Sequences_Train.fa</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">11760406</subfield>
    <subfield code="z">md5:9d1a0e5c9228aa033378af93074109e6</subfield>
    <subfield code="u">https://zenodo.org/record/5502060/files/Sequences_Val.fa</subfield>
  </datafield>
  <datafield tag="542" ind1=" " ind2=" ">
    <subfield code="l">open</subfield>
  </datafield>
  <datafield tag="260" ind1=" " ind2=" ">
    <subfield code="c">2021-09-20</subfield>
  </datafield>
  <datafield tag="909" ind1="C" ind2="O">
    <subfield code="p">openaire_data</subfield>
    <subfield code="o">oai:zenodo.org:5502060</subfield>
  </datafield>
  <datafield tag="100" ind1=" " ind2=" ">
    <subfield code="u">Research Institute of Molecular Pathology (IMP)</subfield>
    <subfield code="0">(orcid)0000-0002-6084-6775</subfield>
    <subfield code="a">de Almeida, Bernardo P</subfield>
  </datafield>
  <datafield tag="245" ind1=" " ind2=" ">
    <subfield code="a">DeepSTARR manuscript data</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;This repository holds the&amp;nbsp;trained DeepSTARR model&amp;nbsp;and the data&amp;nbsp;used to train and evaluate the model.&lt;/p&gt;

&lt;p&gt;&lt;strong&gt;Files:&lt;/strong&gt;&lt;/p&gt;

&lt;ul&gt;
	&lt;li&gt;&lt;strong&gt;&amp;lt;set&amp;gt;.fa&lt;/strong&gt;

	&lt;ul&gt;
		&lt;li&gt;FASTA files with DNA sequences of genomic regions from train/val/test sets.&lt;/li&gt;
	&lt;/ul&gt;
	&lt;/li&gt;
	&lt;li&gt;&lt;strong&gt;&amp;lt;set&amp;gt;*.txt&lt;/strong&gt;
	&lt;ul&gt;
		&lt;li&gt;Files with developmental and housekeeping activity of genomic regions from train/val/test sets.&lt;/li&gt;
	&lt;/ul&gt;
	&lt;/li&gt;
	&lt;li&gt;&lt;strong&gt;DeepSTARR.model.h5 &lt;/strong&gt;and&lt;strong&gt;&amp;nbsp;DeepSTARR.model.json&lt;/strong&gt;
	&lt;ul&gt;
		&lt;li&gt;DeepSTARR Keras model&lt;/li&gt;
	&lt;/ul&gt;
	&lt;/li&gt;
&lt;/ul&gt;</subfield>
  </datafield>
  <datafield tag="773" ind1=" " ind2=" ">
    <subfield code="n">doi</subfield>
    <subfield code="i">isVersionOf</subfield>
    <subfield code="a">10.5281/zenodo.5502059</subfield>
  </datafield>
  <datafield tag="024" ind1=" " ind2=" ">
    <subfield code="a">10.5281/zenodo.5502060</subfield>
    <subfield code="2">doi</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">dataset</subfield>
  </datafield>
</record>
828
4,595
views
downloads
All versions This version
Views 828828
Downloads 4,5954,595
Data volume 47.2 GB47.2 GB
Unique views 743743
Unique downloads 1,6041,604

Share

Cite as