Other Open Access

DNase-seq and histone mark ChIP-seq convolutional autoencoders

Lekschas, Fritz; Peterson, Brant; Haehn, Daniel; Ma, Eric; Gehlenborg, Nils; Pfister, Hanspeter


DataCite XML Export

<?xml version='1.0' encoding='utf-8'?>
<resource xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns="http://datacite.org/schema/kernel-4" xsi:schemaLocation="http://datacite.org/schema/kernel-4 http://schema.datacite.org/meta/kernel-4.1/metadata.xsd">
  <identifier identifierType="DOI">10.5281/zenodo.2609763</identifier>
  <creators>
    <creator>
      <creatorName>Lekschas, Fritz</creatorName>
      <givenName>Fritz</givenName>
      <familyName>Lekschas</familyName>
      <nameIdentifier nameIdentifierScheme="ORCID" schemeURI="http://orcid.org/">0000-0001-8432-4835</nameIdentifier>
      <affiliation>Harvard University</affiliation>
    </creator>
    <creator>
      <creatorName>Peterson, Brant</creatorName>
      <givenName>Brant</givenName>
      <familyName>Peterson</familyName>
      <affiliation>Novartis Institutes for BioMedical Research</affiliation>
    </creator>
    <creator>
      <creatorName>Haehn, Daniel</creatorName>
      <givenName>Daniel</givenName>
      <familyName>Haehn</familyName>
      <nameIdentifier nameIdentifierScheme="ORCID" schemeURI="http://orcid.org/">0000-0001-9144-3461</nameIdentifier>
      <affiliation>Harvard University</affiliation>
    </creator>
    <creator>
      <creatorName>Ma, Eric</creatorName>
      <givenName>Eric</givenName>
      <familyName>Ma</familyName>
      <nameIdentifier nameIdentifierScheme="ORCID" schemeURI="http://orcid.org/">0000-0003-0041-5989</nameIdentifier>
      <affiliation>Novartis Institutes for BioMedical Research</affiliation>
    </creator>
    <creator>
      <creatorName>Gehlenborg, Nils</creatorName>
      <givenName>Nils</givenName>
      <familyName>Gehlenborg</familyName>
      <nameIdentifier nameIdentifierScheme="ORCID" schemeURI="http://orcid.org/">0000-0003-0327-8297</nameIdentifier>
      <affiliation>Harvard Medical School</affiliation>
    </creator>
    <creator>
      <creatorName>Pfister, Hanspeter</creatorName>
      <givenName>Hanspeter</givenName>
      <familyName>Pfister</familyName>
      <nameIdentifier nameIdentifierScheme="ORCID" schemeURI="http://orcid.org/">0000-0002-3620-2582</nameIdentifier>
      <affiliation>Harvard University</affiliation>
    </creator>
  </creators>
  <titles>
    <title>DNase-seq and histone mark ChIP-seq convolutional autoencoders</title>
  </titles>
  <publisher>Zenodo</publisher>
  <publicationYear>2019</publicationYear>
  <subjects>
    <subject>Autoencoder</subject>
    <subject>CNN</subject>
    <subject>DNase-seq</subject>
    <subject>ChIP-seq</subject>
    <subject>histone mark ChIP-seq</subject>
  </subjects>
  <dates>
    <date dateType="Issued">2019-03-26</date>
  </dates>
  <resourceType resourceTypeGeneral="Other"/>
  <alternateIdentifiers>
    <alternateIdentifier alternateIdentifierType="url">https://zenodo.org/record/2609763</alternateIdentifier>
  </alternateIdentifiers>
  <relatedIdentifiers>
    <relatedIdentifier relatedIdentifierType="DOI" relationType="IsSupplementTo">10.1101/597518</relatedIdentifier>
    <relatedIdentifier relatedIdentifierType="DOI" relationType="IsVersionOf">10.5281/zenodo.2609762</relatedIdentifier>
  </relatedIdentifiers>
  <version>1.0.0</version>
  <rightsList>
    <rights rightsURI="http://creativecommons.org/licenses/by/4.0/legalcode">Creative Commons Attribution 4.0 International</rights>
    <rights rightsURI="info:eu-repo/semantics/openAccess">Open Access</rights>
  </rightsList>
  <descriptions>
    <description descriptionType="Abstract">&lt;p&gt;We provide 6 convolutional autoencoders for encoding DNase-seq and histone mark ChIP-seq regions of 3 kilobase pairs, 12 kilobase pairs, and 120 kilobase pairs at 25 base pair, 100 base pair, and 1000 base pair resolution respectively. The histone mark ChIP-seq autoencoders were trained on 49 experiments from the &lt;a href="http://www.roadmapepigenomics.org"&gt;Roadmap Epigenetics&lt;/a&gt; projects targeting&amp;nbsp;H3K4me1, H3K4me3, H3K27ac, H3K9ac, H3K27me3, H3K9me3, and H3K36me (see experiment IDs below). The DNase-seq autoencoders were trained on 120 experiments from the &lt;a href="https://www.encodeproject.org"&gt;ENCODE projects&lt;/a&gt;&amp;nbsp;(see accession numbers below).&lt;/p&gt;

&lt;p&gt;These autoencoders were produced as part of the &lt;a href="http://peax.lekschas.de"&gt;Peax project&lt;/a&gt;.&lt;/p&gt;

&lt;p&gt;Roadmap Epigenomics experiment IDs:&lt;/p&gt;

&lt;p&gt;E003, E004, E005, E006, E007, E008, E011, E014, E015, E016, E017, E019, E020, E026, E038, E047, E049, E062, E063, E066, E067, E068, E069, E072, E073, E074, E075, E076, E087, E101, E102, E103, E108, E111, E114, E115, E116, E117, E118, E119, E120, E121, E122, E123, E124, E125, E126, E127, E128&lt;/p&gt;

&lt;p&gt;ENCODE access numbers:&lt;/p&gt;

&lt;p&gt;ENCSR000EQB (2), ENCSR316UDN (1), ENCSR317SIH (1), ENCSR000EJO (1), ENCSR038XTK (1), ENCSR158VAT (1), ENCSR680SDS (1), ENCSR440FZS (1), ENCSR678PDD (1), ENCSR299INS (1), ENCSR000ENZ (1), ENCSR121ZSL (1), ENCSR796SJV (1), ENCSR035QHH (1), ENCSR515EWI (2), ENCSR000EQD (1), ENCSR271QSV (1), ENCSR426IEA (1), ENCSR000EPG (2), ENCSR000EIY (1), ENCSR595CSH (1), ENCSR000EQJ (1), ENCSR383BLX (1), ENCSR628IRM (1), ENCSR477RTP (1), ENCSR512CWR (1), ENCSR000EQI (1), ENCSR945RWN (1), ENCSR272RQX (1), ENCSR814KRX (1), ENCSR548MMD (1), ENCSR141VGA (1), ENCSR645GJD (1), ENCSR594NOE (1), ENCSR691MQJ (2), ENCSR000EPI (1), ENCSR381PXW (1), ENCSR468ZXN (1), ENCSR000EPE (2), ENCSR434OBM (1), ENCSR931UQB (1), ENCSR217RVH (1), ENCSR325LYJ (1), ENCSR004SUL (1), ENCSR035RVH (1), ENCSR217TAW (1), ENCSR184LMY (1), ENCSR940NLN (1), ENCSR000FFJ (1), ENCSR153LHP (1), ENCSR383SNM (1), ENCSR052AWE (1), ENCSR672EWY (2), ENCSR098PTC (2), ENCSR452DCM (1), ENCSR265TEK (1), ENCSR852TRT (1), ENCSR120LVW (1), ENCSR251UPG (1), ENCSR564JUY (1), ENCSR782XFY (1), ENCSR774RCO (1), ENCSR405TXU (1), ENCSR154ZNQ (1), ENCSR257BGZ (1), ENCSR148VUP (1), ENCSR593LTJ (1), ENCSR622TWS (1), ENCSR649KBB (1), ENCSR000ELO (1), ENCSR696TPW (1), ENCSR191EII (1), ENCSR019JDO (1), ENCSR000EML (1), ENCSR458LIB (2), ENCSR269SIA (2), ENCSR000EMR (1), ENCSR385AMY (1), ENCSR208DMX (1), ENCSR033STL (1), ENCSR683QJJ (1), ENCSR845CFB (1), ENCSR228VNQ (2), ENCSR517NHP (1), ENCSR337IRF (1), ENCSR000EPK (2), ENCSR554WUJ (1), ENCSR770DEN (1), ENCSR724CND (1), ENCSR911LTI (1), ENCSR857AEB (1), ENCSR959ZXU (1), ENCSR000EPD (1), ENCSR714DIF (1), ENCSR141NSQ (1), ENCSR083STA (1), ENCSR346IHH (1), ENCSR164WOF (1), ENCSR224FOA (2), ENCSR000EJQ (1), ENCSR621ENC (1), ENCSR228IKB (1), ENCSR954AJK (1), ENCSR206FSY (1), ENCSR275ICP (1), ENCSR552XJI (1), ENCSR445XYW (1), ENCSR166KPV (1), ENCSR935EVZ (1), ENCSR236SFP (1), ENCSR792ZXA (1), ENCSR426TPQ (1), ENCSR582IPV (2), ENCSR524OCB (1), ENCSR000EMV (1), ENCSR902XFY (1), ENCSR000EIS (1), ENCSR921NMD (1), ENCSR873ANE (1), ENCSR850YHJ (1)&lt;/p&gt;

&lt;p&gt;In paratheses are the replicate IDs.&lt;/p&gt;</description>
  </descriptions>
</resource>
180
46
views
downloads
All versions This version
Views 180180
Downloads 4646
Data volume 5.8 GB5.8 GB
Unique views 167167
Unique downloads 1515

Share

Cite as