lsmyrnaios
/
dnet-hadoop
forked from D-Net/dnet-hadoop
1
0
Fork 0
Code Pull Requests Activity

[EOSC DUMP] added resources needed for the review as test

This commit is contained in:
Miriam Baglioni 2022-11-25 17:16:20 +01:00
parent 33a2b1b5dc
commit 29d3da85f1
4 changed files with 323 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
dhp-workflows/dhp-graph-mapper/src/test/java/eu/dnetlib/dhp/oa/graph/raw/MappersTest.java
View File

@ -12,6 +12,7 @@ import java.util.Objects;
import java.util.Optional;
import java.util.stream.Collectors;
import com.fasterxml.jackson.core.JsonProcessingException;
import org.apache.commons.io.IOUtils;
import org.apache.commons.lang3.StringUtils;
import org.dom4j.DocumentException;
@ -991,6 +992,21 @@ class MappersTest {
assertTrue(actual.isEmpty());
}
@Test
void testEoscFutureHackZenodo() throws IOException {
final String xml = IOUtils
.toString(Objects.requireNonNull(getClass().getResourceAsStream("zenodo7351221.xml")));
final List<Oaf> actual = new OdfToOafMapper(vocs, false, true).processMdRecord(xml);
actual.forEach(a -> {
try {
System.out.println(new ObjectMapper().writeValueAsString(a));
} catch (JsonProcessingException e) {
e.printStackTrace();
}
});
}
private void assertValidId(final String id) {
// System.out.println(id);

118
dhp-workflows/dhp-graph-mapper/src/test/resources/eu/dnetlib/dhp/oa/graph/raw/zenodo7351221.xml Normal file
View File

@ -0,0 +1,118 @@
<?xml version='1.0' encoding='utf-8'?>
<record xmlns:oaf="http://namespace.openaire.eu/oaf"
xmlns:oai="http://www.openarchives.org/OAI/2.0/"
xmlns:datacite="http://datacite.org/schema/kernel-3"
xmlns:dr="http://www.driver-repository.eu/namespace/dr"
xmlns:dri="http://www.driver-repository.eu/namespace/dri">>
<header xmlns="http://www.openarchives.org/OAI/2.0/">
<identifier>oai:zenodo.org:7351221</identifier>
<datestamp>2020-01-20T16:45:20Z</datestamp>
<setSpec>openaire</setSpec>
<dri:objIdentifier>od______2659::040cee965a4544e343a2ba149783c3fc</dri:objIdentifier>
<dri:dateOfCollection>2022-11-25T01:08:31Z</dri:dateOfCollection>
</header>
<metadata>
<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.7351221</identifier>
<creators>
<creator>
<creatorName>Karki, Reagon</creatorName>
<givenName>Reagon</givenName>
<familyName>Karki</familyName>
<nameIdentifier nameIdentifierScheme="ORCID" schemeURI="http://orcid.org/">0000-0002-1815-0037</nameIdentifier>
<affiliation>Fraunhofer Institute of Translation Medicine and Pharmacology</affiliation>
</creator>
</creators>
<titles>
<title>COVID-19 Knowledge Graph: A semantic resource embedding biological and chemical entities</title>
</titles>
<publisher>Zenodo</publisher>
<publicationYear>2022</publicationYear>
<contributors>
<contributor contributorType="ContactPerson">
<contributorName>Zaliani, Andrea</contributorName>
<givenName>Andrea</givenName>
<familyName>Zaliani</familyName>
<nameIdentifier nameIdentifierScheme="ORCID" schemeURI="http://orcid.org/">0000-0002-1740-8390</nameIdentifier>
<affiliation>Fraunhofer Institute of Translation Medicine and Pharmacology</affiliation>
</contributor>
<contributor contributorType="ContactPerson">
<contributorName>Gadiya, Yojana</contributorName>
<givenName>Yojana</givenName>
<familyName>Gadiya</familyName>
<nameIdentifier nameIdentifierScheme="ORCID" schemeURI="http://orcid.org/">0000-0002-7683-0452</nameIdentifier>
<affiliation>Fraunhofer Institute of Translation Medicine and Pharmacology</affiliation>
</contributor>
<contributor contributorType="ProjectLeader">
<contributorName>Gribbon, Philip</contributorName>
<givenName>Philip</givenName>
<familyName>Gribbon</familyName>
<nameIdentifier nameIdentifierScheme="ORCID" schemeURI="http://orcid.org/">0000-0001-7655-2459</nameIdentifier>
<affiliation>Fraunhofer Institute of Translation Medicine and Pharmacology</affiliation>
</contributor>
</contributors>
<dates>
<date dateType="Issued">2022-11-23</date>
</dates>
<resourceType resourceTypeGeneral="Software"/>
<alternateIdentifiers>
<alternateIdentifier alternateIdentifierType="url">https://zenodo.org/record/7351221</alternateIdentifier>
</alternateIdentifiers>
<relatedIdentifiers>
<relatedIdentifier relatedIdentifierType="URL" relationType="IsSupplementTo" resourceTypeGeneral="Software">https://github.com/Fraunhofer-ITMP/BY-COVID-KG</relatedIdentifier>
<relatedIdentifier relatedIdentifierType="URL" relationType="IsDerivedFrom" resourceTypeGeneral="Software">https://github.com/Fraunhofer-ITMP/BY-COVID-KG/blob/main/BY_COVID_update_August.ipynb</relatedIdentifier>
<relatedIdentifier relatedIdentifierType="DOI" relationType="IsVersionOf">10.5281/zenodo.7351220</relatedIdentifier>
<relatedIdentifier relatedIdentifierType="URL" relationType="IsPartOf">https://zenodo.org/communities/covid-19</relatedIdentifier>
</relatedIdentifiers>
<version>v1.0.0</version>
<rightsList>
<rights rightsURI="info:eu-repo/semantics/openAccess">Open Access</rights>
</rightsList>
<descriptions>
<description descriptionType="Abstract">&lt;p&gt;A Knowledge graph representation of compounds and associated biological entities in the BY-COVID and EOSC Future project.&lt;/p&gt;
&lt;p&gt;&lt;strong&gt;Current status&lt;/strong&gt;&lt;/p&gt;
&lt;ul&gt;
&lt;li&gt;Number of Nodes: 35952&lt;/li&gt;
&lt;li&gt;Number of Edges: 279462&lt;/li&gt;
&lt;li&gt;Human Proteins: 1347&lt;/li&gt;
&lt;li&gt;Assay: 15835&lt;/li&gt;
&lt;li&gt;Chemical/Compound: 4096&lt;/li&gt;
&lt;li&gt;Mechanism of Action: 739&lt;/li&gt;
&lt;li&gt;Pathway: 1513&lt;/li&gt;
&lt;li&gt;Disease: 1585&lt;/li&gt;
&lt;li&gt;SideEffect: 7420&lt;/li&gt;
&lt;li&gt;Biological Process: 2085&lt;/li&gt;
&lt;li&gt;Molecular Function: 1332&lt;/li&gt;
&lt;/ul&gt;
&lt;p&gt;Please check the BY_COVID_update_August.ipynb for understanding step wise process of KG generation and KG statistics. The KG has been exported to formats such as graphml, sif and so on for visualizations in other platforms. For example, the graphml file can be imported to Cytoscape directly. These files are located in &amp;#39;data\export&amp;#39; folder.&lt;/p&gt;
&lt;p&gt;&amp;nbsp;&lt;/p&gt;</description>
</descriptions>
<fundingReferences>
<fundingReference>
<funderName>European Commission</funderName>
<funderIdentifier funderIdentifierType="Crossref Funder ID">10.13039/100010661</funderIdentifier>
<awardNumber awardURI="info:eu-repo/grantAgreement/EC/Horizon 2020 Framework Programme - Research and Innovation action/101017536/">101017536</awardNumber>
<awardTitle>EOSC Future</awardTitle>
</fundingReference>
<fundingReference>
<funderName>European Commission</funderName>
<funderIdentifier funderIdentifierType="Crossref Funder ID">10.13039/100018693</funderIdentifier>
<awardNumber awardURI="info:eu-repo/grantAgreement/EC/Horizon Europe Framework Programme - HORIZON-RIA\HORIZON Action Grant Budget-Based/101046203/">101046203</awardNumber>
<awardTitle>Beyond COVID</awardTitle>
</fundingReference>
</fundingReferences>
</resource>
<oaf:identifier identifierType="doi">10.5281/zenodo.7351221</oaf:identifier>
<dr:CobjCategory type="software">0029</dr:CobjCategory>
<oaf:accessrights>OPEN</oaf:accessrights>
<oaf:hostedBy name="ZENODO" id="opendoar____::2659"/>
<oaf:collectedFrom name="ZENODO" id="opendoar____::2659"/>
</metadata>
</record>

119
dhp-workflows/dhp-graph-mapper/src/test/resources/eu/dnetlib/dhp/oa/graph/raw/zenodo7351393.xml Normal file
View File

@ -0,0 +1,119 @@
<?xml version='1.0' encoding='utf-8'?>
<record xmlns:oaf="http://namespace.openaire.eu/oaf"
xmlns:oai="http://www.openarchives.org/OAI/2.0/"
xmlns:datacite="http://datacite.org/schema/kernel-3"
xmlns:dr="http://www.driver-repository.eu/namespace/dr"
xmlns:dri="http://www.driver-repository.eu/namespace/dri">>
<header xmlns="http://www.openarchives.org/OAI/2.0/">
<identifier>oai:zenodo.org:7351393</identifier>
<datestamp>2020-01-20T16:45:20Z</datestamp>
<setSpec>openaire</setSpec>
<dri:objIdentifier>od______2659::db2bc6381545f80dc9feec808a173ec0</dri:objIdentifier>
<dri:dateOfCollection>2022-11-25T01:08:31Z</dri:dateOfCollection>
</header>
<metadata>
<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.7351393</identifier>
<creators>
<creator>
<creatorName>Karki, Reagon</creatorName>
<givenName>Reagon</givenName>
<familyName>Karki</familyName>
<nameIdentifier nameIdentifierScheme="ORCID" schemeURI="http://orcid.org/">0000-0002-1815-0037</nameIdentifier>
<affiliation>Fraunhofer Institute of Translation Medicine and Pharmacology</affiliation>
</creator>
<creator>
<creatorName>Andrea, Zaliani</creatorName>
<givenName>Zaliani</givenName>
<familyName>Andrea</familyName>
<nameIdentifier nameIdentifierScheme="ORCID" schemeURI="http://orcid.org/">0000-0002-1740-8390</nameIdentifier>
<affiliation>Fraunhofer Institute of Translation Medicine and Pharmacology</affiliation>
</creator>
<creator>
<creatorName>Gadiya, Yojana</creatorName>
<givenName>Yojana</givenName>
<familyName>Gadiya</familyName>
<nameIdentifier nameIdentifierScheme="ORCID" schemeURI="http://orcid.org/">0000-0002-7683-0452</nameIdentifier>
<affiliation>Fraunhofer Institute of Translation Medicine and Pharmacology</affiliation>
</creator>
<creator>
<creatorName>Gribbon, Philip</creatorName>
<givenName>Philip</givenName>
<familyName>Gribbon</familyName>
<nameIdentifier nameIdentifierScheme="ORCID" schemeURI="http://orcid.org/">0000-0001-7655-2459</nameIdentifier>
<affiliation>Fraunhofer Institute of Translation Medicine and Pharmacology</affiliation>
</creator>
</creators>
<titles>
<title>Monkeypox Knowledge Graph: A semantic resource embedding biological and chemical entities</title>
</titles>
<publisher>Zenodo</publisher>
<publicationYear>2022</publicationYear>
<subjects>
<subject classid="keyword" classname="keyword" schemeid="dnet:subject_classification_typologies" schemename="dnet:subject_classification_typologies" >knowledge graph</subject>
<subject classid="keyword" classname="keyword" schemeid="dnet:subject_classification_typologies" schemename="dnet:subject_classification_typologies" >monkeypox</subject>
<subject classid="keyword" classname="keyword" schemeid="dnet:subject_classification_typologies" schemename="dnet:subject_classification_typologies" >systems biology</subject>
</subjects>
<dates>
<date dateType="Issued">2022-07-28</date>
</dates>
<resourceType resourceTypeGeneral="Software"/>
<alternateIdentifiers>
<alternateIdentifier alternateIdentifierType="url">https://zenodo.org/record/7351393</alternateIdentifier>
</alternateIdentifiers>
<relatedIdentifiers>
<relatedIdentifier relatedIdentifierType="DOI" relationType="IsCitedBy" resourceTypeGeneral="Preprint">10.1101/2022.08.02.502453</relatedIdentifier>
<relatedIdentifier relatedIdentifierType="URL" relationType="IsDerivedFrom" resourceTypeGeneral="Software">https://github.com/Fraunhofer-ITMP/mpox-kg/blob/main/graph.ipynb</relatedIdentifier>
<relatedIdentifier relatedIdentifierType="DOI" relationType="IsVersionOf">10.5281/zenodo.7351392</relatedIdentifier>
</relatedIdentifiers>
<version>v1.0.0</version>
<rightsList>
<rights rightsURI="info:eu-repo/semantics/openAccess">Open Access</rights>
</rightsList>
<descriptions>
<description descriptionType="Abstract">&lt;p&gt;The Monkeypox KG is built using viral and human proteins reported in different resources. Additionally, the KG represents chemicals tested against Monkeypox and their targets, associated biological processes, molecular functions, diseases and side effects.&lt;/p&gt;
&lt;p&gt;&lt;strong&gt;KG status&lt;/strong&gt;&lt;/p&gt;
&lt;p&gt;Version 1 stats:&lt;/p&gt;
&lt;ul&gt;
&lt;li&gt;Number of Nodes: 8235&lt;/li&gt;
&lt;li&gt;Number of Edges: 40422&lt;/li&gt;
&lt;/ul&gt;
&lt;p&gt;Version 2 stats (2nd September) :&lt;/p&gt;
&lt;ul&gt;
&lt;li&gt;Number of Nodes: 9129&lt;/li&gt;
&lt;li&gt;Number of Edges: 44568&lt;/li&gt;
&lt;/ul&gt;
&lt;p&gt;Please check the graph.ipynb for understanding step wise process of KG generation and KG statistics. The KG has been exported to formats such as graphml, sif and so on for visualizations in other platforms. For example, the graphml file can be imported to Cytoscape directly. These files are located in &amp;#39;data\export&amp;#39; folder.&lt;/p&gt;
&lt;p&gt;&amp;nbsp;&lt;/p&gt;</description>
<description descriptionType="Other">If you use this knowledge graph for your analysis, please cite it using this metadata.</description>
</descriptions>
<fundingReferences>
<fundingReference>
<funderName>European Commission</funderName>
<funderIdentifier funderIdentifierType="Crossref Funder ID">10.13039/100010661</funderIdentifier>
<awardNumber awardURI="info:eu-repo/grantAgreement/EC/Horizon 2020 Framework Programme - Research and Innovation action/101017536/">101017536</awardNumber>
<awardTitle>EOSC Future</awardTitle>
</fundingReference>
<fundingReference>
<funderName>European Commission</funderName>
<funderIdentifier funderIdentifierType="Crossref Funder ID">10.13039/100018693</funderIdentifier>
<awardNumber awardURI="info:eu-repo/grantAgreement/EC/Horizon Europe Framework Programme - HORIZON-RIA\HORIZON Action Grant Budget-Based/101046203/">101046203</awardNumber>
<awardTitle>Beyond COVID</awardTitle>
</fundingReference>
</fundingReferences>
</resource>
<oaf:identifier identifierType="doi">10.5281/zenodo.7351393</oaf:identifier>
<dr:CobjCategory type="software">0029</dr:CobjCategory>
<oaf:accessrights>OPEN</oaf:accessrights>
<oaf:hostedBy name="ZENODO" id="opendoar____::2659"/>
<oaf:collectedFrom name="ZENODO" id="opendoar____::2659"/>
</metadata>
</record>

70
dhp-workflows/dhp-graph-mapper/src/test/resources/eu/dnetlib/dhp/oa/graph/raw/zenodo7353841.xml Normal file
View File

@ -0,0 +1,70 @@
<?xml version='1.0' encoding='utf-8'?>
<record xmlns:oaf="http://namespace.openaire.eu/oaf"
xmlns:oai="http://www.openarchives.org/OAI/2.0/"
xmlns:datacite="http://datacite.org/schema/kernel-3"
xmlns:dr="http://www.driver-repository.eu/namespace/dr"
xmlns:dri="http://www.driver-repository.eu/namespace/dri">>
<header xmlns="http://www.openarchives.org/OAI/2.0/">
<identifier>oai:zenodo.org:7353841</identifier>
<datestamp>2020-01-20T16:45:20Z</datestamp>
<setSpec>openaire</setSpec>
<dri:objIdentifier>od______2659::3e4323c221f269e5f3d6db4c61dd2ec8</dri:objIdentifier>
<dri:dateOfCollection>22022-11-24T08:41:37Z</dri:dateOfCollection>
</header>
<metadata>
<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.7353841</identifier>
<creators>
<creator>
<creatorName>Tjerk Krijger</creatorName>
<nameIdentifier nameIdentifierScheme="ORCID" schemeURI="http://orcid.org/">0000-0002-1722-0523</nameIdentifier>
<affiliation>MARIS</affiliation>
</creator>
</creators>
<titles>
<title>ENVRI SP - Dashboard State of the Environment - Ocean Indicators</title>
</titles>
<publisher>Zenodo</publisher>
<publicationYear>2022</publicationYear>
<subjects>
<subject classid="keyword" classname="keyword" schemeid="dnet:subject_classification_typologies" schemename="dnet:subject_classification_typologies" >ENVRI-FAIR</subject>
<subject classid="keyword" classname="keyword" schemeid="dnet:subject_classification_typologies" schemename="dnet:subject_classification_typologies">Science Project</subject>
<subject classid="keyword" classname="keyword" schemeid="dnet:subject_classification_typologies" schemename="dnet:subject_classification_typologies">Dashboard State of the Environment</subject>
<subject classid="keyword" classname="keyword" schemeid="dnet:subject_classification_typologies" schemename="dnet:subject_classification_typologies">EOSC</subject>
<subject classid="keyword" classname="keyword" schemeid="dnet:subject_classification_typologies" schemename="dnet:subject_classification_typologies">EOSC-FUTURE</subject>
</subjects>
<dates>
<date dateType="Issued">2022-11-24</date>
</dates>
<resourceType resourceTypeGeneral="Other"/>
<alternateIdentifiers>
<alternateIdentifier alternateIdentifierType="url">https://zenodo.org/record/7353841</alternateIdentifier>
</alternateIdentifiers>
<relatedIdentifiers>
<relatedIdentifier relatedIdentifierType="DOI" relationType="IsVersionOf">10.5281/zenodo.7353840</relatedIdentifier>
<relatedIdentifier relatedIdentifierType="URL" relationType="IsPartOf">https://zenodo.org/communities/envri</relatedIdentifier>
</relatedIdentifiers>
<rightsList>
<rights rightsURI="https://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;The attached .yaml file is used as input to the Dashboard State of the Environment, which is a science project of the ENVRI-FAIR science cluster within EOSC-FUTURE. The contents of the file&amp;nbsp;enable&amp;nbsp;the visualization of&amp;nbsp;Ocean indicators on the dashboard.&amp;nbsp;It is possible to download the attached file and change the contents to include indicators from different domains such as atmosphere or biodiversity.&amp;nbsp;&lt;/p&gt;</description>
</descriptions>
<fundingReferences>
<fundingReference>
<funderName>European Commission</funderName>
<funderIdentifier funderIdentifierType="Crossref Funder ID">10.13039/100010661</funderIdentifier>
<awardNumber awardURI="info:eu-repo/grantAgreement/EC/Horizon 2020 Framework Programme - Research and Innovation action/101017536/">101017536</awardNumber>
<awardTitle>EOSC Future</awardTitle>
</fundingReference>
</fundingReferences>
</resource>
<oaf:identifier identifierType="doi">10.5281/zenodo.7353841</oaf:identifier>
<dr:CobjCategory type="other">0020</dr:CobjCategory>
<oaf:accessrights>OPEN</oaf:accessrights>
<oaf:hostedBy name="ZENODO" id="opendoar____::2659"/>
<oaf:collectedFrom name="ZENODO" id="opendoar____::2659"/>
</metadata>
</record>