Update metadata and add conformsTo

code/createPage.py

@@ -3,7 +3,10 @@
 import subprocess
 import shutil
 
-docsSubfolders = ['consortia', 'projects', 'theses']
+DOCS_SUBFOLDERS = ['consortia', 'projects', 'theses']
+MAPPINGS = [("employee", "Current project members"), ("alumni", "Previous project members"), ("member", "External contributors"), ("knowsAbout", "Outcomes"), ("parentOrganization", "Parent organization, consortium or research project"), ("subOrganization", "Sub-projects")]
+MAPPINGS_FROM = [i[0] for i in MAPPINGS]
+MAPPINGS_TO = [i[1] for i in MAPPINGS]
 
 def createTableLink(data):
     """
@@ -257,7 +260,7 @@ def processNamesInProject(item) :
         idURL = item["@id"]
         md += f'<a href="{idURL}" target="_blank"><img src = "/images/visit.svg" alt="Visit URL"/> Visit {subTypeURL}</a>\n\n'
     for prop, val in item.items(): 
-        if prop not in ["@type", "@id", "name", "funder", "givenName", "familyName"]:
+        if prop not in ["@type", "@id", "name", "http://purl.org/dc/terms/conformsTo", "funder", "givenName", "familyName"]:
             if prop == 'url':
                 md += renderUrlAsHref(val)
             else :
@@ -274,35 +277,26 @@ def processProjectData(data, jsonFileURL):
     Returns:
         A markdown text with the rendered metadata.
     """
-    mappings = [("employee", "Current project members"), ("alumni", "Previous project members"), ("member", "External contributors"), ("knowsAbout", "Outcomes"), ("parentOrganization", "Parent organization, consortium or research project"), ("subOrganization", "Sub-projects")]
-    mappings_from = [i[0] for i in mappings]
-    mappings_to = [i[1] for i in mappings]
-
     md = ""
 
     for property, value in data.items():
-        if property == 'name':
-            md += f'## {value}\n\n'
-            md += f'<p>{createGetJsonLink(jsonFileURL)}</p>\n'
-
-        if property == "foundingDate" :
-            md += f'_Started in {value}_\n'
-        elif property == 'dissolutionDate':
-            md += f'_Concluded in {value}_\n'
-
-        if property not in ["@type", "@id", "@context", "name", "dissolutionDate", "foundingDate"]:
-            if property in mappings_from :
-                i = mappings_from.index(property)
-                md += f'### {mappings_to[i]}\n\n'
+        if property not in ["@type", "@id", "@context", "http://purl.org/dc/terms/conformsTo", "name", "dissolutionDate", "foundingDate"]:
+            if property in MAPPINGS_FROM :
+                i = MAPPINGS_FROM.index(property)
+                md += f'### {MAPPINGS_TO[i]}\n\n'
             else :
                 md += f'### {property.capitalize()}\n\n'
 
             #ToDo: analyze and refactor code
             if property == 'url':
                 md += renderUrlAsHref(value)
             elif isinstance(value, list):
+                #knowsAbout is a list of objects
+                #there is a bug with inner lists (keywords) and objects (license) inside those objects
                 for item in value:
                     if isinstance(item, (dict, list)):
+                        #each item is an object/dict
+                        #loop on each key, value pair
                         for mdFolderName in item:
                             subItem = item.get(mdFolderName, "")
                             if (isinstance(subItem,(dict, list))):
@@ -327,6 +321,13 @@ def processProjectData(data, jsonFileURL):
                                     md += f'- {subProperty.capitalize()}: {subValue}\n'
             else:
                 md += f'{value}\n'
+        elif property == 'name':
+            md += f'## {value}\n\n'
+            md += f'<p>{createGetJsonLink(jsonFileURL)}</p>\n'
+        elif property == "foundingDate" :
+            md += f'_Started in {value}_\n'
+        elif property == 'dissolutionDate':
+            md += f'_Concluded in {value}_\n'
 
     return md
 
@@ -344,9 +345,9 @@ def prepareDocsSubfolder(docsPath):
     Returns:
         A list with the local path for all docs subfolders corresponding to research projects
     """
-    docsSubfoldersPath = [(docsPath + "/") + subfolder for subfolder in docsSubfolders]
+    docsSubfoldersPath = [(docsPath + "/") + subfolder for subfolder in DOCS_SUBFOLDERS]
     docsSubfoldersPath = [subfolder + "/" for subfolder in docsSubfoldersPath] 
-
+    
     for subfolder in docsSubfoldersPath:
         try:
             shutil.rmtree(subfolder)
@@ -400,7 +401,7 @@ def fromMetadatatoDocs():
                 md = ""
                 folderIndex = -1
                 try:
-                  folderIndex = docsSubfolders.index(mdFolderName)
+                  folderIndex = DOCS_SUBFOLDERS.index(mdFolderName)
                   md = f'# {mdFolderName.capitalize()} metadata\n\n'
                   md += processProjectData(data, jsonFileURL)
                   docFileProjectsPath = os.path.join(docsSubfoldersPath[folderIndex], jsonFileName.removesuffix('.json') + ".md")

docs/consortia/2021_NFDI4DataScience.md

@@ -41,14 +41,16 @@ NFDI, Data Science, Artificial Intelligence
 - Alternatename: German Research Foundation
 - URL: <a href="http://www.dfg.de/en/" target="_blank">http://www.dfg.de/en/</a>
 
+<a href="https://gepris.dfg.de/gepris/projekt/460234259" target="_blank"><img src = "/images/visit.svg" alt="Visit URL"/> Visit Grant</a>
+
 - Identifier: 460234259
 - Description: Project no. 460234259 (corresponding to the NFDI4DataScience consortium)
 
 
 <script type="application/ld+json">
 {
   "@context": "https://schema.org/",
-  "@id": "https://gepris.dfg.de/gepris/projekt/460234259",
+  "@id": "https://gepris.dfg.de/gepris/projekt/460234259#project",
   "@type": "ResearchProject",
   "name": "NFDI4DataScience",
   "foundingDate": "2021-10-01",
@@ -78,6 +80,7 @@ NFDI, Data Science, Artificial Intelligence
   "funding": [
     {
       "@type": "Grant",
+      "@id": "https://gepris.dfg.de/gepris/projekt/460234259",
       "funder": {
         "@type": "Organization",
         "@id": "https://ror.org/018mejw64",

docs/datasets.md

@@ -6,7 +6,7 @@
 <tbody>
 <tr>
 <td>identifier</td>
-<td><a href="https://doi.org/10.5281/zenodo.4903981" target="_blank">https://doi.org/10.5281/zenodo.4903981</a></td>
+<td>DOI:10.5281/zenodo.4903981</td>
 </tr>
 <tr>
 <td>name</td>
@@ -141,7 +141,7 @@
   "@type": "DataCatalog",
   "@id": "https://doi.org/10.5281/zenodo.4903981",
   "http://purl.org/dc/terms/conformsTo": "https://bioschemas.org/profiles/DataCatalog/0.4-DRAFT",
-  "identifier": "https://doi.org/10.5281/zenodo.4903981",
+  "identifier": "DOI:10.5281/zenodo.4903981",
   "name": "Whatizit performance evaluation against CRAFT corpus",
   "description": "Whatizit performance evaluation against CRAFT corpus wrt Gene Ontology annotations",
   "keywords": [
@@ -197,7 +197,7 @@
 <tbody>
 <tr>
 <td>identifier</td>
-<td><a href="https://doi.org/10.5281/zenodo.5035290" target="_blank">https://doi.org/10.5281/zenodo.5035290</a></td>
+<td>DOI:10.5281/zenodo.5035290</td>
 </tr>
 <tr>
 <td>name</td>
@@ -344,7 +344,7 @@
   "@type": "DataCatalog",
   "@id": "https://doi.org/10.5281/zenodo.5035290",
   "http://purl.org/dc/terms/conformsTo": "https://bioschemas.org/profiles/DataCatalog/0.4-DRAFT",
-  "identifier": "https://doi.org/10.5281/zenodo.5035290",
+  "identifier": "DOI:10.5281/zenodo.5035290",
   "name": "Complete Medline abstracts corpus between 2015-2019 annotated Whatizit text annotation tool",
   "description": "Gene Ontology annotations for Medline abstracts from 2015 to 2019 using Whatizit",
   "keywords": [
@@ -878,7 +878,7 @@
 <tbody>
 <tr>
 <td>identifier</td>
-<td><a href="https://doi.org/10.5281/zenodo.7793384" target="_blank">https://doi.org/10.5281/zenodo.7793384</a></td>
+<td>DOI:10.5281/zenodo.7793384</td>
 </tr>
 <tr>
 <td>name</td>
@@ -1017,7 +1017,7 @@
   "@type": "DataCatalog",
   "@id": "https://doi.org/10.5281/zenodo.7793384",
   "http://purl.org/dc/terms/conformsTo": "https://bioschemas.org/profiles/DataCatalog/0.4-DRAFT",
-  "identifier": "https://doi.org/10.5281/zenodo.7793384",
+  "identifier": "DOI:10.5281/zenodo.7793384",
   "name": "Protein Function Embeddings: First Beta Release of Datasets",
   "description": "Datasets generated from a thesis work that explores how information for protein functions can be exploited through embeddings so that the produced information can be used to improve protein function annotations",
   "keywords": [

docs/projects/2021_OntoClue.md

@@ -53,11 +53,11 @@ word-embeddings, document-embeddings, ontology-embeddings, document similarity,
 
 #### NFDI4DataScience
 
-<a href="https://www.nfdi4datascience.de/" target="_blank"><img src = "/images/visit.svg" alt="Visit URL"/> Visit Consortium</a>
+<a href="https://gepris.dfg.de/gepris/projekt/460234259#project" target="_blank"><img src = "/images/visit.svg" alt="Visit URL"/> Visit Consortium</a>
 
 #### STELLA Living Labs Project
 
-<a href="https://stella-project.org/" target="_blank"><img src = "/images/visit.svg" alt="Visit URL"/> Visit ResearchProject</a>
+<a href="ttps://gepris.dfg.de/gepris/projekt/407518790#project" target="_blank"><img src = "/images/visit.svg" alt="Visit URL"/> Visit ResearchProject</a>
 
 ### Funding
 
@@ -68,6 +68,8 @@ word-embeddings, document-embeddings, ontology-embeddings, document similarity,
 - Alternatename: German Research Foundation
 - URL: <a href="http://www.dfg.de/en/" target="_blank">http://www.dfg.de/en/</a>
 
+<a href="https://gepris.dfg.de/gepris/projekt/460234259" target="_blank"><img src = "/images/visit.svg" alt="Visit URL"/> Visit Grant</a>
+
 - Identifier: 460234259
 - Description: Project no. 460234259 (corresponding to the NFDI4DataScience consortium)
 #### Deutsche Forschungsgemeinschaft
@@ -77,6 +79,8 @@ word-embeddings, document-embeddings, ontology-embeddings, document similarity,
 - Alternatename: German Research Foundation
 - URL: <a href="http://www.dfg.de/en/" target="_blank">http://www.dfg.de/en/</a>
 
+<a href="https://gepris.dfg.de/gepris/projekt/407518790" target="_blank"><img src = "/images/visit.svg" alt="Visit URL"/> Visit Grant</a>
+
 - Identifier: 407518790
 - Description: Project no. 407518790 (corresponding to the STELLA project)
 ### Outcomes
@@ -85,26 +89,55 @@ word-embeddings, document-embeddings, ontology-embeddings, document similarity,
 
 <a href="https://doi.org/10.4126/FRL01-006440397" target="_blank"><img src = "/images/visit.svg" alt="Visit URL"/> Visit ScholarlyArticle</a>
 
+- Identifier: DOI:10.4126/FRL01-006440397s
 - Datepublished: 2023-06-22
 #### OntoClue, a framework to compare vector-based approaches for document relatedness using the RELISH corpus - Poster
 
 <a href="https://ceur-ws.org/Vol-3415/paper-38.pdf" target="_blank"><img src = "/images/visit.svg" alt="Visit URL"/> Visit Poster</a>
 
+- Identifier: CEUR:Vol-3415/paper-38
 - Datepublished: 2023-03-01
 #### Ontology Clustering with OWL2Vec*
 
 <a href="https://ceur-ws.org/Vol-2918/short3.pdf" target="_blank"><img src = "/images/visit.svg" alt="Visit URL"/> Visit ScholarlyArticle</a>
 
+- Identifier: CEUR:Vol-2918/short3
 - Datepublished: 2021-07-28
+#### Creative Commons Attribution 4.0 International
+
+<a href="https://spdx.org/licenses/CC-BY-4.0.html" target="_blank"><img src = "/images/visit.svg" alt="Visit URL"/> Visit CreativeWork</a>
+
+- Alternatename: CC BY 4.0
+- URL: <a href="https://creativecommons.org/licenses/by/4.0/" target="_blank">https://creativecommons.org/licenses/by/4.0/</a>
+
 #### Complete Medline abstracts corpus between 2015-2019 annotated Whatizit text annotation tool
 
 <a href="https://doi.org/10.5281/zenodo.5035290" target="_blank"><img src = "/images/visit.svg" alt="Visit URL"/> Visit DataCatalog</a>
 
+- Identifier: DOI:10.5281/zenodo.5035290
+- Description: Gene Ontology annotations for Medline abstracts from 2015 to 2019 using Whatizit
+- Keywords: Whatizit, Semantic annotation, Medline, text-mining
+- License: {'@type': 'CreativeWork', '@id': 'https://spdx.org/licenses/CC-BY-4.0.html', 'name': 'Creative Commons Attribution 4.0 International', 'alternateName': 'CC BY 4.0', 'url': 'https://creativecommons.org/licenses/by/4.0/'}
+- URL: <a href="https://zenodo.org/record/5035290" target="_blank">https://zenodo.org/record/5035290</a>
+
 - Datepublished: 2021-06-27
+#### Creative Commons Attribution 4.0 International
+
+<a href="https://spdx.org/licenses/CC-BY-4.0.html" target="_blank"><img src = "/images/visit.svg" alt="Visit URL"/> Visit CreativeWork</a>
+
+- Alternatename: CC BY 4.0
+- URL: <a href="https://creativecommons.org/licenses/by/4.0/" target="_blank">https://creativecommons.org/licenses/by/4.0/</a>
+
 #### Whatizit performance evaluation against CRAFT corpus
 
 <a href="https://doi.org/10.5281/zenodo.4903981" target="_blank"><img src = "/images/visit.svg" alt="Visit URL"/> Visit DataCatalog</a>
 
+- Identifier: DOI:10.5281/zenodo.4903981
+- Description: Whatizit performance evaluation against CRAFT corpus wrt Gene Ontology annotations
+- Keywords: Whatizit, Semantic annotation, CRAFT, manual annotation, performance
+- License: {'@type': 'CreativeWork', '@id': 'https://spdx.org/licenses/CC-BY-4.0.html', 'name': 'Creative Commons Attribution 4.0 International', 'alternateName': 'CC BY 4.0', 'url': 'https://creativecommons.org/licenses/by/4.0/'}
+- URL: <a href="https://zenodo.org/record/4903981" target="_blank">https://zenodo.org/record/4903981</a>
+
 - Datepublished: 2021-06-05
 ### External contributors
 
@@ -208,18 +241,19 @@ word-embeddings, document-embeddings, ontology-embeddings, document similarity,
     },
     {
       "@type": "Consortium",
-      "@id": "https://www.nfdi4datascience.de/",
+      "@id": "https://gepris.dfg.de/gepris/projekt/460234259#project",
       "name": "NFDI4DataScience"
     },
     {
       "@type": "ResearchProject",
-      "@id": "https://stella-project.org/",
+      "@id": "ttps://gepris.dfg.de/gepris/projekt/407518790#project",
       "name": "STELLA Living Labs Project"
     }
   ],
   "funding": [
     {
       "@type": "Grant",
+      "@id": "https://gepris.dfg.de/gepris/projekt/460234259",
       "funder": {
         "@type": "Organization",
         "@id": "https://ror.org/018mejw64",
@@ -232,6 +266,7 @@ word-embeddings, document-embeddings, ontology-embeddings, document similarity,
     },
     {
       "@type": "Grant",
+      "@id": "https://gepris.dfg.de/gepris/projekt/407518790",
       "funder": {
         "@type": "Organization",
         "@id": "https://ror.org/018mejw64",
@@ -247,31 +282,60 @@ word-embeddings, document-embeddings, ontology-embeddings, document similarity,
     {
       "@type": "ScholarlyArticle",
       "@id": "https://doi.org/10.4126/FRL01-006440397",
+      "http://purl.org/dc/terms/conformsTo": "https://bioschemas.org/profiles/ScholarlyArticle/0.3-DRAFT",
+      "identifier": "DOI:10.4126/FRL01-006440397s",
       "name": "OntoClue, a framework to compare vector-based approaches for document relatedness using the RELISH corpus",
       "datePublished": "2023-06-22"
     },
     {
       "@type": "Poster",
       "@id": "https://ceur-ws.org/Vol-3415/paper-38.pdf",
+      "identifier": "CEUR:Vol-3415/paper-38",
       "name": "OntoClue, a framework to compare vector-based approaches for document relatedness using the RELISH corpus - Poster",
       "datePublished": "2023-03-01"
     },
     {
       "@type": "ScholarlyArticle",
       "@id": "https://ceur-ws.org/Vol-2918/short3.pdf",
+      "http://purl.org/dc/terms/conformsTo": "https://bioschemas.org/profiles/ScholarlyArticle/0.3-DRAFT",
+      "identifier": "CEUR:Vol-2918/short3",
       "name": "Ontology Clustering with OWL2Vec*",
       "datePublished": "2021-07-28"
     },
     {
       "@type": "DataCatalog",
       "@id": "https://doi.org/10.5281/zenodo.5035290",
+      "http://purl.org/dc/terms/conformsTo": "https://bioschemas.org/profiles/DataCatalog/0.4-DRAFT",
+      "identifier": "DOI:10.5281/zenodo.5035290",
       "name": "Complete Medline abstracts corpus between 2015-2019 annotated Whatizit text annotation tool",
+      "description": "Gene Ontology annotations for Medline abstracts from 2015 to 2019 using Whatizit",
+      "keywords": "Whatizit, Semantic annotation, Medline, text-mining",
+      "license": {
+        "@type": "CreativeWork",
+        "@id": "https://spdx.org/licenses/CC-BY-4.0.html",
+        "name": "Creative Commons Attribution 4.0 International",
+        "alternateName": "CC BY 4.0",
+        "url": "https://creativecommons.org/licenses/by/4.0/"
+      },
+      "url": "https://zenodo.org/record/5035290",
       "datePublished": "2021-06-27"
     },
     {
       "@type": "DataCatalog",
       "@id": "https://doi.org/10.5281/zenodo.4903981",
+      "http://purl.org/dc/terms/conformsTo": "https://bioschemas.org/profiles/DataCatalog/0.4-DRAFT",
+      "identifier": "DOI:10.5281/zenodo.4903981",
       "name": "Whatizit performance evaluation against CRAFT corpus",
+      "description": "Whatizit performance evaluation against CRAFT corpus wrt Gene Ontology annotations",
+      "keywords": "Whatizit, Semantic annotation, CRAFT, manual annotation, performance",
+      "license": {
+        "@type": "CreativeWork",
+        "@id": "https://spdx.org/licenses/CC-BY-4.0.html",
+        "name": "Creative Commons Attribution 4.0 International",
+        "alternateName": "CC BY 4.0",
+        "url": "https://creativecommons.org/licenses/by/4.0/"
+      },
+      "url": "https://zenodo.org/record/4903981",
       "datePublished": "2021-06-05"
     }
   ],