Update code and pages

code/createPage.py

@@ -2,10 +2,11 @@
 import json
 import subprocess
 import shutil
+import traceback
 
 DOCS_SUBFOLDERS = ['consortia', 'projects', 'theses']
 RO_CRATE_SUBFOLDERS = ['projects', 'theses']
-MAPPINGS = [("employee", "Current project members"), ("alumni", "Previous project members"), ("alternativeHeadline", "Cite as"), ("citation", "Cite as"), ("member", "External contributors"), ("knowsAbout", "Outcomes"), ("parentOrganization", "Parent organization, consortium or research project"), ("subOrganization", "Sub-projects")]
+MAPPINGS = [("employee", "Current project members"), ("alumni", "Previous project members"), ("alternativeHeadline", "Cite as"), ("citation", "Cite as"), ("member", "External contributors"), ("knowsAbout", "Outcomes"), ("parentOrganization", "Parent organization, consortium or research project"), ("subOrganization", "Sub-projects"), ("targetproduct", "Release")]
 MAPPINGS_FROM = [i[0] for i in MAPPINGS]
 MAPPINGS_TO = [i[1] for i in MAPPINGS]
 
@@ -284,12 +285,52 @@ def processNamesInProject(item) :
         subTypeURL = item["@type"]
         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", "http://purl.org/dc/terms/conformsTo", "funder", "givenName", "familyName"]:
-            if prop == 'url':
-                md += renderUrlAsHref(val)
-            else :
-                md += f'- {prop.capitalize()}: {val}\n'
+    if isinstance(item, (dict)):        
+        for prop, val in item.items(): 
+            if prop not in ["@type", "@id", "name", "http://purl.org/dc/terms/conformsTo", "funder", "givenName", "familyName"]:
+                if prop == 'url':
+                    md += renderUrlAsHref(val)
+                elif prop == 'license':
+                    try:
+                        idURL = val["@id"]
+                        md += f'- License: <a href="{idURL}" target="_blank">{idURL}</a> \n'
+                    except:
+                        md += f'- License: {val}\n'
+                elif (prop == 'author'):
+                    try:
+                        if isinstance(val, list):
+                            md += f'- {prop.capitalize()}s: '
+                            for elem in val:
+                                idURL = elem["@id"]
+                                md += f'<a href="{idURL}" target="_blank">{idURL}</a>. '
+                            md += '\n'
+                        else:
+                            md += f'- {prop.capitalize()}: '
+                            idURL = val["@id"]
+                            md += f'<a href="{idURL}" target="_blank">{idURL}</a> \n'
+                    except:
+                        pass
+                elif (prop == 'targetProduct'):
+                    try:
+                        if isinstance(val, list):
+                            md += f'- Releases: '
+                            for elem in val:
+                                idURL = elem["@id"]
+                                md += f'<a href="{idURL}" target="_blank">{idURL}</a>. '
+                            md += '\n'
+                        else:
+                            md += f'- Release: '
+                            idURL = val["@id"]
+                            md += f'<a href="{idURL}" target="_blank">{idURL}</a> \n'
+                    except:
+                        pass
+                else :
+                    if prop in MAPPINGS_FROM :
+                        i = MAPPINGS_FROM.index(prop)
+                        md += f'- {MAPPINGS_TO[i]}: '
+                    else :
+                        md += f'- {prop.capitalize()}: '
+                    md += f'{val}\n'
     return md
 
 def processProjectData(data, jsonFileURL, rocrateFileURL, htmlFileURL):
@@ -324,10 +365,9 @@ def processProjectData(data, jsonFileURL, rocrateFileURL, htmlFileURL):
                     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))):
-                                md += processNamesInProject(subItem) 
+                        #for keyPair in item:
+                        #    valuePair = item.get(keyPair, "")
+                        #    md += processKeyValuePair(keyPair, valuePair)                             
                         md += processNamesInProject(item)             
             elif isinstance(value, dict):
                 for subProperty, subValue in value.items():
@@ -437,6 +477,7 @@ def fromMetadatatoDocs():
                   folderIndex = DOCS_SUBFOLDERS.index(mdFolderName)                                    
                   jsonFileURL = f"../../metadata/{mdFolderName}/{fileNameNoExt}.json"
                   rocrateFileURL = ""
+                  htmlFileURL = ""
                   if mdFolderName in RO_CRATE_SUBFOLDERS:
                     rocrateFileURL = f"../../metadata/{mdFolderName}/{fileNameNoExt}/ro-crate-metadata.json"
                     htmlFileURL = f"../../metadata/{mdFolderName}/{fileNameNoExt}/ro-crate-preview.html"
@@ -447,7 +488,9 @@ def fromMetadatatoDocs():
                     mdDocFile.write(md)    
                     mdDocFile.write(f'\n\n<script type="application/ld+json">\n{json.dumps(data, indent=2)}\n</script>\n\n')
                 except Exception as e:
-                  #print(e)
+                  print(jsonFileName)
+                  print(e)
+                  #print(traceback.format_exc())
                   jsonFileURL = f"../metadata/{mdFolderName}/{fileNameNoExt}.json"
                   md = generateMDTableFromJSON(data, jsonFileURL)                    
                   with open(docFilePath, "a", encoding="utf-8") as mdDocFile:

docs/consortia/2018_STELLA.md

@@ -45,20 +45,15 @@ Evaluation framework, A/B testing, Interlinking, Information Retrieval, Recommen
 
 #### OntoClue
 
-<a href="https://zbmed-semtec.github.io/projects/2021_OntoClue" target="_blank"><img src = "/images/visit.svg" alt="Visit URL"/> Visit ResearchProject</a>
+<a href="https://w3id.org/zbmed-semtec/projects/2021_OntoClue" target="_blank"><img src = "/images/visit.svg" alt="Visit URL"/> Visit ResearchProject</a>
 
 #### TREC document-to-document relevance assessment
 
-<a href="https://zbmed-semtec.github.io/projects/2022_TREC_doc2doc" target="_blank"><img src = "/images/visit.svg" alt="Visit URL"/> Visit ResearchProject</a>
+<a href="https://w3id.org/zbmed-semtec/projects/2022_TREC_doc2doc" target="_blank"><img src = "/images/visit.svg" alt="Visit URL"/> Visit ResearchProject</a>
 
 ### Funding
 
-#### Deutsche Forschungsgemeinschaft
-
-<a href="https://ror.org/018mejw64" target="_blank"><img src = "/images/visit.svg" alt="Visit URL"/> Visit Organization</a>
-
-- 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)
@@ -107,18 +102,19 @@ Evaluation framework, A/B testing, Interlinking, Information Retrieval, Recommen
   "subOrganization": [
     {
       "@type": "ResearchProject",
-      "@id": "https://zbmed-semtec.github.io/projects/2021_OntoClue",
+      "@id": "https://w3id.org/zbmed-semtec/projects/2021_OntoClue",
       "name": "OntoClue"
     },
     {
       "@type": "ResearchProject",
-      "@id": "https://zbmed-semtec.github.io/projects/2022_TREC_doc2doc",
+      "@id": "https://w3id.org/zbmed-semtec/projects/2022_TREC_doc2doc",
       "name": "TREC document-to-document relevance assessment"
     }
   ],
   "funding": [
     {
       "@type": "Grant",
+      "@id": "https://gepris.dfg.de/gepris/projekt/407518790",
       "funder": {
         "@type": "Organization",
         "@id": "https://ror.org/018mejw64",

docs/consortia/2021_NFDI4DataScience.md

@@ -34,13 +34,6 @@ NFDI, Data Science, Artificial Intelligence
 
 ### Funding
 
-#### Deutsche Forschungsgemeinschaft
-
-<a href="https://ror.org/018mejw64" target="_blank"><img src = "/images/visit.svg" alt="Visit URL"/> Visit Organization</a>
-
-- 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

docs/current_members.md

@@ -90,36 +90,6 @@
 }
 </script>
 
-### Sarker Sunzid Mahmud
-<p><img src = "/images/get.svg" alt="Get JSON-LD"/><a href="../metadata/current_members/mahmud_0009-0003-8268-9090.json" target="_blank" download="metadata.json"> Get JSON-LD</a> | <a href="https://orcid.org/0000-0002-7672-9186" target="_blank"><img src = "/images/visit.svg" alt="Visit URL"/> Visit Person</a></p>
-<table style="background-color: #F5F5F5; width: 100%; text-align: left; border: 1px solid black;">
-<tbody>
-<tr>
-<td>familyName</td>
-<td>Mahmud</td>
-</tr>
-<tr>
-<td>givenName</td>
-<td>Sarker Sunzid</td>
-</tr>
-<tr>
-<td>jobTitle</td>
-<td>Student assistant</td>
-</tr>
-</tbody>
-</table>
-
-<script type="application/ld+json">
-{
-  "@context": "https://schema.org",
-  "@type": "Person",
-  "@id": "https://orcid.org/0000-0002-7672-9186",
-  "familyName": "Mahmud",
-  "givenName": "Sarker Sunzid",
-  "jobTitle": "Student assistant"
-}
-</script>
-
 ### Nelson Quiñones
 <p><img src = "/images/get.svg" alt="Get JSON-LD"/><a href="../metadata/current_members/quinones_0000-0002-5037-0443.json" target="_blank" download="metadata.json"> Get JSON-LD</a> | <a href="https://orcid.org/0000-0002-5037-0443" target="_blank"><img src = "/images/visit.svg" alt="Visit URL"/> Visit Person</a></p>
 <table style="background-color: #F5F5F5; width: 100%; text-align: left; border: 1px solid black;">

docs/metadata/projects/2021_OntoClue.json

@@ -176,6 +176,13 @@
       "alternativeHeadline": "Ravinder R, Fellerhof T, Dadi V, Geist L, Talha M, Rebholz-Schuhmann D, et al. A Comparison of Vector-based Approaches for Document Similarity Using the RELISH Corpus. Proceedings of the 6th Workshop on Semantic Web Solutions for Large-Scale Biomedical Data Analytics co-located with ESWC 2023. CEUR; 2023. Available: https://ceur-ws.org/Vol-3466/paper5.pdf",
       "name": "A Comparison of Vector-based Approaches for Document Similarity Using the RELISH Corpus",
       "datePublished": "2023-03-01",
+      "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://ceur-ws.org/Vol-3466/paper5.pdf#",
       "author": [
         {"@id": "https://orcid.org/0009-0004-4484-6283"},
@@ -196,6 +203,13 @@
       "citation": "Ravinder R, Fellerhoff T, Dadi VV, Geist L, Rocamora G, Talha M, et al. OntoClue, a framework to compare vector-based approaches for document relatedness using the RELISH corpus - Poster. ZB MED - Informationszentrum Lebenswissenschaften; 2023. Available: https://repository.publisso.de/resource/frl:6440397",
       "name": "OntoClue, a framework to compare vector-based approaches for document relatedness using the RELISH corpus",
       "datePublished": "2023-06-22",
+      "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://repository.publisso.de/resource/frl:6440397",
       "author": [
         {"@id": "https://orcid.org/0009-0004-4484-6283"},
@@ -215,6 +229,13 @@
       "alternativeHeadline": "Ravinder R, Fellerhoff T, Dadi V, Geist L, Rocamora G, Talha M, et al. OntoClue, a framework to compare vector-based approaches for document relatedness using the RELISH corpus. CEUR; 2023. Available: https://ceur-ws.org/Vol-3415/paper-38.pdf",
       "name": "OntoClue, a framework to compare vector-based approaches for document relatedness using the RELISH corpus - Poster",
       "datePublished": "2023-03-01",
+      "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://ceur-ws.org/Vol-3415/paper-38.pdf#",
       "author": [
         {"@id": "https://orcid.org/0009-0004-4484-6283"},
@@ -235,6 +256,14 @@
       "alternativeHeadline": "Ritchie A, Chen J, Castro LJ, Rebholz-Schuhmann D, Jimenez-Ruiz E. Ontology Clustering with OWL2Vec*. CEUR Workshop Proceedings. Online: CEUR Workshop Proceedings; 2021. Available: http://ceur-ws.org/",
       "name": "Ontology Clustering with OWL2Vec*",
       "datePublished": "2021-07-28",
+      "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://ceur-ws.org/Vol-2918/short3.pdf#",
       "author": [
         {"@id": "https://zbmed-semtec.github.io/previous_members/#ashley-ritchie"},
         {"@id": "https://chenjiaoyan.github.io/"},

docs/metadata/projects/2022_TREC_doc2doc.json

@@ -110,8 +110,16 @@
       "@id": "https://ceur-ws.org/Vol-3415/paper-12.pdf",
       "http://purl.org/dc/terms/conformsTo": "https://bioschemas.org/profiles/ScholarlyArticle/0.3-DRAFT",
       "identifier": "CEUR:Vol-3415/paper-12",
+      "alternativeHeadline": "Giraldo O, Cadena MF, Robayo-Gama A, Solanki D, Fellerhoff T, Geist L, et al. Document-to-document relevance assessment for TREC Genomics Track 2005. CEUR; 2023. Available: https://ceur-ws.org/Vol-3415/paper-12.pdf",
       "name": "Document-to-document relevance assessment for TREC Genomics Track 2005",
       "datePublished": "2023-06-22",
+      "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://ceur-ws.org/Vol-3415/paper-12.pdf#",
       "author": [
         {"@id": "https://orcid.org/0000-0003-2978-8922"},
@@ -129,11 +137,19 @@
       "@type": "SoftwareApplication",
       "@id": "https://doi.org/10.5281/zenodo.7341391",
       "http://purl.org/dc/terms/conformsTo": "https://bioschemas.org/profiles/ComputationalTool/1.0-RELEASE",
+      "identifier": "DOI:10.5281/zenodo.7341391",
+      "citation": "Talha M, Geist L, Fellerhof T, Ravinder R, Giraldo O, Rebholz-Schuhmann D, et al. TREC-doc-2-doc-relevance assessment interface. Zenodo; 2022. doi:10.5281/zenodo.7341391",
       "name": "TREC-doc-2-doc-relevance assessment interface",
       "description": "The code, data and docs at this release aim at facilitating the creation of a doc-2-doc relevance assessment on PMIDs used in the TREC 2005 Genomics track. A doc-2-doc relevance assessment takes one document as reference and assess a second document regarding its relevance to the reference one. This doc-2-doc collection will be used to evaluate the doc-2-doc recommendations approaches that we are working on.",
       "url": "https://zenodo.org/records/7341391",
       "softwareVersion": "1.0.0",
       "datePublished": "2022-11-21",
+      "license": {
+        "@type": "CreativeWork",
+        "@id": "https://spdx.org/licenses/MIT.html",
+        "name": "MIT License", 
+        "url": "https://opensource.org/license/mit/"
+      },
       "author": [
         {"@id": "https://zbmed-semtec.github.io/previous_members/#muhammad-talha"},
         {"@id": "http://orcid.org/0000-0002-2910-7982"},
@@ -146,10 +162,17 @@
     },{
       "@type": "SoftwareSourceCode",
       "@id": "https://github.com/zbmed-semtec/TREC-doc-2-doc-relevance",
+      "citation": "Talha M, Geist L, Fellerhof T, Ravinder R, Giraldo O, Rebholz-Schuhmann D, et al. TREC-doc-2-doc-relevance [Software source code]. GitHub; 2022.",
       "name": "TREC-doc-2-doc-relevance",
       "description": "This is the software source code facilitating the creation of a doc-2-doc relevance assessment on PMIDs used in the TREC 2005 Genomics track along with its metadata.",
       "url": "https://github.com/zbmed-semtec/TREC-doc-2-doc-relevance",
       "targetProduct": { "@id": "https://doi.org/10.5281/zenodo.7341391" },
+      "license": {
+        "@type": "CreativeWork",
+        "@id": "https://spdx.org/licenses/MIT.html",
+        "name": "MIT License", 
+        "url": "https://opensource.org/license/mit/"
+      },
       "author": [
         {"@id": "https://zbmed-semtec.github.io/previous_members/#muhammad-talha"},
         {"@id": "http://orcid.org/0000-0002-2910-7982"},
@@ -164,6 +187,7 @@
       "@id": "https://doi.org/10.5281/zenodo.7338056",
       "conformsTo": "https://bioschemas.org/profiles/Dataset/1.1-DRAFT", 
       "identifier": "DOI:10.5281/zenodo.7338056",
+      "citation": "Giraldo O, Solanki D, Rebholz-Schuhmann D, Castro LJ. Fleiss kappa for doc-2-doc relevance assessment. Zenodo; 2022. doi:10.5281/zenodo.7338056",
       "name": "Fleiss kappa for doc-2-doc relevance assessment",
       "description": "Fleiss' kappa measuring inter-annotator agreement on a document-to-document relevance assessment task. The table contains 7 columns, the first one presents the topics, 8 in total. The second column shows the “reference articles”, represented by their PubMed-ID and organized by topic. The third column shows the Fleiss’ Kappa results. The fourth column shows the interpretation of the Fleiss' Kappa results being: i) “Poor” results <0.20, ii) “Fair” results within 0.21 - 0.40, and iii) “Moderate” results within 0.41 - 0.60. The fifth column shows the PubMed-IDs of evaluation articles rated by the four annotators as “Relevant” regarding its corresponding “reference article”. The sixth column shows the PubMed-IDs of evaluation articles rated by the four annotators as “Partially relevant” regarding its corresponding “reference article”. The seventh column shows the PubMed-IDs of evaluation articles rated by the four annotators as “Non-relevant” regarding its corresponding “reference article”",
       "keywords": "Fleiss' Kappa, Inter-annoator agreement, TREC Genomics Track 2005, relevance assessment", 
@@ -187,6 +211,7 @@
       "@id": "https://doi.org/10.5281/zenodo.7324822",
       "http://purl.org/dc/terms/conformsTo": "https://bioschemas.org/profiles/Dataset/1.1-DRAFT", 
       "identifier": "DOI:10.5281/zenodo.7324822",
+      "citation": "Giraldo O, Solanki D, Cadena F, Robayo-Gama A, Rebholz-Schuhmann D, Castro LJ. Document-to-document relevant assessment for TREC Genomics Track 2005. Zenodo; 2022. doi:10.5281/zenodo.7324822",
       "name": "Document-to-document relevant assessment for TREC Genomics Track 2005",
       "description": "A CSV table with document-to-document relevance assessment judgements on a subset of the TREC Genomics Track 2005 produced by four annotators. The 'raw data document evaluation' contains six columns, first row consecutive id, second original TREC topic, third PubMed Id used as reference document, fourth PMID used to evaluate the relevance wrt the reference document, fifth the relevance score (2 definitely relevant, 1 partially relevant, 0 non-relevant), and sixth annotator id",
       "keywords": "Document-to-document relevance, TREC GEnomics Track 2005, relevance assessment",