From b5e38b960c380f0f7868d8fc4038ea3c3a0c52ee Mon Sep 17 00:00:00 2001
From: Pjotr Prins
Date: Mon, 13 Jul 2020 08:50:25 +0100
Subject: Add ontology and schema for license information. For review.

---
 bh20sequploader/bh20seq-options.yml      |  4 ++
 bh20sequploader/bh20seq-schema.yml       | 25 ++++++++++++
 doc/blog/using-covid-19-pubseq-part5.org | 68 +++++++++++++++++++++++++++++++-
 example/maximum_metadata_example.yaml    | 10 ++++-
 4 files changed, 104 insertions(+), 3 deletions(-)

diff --git a/bh20sequploader/bh20seq-options.yml b/bh20sequploader/bh20seq-options.yml
index c553f41..d1ea398 100644
--- a/bh20sequploader/bh20seq-options.yml
+++ b/bh20sequploader/bh20seq-options.yml
@@ -3,6 +3,10 @@
 # being unique or at least using the same options in different containing
 # types.
 
+license_type:
+  CC0 Public Domain Dedication: http://creativecommons.org/publicdomain/zero/1.0/
+  CC-BY-4.0 Attribution 4.0 International: http://creativecommons.org/licenses/by/4.0/
+
 host_age_unit:
   Years: http://purl.obolibrary.org/obo/UO_0000036
   Months: http://purl.obolibrary.org/obo/UO_0000035
diff --git a/bh20sequploader/bh20seq-schema.yml b/bh20sequploader/bh20seq-schema.yml
index a8ab920..b3d4d12 100644
--- a/bh20sequploader/bh20seq-schema.yml
+++ b/bh20sequploader/bh20seq-schema.yml
@@ -1,5 +1,6 @@
 $base: http://biohackathon.org/bh20-seq-schema
 $namespaces:
+  cc:  http://creativecommons.org/ns#
   sch: https://schema.org/
   efo: http://www.ebi.ac.uk/efo/
   obo: http://purl.obolibrary.org/obo/
@@ -9,6 +10,30 @@ $namespaces:
 
 $graph:
 
+- name: licenseSchema
+  type: record
+  fields:
+    license_type:
+      doc: License types as defined in https://wiki.creativecommons.org/images/d/d6/Ccrel-1.0.pdf
+      type: string?
+      jsonldPredicate:
+          _id: https://creativecommons.org/ns#License
+    title:
+      doc: Attribution title related to data license
+      type: string?
+      jsonldPredicate:
+          _id: http://semanticscience.org/resource/SIO_001167
+    attribution_url:
+      doc: Attribution URL related to data license
+      type: string?
+      jsonldPredicate:
+          _id: https://creativecommons.org/ns#Work
+    attribution_source:
+      doc: Attribution source URL related to data license
+      type: string?
+      jsonldPredicate:
+          _id: https://creativecommons.org/ns#Work
+
 - name: hostSchema
   type: record
   fields:
diff --git a/doc/blog/using-covid-19-pubseq-part5.org b/doc/blog/using-covid-19-pubseq-part5.org
index fe1908a..4b0ea64 100644
--- a/doc/blog/using-covid-19-pubseq-part5.org
+++ b/doc/blog/using-covid-19-pubseq-part5.org
@@ -40,7 +40,7 @@ All from that one metadata schema.
 
 * Modifying the schema
 
-One of the first things we wanted to do is to add a field for the data
+One of the first things we want to do is to add a field for the data
 license. Initially we only support CC-4.0 as a license by default, but
 now we want to give uploaders the option to make it an even more
 liberal CC0 license. The first step is to find a good ontology term
@@ -51,4 +51,70 @@ attribution license https://creativecommons.org/licenses/by/4.0/.
 According to this [[https://wiki.creativecommons.org/images/d/d6/Ccrel-1.0.pdf][document]] we should really also add fields for
 attributionName and attributionURL.
 
+A minimal triple should be
+
+: id  xhtml:license  <http://creativecommons.org/licenses/by/4.0/> .
+
+Other suggestions are
+
+: id  dc:title "Description" .
+: id  cc:attributionName "Your Name" .
+: id  cc:attributionURL <http://resource.org/id>
+
+and 'dc:source' which indicates the original source of any modified
+work, specified as a URI.
+The prefix 'cc:' is an abbreviation for http://creativecommons.org/ns#.
+
+Going back to the schema, where does it fit? Under host, sample,
+virus, technology or submitter block? It could fit under sample, but
+actually the license concerns the whole metadata block and sequence,
+so I think we can fit under its own license tag. For example
+
+
+id: placeholder
+
+: license:
+:     license_type: http://creativecommons.org/licenses/by/4.0/
+:     attribution_title: "Sample ID"
+:     attribution_name: "John doe, Joe Boe, Jonny Oe"
+:     attribution_url: http://covid19.genenetwork.org/id
+:     attribution_source: https://www.ncbi.nlm.nih.gov/pubmed/323088888
+
+So, let's update the example. Notice the license info is optional - if it is missing
+we just assume the default CC-4.0.
+
+One thing that is interesting is that in the name space https://creativecommons.org/ns there
+is no mention of a title. I think it is useful, however, because we have no such field.
+So, we'll add it simply as a title field. Now the draft schema is
+
+#+BEGIN_SRC js
+- name: licenseSchema
+  type: record
+  fields:
+    license_type:
+      doc: License types as refined in https://wiki.creativecommons.org/images/d/d6/Ccrel-1.0.pdf
+      type: string?
+      jsonldPredicate:
+          _id: https://creativecommons.org/ns#License
+    title:
+      doc: Attribution title related to license
+      type: string?
+      jsonldPredicate:
+          _id: http://semanticscience.org/resource/SIO_001167
+    attribution_url:
+      doc: Attribution URL related to license
+      type: string?
+      jsonldPredicate:
+          _id: https://creativecommons.org/ns#Work
+    attribution_source:
+      doc: Attribution source URL
+      type: string?
+      jsonldPredicate:
+          _id: https://creativecommons.org/ns#Work
+#+END_SRC
+
+Now, we are no ontology experts, right? So, next we submit a patch to our source tree and
+ask for feedback before wiring it up in the data entry form. The pull request was
+submitted here FIXME.
+
 /Note: work in progress/
diff --git a/example/maximum_metadata_example.yaml b/example/maximum_metadata_example.yaml
index 432877c..54736f8 100644
--- a/example/maximum_metadata_example.yaml
+++ b/example/maximum_metadata_example.yaml
@@ -1,5 +1,11 @@
 id: placeholder
 
+license:
+    license_type: http://creativecommons.org/licenses/by/4.0/
+    title: "Sample"
+    attribution_name: "John doe, Joe Boe, Jonny Oe"
+    attribution_url: http://covid19.genenetwork.org/id
+
 host:
     host_id: XX1
     host_species: http://purl.obolibrary.org/obo/NCBITaxon_9606
@@ -13,9 +19,9 @@ host:
     additional_host_information: Optional free text field for additional information
 
 sample:
-    sample_id: Id of the sample as defined by the submitter 
+    sample_id: Id of the sample as defined by the submitter
     collector_name: Name of the person that took the sample
-    collecting_institution: Institute that was responsible of sampling  
+    collecting_institution: Institute that was responsible of sampling
     specimen_source: [http://purl.obolibrary.org/obo/NCIT_C155831,http://purl.obolibrary.org/obo/NCIT_C155835]
     collection_date: "2020-01-01"
     collection_location: http://www.wikidata.org/entity/Q148
-- 
cgit v1.2.3