From 9c9512a7e040f8247d259bdc6f9cf55d5d276baf Mon Sep 17 00:00:00 2001 From: Pjotr Prins Date: Wed, 15 Jul 2020 12:48:12 +0100 Subject: Load metadata locally without pkg_resources --- doc/blog/using-covid-19-pubseq-part5.org | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) (limited to 'doc/blog/using-covid-19-pubseq-part5.org') diff --git a/doc/blog/using-covid-19-pubseq-part5.org b/doc/blog/using-covid-19-pubseq-part5.org index 4b0ea64..aa06d5e 100644 --- a/doc/blog/using-covid-19-pubseq-part5.org +++ b/doc/blog/using-covid-19-pubseq-part5.org @@ -13,6 +13,7 @@ - [[#what-is-the-schema][What is the schema?]] - [[#how-is-the-website-generated][How is the website generated?]] - [[#modifying-the-schema][Modifying the schema]] + - [[#adding-fields-to-the-form][Adding fields to the form]] * Modify Metadata @@ -113,8 +114,15 @@ So, we'll add it simply as a title field. Now the draft schema is _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. +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 [[https://github.com/arvados/bh20-seq-resource/pull/97][here]] and reviewed on the +gitter channel and I merged it. + +* Adding fields to the form + +To add the new fields to the form we have to modify it a little. If we +go to the upload form we need to add the license box. The schema is +loaded in [[https://github.com/arvados/bh20-seq-resource/blob/a0c8ebd57b875f265e8b0efec4abfaf892eb6c45/bh20simplewebuploader/main.py#L229][main.py]] in the 'generate_form' function. /Note: work in progress/ -- cgit v1.2.3 From f4ed46dae20abe5147871495ede2d6ac2b0854bc Mon Sep 17 00:00:00 2001 From: Pjotr Prins Date: Wed, 15 Jul 2020 14:30:56 +0100 Subject: Add RDF output --- bh20sequploader/bh20seq-schema.yml | 9 +++++++-- bh20sequploader/bh20seq-shex.rdf | 24 +++++++++++++++++------- doc/blog/using-covid-19-pubseq-part5.org | 2 ++ 3 files changed, 26 insertions(+), 9 deletions(-) (limited to 'doc/blog/using-covid-19-pubseq-part5.org') diff --git a/bh20sequploader/bh20seq-schema.yml b/bh20sequploader/bh20seq-schema.yml index 29ac22c..c690e8a 100644 --- a/bh20sequploader/bh20seq-schema.yml +++ b/bh20sequploader/bh20seq-schema.yml @@ -23,16 +23,21 @@ $graph: type: string? jsonldPredicate: _id: http://semanticscience.org/resource/SIO_001167 + attribution_name: + doc: Attribution NAME related to data license + type: string? + jsonldPredicate: + _id: https://creativecommons.org/ns#attributionName attribution_url: doc: Attribution URL related to data license type: string? jsonldPredicate: - _id: https://creativecommons.org/ns#Work + _id: https://creativecommons.org/ns#attributionURL attribution_source: doc: Attribution source URL related to data license type: string? jsonldPredicate: - _id: https://creativecommons.org/ns#Work + _id: https://creativecommons.org/ns#attributionSource - name: hostSchema type: record diff --git a/bh20sequploader/bh20seq-shex.rdf b/bh20sequploader/bh20seq-shex.rdf index 965229c..c48267d 100644 --- a/bh20sequploader/bh20seq-shex.rdf +++ b/bh20sequploader/bh20seq-shex.rdf @@ -1,6 +1,7 @@ PREFIX : PREFIX MainSchema: PREFIX hostSchema: +PREFIX cc: PREFIX xsd: PREFIX obo: PREFIX sio: @@ -15,10 +16,11 @@ PREFIX wikidata: MainSchema:submitter @:submitterShape ; MainSchema:technology @:technologyShape ; MainSchema:virus @:virusShape; + MainSchema:license @:licenseShape; } :hostShape { - efo:EFO_0000532 [ obo:NCBITaxon_~ ] ; + efo:EFO_0000532 [ obo:NCBITaxon_~ ] ; sio:SIO_000115 xsd:string ?; obo:PATO_0000047 [ obo:PATO_0000384 obo:PATO_0000383 obo:PATO_0001340] ?; obo:PATO_0000011 xsd:integer ?; @@ -32,14 +34,14 @@ PREFIX wikidata: :sampleShape { sio:SIO_000115 xsd:string; - evs:C25164 xsd:string; - obo:GAZ_00000448 [wikidata:~] ; + evs:C25164 xsd:string; + obo:GAZ_00000448 [wikidata:~] ; obo:OBI_0001895 xsd:string ?; obo:NCIT_C41206 xsd:string ?; obo:OBI_0001479 IRI {0,2}; obo:OBI_0001472 xsd:string ?; sio:SIO_001167 xsd:string ?; - edam:data_2091 IRI {0,3}; + edam:data_2091 IRI {0,3}; } :submitterShape { @@ -47,7 +49,7 @@ PREFIX wikidata: sio:SIO_000116 xsd:string *; sio:SIO_000172 xsd:string ?; obo:NCIT_C37984 xsd:string ?; - obo:NCIT_C37900 xsd:string ?; + obo:NCIT_C37900 xsd:string ?; efo:EFO_0001741 xsd:string ?; obo:NCIT_C42781 xsd:string ?; obo:NCIT_C19026 xsd:string ?; @@ -63,6 +65,14 @@ PREFIX wikidata: } :virusShape{ - edam:data_1875 [ obo:NCBITaxon_~ ] ; - sio:SIO_010055 xsd:string ?; + edam:data_1875 [ obo:NCBITaxon_~ ] ; + sio:SIO_010055 xsd:string ?; } + +:licenseShape{ + cc:License xsd:string; + sio:SIO_001167 xsd:string ?; + cc:attributionName xsd:string ?; + cc:attributionURL xsd:string ?; + cc:attributionSource xsd:string ?; +} \ No newline at end of file diff --git a/doc/blog/using-covid-19-pubseq-part5.org b/doc/blog/using-covid-19-pubseq-part5.org index aa06d5e..cb11f43 100644 --- a/doc/blog/using-covid-19-pubseq-part5.org +++ b/doc/blog/using-covid-19-pubseq-part5.org @@ -125,4 +125,6 @@ To add the new fields to the form we have to modify it a little. If we go to the upload form we need to add the license box. The schema is loaded in [[https://github.com/arvados/bh20-seq-resource/blob/a0c8ebd57b875f265e8b0efec4abfaf892eb6c45/bh20simplewebuploader/main.py#L229][main.py]] in the 'generate_form' function. +With this [[https://github.com/arvados/bh20-seq-resource/commit/b9691c7deae30bd6422fb7b0681572b7b6f78ae3][patch]] the website adds the license input fields on the form. + /Note: work in progress/ -- cgit v1.2.3 From 712614e5627e54df7ec6ab975dc86a1055051455 Mon Sep 17 00:00:00 2001 From: Pjotr Prins Date: Wed, 15 Jul 2020 14:54:59 +0100 Subject: License RDF --- bh20sequploader/bh20seq-schema.yml | 3 ++- bh20sequploader/bh20seq-shex.rdf | 3 ++- doc/blog/using-covid-19-pubseq-part5.org | 29 +++++++++++++++++++++++------ 3 files changed, 27 insertions(+), 8 deletions(-) (limited to 'doc/blog/using-covid-19-pubseq-part5.org') diff --git a/bh20sequploader/bh20seq-schema.yml b/bh20sequploader/bh20seq-schema.yml index c690e8a..ef55c55 100644 --- a/bh20sequploader/bh20seq-schema.yml +++ b/bh20sequploader/bh20seq-schema.yml @@ -1,6 +1,7 @@ $base: http://biohackathon.org/bh20-seq-schema $namespaces: cc: http://creativecommons.org/ns# + dc: http://purl.org/metadata/dublin_core_elements# sch: https://schema.org/ efo: http://www.ebi.ac.uk/efo/ obo: http://purl.obolibrary.org/obo/ @@ -22,7 +23,7 @@ $graph: doc: Attribution title related to data license type: string? jsonldPredicate: - _id: http://semanticscience.org/resource/SIO_001167 + _id: http://purl.org/metadata/dublin_core_elements#Title attribution_name: doc: Attribution NAME related to data license type: string? diff --git a/bh20sequploader/bh20seq-shex.rdf b/bh20sequploader/bh20seq-shex.rdf index c48267d..9fab334 100644 --- a/bh20sequploader/bh20seq-shex.rdf +++ b/bh20sequploader/bh20seq-shex.rdf @@ -2,6 +2,7 @@ PREFIX : PREFIX hostSchema: PREFIX cc: +PREFIX dc: PREFIX xsd: PREFIX obo: PREFIX sio: @@ -71,7 +72,7 @@ PREFIX wikidata: :licenseShape{ cc:License xsd:string; - sio:SIO_001167 xsd:string ?; + dc:Title xsd:string ?; cc:attributionName xsd:string ?; cc:attributionURL xsd:string ?; cc:attributionSource xsd:string ?; diff --git a/doc/blog/using-covid-19-pubseq-part5.org b/doc/blog/using-covid-19-pubseq-part5.org index cb11f43..98c2c31 100644 --- a/doc/blog/using-covid-19-pubseq-part5.org +++ b/doc/blog/using-covid-19-pubseq-part5.org @@ -14,19 +14,20 @@ - [[#how-is-the-website-generated][How is the website generated?]] - [[#modifying-the-schema][Modifying the schema]] - [[#adding-fields-to-the-form][Adding fields to the form]] + - [[#testing-the-license-fields][Testing the license fields]] * Modify Metadata The public sequence resource uses multiple data formats listed on the -[[./download][DOWNLOAD]] page. One of the most exciting features is the full support +[[http://covid19.genenetwork.org/download][download]] page. One of the most exciting features is the full support for RDF and semantic web/linked data ontologies. This technology allows for querying data in unprescribed ways - that is, you can formulate your own queries without dealing with a preset model of that data (so typical of CSV files and SQL tables). Examples of exploring -data are listed [[./blog?id=using-covid-19-pubseq-part1][here]]. +data are listed [[http://covid19.genenetwork.org/blog?id=using-covid-19-pubseq-part1][here]]. In this BLOG we are going to look at the metadata entered on the -[[./][COVID-19 PubSeq]] website (or command line client). It is important to +COVID-19 PubSeq website (or command line client). It is important to understand that anyone, including you, can change that information! * What is the schema? @@ -42,8 +43,8 @@ All from that one metadata schema. * Modifying the schema 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 +license. Initially we only supported CC-4.0 as a license, but +we wanted to give uploaders the option to use an even more liberal CC0 license. The first step is to find a good ontology term for the field. Searching for `creative commons cc0 rdf' rendered this useful [[https://creativecommons.org/ns][page]]. We also find an [[https://wiki.creativecommons.org/wiki/CC_License_Rdf_Overview][overview]] where CC0 is represented as URI @@ -127,4 +128,20 @@ loaded in [[https://github.com/arvados/bh20-seq-resource/blob/a0c8ebd57b875f265e With this [[https://github.com/arvados/bh20-seq-resource/commit/b9691c7deae30bd6422fb7b0681572b7b6f78ae3][patch]] the website adds the license input fields on the form. -/Note: work in progress/ +Finally, to make RDF output work we need to add expressions to bh20seq-shex.rdf. This +was done with this [[https://github.com/arvados/bh20-seq-resource/commit/f4ed46dae20abe5147871495ede2d6ac2b0854bc][patch]]. In the end we decided to use the Dublin core title, +http://purl.org/metadata/dublin_core_elements#Title: + +#+BEGIN_SRC js +:licenseShape{ + cc:License xsd:string; + dc:Title xsd:string ?; + cc:attributionName xsd:string ?; + cc:attributionURL xsd:string ?; + cc:attributionSource xsd:string ?; +} +#+END_SRC + +Note that cc:AttributionSource is not really defined in the cc standard. + +* TODO Testing the license fields -- cgit v1.2.3 From 73be46fd1db58f132fa60ff30d33d67927a341a7 Mon Sep 17 00:00:00 2001 From: Pjotr Prins Date: Thu, 16 Jul 2020 09:48:31 +0100 Subject: Addes ESR logo and cropped CWL logo --- bh20simplewebuploader/static/image/CWL.png | Bin 0 -> 11066 bytes bh20simplewebuploader/static/image/ESR.png | Bin 0 -> 67869 bytes bh20simplewebuploader/templates/footer.html | 6 +++++- doc/blog/using-covid-19-pubseq-part5.org | 4 ++++ 4 files changed, 9 insertions(+), 1 deletion(-) create mode 100644 bh20simplewebuploader/static/image/CWL.png create mode 100644 bh20simplewebuploader/static/image/ESR.png (limited to 'doc/blog/using-covid-19-pubseq-part5.org') diff --git a/bh20simplewebuploader/static/image/CWL.png b/bh20simplewebuploader/static/image/CWL.png new file mode 100644 index 0000000..81d1807 Binary files /dev/null and b/bh20simplewebuploader/static/image/CWL.png differ diff --git a/bh20simplewebuploader/static/image/ESR.png b/bh20simplewebuploader/static/image/ESR.png new file mode 100644 index 0000000..557c798 Binary files /dev/null and b/bh20simplewebuploader/static/image/ESR.png differ diff --git a/bh20simplewebuploader/templates/footer.html b/bh20simplewebuploader/templates/footer.html index a1dd4fd..37a6b64 100644 --- a/bh20simplewebuploader/templates/footer.html +++ b/bh20simplewebuploader/templates/footer.html @@ -21,7 +21,7 @@
- +
@@ -29,6 +29,10 @@
+
+ +
+
diff --git a/doc/blog/using-covid-19-pubseq-part5.org b/doc/blog/using-covid-19-pubseq-part5.org index 98c2c31..78eea66 100644 --- a/doc/blog/using-covid-19-pubseq-part5.org +++ b/doc/blog/using-covid-19-pubseq-part5.org @@ -144,4 +144,8 @@ http://purl.org/metadata/dublin_core_elements#Title: Note that cc:AttributionSource is not really defined in the cc standard. +When pushing the license info we discovered the workflow broke because +the existing data had no licensing info. So we changed the license +field to be optional - a missing license assumes it is CC-BY-4.0. + * TODO Testing the license fields -- cgit v1.2.3