From c69046ee9a5e24eadcd8cb885633328b0fd88011 Mon Sep 17 00:00:00 2001 From: Pjotr Prins Date: Fri, 17 Jul 2020 11:06:33 +0100 Subject: Update generated docs --- doc/blog/using-covid-19-pubseq-part1.html | 192 +++++++++++++++-------------- doc/blog/using-covid-19-pubseq-part4.html | 44 +++++-- doc/blog/using-covid-19-pubseq-part5.html | 194 ++++++++++++++++++++++++++---- 3 files changed, 305 insertions(+), 125 deletions(-) (limited to 'doc/blog') diff --git a/doc/blog/using-covid-19-pubseq-part1.html b/doc/blog/using-covid-19-pubseq-part1.html index 1959fac..0e6136c 100644 --- a/doc/blog/using-covid-19-pubseq-part1.html +++ b/doc/blog/using-covid-19-pubseq-part1.html @@ -3,7 +3,7 @@ "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"> - + COVID-19 PubSeq (part 1) @@ -248,20 +248,20 @@ for the JavaScript code in this tag.

Table of Contents

-
-

1 What does this mean?

+
+

1 What does this mean?

@@ -314,8 +314,8 @@ initiative!
-
-

2 Fetch sequence data

+
+

2 Fetch sequence data

The latest run of the pipeline can be viewed here. Each of these @@ -339,8 +339,8 @@ these identifiers throughout.

-
-

3 Predicates

+
+

3 Predicates

To explore an RDF dataset, the first query we can do is open and gets @@ -350,10 +350,10 @@ the following in a SPARQL end point

-
select distinct ?p
-{
+
select distinct ?p
+{
    ?o ?p ?s
-}
+}
 
@@ -364,10 +364,10 @@ To get a -
select distinct ?g
-{
-    GRAPH ?g {?s ?p ?o}
-}
+
select distinct ?g
+{
+    GRAPH ?g {?s ?p ?o}
+}
 
@@ -383,10 +383,10 @@ To list all submitters, try

-
select distinct ?s
-{
-   ?o <http://biohackathon.org/bh20-seq-schema#MainSchema/submitter> ?s
-}
+
select distinct ?s
+{
+   ?o <http://biohackathon.org/bh20-seq-schema#MainSchema/submitter> ?s
+}
 
@@ -397,11 +397,11 @@ and by

-
select distinct ?s
-{
-   ?o <http://biohackathon.org/bh20-seq-schema#MainSchema/submitter> ?id .
+
select distinct ?s
+{
+   ?o <http://biohackathon.org/bh20-seq-schema#MainSchema/submitter> ?id .
    ?id ?p ?s
-}
+}
 
@@ -415,12 +415,12 @@ To lift the full URL out of the query you can use a header like

-
PREFIX pubseq: <http://biohackathon.org/bh20-seq-schema#MainSchema/>
-select distinct ?dataset ?submitter
-{
+
PREFIX pubseq: <http://biohackathon.org/bh20-seq-schema#MainSchema/>
+select distinct ?dataset ?submitter
+{
    ?dataset pubseq:submitter ?id .
    ?id ?p ?submitter
-}
+}
 
@@ -438,32 +438,32 @@ Now we got this far, lets -
PREFIX pubseq: <http://biohackathon.org/bh20-seq-schema#MainSchema/>
-select (COUNT(distinct ?dataset) as ?num)
-{
+
PREFIX pubseq: <http://biohackathon.org/bh20-seq-schema#MainSchema/>
+select (COUNT(distinct ?dataset) as ?num)
+{
    ?dataset pubseq:submitter ?id .
    ?id ?p ?submitter
-}
+}
 
-
-

4 Fetch submitter info and other metadata

+
+

4 Fetch submitter info and other metadata

To get dataests with submitters we can do the above

-
PREFIX pubseq: <http://biohackathon.org/bh20-seq-schema#MainSchema/>
-select distinct ?dataset ?p ?submitter
-{
+
PREFIX pubseq: <http://biohackathon.org/bh20-seq-schema#MainSchema/>
+select distinct ?dataset ?p ?submitter
+{
    ?dataset pubseq:submitter ?id .
    ?id ?p ?submitter
-}
+}
 
@@ -480,13 +480,13 @@ Let's focus on one sample with

-
PREFIX pubseq: <http://biohackathon.org/bh20-seq-schema#MainSchema/>
-select distinct ?dataset ?submitter
-{
+
PREFIX pubseq: <http://biohackathon.org/bh20-seq-schema#MainSchema/>
+select distinct ?dataset ?submitter
+{
    ?dataset pubseq:submitter ?id .
    ?id ?p ?submitter .
-   FILTER(CONTAINS(?submitter,"Roychoudhury")) .
-}
+   FILTER(CONTAINS(?submitter,"Roychoudhury")) .
+}
 
@@ -496,12 +496,12 @@ see if we can get a sample ID by listing sample predicates

-
PREFIX pubseq: <http://biohackathon.org/bh20-seq-schema#MainSchema/>
-select distinct ?p
-{
+
PREFIX pubseq: <http://biohackathon.org/bh20-seq-schema#MainSchema/>
+select distinct ?p
+{
    ?dataset ?p ?o .
    ?dataset pubseq:submitter ?id .
-}
+}
 
@@ -513,15 +513,15 @@ Let's zoom in on those of Roychoudhury with
-
PREFIX pubseq: <http://biohackathon.org/bh20-seq-schema#MainSchema/>
-select distinct ?sid ?sample ?p1 ?dataset ?submitter
-{
+
PREFIX pubseq: <http://biohackathon.org/bh20-seq-schema#MainSchema/>
+select distinct ?sid ?sample ?p1 ?dataset ?submitter
+{
    ?dataset pubseq:submitter ?id .
    ?id ?p ?submitter .
-   FILTER(CONTAINS(?submitter,"Roychoudhury")) .
+   FILTER(CONTAINS(?submitter,"Roychoudhury")) .
    ?dataset pubseq:sample ?sid .
    ?sid ?p1 ?sample
-}
+}
 
@@ -532,18 +532,13 @@ this database. Let's focus on one sample "MT326090.1" with predicate

-
PREFIX pubseq: <http://biohackathon.org/bh20-seq-schema#MainSchema/>
-PREFIX sio: <http://semanticscience.org/resource/>
-select distinct ?sample ?p ?o
-{
+
PREFIX pubseq: <http://biohackathon.org/bh20-seq-schema#MainSchema/>
+PREFIX sio: <http://semanticscience.org/resource/>
+select distinct ?sample ?p ?o
+{
    ?sample sio:SIO_000115 "MT326090.1" .
    ?sample ?p ?o .
-}
+}
 
@@ -561,8 +556,8 @@ to view/query the database.
-
-

5 Fetch all sequences from Washington state

+
+

5 Fetch all sequences from Washington state

Now we know how to get at the origin we can do it the other way round @@ -570,15 +565,11 @@ and fetch all sequences referring to Washington state

-
-select ?seq ?sample
-{
-    ?seq <http://biohackathon.org/bh20-seq-schema#MainSchema/sample> ?sample .
-    ?sample <http://purl.obolibrary.org/obo/GAZ_00000448> <http://www.wikidata.org/entity/Q1223>
-}
+
select ?seq ?sample
+{
+    ?seq <http://biohackathon.org/bh20-seq-schema#MainSchema/sample> ?sample .
+    ?sample <http://purl.obolibrary.org/obo/GAZ_00000448> <http://www.wikidata.org/entity/Q1223>
+}
 
@@ -586,11 +577,26 @@ and fetch all sequences referring to Washington state which lists 300 sequences originating from Washington state! Which is almost half of the set coming out of GenBank.

+ +

+Likewise to list all sequences from Turkey we can find the wikidata +entity is Q43: +

+ +
+
select ?seq ?sample
+{
+    ?seq <http://biohackathon.org/bh20-seq-schema#MainSchema/sample> ?sample .
+    ?sample <http://purl.obolibrary.org/obo/GAZ_00000448> <http://www.wikidata.org/entity/Q43>
+}
+
+
+ -
-

6 Discussion

+
+

6 Discussion

The public sequence uploader collects sequences, raw data and @@ -601,8 +607,8 @@ referenced in publications and origins are citeable.

-
-

7 Acknowledgements

+
+

7 Acknowledgements

The overall effort was due to magnificent freely donated input by a @@ -617,7 +623,7 @@ Garrison this initiative would not have existed!

-
Created by Pjotr Prins (pjotr.public768 at thebird 'dot' nl) using Emacs org-mode and a healthy dose of Lisp!
Modified 2020-05-29 Fri 12:06
. +
Created by Pjotr Prins (pjotr.public768 at thebird 'dot' nl) using Emacs org-mode and a healthy dose of Lisp!
Modified 2020-07-17 Fri 05:02
.
diff --git a/doc/blog/using-covid-19-pubseq-part4.html b/doc/blog/using-covid-19-pubseq-part4.html index b5a05ca..c975c21 100644 --- a/doc/blog/using-covid-19-pubseq-part4.html +++ b/doc/blog/using-covid-19-pubseq-part4.html @@ -3,7 +3,7 @@ "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"> - + COVID-19 PubSeq (part 4) @@ -161,6 +161,19 @@ .footdef { margin-bottom: 1em; } .figure { padding: 1em; } .figure p { text-align: center; } + .equation-container { + display: table; + text-align: center; + width: 100%; + } + .equation { + vertical-align: middle; + } + .equation-label { + display: table-cell; + text-align: right; + vertical-align: middle; + } .inlinetask { padding: 10px; border: 2px solid gray; @@ -186,7 +199,7 @@ @licstart The following is the entire license notice for the JavaScript code in this tag. -Copyright (C) 2012-2018 Free Software Foundation, Inc. +Copyright (C) 2012-2020 Free Software Foundation, Inc. The JavaScript code in this tag is free software: you can redistribute it and/or modify it under the terms of the GNU @@ -235,15 +248,16 @@ for the JavaScript code in this tag.

Table of Contents

-
-

1 What does this mean?

+
+

1 What does this mean?

This means that when someone uploads a SARS-CoV-2 sequence using one @@ -253,18 +267,28 @@ which triggers a rerun of our workflows.

- -
-

2 Modify Workflow

+
+

2 Where can I find the workflows?

+Workflows are written in the common workflow language (CWL) and listed +on github. PubSeq being an open project these workflows can be studied +and modified! +

+
+
+ +
+

3 Modify Workflow

+
+

Work in progress!

-
Created by Pjotr Prins (pjotr.public768 at thebird 'dot' nl) using Emacs org-mode and a healthy dose of Lisp!
Modified 2020-07-12 Sun 06:24
. +
Created by Pjotr Prins (pjotr.public768 at thebird 'dot' nl) using Emacs org-mode and a healthy dose of Lisp!
Modified 2020-07-17 Fri 01:47
.
diff --git a/doc/blog/using-covid-19-pubseq-part5.html b/doc/blog/using-covid-19-pubseq-part5.html index 80bf559..4caa5ac 100644 --- a/doc/blog/using-covid-19-pubseq-part5.html +++ b/doc/blog/using-covid-19-pubseq-part5.html @@ -3,7 +3,7 @@ "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"> - + COVID-19 PubSeq (part 4) @@ -161,6 +161,19 @@ .footdef { margin-bottom: 1em; } .figure { padding: 1em; } .figure p { text-align: center; } + .equation-container { + display: table; + text-align: center; + width: 100%; + } + .equation { + vertical-align: middle; + } + .equation-label { + display: table-cell; + text-align: right; + vertical-align: middle; + } .inlinetask { padding: 10px; border: 2px solid gray; @@ -186,7 +199,7 @@ @licstart The following is the entire license notice for the JavaScript code in this tag. -Copyright (C) 2012-2018 Free Software Foundation, Inc. +Copyright (C) 2012-2020 Free Software Foundation, Inc. The JavaScript code in this tag is free software: you can redistribute it and/or modify it under the terms of the GNU @@ -235,38 +248,40 @@ for the JavaScript code in this tag.

Table of Contents

-
-

1 Modify Metadata

+
+

1 Modify Metadata

The public sequence resource uses multiple data formats listed on the -DOWNLOAD page. One of the most exciting features is the full support +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 here. +data are listed 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!

-
-

2 What is the schema?

+
+

2 What is the schema?

The default metadata schema is listed here. @@ -274,8 +289,8 @@ The default metadata schema is listed -

3 How is the website generated?

+
+

3 How is the website generated?

Using the schema we use pyshex shex expressions and schema salad to @@ -285,13 +300,13 @@ All from that one metadata schema.

-
-

4 Modifying the schema

+
+

4 Modifying the schema

-One of the first things we wanted 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 +One of the first things we want to do is to add a field for the data +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 page. We also find an overview where CC0 is represented as URI @@ -302,13 +317,148 @@ attributionName and attributionURL.

-Note: work in progress +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

+ +
+
- 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
+
+
+ +

+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 and reviewed on the +gitter channel and I merged it. +

+
+ +
+

5 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 main.py in the 'generateform' function. +

+ +

+With this patch the website adds the license input fields on the form. +

+ +

+Finally, to make RDF output work we need to add expressions to bh20seq-shex.rdf. This +was done with this patch. In the end we decided to use the Dublin core title, +http://purl.org/metadata/dublin_core_elements#Title: +

+ +
+
:licenseShape{
+    cc:License xsd:string;
+    dc:Title xsd:string ?;
+    cc:attributionName xsd:string ?;
+    cc:attributionURL xsd:string ?;
+    cc:attributionSource xsd:string ?;
+}
+
+
+ +

+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. +

+
+
+ +
+

6 TODO Testing the license fields

-
Created by Pjotr Prins (pjotr.public768 at thebird 'dot' nl) using Emacs org-mode and a healthy dose of Lisp!
Modified 2020-07-12 Sun 06:24
. +
Created by Pjotr Prins (pjotr.public768 at thebird 'dot' nl) using Emacs org-mode and a healthy dose of Lisp!
Modified 2020-07-16 Thu 03:27
.
-- cgit v1.2.3