Merge pull request #4750 from galaxyproject/gmod

GMOD topic, small home re-org

_layouts/home.html

@@ -32,6 +32,62 @@ <h2 class="alert-heading">{{ site.announcement.title }}</h2>
     <div class="row">
         <div class="col-lg-7 col-md-7 col-sm-12">
             <h2>Galaxy for Scientists</h2>
+	    <p>We have separated the tutorials into several categories based on field and technology. We are exploring other ways to organise the tutorials going forward!</p>
+
+	    <h3>Introduction</h3>
+            <table class="table table-striped">
+                <thead>
+                    <tr>
+                        <th scope="col">Topic</th>
+                        <th scope="col">Tutorials</th>
+                    </tr>
+                </thead>
+                <tbody>
+                {% for topic_name in sorted_topics %}
+                    {% assign topic = site.data[topic_name] %}
+                    {% if topic.name == "introduction" %}
+                    {% if topic.draft != true or jekyll.environment != "production" %}
+                    <tr>
+                        {% assign tutorial_number = site | topic_filter_tutorial_count:topic.name %}
+                        <td><a href="{{ site.baseurl }}/topics/{{ topic.name }}/">{{ topic.title }}</a>{% if topic.draft %} <div class="label label-default tutorial_tag" style="{{ 'work-in-progress' | colour_tag }}">work-in-progress</div>{% endif %}</td>
+                        <td>{{ tutorial_number }}</td>
+                    </tr>
+                    {% endif %}
+                    {% endif %}
+                {% endfor %}
+                </tbody>
+            </table>
+
+
+            <h3>Fields</h3>
+            <table class="table table-striped">
+                <thead>
+                    <tr>
+                        <th scope="col">Topic</th>
+                        <th scope="col">Tutorials</th>
+                    </tr>
+                </thead>
+                <tbody>
+                {% for topic_name in sorted_topics %}
+                    {% assign topic = site.data[topic_name] %}
+                    {% if topic.type == "use" %}
+                    {% if topic.name != "introduction" %}
+                    {% if topic.topic_type != "technology" %}
+                    {% if topic.draft != true or jekyll.environment != "production" %}
+                    <tr>
+                        {% assign tutorial_number = site | topic_filter_tutorial_count:topic.name %}
+                        <td><a href="{{ site.baseurl }}/topics/{{ topic.name }}/">{{ topic.title }}</a>{% if topic.draft %} <div class="label label-default tutorial_tag" style="{{ 'work-in-progress' | colour_tag }}">work-in-progress</div>{% endif %}</td>
+                        <td>{{ tutorial_number }}</td>
+                    </tr>
+                    {% endif %}
+                    {% endif %}
+                    {% endif %}
+                    {% endif %}
+                {% endfor %}
+                </tbody>
+            </table>
+
+            <h3>Technologies</h3>
             <table class="table table-striped">
                 <thead>
                     <tr>
@@ -43,6 +99,7 @@ <h2>Galaxy for Scientists</h2>
                 {% for topic_name in sorted_topics %}
                     {% assign topic = site.data[topic_name] %}
                     {% if topic.type == "use" %}
+                    {% if topic.topic_type == "technology" %}
                     {% if topic.draft != true or jekyll.environment != "production" %}
                     <tr>
                         {% assign tutorial_number = site | topic_filter_tutorial_count:topic.name %}
@@ -51,6 +108,7 @@ <h2>Galaxy for Scientists</h2>
                     </tr>
                     {% endif %}
                     {% endif %}
+                    {% endif %}
                 {% endfor %}
                 </tbody>
             </table>

_plugins/jekyll-topic-filter.rb

@@ -119,16 +119,33 @@ def self.list_materials_structured(site, topic_name)
         'subtopic' => { 'title' => 'Other', 'description' => 'Assorted Tutorials', 'id' => 'other' },
         'materials' => all_topics_for_tutorial.reject { |x| seen_ids.include?(x['id']) }
       }
-    elsif site.data[topic_name]['tag_based'] && site.data[topic_name]['custom_ordering']
-      # TODO
-      Jekyll.logger.error 'UNIMPLEMENTED'
+    elsif site.data[topic_name]['tag_based'] && site.data[topic_name].key?('subtopics')
       out = {}
+      seen_ids = []
+      tn = topic_name.gsub('by_tag_', '')
+      materials = filter_by_tag(site, tn)
+
+      # For each subtopics
+      site.data[topic_name]['subtopics'].each do |subtopic|
+        # Find matching tag-based tutorials in our filtered-by-tag materials
+        specific_resources = materials.select { |x| (x['tags'] || []).include?(subtopic['id']) }
+        out[subtopic['id']] = {
+          'subtopic' => subtopic,
+          'materials' => specific_resources
+        }
+        seen_ids += specific_resources.map { |x| x['id'] }
+      end
+
+      filter_by_tag(site, tn)
+      out['__OTHER__'] = {
+        'subtopic' => { 'title' => 'Other', 'description' => 'Assorted Tutorials', 'id' => 'other' },
+        'materials' => materials.reject { |x| seen_ids.include?(x['id']) }
+      }
     elsif site.data[topic_name]['tag_based'] # Tag based Topic
       # We'll construct a new hash of subtopic(parent topic) => tutorials
       out = {}
       seen_ids = []
       tn = topic_name.gsub('by_tag_', '')
-
       materials = filter_by_tag(site, tn)
 
       # Which topics are represented in those materials?
@@ -211,8 +228,6 @@ def self.extract_workflow_tool_list(data)
   # Returns:
   # +Hash+:: The annotation
   #
-  # This is a bit of a hack, but it works for now.
-  #
   # Example:
   #  /topics/assembly/tutorials/velvet-assembly/tutorial.md
   #  => {
@@ -245,6 +260,9 @@ def self.annotate_path(path, layout)
 
     return nil if parts[-1] =~ /data[_-]library.yaml/ || parts[-1] =~ /data[_-]manager.yaml/
 
+    # Check if it's a symlink
+    material['symlink'] = true if File.symlink?(material['dir'])
+
     if parts[4] =~ /tutorial.*\.md/ || layout == 'tutorial_hands_on'
       material['type'] = 'tutorial'
     elsif parts[4] =~ /slides.*\.html/ || %w[tutorial_slides base_slides introduction_slides].include?(layout)
@@ -357,6 +375,7 @@ def self.collate_materials(site, pages)
       page.data['tutorial_name'] = material_meta['tutorial_name']
       page.data['dir'] = material_meta['dir']
       page.data['short_id'] = shortlinks_reversed[page.data['url']]
+      page.data['symlink'] = material_meta['symlink']
 
       interesting[mk]['resources'].push([material_meta['type'], page])
     end
@@ -538,7 +557,7 @@ def self.resolve_material(site, material)
     domain = if !site.config.nil? && site.config.key?('url')
                "#{site.config['url']}#{site.config['baseurl']}"
              else
-               'http://localhost:4000//training-material/'
+               'http://localhost:4000/training-material/'
              end
     # Similar as above.
     workflows = Dir.glob("#{folder}/workflows/*.ga") # TODO: support gxformat2

bin/schema-topic.yaml

@@ -37,6 +37,14 @@ mapping:
 
             `instructors`
             :  Specific to topics related to instruction of Galaxy
+    topic_type:
+        type: str
+        required: false
+        enum:
+            - technology
+            - field
+        description: |
+          These are used to organise the home page tutorials only, not used anywhere else.
     title:
         type: str
         required: true
@@ -184,7 +192,7 @@ mapping:
         type: bool
         required: false
         description: |
-            If this is a synthetic tag based topic (no tutorials of it's own)
+            If this is a tag based topic (no tutorials of it's own)
             then you must set this flag to indicate it as such, otherwise you
             will find yourself with an empty topic page.
     og_image:

learning-pathways/clinical-metaproteomics.md

@@ -9,6 +9,8 @@ description: |
   This learning path aims to teach you the basics of how to perform metaproteomics analysis of the clinical data within the Galaxy platform. You will learn how to use Galaxy for analysis, and will be guided through the most common first steps of any metaproteomics database generation to searching the database, verifying the proteins/peptides, and data analysis.
 
 priority: 3
+editorial_board:
+- subinamehta
 
 pathway:
   - section: "Module 1: Database generation"
@@ -53,5 +55,5 @@ pathway:
         topic: proteomics
 ---
 
-New to Galaxy and/or the field of genomics? Follow this learning path to get familiar with the basics!
+New to Galaxy and/or the field of metaproteomics? Follow this learning path to get familiar with the basics!
 

metadata/covid19.yaml

@@ -1,6 +1,7 @@
 ---
 name: "covid19"
 type: "use"
+topic_type: field
 title: "SARS-CoV-2"
 summary: "Tutorials covering analysis of SARS-CoV-2 (COVID 19)"
 tag_based: true

metadata/gmod.yaml

@@ -0,0 +1,35 @@
+---
+name: gmod
+type: use
+topic_type: technology
+title: GMOD
+summary: |
+  Tutorials from the world of the Generic Model Organism Database (GMOD)
+
+  GMOD is a collection of open source software tools for managing, visualising, storing, and disseminating genetic and genomic data, many of which are directly interoperable.
+edam_ontology: ["topic_0362"]
+
+tag_based: true
+
+gitter: galaxy-genome-annotation/Lobby
+og_image: /assets/images/GMOD-cogs.png
+logo: /training-material/assets/images/GMOD-cogs.png
+logo_alt: "The GMOD logo where the O is three interlocking gears"
+
+editorial_board:
+  - hexylena
+  - abretaud
+
+subtopics:
+  - id: jbrowse1
+    title: "JBrowse 1"
+    description: Learn to use JBrowse v1 here.
+  - id: maker
+    title: MAKER
+    description: Genome Annotation with MAKER.
+  - id: intermine
+    title: InterMine
+    description: InterMine is a data warehouse you can query for interesting features and data.
+  - id: apollo2
+    title: Apollo v2
+    description: Apollo is a collaborative, real time genome annotation editor.

metadata/one-health.yaml

@@ -1,6 +1,7 @@
 ---
 name: "one-health"
 type: "use"
+topic_type: field
 title: "One Health"
 summary: |
   One Health is unified approach that aims to sustainably balance the health of humans, animals, and ecosystems, as all of the health of each of these groups is closely interlinked.

news/_posts/2024-02-29-new-gmod-topic.md

@@ -0,0 +1,28 @@
+---
+title: "GTN ❤️ GMOD"
+tags: [new topic, new feature, genome annotation]
+contributions:
+  authorship: [hexylena, abretaud]
+  infrastructure: [hexylena]
+layout: news
+tutorial: topics/gmod/index.html
+---
+
+Building upon the work previously done for the [SARS-Cov-2 Topic](/training-material/news/2023/01/23/new-covid19-topic.html) we have further expanded the 'tag based topics' to support a new GMOD topic. 
+
+# Generic Model Organism Database
+
+> the Generic Model Organism Database (GMOD) project, a collection of open source software tools for managing, visualising, storing, and disseminating genetic and genomic data.
+{: .quote cite="http://gmod.org/wiki/Main_Page"}
+
+Galaxy Project itself has long been a GMOD component, but you'll recognise some other familiar faces there as well, if you are interested in Genome Annotation. JBrowse, used throughout the GTN in a number of tutorials to render genomic data, and Apollo are both members that you'll find tutorials for within the GTN.
+
+## Current State
+
+As such we've created a new topic to help aggregate all of the GMOD related material together. This currently includes tutorials on the use of [JBrowse](/training-material/topics/gmod/#st-jbrowse1), [Apollo](/training-material/topics/gmod/#st-apollo2), [InterMine](/training-material/topics/gmod/#st-intermine), and [MAKER](/training-material/topics/gmod/#st-maker)!
+
+For teachers, tag based topics now support a second level of organisation, in 'subtopics'. We've used that to add a new topic, using subtopics to organise each GMOD component.
+
+## Future
+
+For now the topic includes all GTN tutorials which use a GMOD component (that isn't galaxy), all of these tutorials generally also include Galaxy based steps. In the future we may expand this to include tutorials for other GMOD components which don't necessary interface with Galaxy. @gtn:hexylena has some ideas about a Chado tutorial using the new [`pglite`](https://github.com/electric-sql/pglite) project, and perhaps @gtn:abretaud will contribute a Tripal tutorial!

topics/ai4life/metadata.yaml

@@ -1,6 +1,7 @@
 ---
 name: ai4life
 type: use
+topic_type: technology
 draft: true
 title: Image analysis using Deep Learning
 summary: |

topics/assembly/metadata.yaml

@@ -1,6 +1,7 @@
 ---
 name: "assembly"
 type: "use"
+topic_type: technology
 title: "Assembly"
 summary: "DNA sequence data has become an indispensable tool for Molecular Biology & Evolutionary Biology. Study in these fields now require a genome sequence to work from. We call this a 'Reference Sequence.' We need to build a reference for each species. We do this by Genome Assembly. De novo Genome Assembly is the process of reconstructing the original DNA sequence from the fragment reads alone."
 docker_image: "quay.io/galaxy/assembly-training"

topics/assembly/tutorials/chloroplast-assembly/tutorial.md

@@ -6,6 +6,7 @@ zenodo_link: "http://doi.org/10.5281/zenodo.3567224"
 tags:
   - plants
   - nanopore
+  - jbrowse1
 questions:
   - "How can we assemble a chloroplast genome?"
 objectives:
@@ -89,7 +90,7 @@ We will look at the quality of the nanopore reads.
 > > <solution-title></solution-title>
 > > This will depend on the aim of your analysis, but usually:
 > > * **Sequencing depth** (the number of reads covering each base position; also called "coverage"). Higher depth is usually better, but at very high depths it may be better to subsample the reads, as errors can swamp the assembly graph.
-> > * **Sequencing quality** (the quality score indicates probability of base call being correct). You may trim or filter reads on quality. Phred quality scores are logarithmic: phred quality 10 = 90% chance of base call being correct; phred quality 20 = 99% chance of base call being correct. More detail [here](https://en.wikipedia.org/wiki/Phred_quality_score).
+> > * **Sequencing quality** (the quality score indicates probability of base call being correct). You may trim or filter reads on quality. Phred quality scores are logarithmic: phred quality 10 = 90% chance of base call being correct; phred quality 20 = 99% chance of base call being correct. More detail [on Wikipedia](https://en.wikipedia.org/wiki/Phred_quality_score).
 > > * **Read lengths** (read lengths histogram, and reads lengths vs. quality plots). Your analysis or assembly may need reads of a certain length.
 > {: .solution}
 {: .question}

topics/assembly/tutorials/ecoli_comparison/tutorial.md

@@ -10,8 +10,10 @@ requirements:
     tutorials:
       - unicycler-assembly
 tags:
+  - gmod
   - prokaryote
   - microgalaxy
+  - jbrowse1
 questions:
   - "I just assembled a genome. How does it compare with already sequenced genomes?"
   - "How do I find rearranged, inserted, or deleted regions?"

topics/assembly/tutorials/mrsa-nanopore/tutorial.md

@@ -25,6 +25,8 @@ tags:
 - nanopore
 - assembly
 - amr
+- gmod
+- jbrowse1
 
 contributions:
   authorship:

topics/climate/metadata.yaml

@@ -1,6 +1,7 @@
 ---
 name: climate
 type: use
+topic_type: field
 title: Climate
 summary: Learn to analyze climate data through Galaxy.
 requirements:

topics/computational-chemistry/metadata.yaml

@@ -1,6 +1,7 @@
 ---
 name: computational-chemistry
 type: use
+topic_type: field
 title: Computational chemistry
 summary: Modelling, simulation and analysis of biomolecular systems
 docker_image: "quay.io/galaxy/computational-chemistry-training"

topics/contributing/tutorials/create-new-topic/tutorial.md

@@ -207,7 +207,7 @@ For tag based topics, first ensure that all of the relevant tutorials share a si
 
 Compare with other topic level metadata files in the `metadata/` directory of the training material. Then create a file of your own naming the topic and providing editorial board members and so on. We will use the Covid-19 synthetic topic as an example:
 
-```
+```yaml
 ---
 name: "covid19"
 type: "use"
@@ -229,6 +229,31 @@ As you can see it is very short, and there are only a handful of important point
 
 With this done, all materials tagged `covid19` will be aggregated and available under this synthetic topic. They are organised by the "parent" topic, so e.g. assembly tutorials are collected together and transcriptomics tutorials are also in a section together, similar to how other tutorials define subtopics.
 
+## More manual tag based topics
+
+If you wish to more manually curate the tutorials listed in your tag-based topic, you can provide subtopics. These must have IDs that match tags that are expected to be found within your tag-based topic.
+
+```yaml
+---
+name: gmod
+type: use
+topic_type: technology
+title: GMOD
+edam_ontology: ["topic_0362"]
+
+tag_based: true
+
+subtopics:
+  - id: jbrowse1
+    title: "JBrowse 1"
+    description: Learn to use JBrowse v1 here.
+  - id: apollo2
+    title: Apollo v2
+    description: Apollo is a collaborative, real time genome annotation editor.
+```
+
+Here anything with a tag `jbrowse1` will appear under the JBrowse section, same for `apollo2` and the Apollo section. Tutorials may appear multiple times, but this is still useful as it gives you a way to provide additional organisation within your topic.
+
 
 # Conclusion
 

topics/ecology/metadata.yaml

@@ -1,6 +1,7 @@
 ---
 name: "ecology"
 type: "use"
+topic_type: field
 title: "Ecology"
 summary: "Learn to analyse Ecological data through Galaxy."
 docker_image: "quay.io/galaxy/ecology-training"

topics/epigenetics/metadata.yaml

@@ -1,6 +1,7 @@
 ---
 name: "epigenetics"
 type: "use"
+topic_type: technology
 title: "Epigenetics"
 summary: "DNA methylation is an epigenetic mechanism used by higher eukaryotes and involved in e.g. gene expression, X-Chromosome inactivating, imprinting, and gene silencing of germline specific gene and repetitive elements."
 docker_image: "quay.io/galaxy/epigenetics-training"