Merge branch 'master' into issue-514-remove-bdbag-refs

.github/workflows/deploy.yaml

@@ -0,0 +1,58 @@
+name: Deploy Jekyll site to Pages
+
+on:
+  # Allow the workflow to be triggered manually. In particular, this allows it to be triggered
+  # from a workflow in the go-site repository.
+  workflow_dispatch:
+  push:
+    branches: ["master"]
+
+# Sets permissions of the GITHUB_TOKEN to allow deployment to GitHub Pages
+permissions:
+  contents: read
+  pages: write
+  id-token: write
+
+# Allow only one concurrent deployment, skipping runs queued between the run in-progress and latest queued.
+# However, do NOT cancel in-progress runs as we want to allow these production deployments to complete.
+concurrency:
+  group: "pages"
+  cancel-in-progress: false
+
+jobs:
+  # Build job
+  build:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+      - name: Setup Ruby
+        uses: ruby/setup-ruby@v1
+        with:
+          ruby-version: '2.7'
+          bundler-cache: true # runs 'bundle install' and caches installed gems automatically
+      - name: Setup Pages
+        id: pages
+        uses: actions/configure-pages@v4
+      - name: Fetch GO_REFs
+        run: make _data/gorefs.yaml
+      - name: Build with Jekyll
+        # Outputs to the './_site' directory by default
+        run: bundle exec jekyll build --baseurl "${{ steps.pages.outputs.base_path }}"
+        env:
+          JEKYLL_ENV: production
+      - name: Upload artifact
+        # Automatically uploads an artifact from the './_site' directory by default
+        uses: actions/upload-pages-artifact@v3
+
+  # Deployment job
+  deploy:
+    environment:
+      name: github-pages
+      url: ${{ steps.deployment.outputs.page_url }}
+    runs-on: ubuntu-latest
+    needs: build
+    steps:
+      - name: Deploy to GitHub Pages
+        id: deployment
+        uses: actions/deploy-pages@v4

.gitignore

@@ -30,6 +30,10 @@ tramp
 .org-id-locations
 *_archive
 
+## Other IDEs
+.vscode
+.idea
+
 ###
 ### From upstream jekyll theme.
 ###
@@ -42,3 +46,6 @@ _site
 vendor/bundle
 
 _algolia_api_key
+
+## Transient data
+_data/gorefs.yaml

Gemfile

@@ -14,7 +14,10 @@ group :jekyll_plugins do
    gem "jekyll-redirect-from"
    gem "jekyll-seo-tag"
    gem 'jekyll-algolia', '~> 1.0'
+   gem 'jekyll-datapage-generator'
 end
 
 # Windows does not include zoneinfo files, so bundle the tzinfo-data gem
 gem 'tzinfo-data', platforms: [:mingw, :mswin, :x64_mingw, :jruby]
+
+gem "rinku", "~> 2.0"

Gemfile.lock

@@ -34,6 +34,7 @@ GEM
       nokogiri (~> 1.6)
       progressbar (~> 1.9)
       verbal_expressions (~> 0.1.5)
+    jekyll-datapage-generator (1.4.0)
     jekyll-feed (0.11.0)
       jekyll (~> 3.3)
     jekyll-redirect-from (0.16.0)
@@ -65,6 +66,7 @@ GEM
     rb-fsevent (0.11.0)
     rb-inotify (0.10.1)
       ffi (~> 1.0)
+    rinku (2.0.6)
     rouge (1.11.1)
     safe_yaml (1.0.5)
     sass (3.7.4)
@@ -81,10 +83,12 @@ PLATFORMS
 DEPENDENCIES
   jekyll (= 3.4.3)
   jekyll-algolia (~> 1.0)
+  jekyll-datapage-generator
   jekyll-feed
   jekyll-redirect-from
   jekyll-seo-tag
   jekyll-sitemap
+  rinku (~> 2.0)
   tzinfo-data
   webrick
 

Makefile

@@ -0,0 +1,4 @@
+.PHONY: _data/gorefs.yaml
+
+_data/gorefs.yaml:
+	wget -O $@ https://raw.githubusercontent.com/geneontology/go-site/master/metadata/gorefs.yaml

_config.yml

@@ -23,13 +23,15 @@ gems:
   - jekyll-redirect-from
   - jekyll-seo-tag
   - jekyll-sitemap
+  - jekyll-datapage-generator
 
 exclude:
   - Gemfile
   - Gemfile.lock
   - .idea/
   - .gitignore
   - README.md
+  - vendor  # In GitHub workflows, the ruby/setup-ruby action will install gems here
 timezone: America/Los_Angeles
 defaults:
 
@@ -60,9 +62,6 @@ collections:
     permalink: /blog/:year/:month/:day/:title/
     output: true
 
-plugins_dir:
-- jekyll-redirect-from
-
 sass:
   sass_dir: _sass
 
@@ -81,3 +80,9 @@ algolia:
     - covid-19.html
 #   nodes_to_index: 'article' # elements to be indexed 
   nodes_to_index: 'p,blockquote,li,div,paragraph,td,span,h1,h2,h3'
+
+page_gen:
+  - data: gorefs
+    template: goref
+    dir: GO_REF
+    name_expr: "record['id'].sub('GO_REF:', '')"

_docs/download-go-annotations.md

@@ -9,23 +9,69 @@ redirect_from:
 
 # Download annotations
 
-## Current GO annotation downloads
-The [GAF download page](http://current.geneontology.org/products/pages/downloads.html) has GAF files for selected species.
+### Getting annotations for a selected organism
 
-GAF & GPAD+GPI files are also available from the [/annotations/](http://current.geneontology.org/annotations/index.html){:target="blank"} directory of the current release: [http://current.geneontology.org](http://current.geneontology.org){:target="blank"}
+This page has instructions for getting GO annotations for almost any organism. If your organism is not available in the [official GO products](http://current.geneontology.org/products/pages/downloads.html), [UniProt GAFs by proteome](https://ftp.ebi.ac.uk/pub/databases/GO/goa/proteomes/){:target="blank"}, or [NCBI RefSeq](https://ftp.ncbi.nlm.nih.gov/genomes/refseq/){:target="blank"}, we recommend using the latest version of [InterProScan](https://interproscan-docs.readthedocs.io/en/latest/){:target="blank"} for unannotated organisms.
 
-### Other species
-If your organism is not available in the above links, you can use [AmiGO's annotation search](https://amigo.geneontology.org/amigo/search/annotation) feature to view or download annotations.  [See our FAQ](https://geneontology.org/docs/faq/#where-can-i-view-or-download-the-complete-sets-of-go-annotations) for further information as well as how to retrieve annotations for species that are not available in AmiGO.
+Jump to a section:
+- [Commonly studied organisms](/docs/download-go-annotations/#1-commonly-studied-organisms)
+- [All other organisms](/docs/download-go-annotations/#2-all-other-organisms)
 
-## About GO annotation formats
-+ Released monthly
-+ Files are taxon-specific, with a few exceptions including the Reactome and *Candida* Genome Database files
+#### Required Files
+Most tools that use GO annotations take two input files: 
+1. a file with the **annotations** (in Gene Annotation Format, or GAF)
+2. a file with the GO **ontology** structure (in Open Biomedical Ontology Format, or OBO)
+
+Because the ontology and annotations are constantly being improved over time, we recommend downloading the latest version of the annotations for your organism and the corresponding ontology file for that GO version. The version should be specified in the header of the annotation file. 
+
+#### Citing GO
+To ensure reproducibility for any publication where GO was used at any point in the research, please include:
+* [appropriate GO publication(s)- refer to the full GO citation policy](/docs/go-citation-policy/)
+* the URL where the files were obtained
+* the date on the header of the GAF file
+* the ontology version number
+
+### [1. Commonly studied organisms](http://current.geneontology.org/products/pages/downloads.html)
+[This GAF download page has annotations for selected commonly-studied species](http://current.geneontology.org/products/pages/downloads.html).
+
+For organisms with many expert-curated GO annotations (those with MODs, dedicated databases, etc.), we recommend downloading annotations from the links in the above-linked table. These organisms often have a large number of manual annotations supported by direct experimental evidence as well as annotations based on other evidence types.
+<!-- * Most of these have two downloads available, one with the full set of GO annotations, and one with only the “core” function annotations (PAN-GO) for each organism. /-->
+* These annotations should be used with the [latest version of the GO ontology](http://current.geneontology.org/ontology/index.html).
+* Annotations for these organisms are also available as GPAD/GPI companion files; see the [/annotations/](http://current.geneontology.org/annotations/index.html){:target="blank"} directory of the current release [http://current.geneontology.org](http://current.geneontology.org){:target="blank"}. For more information on these infrequently used filetypes see the format pages for [GPAD](/docs/gene-product-association-data-gpad-format/)+[GPI](/docs/gene-product-information-gpi-format/).
+
+### 2. All other organisms
+For all other organisms we recommend downloading annotations from one of the following sources: UniProt or NCBI RefSeq. Both of these provide highly accurate computational methods. The header of the annotation file specifies the version of the ontology you should use to accompany the annotation file. Older versions of the [GO ontology can be downloaded from the GO download archives](http://release.geneontology.org/).
+
+* [UniProt GAFs by proteome](https://ftp.ebi.ac.uk/pub/databases/GO/goa/proteomes/){:target="blank"}: Annotation files are available for about 20,000 complete proteomes (one protein sequence per protein-coding gene). Use these files if you want to use **UniProtKB identifiers**.
+  * Go to [https://ftp.ebi.ac.uk/pub/databases/GO/goa/proteomes/](https://ftp.ebi.ac.uk/pub/databases/GO/goa/proteomes/){:target="blank"}
+  * Navigate to your organism & download the `.goa` file, e.g. [`22426.A_gambiae.goa`](https://ftp.ebi.ac.uk/pub/databases/GO/goa/proteomes/22426.A_gambiae.goa){:target="blank"}  
+    *Tip: use your browser's in-page search to find the species name.*
+
+* [NCBI RefSeq](https://ftp.ncbi.nlm.nih.gov/genomes/refseq/){:target="blank"}: If your organism has a reference genome assembly in NCBI, GO annotations are available in GAF format through NCBI Gene identifiers. Annotation files are available for all eukaryotic genomes available at NCBI RefSeq. Note that GO annotations are not currently available for archaea, bacteria or viruses.
+  * Go to [NCBI](https://www.ncbi.nlm.nih.gov/){:target="blank"}
+  * Navigate to your organism, e.g. [Anopheles gambiae](https://www.ncbi.nlm.nih.gov/search/all/?term=Anopheles%20gambiae){:target="blank"}
+  * Follow the ["Genomes" link](https://www.ncbi.nlm.nih.gov/datasets/genome/?taxon=7165){:target="blank"}
+  * Select the [reference assembly](https://www.ncbi.nlm.nih.gov/datasets/genome/GCF_943734735.2/) at the top of the list; this entry is indicated with a green "reference genome" icon and a GCF identifer listed in the RefSeq column
+  * Click on the [FTP link](https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/943/734/735/GCF_943734735.2_idAnoGambNW_F1_1/){:target="blank"}
+  * Download the file with the suffix `gene_ontology.gaf.gz`, e.g. `GCF_943734735.2-RS_2023_12_gene_ontology.gaf.gz`
+
+### 3. If you cannot find annotations for your organism for download as described above
+[Get help from the GO helpdesk](https://help.geneontology.org/).
+
+### 4. If your organism’s genome sequence is not yet publicly available
+For example, if you have a set of new (protein) sequences that you want to annotate with GO terms, we recommend that you generate annotations using the latest version of InterProScan.
+For most genomic analyses, your input file should have one protein sequence per protein-coding gene, though any set of protein sequences can be used.
+Download InterProScan at [https://www.ebi.ac.uk/interpro/about/interproscan](https://www.ebi.ac.uk/interpro/about/interproscan/){:target="blank"}.
+
+## More information on GO annotation formats
++ GO has monthly releases
++ Annotation files are taxon-specific, with a few exceptions including the Reactome and *Candida* Genome Database files
 + Current format guides:
-  + [GAF format](/docs/go-annotation-file-gaf-format-2.2/)
+  + [GAF format 2.2](/docs/go-annotation-file-gaf-format-2.2/)
   + [GPAD](/docs/gene-product-association-data-gpad-format/) + [GPI](/docs/gene-product-information-gpi-format/) companion files
 
 ## Programmatic access to GO annotations
 As for any resource in GO, GO annotations are accessible through the DOI-versioned release stored in [Zenodo](https://doi.org/10.5281/zenodo.1205159){:target="blank"}.
 
-## Error or omission ?
-Any errors or omissions in annotations should be reported by writing to the [GO helpdesk](http://help.geneontology.org/){:target="blank"}
+## Error or omission?
+Any errors or omissions in annotations should be reported by writing to the [GO helpdesk](http://help.geneontology.org/){:target="blank"}.

_docs/download-go-cams.md

@@ -26,4 +26,4 @@ permalink: /docs/download-go-cams/
 As for any resource in GO, GO-CAMs are accessible through the DOI-versioned release stored in [Zenodo](https://doi.org/10.5281/zenodo.1205159){:target="blank"}.
 
 ## Error or omission ?
-Any errors or omissions in annotations should be reported by writing to the [GO helpdesk](https://help.geneontology.org/){:target="blank"}
+Any errors or omissions in annotations should be reported by writing to the [GO helpdesk](https://help.geneontology.org/){:target="blank"}.

_docs/download-ontology.md

@@ -30,7 +30,7 @@ Files are available in the following formats:
 
 |**Subset name**|**Maintainer**|**File name**|**OBO format**|**OWL format**|**json format**|
 |------------------|-------------|-------------|-------------|------------|-------------|
-|**GO slim AGR subset**|Developed by GO Consortium for the [Alliance of Genomes Resources](https://www.alliancegenome.org/){:target="blank"} |goslim_agr  |[obo](https://current.geneontology.org/ontology/subsets/goslim_agr.obo) |[owl](https://current.geneontology.org/ontology/subsets/goslim_agr.owl){:target="blank"}  |[json](https://current.geneontology.org/ontology/subsets/goslim_agr.json){:target="blank"}  |
+|***A*lliance of *G*enome *R*esources subset**|Developed by GO Consortium for the [Alliance of Genomes Resources](https://www.alliancegenome.org/){:target="blank"} |goslim_agr  |[obo](https://current.geneontology.org/ontology/subsets/goslim_agr.obo) |[owl](https://current.geneontology.org/ontology/subsets/goslim_agr.owl){:target="blank"}  |[json](https://current.geneontology.org/ontology/subsets/goslim_agr.json){:target="blank"}  |
 |**Generic GO subset**|[GO Consortium](https://help.geneontology.org/){:target="blank"} |goslim_generic|[obo](https://current.geneontology.org/ontology/subsets/goslim_generic.obo)| [owl](https://current.geneontology.org/ontology/subsets/goslim_generic.owl){:target="blank"}  |[json](https://current.geneontology.org/ontology/subsets/goslim_generic.json){:target="blank"}  |
 |*__Aspergillus__* **subset**|[_Aspergillus_ Genome Data](http://www.aspgd.org/){:target="blank"} |goslim_aspergillus|[obo](https://current.geneontology.org/ontology/subsets/goslim_aspergillus.obo) |[owl](https://current.geneontology.org/ontology/subsets/goslim_aspergillus.owl){:target="blank"}  |[json](https://current.geneontology.org/ontology/subsets/goslim_aspergillus.json){:target="blank"}  |
 |*__Candida albicans__* **subset**|[_Candida_ Genome Database](http://www.candidagenome.org/){:target="blank"} |goslim_candida|[obo](https://current.geneontology.org/ontology/subsets/goslim_candida.obo)|[owl](https://current.geneontology.org/ontology/subsets/goslim_candida.owl){:target="blank"}  |[json](https://current.geneontology.org/ontology/subsets/goslim_candida.json){:target="blank"}  |
@@ -52,8 +52,6 @@ For internal checking purposes, GO maintains two "anti-slims", terms to which an
 |**Subset name**|**Usage** |**File name** |**OBO format** |**OWL format** |**json format** |
 |------------------|----------|----------|----------|----------|----------|
 |**Do not annotate**|The set of high level terms that are useful for grouping, but should have no direct annotations| gocheck_do_not_annotate |[obo](https://current.geneontology.org/ontology/subsets/gocheck_do_not_annotate.obo)| [owl](https://current.geneontology.org/ontology/subsets/gocheck_do_not_annotate.owl){:target="blank"}  |[json](https://current.geneontology.org/ontology/subsets/gocheck_do_not_annotate.json){:target="blank"}  |
-|**Do not manually annotate**|The set of high level terms that are useful for grouping, but should have no direct annotations except from automated tools| gocheck_do_not_manually_annotate|[obo](https://current.geneontology.org/ontology/subsets/gocheck_do_not_manually_annotate.obo)|[owl](https://current.geneontology.org/ontology/subsets/gocheck_do_not_manually_annotate.owl){:target="blank"}  |[json](https://current.geneontology.org/ontology/subsets/gocheck_do_not_manually_annotate.json){:target="blank"}  |
-
 
 ## Cross-references of GO to other classification systems
 

_docs/faq.md

@@ -822,19 +822,22 @@ No - the term will always have the same children wherever, and however many time
 {::comment}
 
 <span class="rdf-meta element-hidden" property="dc:title" content="How do I get the term names for my list of GO IDs? How do I get GO IDs for my GO terms? What about definitions?"></span>
-FAQ tags: 
+FAQ tags:
 
 [mappings](/faq-tags/mappings)
 
 [ontology](/faq-tags/ontology)
 {:/comment}
 
-You can use the YeastMine Analyze tool available at SGD! This tool will return a table of GO ID, GO term name, GO term namespace (cellular component, molecular function, or biological process) and GO term description for each valid GO ID you supply. This will work for any organism, as the GO is the same!
+You can use the AllianceMine's Upload List tool available at the Alliance website! This tool will return a table of GO ID, GO term name, and GO term description for each valid GO ID you supply. This will work for any organism, as the GO is the same! 
+
+1.  Go to the [Upload List tool on AllianceMine](https://www.alliancegenome.org/bluegenes/alliancemine/upload/input){:target="blank"}
+2.  In the List Type pull down, select `GO Term`
+3.  Enter your GO ids or upload a file, making sure GO IDs have the correct format (GO:0016020, GO:0016301...)
+4.  Click on `Continue`, and then on the next page use the `Save List` button.
+5.  You can use the `Save list` button on the next page to use this list in AllianceMine, or use the `Export` button to see download options.
 
-1.  Go to the [Analyze tool on YeastMine](http://yeastmine.yeastgenome.org/yeastmine/bag.do){:target="blank"}
-2.  In the Select Type pull down, select `GO Term`
-3.  Enter your GO ids or upload a list in the full format (GO:0016020, GO:0016301...)
-4.  Click on `Create List`. The tool offers several options to download the list when you use the `Save a list of...` button.
+If you need the aspect (cellular component, molecular function, or biological process) for each term, you can add this to the results before saving. Use the `Add Columns`, click `Namespace` to highlight that option, then click the `Add 1 columns` button in the lower right. You can also use the AllianceMine features to filter your list, for example to select only molecular_function terms in your list.
 
 If you have a list of GO terms and wish to retrieve GO IDs and/or definitions, you can use the steps above. Make sure multi-word GO terms are in double quotes (sporulation,"lactase activity","codeine metabolic process") as the tool will otherwise recognise spaces as delimiters.
 
@@ -843,7 +846,7 @@ If you have a list of GO terms and wish to retrieve GO IDs and/or definitions, y
 {::comment}
 
 <span class="rdf-meta element-hidden" property="dc:title" content="Can I download the ontologies as an Excel spreadsheet?"></span>
-FAQ tags: 
+FAQ tags:
 
 [ontology](/faq-tags/ontology)
 {:/comment}