Merge pull request #4 from supernord/main

Add GoogleSheet import feature from field guide

.github/workflows/jekyll.yml

@@ -13,6 +13,7 @@ permissions:
   id-token: write
 
 jobs:
+
   build:
     runs-on: ubuntu-latest
     steps:

.github/workflows/update_guides.yml

@@ -0,0 +1,38 @@
+
+name: Update guides
+
+on:
+  workflow_dispatch:
+
+jobs:
+
+  update_guides:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+
+      - name: setup python
+        uses: actions/setup-python@v2
+        with:
+          python-version: '3.8.16'
+
+      - name: install python packages
+        run: |
+          python -m pip install --upgrade pip
+          pip install -r requirements.txt
+
+      - name: execute table conversion script
+        run: python scripts/guides_table_conversion.py
+
+      - name: Commit if updated
+        run: |
+          git config --local user.email "[email protected]"
+          git config --local user.name "GitHub Action"
+          git add -A
+          git diff-index --quiet HEAD || git commit -m "update guides"
+
+      - name: Push if changes
+        uses: ad-m/[email protected]
+        with:
+          github_token: ${{ secrets.GITHUB_TOKEN }}
+          branch: main

_data/tool_and_resource_list.yml

@@ -1,52 +1,67 @@
-- id: genome-assembly-hifi
-  description:
-    This How-to-Guide describes the steps required to assemble your genome on the Galaxy Australia platform, using multiple workflows developed in consultation between the Bioplatforms Australia Threatened Species Initiative, Galaxy Australia, and the Australian BioCommons.
-  url: https://australianbiocommons.github.io/how-to-guides/genome_assembly/hifi_assembly
+- description: This How-to-Guide describes the steps required to assemble your genome
+    on the Galaxy Australia platform, using multiple workflows developed in consultation
+    between the Bioplatforms Australia Threatened Species Initiative, Galaxy Australia,
+    and the Australian BioCommons.
+  id: genome-assembly-hifi
   name: Genome assembly with `hifiasm` on Galaxy Australia
   registry:
     tess: genome assembly
     wfh-collection: https://workflowhub.eu/collections/5
   related_pages:
-    - genome_assembly
-- id: genome-assembly-qc
-  description:
-    Once a genome has been assembled, it is important to assess the quality of the assembly, and in the first instance, this quality control (QC) can be achieved using the workflow described here.
-  url: https://australianbiocommons.github.io/how-to-guides/genome_assembly/assembly_qc
+  - genome_assembly
+  url: https://australianbiocommons.github.io/how-to-guides/genome_assembly/hifi_assembly
+- description: Once a genome has been assembled, it is important to assess the quality
+    of the assembly, and in the first instance, this quality control (QC) can be achieved
+    using the workflow described here.
+  id: genome-assembly-qc
   name: Assess the quality of your genome assembly
   registry:
     tess: genome assembly
     wfh: https://workflowhub.eu/workflows/403
   related_pages:
-    - genome_assembly
-- id: how-to-create-guide
-  description:
-    This web page describes How-to create new How-to Guide websites using a GitHub repository template.
-  url: https://australianbiocommons.github.io/how-to-guide-template/
+  - genome_assembly
+  url: https://australianbiocommons.github.io/how-to-guides/genome_assembly/assembly_qc
+- description: This web page describes How-to create new How-to Guide websites using
+    a GitHub repository template.
+  id: how-to-create-guide
   name: How-to Guide for creating a How-to Guide
-  related_pages:
-    - documentation
   registry:
     doi: https://doi.org/10.5281/zenodo.8210268
     template: https://github.com/AustralianBioCommons/guide-template
-- id: doc-guidelines
-  description:
-    The Australian BioCommons has been working with community bioinformaticians and our infrastructure partners to establish a guidelines repository that can act as a template for documentation of tools and workflows.
-  url: https://australianbiocommons.github.io/how-to-doc-guidelines/
-  name: How-to use the Australian BioCommons documentation guidelines
   related_pages:
-    - documentation
+  - documentation
+  url: https://australianbiocommons.github.io/how-to-guide-template/
+- description: The Australian BioCommons has been working with community bioinformaticians
+    and our infrastructure partners to establish a guidelines repository that can
+    act as a template for documentation of tools and workflows.
+  id: doc-guidelines
+  name: How-to use the Australian BioCommons documentation guidelines
   registry:
     template: https://github.com/AustralianBioCommons/doc_guidelines
-- id: stacks
-  description:
-    This How-to Guide describes the steps required to run the Stacks workflows on Galaxy Australia to analyse RADseq data, using workflows developed in consultations between the Bioplatforms Australia Threatened Species Initiative, Galaxy Australia, and the Australian BioCommons.
-  url: https://australianbiocommons.github.io/how-to-guides/stacks_workflows/stacks
+  related_pages:
+  - documentation
+  url: https://australianbiocommons.github.io/how-to-doc-guidelines/
+- description: This How-to Guide describes the steps required to run the Stacks workflows
+    on Galaxy Australia to analyse RADseq data, using workflows developed in consultations
+    between the Bioplatforms Australia Threatened Species Initiative, Galaxy Australia,
+    and the Australian BioCommons.
+  id: stacks
   name: Stacks workflows in Galaxy Australia using RADseq
   registry:
     biotools: stacks
     tess: RAD seq
   related_pages:
-    - pop_gen
+  - pop_gen
+  url: https://australianbiocommons.github.io/how-to-guides/stacks_workflows/stacks
+- description: This How-to Guide describes how to use the shotgun metagenomics workflow
+    with MetaPhlAn2 on Galaxy Australia. The workflow is using the tools MetaPhlAn2
+    for taxonomy classification and HUMAnN2 for functional profiling of the metagenomes.
+  id: shotgun-metagenomics-metaphlanv2
+  name: Shotgun metagenomics workflow with MetaPhlAn2 on Galaxy Australia
+  registry: {}
+  related_pages:
+  - metagenomics
+  url: https://vmurigneu.github.io/shotgun_howto_ga_workflows/shotgun_wf_guide
 - id: scrnaseq_howto_ga_workflows
   description: This guide describes how to use some scanpy-based single cell RNAseq workflows on Galaxy Australia.
   url: https://swbioinf.github.io/scrnaseq_howto_ga_workflows/scrnaseq_wf_guide

index.md

@@ -20,6 +20,8 @@ If you have an idea for a new How-to Guide, or a new category, please visit the
 
 ## Acknowledgements
 
+The authors would like to acknowledge Marion Shadbolt (@mshadbolt) for developing the GoogleSheet import and parsing that is being reused for the How-to Hub.
+
 This work is supported by the [Australian BioCommons](https://www.biocommons.org.au/) via funding from [Bioplatforms Australia](https://bioplatforms.com/), the Australian Research Data Commons (https://doi.org/10.47486/PL105) and the Queensland Government Research Infrastructure Co-investment Fund (RICF) programme. Bioplatforms Australia and the Australian Research Data Commons are funded by the National Collaborative Research Infrastructure Strategy (NCRIS).
 
 This guide makes use of the [ELIXIR toolkit theme](https://github.com/ELIXIR-Belgium/elixir-toolkit-theme)

pages/metagenomics.md

@@ -0,0 +1,9 @@
+---
+title: Metagenomics
+type: category
+page_id: metagenomics
+description: How-to Guides focused on metagenomics.
+---
+
+
+

requirements.txt

@@ -0,0 +1,6 @@
+pandas
+requests
+argparse
+PyYAML
+python-frontmatter
+urllib3

scripts/guides_table_conversion.py

@@ -0,0 +1,47 @@
+"""
+Adapted from https://github.com/elixir-europe/rdmkit/blob/master/var/conversions.py
+Adapted from https://github.com/AustralianBioCommons/human-omics-data-sharing-field-guide/blob/328e84634d10b0df51e798dbf1cc114c7cb26357/var/tools_table_conversion.py
+"""
+
+import pandas as pd
+import yaml
+import os
+
+# --------- Variables ---------
+
+google_id = "1CWSW5CAg0f8e5XB9Bl80jiDT8QCWOWhuCxKjDWLi5a4"
+gid = "0"
+url = f"https://docs.google.com/spreadsheets/d/{google_id}/export?format=csv&gid={gid}"
+output_path = "_data/tool_and_resource_list.yml"
+rootdir = '../pages'
+allowed_registries = ['biotools', 'fairsharing', 'tess', 'wfh-collection', 'wfh', 'doi', 'template']
+
+# --------- Converting the table ---------
+
+print(f"----> Converting GoogleSheets table to {output_path} started.")
+resource_table = pd.read_csv(url, dtype={'name': str, 'url': str, 'description': str, 'id': str, 'fairsharing': str,
+                                         'biotools': str, 'tess': str, 'wfh-collection': str, 'wfh': str,
+                                         'doi': str, 'template': str, 'related_pages': str})
+resource_list = resource_table.to_dict("records")
+clean_resource_list = []
+for resource in resource_list:
+    if not pd.isna(resource['related_pages']):
+        category_list = resource['related_pages'].rsplit(sep=",")
+    else:
+        category_list = ""
+    registry_dict = {}
+    for registry in allowed_registries:
+        if not pd.isna(resource[registry]):
+            registry_dict[registry] = resource[registry]
+        del(resource[registry])
+    clean_resource = {k: resource[k] for k in resource if not pd.isna(resource[k])}
+    clean_resource_list.append(clean_resource)
+    clean_resource['registry'] = registry_dict
+    if category_list != "":
+        clean_resource['related_pages'] = category_list
+
+print(os.getcwd())
+with open(output_path, 'w+') as yaml_file:
+    documents = yaml.dump(clean_resource_list, yaml_file)
+
+print("----> YAML is dumped successfully")