add reference genomes sourcing from Reference-Genomes repo

.github/workflows/benchmark.yml

@@ -17,6 +17,12 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v3
+      - name: Install site benchmark dependencies
+        run: npm ci
+      - name: Build site for Playwright and get ref genome data
+        env: 
+          VITE_OFFLINE_VERSION: true
+        run: npm run build
       - name: Setup cli benchmark dependencies
         run: |
             cd e2e/tests/
@@ -28,12 +34,6 @@ jobs:
       - uses: actions/setup-node@v3
         with:
           node-version: 18
-      - name: Install site benchmark dependencies
-        run: npm ci
-      - name: Build site for Playwright
-        env: 
-          VITE_OFFLINE_VERSION: true
-        run: npm run build
       - name: Get installed Playwright version
         id: playwright-version
         run: echo "PLAYWRIGHT_VERSION=$(node -e "console.log(require('./package.json').devDependencies['@playwright/test'])")" >> $GITHUB_ENV

.github/workflows/update-data.yml

@@ -0,0 +1,63 @@
+name: update ref genome data
+
+on:
+  # Allows you to run this workflow manually from the Actions tab
+  workflow_dispatch:
+  # Allows you to run this workflow every Tuesday and Friday at 12:12 UTC
+  schedule:
+    - cron: '12 12 * * 2,5'
+
+# Sets the GITHUB_TOKEN permissions to allow deployment to GitHub Pages
+permissions:
+  contents: write
+  pages: write
+  id-token: write
+
+# Allow one concurrent deployment
+concurrency:
+  group: 'update-data'
+  cancel-in-progress: true
+
+jobs:
+  deploy:
+    timeout-minutes: 60
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+      - uses: actions/setup-node@v3
+        with:
+          node-version: 18
+      - name: Install dependencies
+        run: npm ci
+      - name: Build offline mode
+        env: 
+          VITE_OFFLINE_VERSION: true
+        run: npm run build
+      - name: Push updated ref genome data and offline mode to master
+        run: |  
+          zip -r viralwasm-consensus-offline.zip dist/ run_website.py
+          git config --global user.name 'GitHub Actions'
+          git config --global user.email '[email protected]'
+          git add .
+
+          # Check for changes
+          if git diff-index --quiet HEAD --; then
+            # No changes
+            echo "No changes to commit"
+          else
+            # Changes detected
+            git commit -m "Add updated ref genome data and offline mode zip"
+            git push origin master
+          fi
+      - name: Build for github pages
+        run: npm run build
+      - name: Setup Pages
+        uses: actions/configure-pages@v3
+      - name: Upload artifact
+        uses: actions/upload-pages-artifact@v1
+        with:
+          # Upload dist repository
+          path: './dist'
+      - name: Deploy to GitHub Pages
+        id: deployment
+        uses: actions/deploy-pages@v1

e2e/tests/download-benchmark-data.sh

@@ -6,7 +6,7 @@ cd $SCRIPTPATH
 mkdir data
 cd data
 curl -LO https://github.com/niemasd/ViralConsensus-Paper/raw/main/data/time_memory_benchmark/reads.fastq.gz
-curl -LO https://github.com/Niema-Lab/ViralWasm-Consensus/raw/master/public/data/ref_genomes/NC_045512/NC_045512.fas
+cp ../../public/data/Reference-Genomes/NC_045512/NC_045512.fas NC_045512.fas
 
 for n in 10000 20000 40000 100000 200000 400000; do
 	for r in $(seq 1 $TEST_COUNT); do

package.json

@@ -5,7 +5,7 @@
   "type": "module",
   "scripts": {
     "dev": "vite --host",
-    "build": "vite build",
+    "build": "cd scripts && bash update-data.sh && cd .. && vite build",
     "lint": "eslint src --ext js,jsx --report-unused-disable-directives --max-warnings 0",
     "preview": "vite preview",
     "host": "python3 run_website.py",

public/data/REFS.json

@@ -0,0 +1 @@
+{"NC_001477": {"name": "Dengue Virus 1", "shortname": ["denv1", "dengue1", "denguevirus1"]}, "NC_002549": {"name": "Ebola Virus (Zaire ebolavirus)", "shortname": ["ebola", "ebolavirus", "zaire", "zaireebola", "zaireebolavirus"]}, "NC_009824": {"name": "HCV genotype 3", "shortname": ["hcv3"]}, "NC_004161": {"name": "Reston Virus (Reston ebolavirus)", "shortname": ["reston", "restonvirus", "restonebola", "restonebolavirus"]}, "NC_004162": {"name": "Chikungunya Virus", "shortname": ["chikv", "chikungunya", "chikungunyavirus"]}, "NC_001802": {"name": "HIV-1", "shortname": ["hiv1"]}, "NC_014373": {"name": "Bundibugyo Virus (Bundibugyo ebolavirus)", "shortname": ["bundibugyo", "bundibugyovirus"]}, "NC_009825": {"name": "HCV genotype 4", "shortname": ["hcv4"]}, "NC_004102": {"name": "HCV genotype 1", "shortname": ["hcv1"]}, "NC_001475": {"name": "Dengue Virus 3", "shortname": ["denv3", "dengue3", "denguevirus3"]}, "NC_063383": {"name": "Mpox Virus", "shortname": ["mpox", "mpoxvirus", "monkeypox", "monkeypoxvirus"]}, "NC_009823": {"name": "HCV genotype 2", "shortname": ["hcv2"]}, "NC_001474": {"name": "Dengue Virus 2", "shortname": ["denv2", "dengue2", "denguevirus2"]}, "NC_009827": {"name": "HCV genotype 6", "shortname": ["hcv6"]}, "NC_045512": {"name": "SARS-CoV-2 (COVID-19)", "shortname": ["sc2", "sarscov2", "covid", "covid19"]}, "NC_038882": {"name": "HCV genotpye 1 (isolate H77)", "shortname": ["hcv1h77"]}, "NC_001722": {"name": "HIV-2", "shortname": ["hiv2"]}, "NC_001498": {"name": "Measles Virus (Measles morbillivirus)", "shortname": ["measles", "measlesvirus", "measlesmorbillivirus"]}, "NC_002640": {"name": "Dengue Virus 4", "shortname": ["denv4", "dengue4", "denguevirus4"]}, "NC_006432": {"name": "Sudan Virus (Sudan ebolavirus)", "shortname": ["sudan", "sudanvirus", "sudanebola", "sudanebolavirus"]}, "NC_009826": {"name": "HCV genotype 5", "shortname": ["hcv5"]}, "NC_030791": {"name": "HCV genotype 7", "shortname": ["hcv7"]}, "NC_014372": {"name": "Tai Forest Virus (Tai Forest ebolavirus, Cote d'Ivoire ebolavirus)", "shortname": ["taiforest", "taiforestvirus", "taiforestebola", "taiforestebolavirus", "cotedivoire", "cotedivoirevirus", "cotedivoireebola", "cotedivoireebolavirus"]}, "NC_039345": {"name": "Bombali Virus (Bombali ebolavirus)", "shortname": ["bombali", "bombalivirus"]}}

public/data/Reference-Genomes/.gitignore

@@ -0,0 +1,163 @@
+# files created here
+REFS.json
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/