Merge pull request #1244 from GenSpectrum/main

chore: update prod from main

Author: fhennig

.github/dependabot.yml

@@ -6,6 +6,8 @@ updates:
       interval: weekly
     commit-message:
       prefix: "chore(github-actions)"
+    cooldown:
+      default-days: 7
   - package-ecosystem: npm
     directory: website/
     schedule:
@@ -16,6 +18,8 @@ updates:
     commit-message:
       prefix: "chore(website)"
     target-branch: "main"
+    cooldown:
+      default-days: 7
   - package-ecosystem: npm
     directory: website/
     schedule:
@@ -27,6 +31,8 @@ updates:
           - "patch"
     commit-message:
       prefix: "chore(website)"
+    cooldown:
+      default-days: 7
   - package-ecosystem: gradle
     directory: backend/
     schedule:
@@ -38,3 +44,5 @@ updates:
           - "patch"
     commit-message:
       prefix: "chore(backend)"
+    cooldown:
+      default-days: 7

.github/workflows/e2e.yml

@@ -70,6 +70,22 @@ jobs:
       env:
         BACKEND_URL: http://localhost:9021
 
+    - name: Collect container logs
+      if: ${{ always() && !cancelled() }}
+      run: |
+        mkdir -p /tmp/container-logs
+        services="$(docker compose -f ../docker-compose.yml config --services || true)"
+        for service in $services; do
+          docker compose -f ../docker-compose.yml logs --no-color "$service" > "/tmp/container-logs/${service}.log" || true
+        done
+
+    - uses: actions/upload-artifact@v7
+      if: ${{ always() && !cancelled() }}
+      with:
+        name: container-logs
+        path: /tmp/container-logs/
+        retention-days: 7
+
     - uses: actions/upload-artifact@v7
       if: ${{ !cancelled() }}
       with:

.github/workflows/rebaseProd.yml

@@ -26,9 +26,9 @@ jobs:
             echo "PR to update prod from main already exists - skipping creation"
           else
             body="This pull request updates the \`prod\` branch with the latest changes from the \`main\` branch.
-  
-            ### Make sure to merge this creating a merge commit.
-            **Do not squash-merge** this PR. **Do not rebase and merge**."
-        
+
+            # ⚠️ Do not squash-merge! ⚠️
+            Make sure to merge this creating a merge commit."
+
             gh pr create --base prod --head main --title "chore: update prod from main" --body "$body"
           fi

collection-seeding/README.md

@@ -5,6 +5,8 @@ Seeds the backend with example collections:
 - **covid-resistance-mutations** — resistance mutation data for 3CLpro, RdRp, and Spike mAb
 - **covid-pango-lineages** — one collection per pango lineage, with nucleotide substitutions as variants
 - **covid-pango-lineages-sample** — same as above but limited to 10 lineages, for quick testing
+- **rsv-a-resistance-mutations** — RSV-A F protein resistance mutations against Nirsevimab and Palivizumab (fetched live from ViralZone)
+- **rsv-b-resistance-mutations** — RSV-B F protein resistance mutations against Nirsevimab and Palivizumab (fetched live from ViralZone)
 
 The script is idempotent — re-running it will create new collections or update existing ones (matched by name). If a collection's name changes in the source, the old entry is orphaned and a new one is created.
 
@@ -30,11 +32,18 @@ Then use the provided tasks:
 
 ```bash
 pixi run seed                    # all sources
-pixi run seed-resistance         # resistance mutations only
+pixi run seed-resistance         # COVID resistance mutations only
 pixi run seed-lineages           # pango lineages only
 pixi run seed-lineages-sample    # first 10 pango lineages (quick test)
 ```
 
+RSV sources don't have dedicated tasks — use `--source` directly:
+
+```bash
+pixi run seed --source rsv-a-resistance-mutations
+pixi run seed --source rsv-b-resistance-mutations
+```
+
 To target a different backend:
 
 ```bash

…ection-seeding/sources/pango_lineages.py …-seeding/sources/covid_pango_lineages.pycollection-seeding/sources/pango_lineages.py renamed to collection-seeding/sources/covid_pango_lineages.py collection-seeding/sources/pango_lineages.py renamed to collection-seeding/sources/covid_pango_lineages.py

@@ -9,7 +9,7 @@
 )
 
 
-class PangoLineagesSource(Source):
+class CovidPangoLineagesSource(Source):
     """Source: Pango lineage definitions from corneliusroemer/pango-sequences.
 
     Creates one collection per lineage, with nucleotide substitutions as variants.
@@ -82,8 +82,8 @@ def _build_collection(self, entry: dict) -> Collection:
         }
 
 
-class PangoLineagesSampleSource(PangoLineagesSource):
-    """Same as PangoLineagesSource but limited to the first 10 lineages, for quick testing."""
+class CovidPangoLineagesSampleSource(CovidPangoLineagesSource):
+    """Same as CovidPangoLineagesSource but limited to the first 10 lineages, for quick testing."""
 
     name = "covid-pango-lineages-sample"
     include_in_default_run = False

…-seeding/sources/resistance_mutations.py …ng/sources/covid_resistance_mutations.pycollection-seeding/sources/resistance_mutations.py renamed to collection-seeding/sources/covid_resistance_mutations.py collection-seeding/sources/resistance_mutations.py renamed to collection-seeding/sources/covid_resistance_mutations.py

@@ -2,7 +2,7 @@
 from sources import Source
 
 
-class ResistanceMutationsSource(Source):
+class CovidResistanceMutationsSource(Source):
     """Source: SARS-CoV-2 antiviral resistance mutations (ported from seed.mjs).
 
     Three collections covering 3CLpro, RdRp, and Spike mAb resistance mutations

collection-seeding/sources/registry.py

@@ -4,12 +4,15 @@
 place that needs to change — seed.py discovers sources exclusively through this list.
 """
 
-from sources.pango_lineages import PangoLineagesSource, PangoLineagesSampleSource
-from sources.resistance_mutations import ResistanceMutationsSource
+from sources.covid_pango_lineages import CovidPangoLineagesSource, CovidPangoLineagesSampleSource
+from sources.covid_resistance_mutations import CovidResistanceMutationsSource
+from sources.rsv_resistance_mutations import RsvAResistanceMutationsSource, RsvBResistanceMutationsSource
 from sources import Source
 
 ALL_SOURCES: list[type[Source]] = [
-    ResistanceMutationsSource,
-    PangoLineagesSource,
-    PangoLineagesSampleSource,
+    CovidResistanceMutationsSource,
+    RsvAResistanceMutationsSource,
+    RsvBResistanceMutationsSource,
+    CovidPangoLineagesSource,
+    CovidPangoLineagesSampleSource,
 ]

collection-seeding/sources/rsv_resistance_mutations.py

@@ -0,0 +1,81 @@
+import re
+import requests
+
+from models import Collection, Variant
+from sources import Source
+
+DATA_URL = "https://viralzone.expasy.org/resources/RSV/F_RSV_human.txt"
+
+# Regex for row parsing. The file is a TSV file, but sometimes also uses spaces.
+# Columns 1 (A/B) and 2 (mutation) never contain spaces; column 3 (comment) may.
+_ROW_RE = re.compile(r"^\s*([AB])\s+(\S+)\s+(.+)")
+
+
+def _fetch_rows() -> list[tuple[str, list[str], str, str]]:
+    response = requests.get(DATA_URL, timeout=60)
+    response.raise_for_status()
+    return _parse_rows(response.text)
+
+
+def _parse_rows(text: str) -> list[tuple[str, list[str], str, str]]:
+    """Parse ViralZone RSV resistance text into (rsv_type, aa_mutations, antibody, resistance_type) tuples."""
+    rows = []
+    for line in text.splitlines():
+        m = _ROW_RE.match(line)
+        if not m:
+            continue
+        rsv_type, aa_str, comment = m.group(1), m.group(2), m.group(3).strip()
+        aa_mutations = [f"F:{part}" for part in aa_str.split("+")]
+        if "Nirsevimab" in comment:
+            antibody = "Nirsevimab"
+        elif "Palivizumab" in comment:
+            antibody = "Palivizumab"
+        else:
+            continue
+        resistance_type = "Partial resistance" if "Partial resistance" in comment else "Resistance"
+        rows.append((rsv_type, aa_mutations, antibody, resistance_type))
+    return rows
+
+
+def _build_collections(rsv_type: str, organism: str, owned_tag: str) -> list[Collection]:
+    all_rows = _fetch_rows()
+    type_rows = [(aa, ab, res) for (t, aa, ab, res) in all_rows if t == rsv_type]
+    collections = []
+    for antibody in ("Nirsevimab", "Palivizumab"):
+        variants: list[Variant] = [
+            {
+                "type": "filterObject",
+                "name": res_type,
+                "filterObject": {"aminoAcidMutations": aa},
+            }
+            for (aa, ab, res_type) in type_rows
+            if ab == antibody
+        ]
+        collections.append({
+            "name": f"{antibody} resistance mutations",
+            "organism": organism,
+            "description": (
+                f"RSV F protein resistance mutations against {antibody} "
+                f"as per ViralZone (https://viralzone.expasy.org/11605). {owned_tag}"
+            ),
+            "variants": variants,
+        })
+    return collections
+
+
+class RsvAResistanceMutationsSource(Source):
+    name = "rsv-a-resistance-mutations"
+    organism = "rsvA"
+    owned_tag = "#resistance-mutation"
+
+    def get_collections(self) -> list[Collection]:
+        return _build_collections("A", self.organism, self.owned_tag)
+
+
+class RsvBResistanceMutationsSource(Source):
+    name = "rsv-b-resistance-mutations"
+    organism = "rsvB"
+    owned_tag = "#resistance-mutation"
+
+    def get_collections(self) -> list[Collection]:
+        return _build_collections("B", self.organism, self.owned_tag)

collection-seeding/tests/test_pango_lineages.py

@@ -1,6 +1,6 @@
 import responses as rsps_lib
 
-from sources.pango_lineages import PangoLineagesSource, DATA_URL
+from sources.covid_pango_lineages import CovidPangoLineagesSource, DATA_URL
 
 SAMPLE_DATA = {
     "BA.2": {
@@ -40,39 +40,39 @@
 
 
 def test_name():
-    assert PangoLineagesSource.name == "covid-pango-lineages"
+    assert CovidPangoLineagesSource.name == "covid-pango-lineages"
 
 
 # --- _build_collection ---
 
 
 def test_build_collection_basic():
-    col = PangoLineagesSource()._build_collection(SAMPLE_DATA["BA.2"])
+    col = CovidPangoLineagesSource()._build_collection(SAMPLE_DATA["BA.2"])
     assert col["name"] == "BA.2"
     assert col["organism"] == "covid"
 
 
 def test_build_collection_description_format():
-    col = PangoLineagesSource()._build_collection(SAMPLE_DATA["BA.2"])
+    col = CovidPangoLineagesSource()._build_collection(SAMPLE_DATA["BA.2"])
     assert "BA.2" in col["description"]
     assert "BA" in col["description"]  # parent
     assert "22C" in col["description"]  # clade
     assert "2022-01-20" in col["description"]
 
 
 def test_build_collection_missing_fields_use_defaults():
-    col = PangoLineagesSource()._build_collection(SAMPLE_DATA["XBB"])
+    col = CovidPangoLineagesSource()._build_collection(SAMPLE_DATA["XBB"])
     assert "—" in col["description"]  # parent and clade fallback
     assert "unknown" in col["description"]  # date fallback
 
 
 def test_build_collection_always_four_variants():
-    col = PangoLineagesSource()._build_collection(SAMPLE_DATA["BA.2"])
+    col = CovidPangoLineagesSource()._build_collection(SAMPLE_DATA["BA.2"])
     assert len(col["variants"]) == 4
 
 
 def test_build_collection_variant_names():
-    col = PangoLineagesSource()._build_collection(SAMPLE_DATA["BA.2"])
+    col = CovidPangoLineagesSource()._build_collection(SAMPLE_DATA["BA.2"])
     names = [v["name"] for v in col["variants"]]
     assert names == [
         "Nucleotide substitutions",
@@ -83,7 +83,7 @@ def test_build_collection_variant_names():
 
 
 def test_build_collection_variant_filter_keys():
-    col = PangoLineagesSource()._build_collection(SAMPLE_DATA["BA.2"])
+    col = CovidPangoLineagesSource()._build_collection(SAMPLE_DATA["BA.2"])
     variants = col["variants"]
     assert "nucleotideMutations" in variants[0]["filterObject"]
     assert "aminoAcidMutations" in variants[1]["filterObject"]
@@ -92,7 +92,7 @@ def test_build_collection_variant_filter_keys():
 
 
 def test_build_collection_variant_contents():
-    col = PangoLineagesSource()._build_collection(SAMPLE_DATA["BA.2"])
+    col = CovidPangoLineagesSource()._build_collection(SAMPLE_DATA["BA.2"])
     variants = col["variants"]
     assert variants[0]["filterObject"]["nucleotideMutations"] == ["C241T", "A23403G"]
     assert variants[1]["filterObject"]["aminoAcidMutations"] == ["S:N501Y"]
@@ -101,15 +101,15 @@ def test_build_collection_variant_contents():
 
 
 def test_build_collection_filters_blank_subs():
-    col = PangoLineagesSource()._build_collection(SAMPLE_DATA["BA.2"])
+    col = CovidPangoLineagesSource()._build_collection(SAMPLE_DATA["BA.2"])
     # nucSubstitutions has ["C241T", "A23403G", ""] — blank should be dropped
     nuc = col["variants"][0]["filterObject"]["nucleotideMutations"]
     assert "" not in nuc
     assert len(nuc) == 2
 
 
 def test_build_collection_empty_lists_when_all_blanks():
-    col = PangoLineagesSource()._build_collection(SAMPLE_DATA["XBB"])
+    col = CovidPangoLineagesSource()._build_collection(SAMPLE_DATA["XBB"])
     assert len(col["variants"]) == 4
     for v in col["variants"]:
         lists = list(v["filterObject"].values())
@@ -122,15 +122,15 @@ def test_build_collection_empty_lists_when_all_blanks():
 @rsps_lib.activate
 def test_get_collections_fetches_data_url():
     rsps_lib.add(rsps_lib.GET, DATA_URL, json=SAMPLE_DATA, status=200)
-    PangoLineagesSource().get_collections()
+    CovidPangoLineagesSource().get_collections()
     assert len(rsps_lib.calls) == 1
     assert rsps_lib.calls[0].request.url == DATA_URL
 
 
 @rsps_lib.activate
 def test_get_collections_includes_all_lineages():
     rsps_lib.add(rsps_lib.GET, DATA_URL, json=SAMPLE_DATA, status=200)
-    cols = PangoLineagesSource().get_collections()
+    cols = CovidPangoLineagesSource().get_collections()
     # All lineages included regardless of empty subs
     names = [c["name"] for c in cols]
     assert "BA.2" in names
@@ -141,12 +141,12 @@ def test_get_collections_includes_all_lineages():
 @rsps_lib.activate
 def test_get_collections_respects_limit():
     rsps_lib.add(rsps_lib.GET, DATA_URL, json=SAMPLE_DATA, status=200)
-    cols = PangoLineagesSource(limit=1).get_collections()
+    cols = CovidPangoLineagesSource(limit=1).get_collections()
     assert len(cols) <= 1
 
 
 @rsps_lib.activate
 def test_get_collections_no_limit_returns_all():
     rsps_lib.add(rsps_lib.GET, DATA_URL, json=SAMPLE_DATA, status=200)
-    cols = PangoLineagesSource().get_collections()
+    cols = CovidPangoLineagesSource().get_collections()
     assert len(cols) == 3

collection-seeding/tests/test_resistance_mutations.py

@@ -1,8 +1,8 @@
-from sources.resistance_mutations import ResistanceMutationsSource, _mature_name
+from sources.covid_resistance_mutations import CovidResistanceMutationsSource, _mature_name
 
 
 def test_name():
-    assert ResistanceMutationsSource.name == "covid-resistance-mutations"
+    assert CovidResistanceMutationsSource.name == "covid-resistance-mutations"
 
 
 # --- _mature_name ---
@@ -31,17 +31,17 @@ def test_mature_name_deletion():
 
 
 def test_get_collections_returns_three():
-    cols = ResistanceMutationsSource().get_collections()
+    cols = CovidResistanceMutationsSource().get_collections()
     assert len(cols) == 3
 
 
 def test_get_collections_all_covid():
-    for col in ResistanceMutationsSource().get_collections():
+    for col in CovidResistanceMutationsSource().get_collections():
         assert col["organism"] == "covid"
 
 
 def test_get_collections_variant_structure():
-    for col in ResistanceMutationsSource().get_collections():
+    for col in CovidResistanceMutationsSource().get_collections():
         assert col["variants"], f"'{col['name']}' has no variants"
         for v in col["variants"]:
             assert v["type"] == "filterObject"