Merge branch 'release-2025.5.0' into jstone-dev/score-set-search-result-optimization

Author: jstone-dev

src/mavedb/routers/alphafold.py

@@ -0,0 +1,50 @@
+from fastapi import APIRouter, HTTPException
+import httpx
+import xml.etree.ElementTree as ET
+import re
+
+from mavedb.lib.logging.logged_route import LoggedRoute
+
+ALPHAFOLD_BASE = "https://alphafold.ebi.ac.uk/files/"
+
+router = APIRouter(
+    prefix="/api/v1",
+    tags=["alphafold files"],
+    responses={404: {"description": "Not found"}},
+    route_class=LoggedRoute,
+)
+
+@router.get("/alphafold-files/version")
+async def proxy_alphafold_index():
+    """
+    Proxy the AlphaFold files index (XML document).
+    """
+    async with httpx.AsyncClient(follow_redirects=True, timeout=30) as client:
+        resp = await client.get(ALPHAFOLD_BASE, headers={"Accept": "application/xml"})
+    if resp.status_code != 200:
+        raise HTTPException(status_code=resp.status_code, detail="Upstream error fetching AlphaFold files index")
+
+    # parse XML response
+    try:
+        root = ET.fromstring(resp.content)
+
+        # Detect default namespace
+        if root.tag.startswith("{"):
+            ns_uri = root.tag.split("}", 1)[0][1:]
+            ns = {"x": ns_uri}
+            next_marker_tag = "x:NextMarker"
+        else:
+            ns = {}
+            next_marker_tag = "NextMarker"
+
+        next_marker_el = root.find(next_marker_tag, ns)
+        next_marker = next_marker_el.text if next_marker_el is not None else None
+
+        match = re.search(r"model_(v\d+)\.pdb$", next_marker, re.IGNORECASE)
+        if not match:
+            raise HTTPException(status_code=500, detail="Malformed AlphaFold PDB ID in XML")
+        version = match.group(1)
+        return {"version": version.lower()}
+
+    except ET.ParseError as e:
+        raise HTTPException(status_code=502, detail=f"Failed to parse upstream XML: {e}")

src/mavedb/routers/score_sets.py

@@ -179,10 +179,12 @@ def search_score_sets(
 
     score_sets, num_score_sets = _search_score_sets(db, None, search).values()
     enriched_score_sets = []
-    for ss in score_sets:
-        enriched_experiment = enrich_experiment_with_num_score_sets(ss.experiment, user_data)
-        response_item = score_set.ScoreSet.model_validate(ss).copy(update={"experiment": enriched_experiment})
-        enriched_score_sets.append(response_item)
+    if search.include_experiment_score_set_urns_and_count and updated_score_sets:
+        for ss in score_sets:
+            enriched_experiment = enrich_experiment_with_num_score_sets(ss.experiment, user_data)
+            response_item = score_set.ScoreSet.model_validate(ss).copy(update={"experiment": enriched_experiment})
+            enriched_score_sets.append(response_item)
+        score_sets = enriched_score_sets
 
     return {"score_sets": enriched_score_sets, "num_score_sets": num_score_sets}
 

src/mavedb/server_main.py

@@ -7,6 +7,7 @@
 from fastapi.encoders import jsonable_encoder
 from fastapi.exceptions import RequestValidationError
 from fastapi.middleware.cors import CORSMiddleware
+from fastapi.middleware.gzip import GZipMiddleware
 from fastapi.openapi.utils import get_openapi
 from sqlalchemy.orm import configure_mappers
 from starlette import status
@@ -58,6 +59,7 @@
     taxonomies,
     users,
     variants,
+    alphafold,
 )
 
 logger = logging.getLogger(__name__)
@@ -82,6 +84,7 @@
     allow_methods=["*"],
     allow_headers=["*"],
 )
+app.add_middleware(GZipMiddleware, minimum_size=1000, compresslevel=5)
 app.include_router(access_keys.router)
 app.include_router(api_information.router)
 app.include_router(collections.router)
@@ -106,6 +109,7 @@
 app.include_router(taxonomies.router)
 app.include_router(users.router)
 app.include_router(variants.router)
+app.include_router(alphafold.router)
 
 
 @app.exception_handler(PermissionException)

src/mavedb/view_models/search.py

@@ -27,6 +27,7 @@ class ScoreSetsSearch(BaseModel):
     publication_identifiers: Optional[list[str]] = None
     keywords: Optional[list[str]] = None
     text: Optional[str] = None
+    include_experiment_score_set_urns_and_count: Optional[bool] = True
     offset: Optional[int] = None
     limit: Optional[int] = None