Endpoint refactor & delete UMAP

Dockerfile

@@ -27,12 +27,19 @@ COPY app/ ./app/
 # Copy built frontend from GitHub Actions build
 COPY ui/dist ./ui/dist
 
-# Expose port
-EXPOSE 8000
+# Create startup script that properly handles runtime PORT variable
+RUN echo '#!/bin/sh\n\
+PORT="${PORT:-8080}"\n\
+echo "Starting server on port $PORT"\n\
+exec /app/.venv/bin/uvicorn app.main:app --host 0.0.0.0 --port "$PORT"' > /app/start.sh && \
+  chmod +x /app/start.sh
+
+# Expose port 8080 (Cloud Run default)
+EXPOSE 8080
 
 # Health check
 HEALTHCHECK --interval=30s --timeout=30s --start-period=5s --retries=3 \
-  CMD curl -f http://localhost:8000/ || exit 1
+  CMD curl -f http://localhost:${PORT:-8080}/ || exit 1
 
 # Run the application
-CMD ["/app/.venv/bin/uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "8000"]
+CMD ["/app/start.sh"]

app/config.py

@@ -12,18 +12,29 @@ class DevelopmentConfig(BaseConfig):
     CORS_ORIGINS = [
         "http://localhost:3000",
         "http://localhost:5173",  # Vite dev server
+        "http://localhost:5174",  # Vite dev server
         "http://127.0.0.1:5173",  # Vite dev server alternative
+        "http://127.0.0.1:5174",  # Vite dev server alternative
         "http://localhost:4173",  # Vite preview server
         "http://127.0.0.1:4173",  # Vite preview server alternative
+        "http://localhost:8080",  # Docker local
+        "http://localhost:8000",  # Alternative local
     ]
 
 
 class ProductionConfig(BaseConfig):
     DEBUG = False
-    CORS_ORIGINS = [""]
+    # For Cloud Run, you need to add your actual domain
+    CORS_ORIGINS = (
+        os.getenv("CORS_ORIGINS", "").split(",") if os.getenv("CORS_ORIGINS") else ["*"]
+    )
 
 
 def get_config():
+    # Check for DEBUG env var first, then APP_ENV
+    if os.getenv("DEBUG", "").lower() == "true":
+        return DevelopmentConfig
+
     env = os.getenv("APP_ENV", "development")
     if env == "production":
         return ProductionConfig

app/main.py

@@ -6,8 +6,6 @@
 from starlette.exceptions import HTTPException as StarletteHTTPException
 from starlette.responses import JSONResponse
 from app.config import get_config
-from app.routers.pathways import router as pathways_router
-from app.routers.umap_router import router 
 from app.routers import gsea
 from app.scripts.prepare_gene_lists import generate_all_library_gene_lists
 
@@ -45,8 +43,6 @@
 
 # Include routers
 app.include_router(gsea.router, prefix="/api", tags=["GSEA"])
-app.include_router(pathways_router)
-app.include_router(router, prefix="/umap")
 
 
 # Mount static files for the React app

app/models/__init__.py

@@ -0,0 +1,3 @@
+from app.models.gsea import Gene, GseaJsonRequest
+
+__all__ = ["Gene", "GseaJsonRequest"]

app/models/gsea.py

@@ -0,0 +1,24 @@
+from pydantic import BaseModel, Field, field_validator
+from typing import List
+
+
+class Gene(BaseModel):
+    """Individual gene with symbol and score."""
+
+    symbol: str = Field(..., description="Gene symbol (e.g., 'BRCA1', 'TP53')")
+    globalScore: float = Field(..., description="Gene score for ranking")
+
+
+class GseaJsonRequest(BaseModel):
+    """Request model for JSON-based GSEA endpoint."""
+
+    genes: List[Gene] = Field(
+        ..., min_length=1, description="List of genes with symbols and scores"
+    )
+
+    @field_validator("genes")
+    @classmethod
+    def validate_genes_not_empty(cls, v):
+        if not v or len(v) == 0:
+            raise ValueError("Genes list cannot be empty")
+        return v

app/routers/__init__.py

@@ -0,0 +1,5 @@
+"""API routers for the Pathways API."""
+
+from app.routers import gsea
+
+__all__ = ["gsea"]

app/routers/gsea.py

@@ -1,53 +1,128 @@
 from fastapi import APIRouter, UploadFile, File, Query, HTTPException
 from typing import Literal
-from app.services.gsea import run_gsea, available_gmt_files
+from app.services.gsea import run_gsea_from_dataframe, available_gmt_files
+from app.models.gsea import GseaJsonRequest
+from app.utils.gsea_utils import validate_gsea_dataframe, handle_gsea_error
 import tempfile
 import pandas as pd
 import os
 import numpy as np
 
 router = APIRouter()
 
+
 @router.get("/gsea/libraries")
 async def list_gmt_files():
     """List available GMT libraries."""
     return list(available_gmt_files().keys())
 
 
-@router.post("/gsea")
-async def gsea_endpoint(
-    tsv_file: UploadFile = File(..., description="TSV file containing at least 2 columns: 'symbol' and 'globalScore'"),
+@router.post("/gsea/analyze/file")
+async def analyze_gsea_from_file(
+    tsv_file: UploadFile = File(
+        ...,
+        description="TSV file containing at least 2 columns: 'symbol' and 'globalScore'",
+    ),
     gmt_name: str = Query(..., description="GMT library name (without .gmt extension)"),
     analysis_direction: Literal["one_sided_positive", "one_sided_negative", "two_sided"] = Query(
         default="one_sided_positive",
         description="Analysis direction: 'one_sided_positive' filters NES > 0, 'one_sided_negative' filters NES < 0, 'two_sided' returns all results"
-    )
+    ),
 ):
+    """
+    Run GSEA analysis from uploaded TSV file.
+
+    Upload a TSV file with gene symbols and scores to perform Gene Set Enrichment Analysis.
+
+    Example:
+        POST /api/gsea/analyze/file?gmt_name=Reactome/ReactomePathways_2025
+        Content-Type: multipart/form-data
+        Body: file=your_data.tsv
+    """
     # Validate file extension
     if not tsv_file.filename.endswith(".tsv"):
         raise HTTPException(status_code=400, detail="File must be .tsv format")
 
-    # Save to temp file
+    # Read and validate file
     with tempfile.NamedTemporaryFile(delete=False, suffix=".tsv") as tmp:
         content = await tsv_file.read()
         tmp.write(content)
         tsv_path = tmp.name
 
-    # Validate TSV structure
     try:
-        df = pd.read_csv(tsv_path, sep="\t", nrows=1)  # read first row
-        if not {"symbol", "globalScore"}.issubset(df.columns) and not {0, 1}.issubset(df.columns):
-            raise ValueError("TSV must contain 'symbol' and 'globalScore' columns (or two unnamed columns).")
-    except Exception as e:
-        os.unlink(tsv_path)
-        raise HTTPException(status_code=400, detail=f"Invalid TSV format: {str(e)}")
+        # Load and validate DataFrame
+        df = pd.read_csv(tsv_path, sep="\t")
+        df = validate_gsea_dataframe(df)
 
-    # Run GSEA
-    try:
-        res_df, missing_stats = run_gsea(input_tsv=tsv_path, gmt_name=gmt_name)
+        # Run GSEA
+        res_df, input_overlap = run_gsea_from_dataframe(df, gmt_name)
+
+    except HTTPException:
+        raise
+    except Exception as e:
+        raise handle_gsea_error(e)
     finally:
         # Clean up temp file
-        os.unlink(tsv_path)
+        if os.path.exists(tsv_path):
+            os.unlink(tsv_path)
+
+    # Filter by NES based on analysis direction
+    if analysis_direction == "one_sided_positive":
+        res_df = res_df[res_df["NES"] > 0].copy()
+    elif analysis_direction == "one_sided_negative":
+        res_df = res_df[res_df["NES"] < 0].copy()
+
+    # Replace NaN/Inf with JSON-safe values
+    res_df = res_df.replace([np.inf, -np.inf], None)
+    res_df = res_df.where(pd.notna(res_df), None)
+
+    return {
+        "results": res_df.to_dict(orient="records"),
+        "input_overlap": input_overlap,
+    }
+
+
+@router.post("/gsea/analyze/json")
+async def analyze_gsea_from_json(
+    request: GseaJsonRequest,
+    gmt_name: str = Query(..., description="GMT library name (without .gmt extension)"),
+    analysis_direction: Literal["one_sided_positive", "one_sided_negative", "two_sided"] = Query(
+        default="one_sided_positive",
+        description="Analysis direction: 'one_sided_positive' filters NES > 0, 'one_sided_negative' filters NES < 0, 'two_sided' returns all results"
+    ),
+):
+    """
+    Run GSEA analysis from JSON payload.
+
+    Send gene data as JSON to perform Gene Set Enrichment Analysis.
+
+    Example:
+        POST /api/gsea/analyze/json?gmt_name=Reactome/ReactomePathways_2025
+        Content-Type: application/json
+        Body: {
+            "genes": [
+                {"symbol": "BRCA1", "globalScore": 0.95},
+                {"symbol": "TP53", "globalScore": 0.87}
+            ]
+        }
+    """
+    try:
+        # Convert request to DataFrame
+        genes_data = [
+            {"symbol": g.symbol, "globalScore": g.globalScore} for g in request.genes
+        ]
+        df = pd.DataFrame(genes_data)
+
+        # Validate DataFrame (should already be valid via Pydantic, but double-check)
+        df = validate_gsea_dataframe(df)
+
+        # Run GSEA directly (no file I/O needed!)
+        res_df, input_overlap = run_gsea_from_dataframe(df, gmt_name)
+
+    except HTTPException:
+        raise
+    except Exception as e:
+        raise handle_gsea_error(e)
 
     # Filter by NES based on analysis direction
     if analysis_direction == "one_sided_positive":
@@ -61,5 +136,5 @@ async def gsea_endpoint(
 
     return {
         "results": res_df.to_dict(orient="records"),
-        "input_overlap": missing_stats,
+        "input_overlap": input_overlap,
     }