Dockerfile

# MutVar v2 — HuggingFace Spaces Dockerfile
# Runs nginx (port 7860) + uvicorn (localhost:8000) via supervisord.
# Data is read at query time from HuggingFace Datasets via DuckDB httpfs.
# No bulk data in the image → fast build, small image.

FROM python:3.12-slim

# Install nginx + supervisor
RUN apt-get update && apt-get install -y --no-install-recommends \
        nginx \
        supervisor \
    && rm -rf /var/lib/apt/lists/*

WORKDIR /app

# Python dependencies
COPY backend/requirements.txt ./backend/requirements.txt
RUN pip install --no-cache-dir -r backend/requirements.txt

# Pre-install DuckDB httpfs extension (avoids runtime download)
RUN python -c "import duckdb; con = duckdb.connect(); con.execute('INSTALL httpfs'); con.close()"

# Application code (no data/ directory needed)
COPY backend/ ./backend/

# Frontend assets
COPY landing.html      /usr/share/nginx/html/landing.html
COPY index.html        /usr/share/nginx/html/index.html
COPY landscape.html    /usr/share/nginx/html/landscape.html
COPY vcf-upload.html   /usr/share/nginx/html/vcf-upload.html
COPY kinaseatlas.html  /usr/share/nginx/html/kinaseatlas.html
COPY structures/    /usr/share/nginx/html/structures/

# nginx + supervisord config
COPY nginx.conf       /etc/nginx/conf.d/default.conf
COPY supervisord.conf /etc/supervisor/conf.d/mutvar.conf
RUN rm -f /etc/nginx/sites-enabled/default \
 && chmod -R 644 /usr/share/nginx/html/structures/ \
 && chmod 755 /usr/share/nginx/html/structures/

# ── Data source ────────────────────────────────────────────────
# Set HF_DATASET to your HuggingFace dataset repo ID.
# The backend reads Parquet files from there at query time.
# For private datasets, also set HF_TOKEN.
ENV HF_DATASET=edohollou/mutvar-variants

EXPOSE 7860

CMD ["/usr/bin/supervisord", "-c", "/etc/supervisor/conf.d/mutvar.conf"]