Dockerfile

# Use an official Python runtime as a parent image
# Using Python 3.11.14 as specifically requested
FROM python:3.11.14-slim

# Set environment variables
# Prevents Python from writing pyc files to disc
ENV PYTHONDONTWRITEBYTECODE=1
# Prevents Python from buffering stdout and stderr
ENV PYTHONUNBUFFERED=1
# Set R_HOME for rpy2 compatibility
ENV R_HOME=/usr/lib/R

# Install system dependencies
# R is required for the mclust-based domain identification
RUN apt-get update && apt-get install -y --no-install-recommends \
    build-essential \
    r-base \
    r-base-dev \
    libxml2-dev \
    libssl-dev \
    libcurl4-openssl-dev \
    git \
    && rm -rf /var/lib/apt/lists/*

# Install R package 'mclust'
# This is used by the rpy2 interface in spmetatme.utils.utils
RUN R -e "install.packages('mclust', repos='http://cran.rstudio.com/')"

# Set the working directory in the container
WORKDIR /app

# Copy the dependency files first to leverage Docker cache
COPY requirements.txt .
COPY pyproject.toml .

# Install PyTorch and PyTorch Geometric with specified versions
# These versions match the installation guide in README.md for CUDA 12.6
# We install these FIRST to ensure they are the ones used by subsequent libraries
RUN pip install --no-cache-dir --upgrade pip && \
    pip install --no-cache-dir torch==2.7.1 torchvision==0.22.1 torchaudio==2.7.1 --index-url https://download.pytorch.org/whl/cu126 && \
    pip install --no-cache-dir pyg_lib torch_scatter torch_sparse torch_cluster torch_spline_conv -f https://data.pyg.org/whl/torch-2.7.0+cu126.html && \
    pip install --no-cache-dir torch_geometric

# Install other Python dependencies from requirements.txt
RUN pip install --no-cache-dir -r requirements.txt

# Copy the entire project to the container
COPY . .

# Install the package in standard mode to ensure it's copied to site-packages
RUN pip install --no-cache-dir .

# (Optional) Pre-download the metabolic models or other resources if possible
# RUN python -c "from spmetatme.data.Download import get_model_path; get_model_path('breast_cancer')"

# Default command to run the CLI
ENTRYPOINT ["spmetatme"]

# Default argument for the entrypoint
CMD ["--help"]