Add conda-based Docker support for pager - containerize PAGE algorithm workflows

.dockerignore

@@ -0,0 +1,12 @@
+# Docker ignore file for pager
+.git
+__pycache__
+*.pyc
+*.pyo
+*.pyd
+.Python
+env
+pip-log.txt
+pip-delete-this-directory.txt
+.ipynb_checkpoints
+.DS_Store

Dockerfile

@@ -0,0 +1,83 @@
+# Dockerfile for pager - PAGE algorithm and data curation container
+FROM ubuntu:22.04
+
+# Set environment variables to avoid interactive prompts
+ENV DEBIAN_FRONTEND=noninteractive
+ENV TZ=UTC
+
+# Install system dependencies
+RUN apt-get update && apt-get install -y \
+    perl \
+    wget \
+    curl \
+    git \
+    build-essential \
+    unzip \
+    gzip \
+    && rm -rf /var/lib/apt/lists/*
+
+# Install Miniconda
+RUN wget --no-check-certificate https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh -O miniconda.sh && \
+    bash miniconda.sh -b -p /opt/conda && \
+    rm miniconda.sh
+
+# Add conda to PATH
+ENV PATH="/opt/conda/bin:$PATH"
+
+# Initialize conda and create pager environment as described in README
+RUN conda init bash && \
+    conda config --set ssl_verify false && \
+    conda tos accept --override-channels --channel defaults && \
+    conda create -n pager -y && \
+    echo "conda activate pager" >> ~/.bashrc
+
+# Install Python dependencies in the pager environment
+RUN /bin/bash -c "source /opt/conda/etc/profile.d/conda.sh && \
+    conda activate pager && \
+    conda install -y pandas numpy matplotlib"
+
+# Create working directory
+WORKDIR /opt/pager
+
+# Copy pager code
+COPY . .
+
+# Set up environment variables for iPAGE and TEISER using conda env config vars
+# This follows the README conda setup instructions
+RUN /bin/bash -c "source /opt/conda/etc/profile.d/conda.sh && \
+    conda activate pager && \
+    conda env config vars set PAGEDIR=/opt/PAGE && \
+    conda env config vars set TEISERDIR=/opt/TEISER"
+
+# Create directories for external tools
+RUN mkdir -p /opt/PAGE /opt/TEISER
+
+# Make shell scripts executable
+RUN find . -name "*.sh" -exec chmod +x {} \;
+
+# Create a script to help users set up external dependencies
+RUN echo '#!/bin/bash' > /opt/setup_tools.sh && \
+    echo 'echo "To use pager fully, you need to install iPAGE and TEISER:"' >> /opt/setup_tools.sh && \
+    echo 'echo "1. iPAGE: https://github.com/hanig/PAGE"' >> /opt/setup_tools.sh && \
+    echo 'echo "2. TEISER: https://github.com/hanig/TEISER"' >> /opt/setup_tools.sh && \
+    echo 'echo ""' >> /opt/setup_tools.sh && \
+    echo 'echo "Mount these tools into the container at:"' >> /opt/setup_tools.sh && \
+    echo 'echo "  - iPAGE: /opt/PAGE"' >> /opt/setup_tools.sh && \
+    echo 'echo "  - TEISER: /opt/TEISER"' >> /opt/setup_tools.sh && \
+    echo 'echo ""' >> /opt/setup_tools.sh && \
+    echo 'echo "Example run command:"' >> /opt/setup_tools.sh && \
+    echo 'echo "docker run -v /path/to/PAGE:/opt/PAGE -v /path/to/TEISER:/opt/TEISER -v /path/to/data:/data pager"' >> /opt/setup_tools.sh && \
+    chmod +x /opt/setup_tools.sh
+
+# Create entrypoint script that activates conda environment
+RUN echo '#!/bin/bash' > /opt/entrypoint.sh && \
+    echo 'source /opt/conda/etc/profile.d/conda.sh' >> /opt/entrypoint.sh && \
+    echo 'conda activate pager' >> /opt/entrypoint.sh && \
+    echo 'exec "$@"' >> /opt/entrypoint.sh && \
+    chmod +x /opt/entrypoint.sh
+
+# Set the entrypoint to activate conda environment
+ENTRYPOINT ["/opt/entrypoint.sh"]
+
+# Default command shows setup instructions
+CMD ["/opt/setup_tools.sh"]

README.md

@@ -3,6 +3,57 @@ Container of codes and data to run PAGE algorithm and enable further data curati
 
 ## Installation
 
+**Option 1: Docker (Recommended)**
+
+The easiest way to use pager is with Docker. Build and run the container:
+
+```bash
+# Build the Docker image
+docker build -t pager .
+
+# Run with setup instructions
+docker run pager
+
+# Run with your data mounted (interactive shell)
+docker run -v /path/to/your/data:/data -it pager /bin/bash
+
+# If you have iPAGE and TEISER installed locally
+docker run -v /path/to/PAGE:/opt/PAGE -v /path/to/TEISER:/opt/TEISER -v /path/to/data:/data -it pager /bin/bash
+
+# Test the container functionality
+docker run pager /opt/pager/docker_test.sh
+```
+
+Or use docker-compose for easier management:
+
+```bash
+# Edit docker-compose.yml to mount your local directories
+docker compose build
+docker compose run pager
+
+# Or run specific commands
+docker compose run pager python -c "import pager; help(pager)"
+```
+
+**Docker Examples:**
+
+```bash
+# Run iPAGE analysis (assuming you have the tools mounted)
+docker run -v /local/data:/data -v /local/PAGE:/opt/PAGE pager \
+  bash /opt/pager/iPAGE_loop.sh /data/input.txt
+
+# Run Python pager functions
+docker run -v /local/data:/data pager \
+  python -c "
+import sys; sys.path.append('/opt/pager')
+import pager
+df = pager.read_pvmatrix('/data/pvmatrix.txt')
+print(df.head())
+"
+```
+
+**Option 2: Manual Installation**
+
 **Requirements:**
 
 Follw the instructions to install iPAGE and TEISER from the following links:

docker-compose.yml

@@ -0,0 +1,17 @@
+services:
+  pager:
+    build: .
+    image: pager:latest
+    container_name: pager
+    volumes:
+      # Mount your local data directory
+      - ./data:/data
+      # Mount iPAGE and TEISER tools if available locally
+      # - /path/to/your/PAGE:/opt/PAGE
+      # - /path/to/your/TEISER:/opt/TEISER
+    working_dir: /data
+    environment:
+      - PAGEDIR=/opt/PAGE
+      - TEISERDIR=/opt/TEISER
+    # Override default command to start interactive shell
+    command: /bin/bash

docker_test.sh

@@ -0,0 +1,48 @@
+#!/bin/bash
+
+# Example script to test pager functionality in Docker container
+# This script demonstrates basic pager module functionality
+
+echo "=== Pager Docker Container Test ==="
+echo ""
+
+# Test Python import
+echo "Testing Python environment..."
+python -c "
+import sys
+sys.path.append('/opt/pager')
+import pager
+import pandas as pd
+import os
+
+print('✓ Python available via conda')
+print('✓ pager module imported successfully')
+print('✓ pandas available:', pd.__version__)
+print('✓ Working directory:', os.getcwd())
+"
+
+echo ""
+echo "=== Environment Variables ==="
+echo "PAGEDIR: $PAGEDIR"
+echo "TEISERDIR: $TEISERDIR"
+
+echo ""
+echo "=== Available Scripts ==="
+ls -la /opt/pager/*.sh
+
+echo ""
+echo "=== Test Data ==="
+if [ -f "/opt/pager/test/input.txt" ]; then
+    echo "Test input data found:"
+    head -n 5 /opt/pager/test/input.txt
+    echo "... (showing first 5 lines)"
+else
+    echo "No test data found in /opt/pager/test/"
+fi
+
+echo ""
+echo "=== Docker Container Ready ==="
+echo "To get started:"
+echo "1. Mount your data: docker run -v /path/to/data:/data pager"
+echo "2. Mount iPAGE/TEISER tools for full functionality"
+echo "3. Use 'python -c \"import pager; help(pager)\"' to explore the module"