environment.yml

name: gene-analysis
channels:
  - conda-forge
  - bioconda
  - defaults

dependencies:
  # Python version
  - python>=3.8

  # Core data analysis
  - pandas>=1.5.0
  - numpy>=1.21.0

  # Visualization
  - matplotlib>=3.5.0
  - seaborn>=0.11.0
  - plotly>=5.0.0

  # Statistical analysis
  - scipy>=1.7.0
  - scikit-learn>=1.0.0

  # Network analysis
  - networkx>=2.6.0

  # R and R packages (if installing R through conda)
  - r-base>=4.0.0
  - r-dplyr
  - r-readr
  - r-stringr
  - r-httr
  - r-jsonlite
  - r-xml2
  - r-rvest
  - r-curl

  # Bioconductor packages (available through conda-forge/bioconda)
  - bioconductor-reactomepa
  - bioconductor-org.hs.eg.db
  - bioconductor-annotationdbi
  - bioconductor-go.db
  - bioconductor-keggrest

  # Additional Python packages via pip
  - pip
  - pip:
    - matplotlib-venn>=0.11.6
    - venn>=0.1.3
    - adjustText>=0.7.3

# Optional dependencies for advanced users
# Uncomment the following lines if needed:
#   - jupyter
#   - ipywidgets
#   - statsmodels
#   - pingouin

# Development tools (optional)
#   - pytest
#   - black
#   - flake8

# Usage Instructions:
# 1. Create environment: conda env create -f environment.yml
# 2. Activate environment: conda activate gene-analysis
# 3. Install additional R packages: Rscript requirements.R
# 4. Run pipeline: Rscript download_genes.R <phenotype>
# 5. Run analysis: python download_genes_analysis.py <phenotype>