requirements.txt

# SOORENA Prediction Pipeline - Python Dependencies
# For pip-only users (production deployment)
#
# NOTE: For development, use the conda environment (environment.yml) which includes
# additional packages for Jupyter notebooks and analysis. This file contains only
# the core dependencies needed to run the prediction pipeline in production.

# Core ML/NLP
torch>=2.0.0
transformers>=4.41.0
tokenizers>=0.15.0
safetensors>=0.4.0

# Data Processing
pandas>=2.2.0
numpy>=1.26.0
scikit-learn>=1.4.0
pyreadr>=0.5.0
openpyxl>=3.1.0  # For reading Excel files (external resources integration)

# Date parsing
python-dateutil>=2.8.0

# Text processing
regex>=2024.4.16
nltk>=3.9.0

# Progress bars
tqdm>=4.66.0

# HTTP requests for UniProt API
requests>=2.31.0

# Optional: For GPU support, install PyTorch with CUDA
# Visit: https://pytorch.org/get-started/locally/
# For CUDA 11.8: pip install torch --index-url https://download.pytorch.org/whl/cu118
# For CUDA 12.1: pip install torch --index-url https://download.pytorch.org/whl/cu121