# Core data processing
pandas>=2.0.0
numpy>=1.24.0

# XML and HTML processing
beautifulsoup4>=4.12.0
lxml>=4.9.0

# Progress bars and parallel processing
tqdm>=4.65.0

# NCBI/PubMed interaction
biopython>=1.81

# Data storage and compression
pyarrow>=14.0.1  # For parquet file support

# File handling and compression
requests>=2.31.0  # For downloading files
#ftplib3>=0.2.1   # For FTP operations

# Optional but recommended for improved performance
multiprocess>=0.70.15  # For better multiprocessing support