CLEAN Database: providing enzyme function coverage for over 55 million sequences.

CLEAN Database predicts enzyme functions for over 55 million sequences across 1,098,305 strains, advancing enzyme annotation coverage significantly.

• Why it matters: Accurate enzyme function annotation is essential for understanding biological systems and designing enzymes, but experimental data covers only a small fraction of known proteins, creating a large knowledge gap.
• What they did: The authors developed the CLEAN AI model and created the CLEAN Database, which includes more than 55 million enzyme annotations, with a user-friendly web interface and mutation effect prediction tools.
• The result: CLEAN DB provides a comprehensive, accessible resource that supports enzyme discovery and engineering efforts, facilitating research in synthetic biology, metabolic engineering, and drug development.