ABCFold

ABCFold facilitates the use of AlphaFold 3, Boltz-1, and Chai-1 with standardized input to predict atomic structures, enabling easy comparison of results from different methods.

Key Features:

• Standardized Input: ABCFold provides a unified input format for AlphaFold 3, Boltz-1, and Chai-1.
• Automated Installation: Boltz-1 and Chai-1 are installed on runtime if required.
• MSA Generation: MSAs can be generated internally using either the JackHMMER MSA search within AlphaFold 3 or the MMseqs2 API.
• Custom MSA Support: Users can provide their own custom MSAs, allowing AlphaFold 3 to run without downloading the large databases needed for JackHMMer.
• Template Options: Straightforward options to use templates, including custom templates.
• Unified Results Presentation: Results from all packages are treated in a unified fashion for easy comparison.
• Visualization: Visualization options include information on steric clashes.

Scientific Applications:

• Protein Structure Prediction: ABCFold predicts atomic structures of proteins and complexes using AlphaFold 3, Boltz-1, and Chai-1.
• Method Comparison: ABCFold enables comparison of structure prediction results from different deep learning-based methods.

Methodology:

ABCFold is coded in Python and JavaScript.