alphafold-db
Installation
SKILL.md
AlphaFold Database Skill
When to Use
- You have a UniProt accession (e.g.,
P00520) and need to download its AlphaFold-predicted 3D structure in mmCIF or PDB format. - You want to assess prediction reliability using per-residue pLDDT confidence scores.
- You need PAE (Predicted Aligned Error) data to support domain-level interpretation or inter-domain confidence checks.
- You want to programmatically retrieve AlphaFold DB metadata (e.g., model/structure URLs and related fields) for downstream pipelines.
- You are building an automated workflow that fetches structures + confidence metrics for many proteins by UniProt ID.
Key Features
- Fetch AlphaFold DB predicted structures by UniProt accession.
- Download structure files in mmCIF (default) or PDB.
- Retrieve and save metadata JSON, including confidence-related fields (e.g., pLDDT) and URL information.
- Simple CLI workflow suitable for scripting and batch processing.
Dependencies
- Python
>=3.8 requests >=2.25