alphafold-database

Retrieve AlphaFold protein structures by UniProt ID and download PDB/mmCIF files.

16|7|Updated Nov 20, 2025
One-click install
npx skills add https://github.com/jackspace/ClaudeSkillz --skill alphafold-database-jackspace
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: alphafold-database
Source: https://github.com/jackspace/ClaudeSkillz/tree/main/skills/scientific-db-alphafold-database
Command: npx skills add https://github.com/jackspace/ClaudeSkillz --skill alphafold-database-jackspace

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

AlphaFold-DB provides AI-predicted protein structures for millions of proteins. This Skill enables programmatic access to the database, retrieval by UniProt ID, downloading PDB/mmCIF files, and analyzing confidence metrics (pLDDT and PAE) to inform drug discovery and structural biology workflows.

Core Features & Use Cases

  • Retrieve predictions for a UniProt accession and download coordinate files (model_v4.cif, etc.)
  • Access per-residue confidence (pLDDT) and relative-domain confidence (PAE) to identify reliable regions
  • Leverage bulk AlphaFold data via Google Cloud/BigQuery for large-scale analyses

Quick Start

Run a quick fetch for UniProt P00520 and download its CIF/model file to the ./structures directory.

Frequently Asked Questions about alphafold-database

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I retrieve AlphaFold protein structures by UniProt ID?

Retrieve AlphaFold structures by querying the database with a UniProt accession ID, which returns AI-predicted protein coordinates in PDB or mmCIF format. Download model files directly to your local system for structural analysis and visualization.

What are pLDDT and PAE confidence metrics, and why do they matter?

pLDDT measures per-residue confidence in predicted structure, while PAE quantifies relative domain confidence. Both metrics identify reliable regions in AlphaFold predictions, helping you assess which parts of a protein model are trustworthy for drug discovery and structural studies.

Can I access AlphaFold data in bulk for large-scale proteome analysis?

Yes, bulk AlphaFold data is accessible through Google Cloud Platform and BigQuery, enabling large-scale programmatic analysis of multiple proteins or entire proteomes without downloading individual structure files manually.

How do I integrate AlphaFold structures into my Python workflow?

Access AlphaFold-DB via Biopython interfaces or REST API for programmatic retrieval of structures and confidence data. Both methods support automated pipelines for downloading PDB/mmCIF files and extracting metrics into your analysis code.

What file formats does AlphaFold-DB provide for protein structures?

AlphaFold-DB provides mmCIF and PDB coordinate files, including model versions like model_v4.cif. These standard structural biology formats are compatible with most visualization, analysis, and molecular modeling software.

Do I need to know UniProt accessions, or can I search by protein name?

The Skill retrieves structures by UniProt ID or protein name, so you can query using either identifier type. This flexibility accommodates workflows where you have common protein names but need to map them to structure predictions programmatically.