alphafold-database

Fetch AlphaFold predictions and confidence metrics for a UniProt ID.

48|6|Updated Mar 9, 2026
One-click install
npx skills add https://github.com/qinyan-ai/qinyan-academic-skills --skill alphafold-database-qinyan-ai
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: alphafold-database
Source: https://github.com/qinyan-ai/qinyan-academic-skills/tree/main/skills/08-%E8%9B%8B%E7%99%BD%E8%B4%A8%E5%B7%A5%E7%A8%8B%E4%B8%8E%E7%BB%93%E6%9E%84%E7%94%9F%E7%89%A9%E5%AD%A6/alphafold-database
Command: npx skills add https://github.com/qinyan-ai/qinyan-academic-skills --skill alphafold-database-qinyan-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

AlphaFold Database provides ready access to AI-predicted protein structures, enabling researchers to retrieve, download, and analyze structural data and confidence metrics for faster structural biology workflows.

Core Features & Use Cases

  • Retrieve predictions by UniProt ID and access per-residue confidence (pLDDT) and PAE metrics for quality assessment.
  • Download model coordinates in mmCIF/BCIF/PDB formats, along with associated metadata, for downstream analysis and docking.
  • Integrate AlphaFold data into computational pipelines and bulk analyses via Google Cloud and BigQuery.

Quick Start

Analyze a protein by UniProt ID using AlphaFold: fetch the AF entry, inspect pLDDT, and download the model file for visualization and further study.

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 using a UniProt ID?

To retrieve AlphaFold protein structures, provide a UniProt ID to fetch the corresponding AI-predicted model coordinates and associated metadata for downstream structural biology analysis.

What file formats are available when downloading AlphaFold predictions?

Available file formats for downloading AlphaFold predictions include mmCIF, BCIF, PDB, and JSON, providing flexibility for various molecular visualization and computational docking workflows.

How do I assess the reliability of AlphaFold predicted protein structures?

Assess AlphaFold structure reliability by analyzing per-residue pLDDT (predicted local distance difference test) and PAE (predicted aligned error) confidence metrics provided with the fetched predictions.

Can I access AlphaFold database entries in bulk for computational pipelines?

Yes, you can access AlphaFold database entries in bulk for computational pipelines by integrating versioned data via Google Cloud and BigQuery into your batch analysis workflows.

Does this tool provide versioned data access for protein structure predictions?

Yes, the tool provides versioned data access for protein structure predictions, ensuring consistent retrieval of specific AlphaFold model versions and metadata for reproducible research.

What are the limitations of using AlphaFold predictions for drug discovery?

Limitations include relying on AI-predicted static structures rather than experimentally solved dynamics, requiring careful pLDDT and PAE quality checks before integration into drug discovery workflows.