alphafold-database

Retrieve AlphaFold structure predictions and confidence metrics by UniProt ID.

1|Updated Mar 19, 2026
One-click install
npx skills add https://github.com/JosephWoodall/noosphere --skill alphafold-database-josephwoodall
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: alphafold-database
Source: https://github.com/JosephWoodall/noosphere/tree/main/.agent/skills/alphafold-database
Command: npx skills add https://github.com/JosephWoodall/noosphere --skill alphafold-database-josephwoodall

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

AlphaFold DB is a public repository of AI-predicted 3D protein structures for millions of sequences, and this integration enables researchers to programmatically access structure predictions, confidence metrics, and bulk datasets for downstream analysis without manual browsing.

Core Features & Use Cases

  • Retrieve predictions by UniProt ID and download model coordinates in mmCIF/ PDB formats.
  • Access per-residue confidence (pLDDT) and Predicted Aligned Error (PAE) data to assess reliability.
  • Retrieve bulk datasets via Google Cloud or BigQuery and integrate results into pipelines for drug discovery, structural biology, and protein engineering.
  • Compare AlphaFold predictions with experimental data and build structure-based models for variant analysis.

Quick Start

Query AlphaFold predictions by UniProt ID and download corresponding structure files.

Frequently Asked Questions about alphafold-database

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

FAQPage Schema
How do I download AlphaFold protein structures using a UniProt ID?

You can retrieve AlphaFold protein structures by querying with a UniProt ID to download model coordinates in mmCIF or PDB formats. This allows direct integration into structural biology workflows without manual database browsing.

How do I access AlphaFold pLDDT and PAE confidence metrics for structural analysis?

AlphaFold confidence metrics, including per-residue pLDDT and Predicted Aligned Error (PAE) data, are retrieved alongside structure predictions by UniProt ID. These metrics help assess the reliability of specific structural regions.

Can I retrieve bulk AlphaFold datasets via Google Cloud or BigQuery for automated pipelines?

Yes, bulk AlphaFold datasets can be retrieved via Google Cloud or BigQuery. The integration exposes API, cloud, and BigQuery access patterns to facilitate incorporating structure predictions into automated drug discovery pipelines.

What is the best way to programmatically access AlphaFold predictions for drug discovery?

The best way to programmatically access AlphaFold predictions for drug discovery is by querying via UniProt ID to retrieve structure files and confidence metrics, enabling automated structure-based models for variant analysis.

Does this AlphaFold database integration support comparing AI predictions with experimental data?

Yes, you can compare AlphaFold predictions with experimental data by retrieving the predicted mmCIF or PDB files and associated confidence metrics. This supports building structure-based models for downstream variant analysis.