alphafold-database

Retrieve AlphaFold protein structures and analyze pLDDT/PAE metrics via API or Google Cloud bulk access.

8|Updated Nov 19, 2025
One-click install
npx skills add https://github.com/sanand0/scientific-research --skill alphafold-database-sanand0
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: alphafold-database
Source: https://github.com/sanand0/scientific-research/tree/main/.claude/skills/alphafold-database
Command: npx skills add https://github.com/sanand0/scientific-research --skill alphafold-database-sanand0

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires biopython, requests, numpy, matplotlib, pandas, scipy, google-cloud-bigquery, gsutil, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill provides access to over 200 million AI-predicted 3D protein structures, enabling researchers to analyze protein architecture and function even when experimental data is unavailable.

Core Features & Use Cases

  • Structure Retrieval: Download protein structures by UniProt ID in various formats (PDB, mmCIF).
  • Confidence Analysis: Evaluate prediction reliability using pLDDT and PAE metrics.
  • Bulk Data Access: Utilize Google Cloud for large-scale proteome downloads.
  • Use Case: A drug discovery team needs to investigate potential binding sites for a novel therapeutic. They use this Skill to retrieve the predicted structure of their target protein, analyze its confidence, and identify potential pockets for drug interaction.

Quick Start

Use the alphafold-database skill to download the structure for UniProt ID P00520.

Frequently Asked Questions about alphafold-database

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

FAQPage Schema
How do I download AI-predicted protein structures using a UniProt accession?

Retrieve AI-predicted protein structures by querying the AlphaFold database with a UniProt accession or AlphaFold ID, allowing you to download coordinate files in PDB or mmCIF formats for structural biology analysis.

How can I check the confidence of a predicted 3D protein structure?

Evaluate prediction reliability for 3D protein structures by analyzing per-residue confidence using pLDDT metrics and inter-residue confidence using PAE metrics provided with the downloaded coordinate files.

Can I retrieve large-scale proteome data from AlphaFold via Google Cloud?

Yes, bulk data access for large-scale proteome downloads is supported via Google Cloud BigQuery and gsutil, enabling programmatic retrieval of over 200 million AI-predicted protein structures.

Does this AlphaFold database skill provide structures for drug discovery workflows?

Yes, it supports drug discovery workflows by providing programmatic access to predicted 3D protein structures, allowing teams to investigate potential binding sites and identify pockets for therapeutic interaction.

What formats are available when downloading predicted protein structures?

Download AI-predicted protein structures in PDB and mmCIF coordinate file formats, which can be integrated directly into bioinformatics and protein engineering pipelines using Python libraries like Biopython.