alphafold-database

Retrieve AlphaFold protein structures by UniProt ID and analyze pLDDT and PAE metrics.

8|Updated Jan 13, 2026
One-click install
npx skills add https://github.com/hxk622/TokenDance --skill alphafold-database-hxk622
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: alphafold-database
Source: https://github.com/hxk622/TokenDance/tree/main/backend/app/skills/builtin/scientific/research-tools/alphafold-database
Command: npx skills add https://github.com/hxk622/TokenDance --skill alphafold-database-hxk622

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 a vast database of AI-predicted 3D protein structures, enabling researchers to analyze protein function and design new therapeutics without relying solely on experimental data.

Core Features & Use Cases

  • Retrieve Structures: Get protein structures by UniProt ID.
  • Download Files: Obtain PDB/mmCIF coordinate files and confidence metrics.
  • Analyze Confidence: Evaluate prediction reliability using pLDDT and PAE scores.
  • Bulk Access: Download entire proteomes via Google Cloud.
  • Use Case: A drug discovery scientist needs to investigate the structure of a specific human protein to identify potential binding sites for a new drug candidate. They use this Skill to download the predicted structure and analyze its confidence metrics.

Quick Start

Use the alphafold-database skill to download the PDB file 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 AlphaFold predicted protein structures using a UniProt ID?

You can download AlphaFold predicted protein structures by querying the database with a UniProt ID to retrieve PDB or mmCIF coordinate files. This provides direct programmatic access for structural biology and drug discovery workflows.

What do pLDDT and PAE scores tell me about AI-predicted protein structures?

pLDDT and PAE scores are confidence metrics for AI-predicted protein structures. pLDDT evaluates per-residue reliability, while PAE measures inter-residue confidence, helping researchers assess prediction quality for drug discovery applications.

Can I download entire proteome datasets from the AlphaFold database via Google Cloud?

Yes, bulk proteome datasets from the AlphaFold database can be downloaded via Google Cloud Storage. This allows large-scale structural biology analysis without querying individual UniProt IDs.

How do I analyze per-residue confidence metrics for a predicted 3D protein structure?

You analyze per-residue confidence metrics for a predicted 3D protein structure by extracting pLDDT scores from the downloaded coordinate files. These scores indicate local structural reliability for each amino acid position.

Does this AlphaFold database access tool require Biopython and numpy for structural analysis?

Yes, accessing and analyzing AlphaFold database structures requires Biopython and numpy, alongside pandas and scipy, to parse coordinate files and evaluate confidence metrics within Python workflows.