How do I retrieve a protein structure using this skill?

You can retrieve structures by providing a UniProt ID. The skill uses Biopython or direct REST API calls to fetch the relevant mmCIF or PDB coordinate files from the AlphaFold Database.

What file formats does the skill support?

It supports downloading model coordinates in mmCIF/PDBx and traditional PDB formats, along with JSON files for per-residue confidence scores and alignment errors.

What confidence metrics are available for the predictions?

The skill supports pLDDT (per-residue confidence) and PAE (Predicted Aligned Error) matrices to help you evaluate the reliability and relative domain positioning of the AI-predicted model.

Can I download data for entire species or proteomes?

Yes, the skill provides patterns for bulk downloading complete proteomes using Google Cloud Storage (gsutil) based on specific taxonomy IDs.

AlphaFold Protein Database

Name: AlphaFold Protein Database
Author: K-Dense-AI

byK-Dense-AI

•

2,188

Ciencia de Datos y ML

Accesses and analyzes over 200 million AI-predicted protein structures from the AlphaFold DB for structural biology and drug discovery.

Acerca de

This skill enables Claude to interact with the AlphaFold Database, a massive public repository of high-accuracy protein structure predictions maintained by DeepMind and EMBL-EBI. It provides standardized methods for retrieving structures by UniProt ID, downloading atomic coordinates in PDB or mmCIF formats, and interpreting critical confidence metrics like pLDDT and Predicted Aligned Error (PAE). Designed for researchers and bioinformaticians, it streamlines the integration of AI-predicted structures into computational pipelines, ranging from individual protein analysis to bulk proteome processing via Google Cloud Platform.

Características Principales

Support for PDB and mmCIF coordinate file formats
2,188 GitHub stars
Analysis of pLDDT and PAE confidence metrics
Bulk data access via Google Cloud Storage and BigQuery
Retrieval of 200M+ protein structures via UniProt IDs
BioPython integration for structural parsing and contact analysis

Casos de Uso

Performing large-scale proteome analysis for evolutionary studies
Conducting structure-based drug discovery and docking studies
Predicting 3D structures for proteins lacking experimental data

Acerca de

Características Principales

Support for PDB and mmCIF coordinate file formats
2,188 GitHub stars
Analysis of pLDDT and PAE confidence metrics
Bulk data access via Google Cloud Storage and BigQuery
Retrieval of 200M+ protein structures via UniProt IDs
BioPython integration for structural parsing and contact analysis

Casos de Uso

Performing large-scale proteome analysis for evolutionary studies
Conducting structure-based drug discovery and docking studies
Predicting 3D structures for proteins lacking experimental data