What file formats can I download?

You can download structural coordinates in PDB, mmCIF, and BinaryCIF formats, as well as biological assemblies.

Can I search for structures using a protein sequence?

Yes, the skill supports sequence similarity searches using E-value and identity cutoffs to find matching PDB entries.

Does this skill support AlphaFold models?

Yes, entries starting with 'AF_' (AlphaFold) or 'MA_' (ModelArchive) can be accessed alongside experimentally determined structures.

Can I perform batch operations with this skill?

Absolutely. The skill is designed to iterate through multiple PDB IDs to fetch metadata or download files for large-scale computational studies.

Protein Data Bank (PDB) Integration

Name: Protein Data Bank (PDB) Integration
Author: lifangda

bylifangda

•

データサイエンスとML

Accesses and interacts with the RCSB Protein Data Bank to search, retrieve, and analyze 3D structures of biological macromolecules.

概要

The Protein Data Bank (PDB) Integration skill provides a programmatic interface for Claude to interact with the world's primary repository for 3D biological structural data. It enables researchers to perform complex searches across over 200,000 structures using text, sequence similarity, or geometric attributes. By streamlining the download of coordinate files in PDB and mmCIF formats and providing access to detailed metadata via GraphQL, this skill significantly accelerates workflows in drug discovery, protein engineering, and structural biology research.

主な機能

16 GitHub stars
Sequence & Structure Similarity: Find entries matching specific protein sequences or 3D geometries.
Advanced Search: Query by text, organism, resolution, or experimental method.
Batch Processing: Efficiently fetch data for multiple PDB entries in a single workflow.
Coordinate Downloads: Retrieve structures in PDB, mmCIF, and BinaryCIF formats.
Data Retrieval: Access entry-level metadata and polymer information using Schema or GraphQL.

ユースケース

Protein Engineering: Finding homologous structures for homology modeling and stability analysis.
Structural Bioinformatics: Automating the collection of high-resolution structures for machine learning datasets.
Drug Discovery: Identifying drug targets and analyzing ligand-binding sites in protein complexes.

概要

主な機能

16 GitHub stars
Sequence & Structure Similarity: Find entries matching specific protein sequences or 3D geometries.
Advanced Search: Query by text, organism, resolution, or experimental method.
Batch Processing: Efficiently fetch data for multiple PDB entries in a single workflow.
Coordinate Downloads: Retrieve structures in PDB, mmCIF, and BinaryCIF formats.
Data Retrieval: Access entry-level metadata and polymer information using Schema or GraphQL.

ユースケース

Protein Engineering: Finding homologous structures for homology modeling and stability analysis.
Structural Bioinformatics: Automating the collection of high-resolution structures for machine learning datasets.
Drug Discovery: Identifying drug targets and analyzing ligand-binding sites in protein complexes.