PDB Database Access

Note: This skill uses the RCSB PDB web API directly. No Modal deployment needed - all operations run locally via HTTP requests.

Fetching Structures

By PDB ID

# Download PDB file
curl -o 1alu.pdb "https://files.rcsb.org/download/1ALU.pdb"

# Download mmCIF
curl -o 1alu.cif "https://files.rcsb.org/download/1ALU.cif"

Using Python

from Bio.PDB import PDBList

pdbl = PDBList()
pdbl.retrieve_pdb_file("1ABC", pdir="structures/", file_format="pdb")

Using RCSB API

import requests

def fetch_pdb(pdb_id: str, format: str = "pdb") -> str:
    """Fetch structure from RCSB PDB."""
    url = f"https://files.rcsb.org/download/{pdb_id}.{format}"
    response = requests.get(url)
    response.raise_for_status()
    return response.text

def fetch_fasta(pdb_id: str) -> str:
    """Fetch sequence in FASTA format."""
    url = f"https://www.rcsb.org/fasta/entry/{pdb_id}"
    return requests.get(url).text

# Example usage
pdb_content = fetch_pdb("1ALU")
with open("1ALU.pdb", "w") as f:
    f.write(pdb_content)

Structure Preparation

Selecting Chains

from Bio.PDB import PDBParser, PDBIO, Select

class ChainSelect(Select):
    def __init__(self, chain_id):
        self.chain_id = chain_id

    def accept_chain(self, chain):
        return chain.id == self.chain_id

# Extract chain A
parser = PDBParser()
structure = parser.get_structure("protein", "1abc.pdb")
io = PDBIO()
io.set_structure(structure)
io.save("chain_A.pdb", ChainSelect("A"))

Trimming to Binding Region

def trim_around_residues(pdb_file, center_residues, buffer=10.0):
    """Trim structure to region around specified residues."""
    parser = PDBParser()
    structure = parser.get_structure("protein", pdb_file)

    # Get center coordinates
    center_coords = []
    for res in structure.get_residues():
        if res.id[1] in center_residues:
            center_coords.extend([a.coord for a in res.get_atoms()])

    center = np.mean(center_coords, axis=0)

    # Keep residues within buffer
    class RegionSelect(Select):
        def accept_residue(self, res):
            for atom in res.get_atoms():
                if np.linalg.norm(atom.coord - center) < buffer:
                    return True
            return False

    io = PDBIO()
    io.set_structure(structure)
    io.save("trimmed.pdb", RegionSelect())