bio-pdb-structure-io

1

FreedomIntelligence/OpenClaw-Medical-SkillsBiology Medicine and BioinformaticsAudit pendingSnapshot b4b02e37bcb6

Summary

This source did not publish a separate summary. Review SKILL.md before using the skill.

SKILL.md

Version Compatibility

Reference examples tested with: BioPython 1.83+, scanpy 1.10+

Before using code patterns, verify installed versions match. If versions differ:

Python: pip show <package> then help(module.function) to check signatures

If code throws ImportError, AttributeError, or TypeError, introspect the installed package and adapt the example to match the actual API rather than retrying.

Structure I/O

"Read a PDB file" → Parse protein structure files (PDB, mmCIF, MMTF), download from RCSB PDB, and write structures to various formats.

Python: Bio.PDB.PDBParser().get_structure('id', 'file.pdb'), Bio.PDB.MMCIFParser()

Parse, download, and write protein structure files in PDB, mmCIF, and MMTF formats.

Required Imports

from Bio.PDB import PDBParser, MMCIFParser, PDBIO, MMCIFIO, PDBList
from Bio.PDB.MMCIF2Dict import MMCIF2Dict

Supported Formats

Format	Parser	Writer	Description
PDB	`PDBParser`	`PDBIO`	Legacy format, limited to 99999 atoms
mmCIF	`MMCIFParser`	`MMCIFIO`	Modern standard, full metadata
MMTF	`MMTFParser`	-	Compact binary (read-only in Biopython)
BinaryCIF	`BinaryCIFParser`	-	Compact binary, RCSB recommended

Parsing PDB Files

from Bio.PDB import PDBParser

parser = PDBParser(QUIET=True)
structure = parser.get_structure('1abc', '1abc.pdb')

print(f'Structure ID: {structure.id}')
print(f'Number of models: {len(list(structure.get_models()))}')
print(f'Number of chains: {len(list(structure.get_chains()))}')
print(f'Number of residues: {len(list(structure.get_residues()))}')
print(f'Number of atoms: {len(list(structure.get_atoms()))}')

from Bio.PDB import MMCIFParser

parser = MMCIFParser(QUIET=True)
structure = parser.get_structure('1abc', '1abc.cif')

# mmCIF is the modern standard - use for new workflows
print(f'Structure: {structure.id}')

from Bio.PDB.MMTFParser import MMTFParser

parser = MMTFParser()
structure = parser.get_structure('1abc.mmtf')

from Bio.PDB import BinaryCIFParser

parser = BinaryCIFParser()
structure = parser.get_structure('1abc', '1abc.bcif')

from Bio.PDB import PDBList

pdbl = PDBList()

# Download single structure (mmCIF by default)
file_path = pdbl.retrieve_pdb_file('1ABC', pdir='.', file_format='mmCif')
print(f'Downloaded: {file_path}')

# Download as PDB format
file_path = pdbl.retrieve_pdb_file('1ABC', pdir='.', file_format='pdb')

# Download biological assembly
file_path = pdbl.retrieve_pdb_file('1ABC', pdir='.', file_format='mmCif', assembly_num=1)

# Get list of all PDB entries
all_entries = pdbl.get_all_entries()
print(f'Total PDB entries: {len(all_entries)}')

# Get obsolete entries
obsolete = pdbl.get_all_obsolete()

from Bio.PDB import PDBList

pdbl = PDBList()
pdb_ids = ['1ABC', '2XYZ', '3DEF']

for pdb_id in pdb_ids:
    file_path = pdbl.retrieve_pdb_file(pdb_id, pdir='structures/', file_format='mmCif')
    print(f'Downloaded: {pdb_id}')

from Bio.PDB import PDBParser, PDBIO

parser = PDBParser(QUIET=True)
structure = parser.get_structure('1abc', '1abc.pdb')

io = PDBIO()
io.set_structure(structure)
io.save('output.pdb')

from Bio.PDB import MMCIFParser, MMCIFIO

parser = MMCIFParser(QUIET=True)
structure = parser.get_structure('1abc', '1abc.cif')

io = MMCIFIO()
io.set_structure(structure)
io.save('output.cif')

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

parser = PDBParser(QUIET=True)
structure = parser.get_structure('1abc', '1abc.pdb')

io = PDBIO()
io.set_structure(structure)
io.save('chain_A.pdb', ChainSelect('A'))

from Bio.PDB import Select

class CustomSelect(Select):
    def accept_model(self, model):
        return model.id == 0  # Only first model

    def accept_chain(self, chain):
        return chain.id in ['A', 'B']  # Only chains A and B

    def accept_residue(self, residue):
        return residue.id[0] == ' '  # Exclude hetero residues

    def accept_atom(self, atom):
        return atom.element != 'H'  # Exclude hydrogens

from Bio.PDB import PDBParser

parser = PDBParser(QUIET=True)
structure = parser.get_structure('1abc', '1abc.pdb')

header = structure.header
print(f"Name: {header.get('name', 'Unknown')}")
print(f"Resolution: {header.get('resolution', 'N/A')}")
print(f"Structure method: {header.get('structure_method', 'Unknown')}")
print(f"Deposition date: {header.get('deposition_date', 'Unknown')}")

from Bio.PDB.MMCIF2Dict import MMCIF2Dict

mmcif_dict = MMCIF2Dict('1abc.cif')

# Access any mmCIF field
print(f"Entry ID: {mmcif_dict['_entry.id']}")
print(f"Resolution: {mmcif_dict.get('_refine.ls_d_res_high', ['N/A'])[0]}")
print(f"Method: {mmcif_dict.get('_exptl.method', ['Unknown'])[0]}")

# List all available fields
print(f"Available fields: {len(mmcif_dict.keys())}")

from Bio.PDB import PDBParser

parser = PDBParser(QUIET=True)
structure = parser.get_structure('1abc', '1abc.pdb')

print(f'Models: {[m.id for m in structure]}')
for model in structure:
    print(f'  Model {model.id}:')
    for chain in model:
        residues = list(chain.get_residues())
        atoms = list(chain.get_atoms())
        print(f'    Chain {chain.id}: {len(residues)} residues, {len(atoms)} atoms')

from Bio.PDB import PDBParser, MMCIFParser, PDBIO, MMCIFIO

# PDB to mmCIF
parser = PDBParser(QUIET=True)
structure = parser.get_structure('prot', 'protein.pdb')
io = MMCIFIO()
io.set_structure(structure)
io.save('protein.cif')

# mmCIF to PDB
parser = MMCIFParser(QUIET=True)
structure = parser.get_structure('prot', 'protein.cif')
io = PDBIO()
io.set_structure(structure)
io.save('protein.pdb')

from Bio.PDB import PDBParser, PDBIO

parser = PDBParser(QUIET=True)
structure = parser.get_structure('1abc', '1abc.pdb')

# PQR format includes charge and radius instead of occupancy and B-factor
io = PDBIO(is_pqr=True)
io.set_structure(structure)
io.save('output.pqr')

from Bio.PDB import PDBParser
import warnings

# Suppress warnings
parser = PDBParser(QUIET=True)

# Or capture warnings
parser = PDBParser(QUIET=False)
with warnings.catch_warnings(record=True) as w:
    warnings.simplefilter('always')
    structure = parser.get_structure('1abc', '1abc.pdb')
    if w:
        print(f'Warnings: {len(w)}')
        for warning in w:
            print(f'  {warning.message}')