Navigate protein structure hierarchy using Biopython Bio.PDB SMCRA model. Use when accessing models, chains, residues, and atoms, iterating over structure levels, or extracting sequences from PDB files.
Standardmäßig ist der Prompt ausgewählt, der zuerst die Quelle prüft. Sie können zu einem direkten Befehl wechseln oder eine lokale Kopie herunterladen.
Quelldateien prüfen
Lesen Sie SKILL.md und alle von SkillsMP angezeigten Begleitdateien, bevor Sie sich für eine Installation entscheiden.
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Ein direkter Befehl überspringt den Prüf-Prompt. Prüfen Sie die Quelle, bevor Sie ihn ausführen.
Navigate protein structure hierarchy using Biopython Bio.PDB SMCRA model. Use when accessing models, chains, residues, and atoms, iterating over structure levels, or extracting sequences from PDB files.
tool_type
python
primary_tool
Bio.PDB
Structure Navigation
Navigate the Structure-Model-Chain-Residue-Atom (SMCRA) hierarchy to access and iterate over structure components.
Required Imports
from Bio.PDB import PDBParser, PPBuilder, Selection
from Bio.Data.PDBData import protein_letters_3to1
SMCRA Hierarchy
Structure
|
+-- Model (0, 1, ...) # NMR ensembles, crystal asymmetric unit
|
+-- Chain (A, B, ...) # Polypeptide chains, ligands
|
+-- Residue # Amino acids, nucleotides, hetero groups
|
+-- Atom # Individual atoms
Accessing Hierarchy Levels
from Bio.PDB import PDBParser
parser = PDBParser(QUIET=True)
structure = parser.get_structure('protein', 'protein.pdb')
model = structure[]
chain = model[]
residue = chain[]
residue = chain[(, , )]
atom = residue[]
# Access by index/ID
0
# First model
'A'
# Chain A
100
# Residue 100 (simple numbering)
' '
100
' '
# Full residue ID (hetfield, resseq, icode)
'CA'
# C-alpha atom
Iterating Over Structure
# Iterate all levelsfor model in structure:
for chain in model:
for residue in chain:
for atom in residue:
print(f'{chain.id}:{residue.id[1]}:{atom.name}')
# Shortcut iterators (all levels below current)for chain in structure.get_chains():
print(f'Chain: {chain.id}')
for residue in structure.get_residues():
print(f'Residue: {residue.resname}')
for atom in structure.get_atoms():
print(f'Atom: {atom.name} at {atom.coord}')
Residue Identification
# Residue ID is a tuple: (hetfield, resseq, icode)for residue in chain:
hetfield, resseq, icode = residue.idprint(f'Residue {resseq}{icode}: {residue.resname}')
# hetfield values:# ' ' - standard amino acid# 'W' - water# 'H_xxx' - hetero residue (ligand, modified residue)# Filter standard residues only
standard_residues = [r for r in chain if r.id[0] == ' ']
# Filter water
waters = [r for r in chain if r.id[0] == 'W']
# Filter hetero atoms (ligands)
hetero = [r for r in chain if r.id[0].startswith('H_')]
Atom Properties
for atom in residue:
print(f'Name: {atom.name}')
print(f'Element: {atom.element}')
print(f'Coordinates: {atom.coord}')
print(f'B-factor: {atom.bfactor}')
print(f'Occupancy: {atom.occupancy}')
print(f'Full ID: {atom.full_id}')
print(f'Serial number: {atom.serial_number}')
Getting Full Identifiers
# Full hierarchical ID from any entity
atom = structure[0]['A'][100]['CA']
print(atom.get_full_id())
# ('protein', 0, 'A', (' ', 100, ' '), ('CA', ' '))# Components: (structure_id, model_id, chain_id, residue_id, atom_id)
Checking for Children
# Check if entity has childif chain.has_id(100):
residue = chain[100]
# Check if residue has atomif residue.has_id('CA'):
ca = residue['CA']
# Get list of all children
chains = structure[0].get_list()
residues = chain.get_list()
atoms = residue.get_list()
Getting Parent Entity
# Navigate up hierarchy
atom = structure[0]['A'][100]['CA']
residue = atom.get_parent()
chain = residue.get_parent()
model = chain.get_parent()
structure = model.get_parent()
Extracting Polypeptide Sequences
from Bio.PDB import PDBParser, PPBuilder
parser = PDBParser(QUIET=True)
structure = parser.get_structure('protein', 'protein.pdb')
ppb = PPBuilder()
for pp in ppb.build_peptides(structure):
seq = pp.get_sequence()
print(f'Polypeptide: {seq}')
print(f'Length: {len(seq)}')
# Get all sequences as list
sequences = [pp.get_sequence() for pp in ppb.build_peptides(structure)]
Using CaPPBuilder for Broken Chains
from Bio.PDB import CaPPBuilder
# Use when backbone is incomplete# Connects residues if CA atoms are within 4.3 Angstroms
ppb = CaPPBuilder()
for pp in ppb.build_peptides(structure):
print(f'Fragment: {pp.get_sequence()}')
Converting Residue Names
from Bio.Data.PDBData import protein_letters_3to1
# Three-letter to one-letter conversion
three_letter = 'ALA'
one_letter = protein_letters_3to1.get(three_letter, 'X')
print(f'{three_letter} -> {one_letter}') # ALA -> A# Build sequence manually
sequence = ''for residue in chain:
if residue.id[0] == ' ': # Standard residue
code = protein_letters_3to1.get(residue.resname, 'X')
sequence += code
print(f'Sequence: {sequence}')
Using Selection.unfold_entities
from Bio.PDB import Selection
# Extract entities at specific level# Codes: S=structure, M=model, C=chain, R=residue, A=atom# Get all residues from structure
residues = Selection.unfold_entities(structure, 'R')
print(f'Total residues: {len(residues)}')
# Get all atoms from a chain
atoms = Selection.unfold_entities(chain, 'A')
print(f'Atoms in chain: {len(atoms)}')
# Get all chains from model
chains = Selection.unfold_entities(model, 'C')
Handling Disordered Atoms
# Check for disorderif atom.is_disordered():
print(f'Atom {atom.name} has multiple conformations')
print(f'Alt locations: {atom.disordered_get_id_list()}')
# Select specific conformation
atom.disordered_select('A')
print(f'Coord for alt A: {atom.coord}')
# Get all conformationsfor altloc in atom.disordered_get_id_list():
atom.disordered_select(altloc)
print(f' {altloc}: {atom.coord}')
# Get unpacked list (all conformations)
all_atoms = atom.disordered_get_list()
Handling Disordered Residues
# Point mutations at same positionif residue.is_disordered():
print(f'Disordered residue at {residue.id}')
names = residue.disordered_get_id_list()
print(f'Alternative residues: {names}')
# Select specific residue type
residue.disordered_select('ALA')
Finding Specific Atoms
# Get backbone atoms
backbone_names = ['N', 'CA', 'C', 'O']
for residue in chain:
backbone = [residue[name] for name in backbone_names if residue.has_id(name)]
# Get all C-alpha atoms
ca_atoms = [r['CA'] for r in structure.get_residues() if r.has_id('CA')]
print(f'Found {len(ca_atoms)} CA atoms')
# Get sidechain atomsfor residue in chain:
sidechain = [a for a in residue if a.name notin ['N', 'CA', 'C', 'O']]
Filtering by Residue Type
# Get only amino acids
amino_acids = [r for r in chain if r.id[0] == ' ']
# Get specific amino acid types
arginines = [r for r in chain if r.resname == 'ARG']
charged = [r for r in chain if r.resname in ['ARG', 'LYS', 'ASP', 'GLU']]
# Get hetero atoms
ligands = [r for r in chain if r.id[0].startswith('H_')]
for lig in ligands:
print(f'Ligand: {lig.resname} at position {lig.id[1]}')
Counting Entities
# Count at each level
n_models = len(list(structure.get_models()))
n_chains = len(list(structure.get_chains()))
n_residues = len(list(structure.get_residues()))
n_atoms = len(list(structure.get_atoms()))
print(f'Models: {n_models}, Chains: {n_chains}')
print(f'Residues: {n_residues}, Atoms: {n_atoms}')
# Count per chainfor chain in structure.get_chains():
n_res = len([r for r in chain if r.id[0] == ' '])
print(f'Chain {chain.id}: {n_res} amino acids')
Working with NMR Ensembles
# NMR structures have multiple models
parser = PDBParser(QUIET=True)
structure = parser.get_structure('nmr', 'nmr_structure.pdb')
n_models = len(list(structure.get_models()))
print(f'NMR ensemble with {n_models} conformers')
# Iterate over modelsfor model in structure:
# Each model is a separate conformation
ca_coords = [r['CA'].coord for r in model.get_residues() if r.has_id('CA')]
print(f'Model {model.id}: {len(ca_coords)} CA atoms')
