from Bio.Clustalw import MultipleAlignCL
from Bio.Clustalw import do_alignment
cl = MultipleAlignCL('3seqs.fas')
cl.type='protein'
cl.set_output('3out.aln',output_order='ALIGNED')
print cl
align = do_alignment(cl)
# Show align.
print align
PDB files (are expected to) follow a SMCRA model:
(Graph taken from Biopython Tutorial and Cookbook).
This program walks over a PDB record (4hhb) and extract selected data. The file '4hhb.pdb.gz' is included in the data package.
import urllib
import gzip
from Bio.PDB.PDBParser import PDBParser
def disorder(structure):
for chain in structure[0].get_list():
for residue in chain.get_list():
for atom in residue.get_list():
if atom.is_disordered():
print residue, atom
return None
# Uncomment lines with ## to retrieve the file from the net:
##pdburl = 'http://www.rcsb.org/pdb/files/4hhb.pdb.gz'
##handle = urllib.urlopen(pdburl)
##fh = open('4hhb.pdb.gz','w')
##fh.write(handle.read())
##fh.close()
# Uncompress
handle = gzip.open('4hhb.pdb.gz')
# Parse the pdb file
parser = PDBParser(PERMISSIVE=1)
structure = parser.get_structure("test", handle)
disorder(structure)
model = structure[0]
print model.child_list
chain = model['B']
print chain.child_list[:5]
residue = chain[4]
print residue.child_list
atom = residue['CB']
print atom.bfactor
print atom.coord