In [1]:

    

from __future__ import print_function


import numpy as np
import pandas as pd

from Bio import PDB


    

In [2]:

    

#!rm -f 1tup.cif 2>/dev/null
#!wget "http://www.rcsb.org/pdb/download/downloadFile.do?fileFormat=cif&compression=NO&structureId=1TUP" -O 1tup.cif
#parser = PDB.MMCIFParser()
#p53_1tup = parser.get_structure('P53', '1tup.cif')


    

In [3]:

    

repository = PDB.PDBList()
parser = PDB.PDBParser()
repository.retrieve_pdb_file('1TUP', pdir='.')
p53_1tup = parser.get_structure('P 53', 'pdb1tup.ent')


    

    




Structure exists: './pdb1tup.ent' 






    




/home/tra/Dropbox/soft/biopython/Bio/PDB/StructureBuilder.py:87: PDBConstructionWarning: WARNING: Chain A is discontinuous at line 6146.
  PDBConstructionWarning)
/home/tra/Dropbox/soft/biopython/Bio/PDB/StructureBuilder.py:87: PDBConstructionWarning: WARNING: Chain B is discontinuous at line 6147.
  PDBConstructionWarning)
/home/tra/Dropbox/soft/biopython/Bio/PDB/StructureBuilder.py:87: PDBConstructionWarning: WARNING: Chain C is discontinuous at line 6148.
  PDBConstructionWarning)
/home/tra/Dropbox/soft/biopython/Bio/PDB/StructureBuilder.py:87: PDBConstructionWarning: WARNING: Chain E is discontinuous at line 6149.
  PDBConstructionWarning)
/home/tra/Dropbox/soft/biopython/Bio/PDB/StructureBuilder.py:87: PDBConstructionWarning: WARNING: Chain F is discontinuous at line 6171.
  PDBConstructionWarning)
/home/tra/Dropbox/soft/biopython/Bio/PDB/StructureBuilder.py:87: PDBConstructionWarning: WARNING: Chain A is discontinuous at line 6185.
  PDBConstructionWarning)
/home/tra/Dropbox/soft/biopython/Bio/PDB/StructureBuilder.py:87: PDBConstructionWarning: WARNING: Chain B is discontinuous at line 6383.
  PDBConstructionWarning)
/home/tra/Dropbox/soft/biopython/Bio/PDB/StructureBuilder.py:87: PDBConstructionWarning: WARNING: Chain C is discontinuous at line 6453.
  PDBConstructionWarning)

In [4]:

    

my_residues = set()
for residue in p53_1tup.get_residues():
    my_residues.add(residue.id[0])
print(my_residues)


    

    




set([' ', 'H_ ZN', 'W'])

In [10]:

    

def get_mass(atoms, accept_fun=lambda atom: atom.parent.id[0] != 'W'):
    return sum([atom.mass for atom in atoms if accept_fun(atom)])

chain_names = [chain.id for chain in p53_1tup.get_chains()]
my_mass = np.ndarray((len(chain_names), 3))
for i, chain in enumerate(p53_1tup.get_chains()):
    my_mass[i, 0] = get_mass(chain.get_atoms())
    my_mass[i, 1] = get_mass(chain.get_atoms(), accept_fun=lambda atom: atom.parent.id[0] not in [' ', 'W'])
    my_mass[i, 2] = get_mass(chain.get_atoms(), accept_fun=lambda atom: atom.parent.id[0] == 'W')
masses = pd.DataFrame(my_mass, index=chain_names, columns=['No Water', 'Zincs', 'Water'])
masses


    

    
Out[10]:






  

    

      

      
No Water
      
Zincs
      
Water
    
  
  

    

      
E
      
6068.04412
      
0.00
      
351.9868
    
    

      
F
      
6258.20442
      
0.00
      
223.9916
    
    

      
A
      
20548.26300
      
65.39
      
3167.8812
    
    

      
B
      
20368.18840
      
65.39
      
1119.9580
    
    

      
C
      
20466.22540
      
65.39
      
1279.9520
    
  

In [6]:

    

def get_center(atoms, weight_fun=lambda atom: 1 if atom.parent.id[0] != 'W' else 0):
    xsum = ysum = zsum = 0.0
    acum = 0.0
    for atom in atoms:
        x, y, z = atom.coord
        weight = weight_fun(atom)
        acum += weight
        xsum += weight * x
        ysum += weight * y
        zsum += weight * z
    return xsum / acum, ysum / acum, zsum / acum


    

In [7]:

    

print(get_center(p53_1tup.get_atoms()))
print(get_center(p53_1tup.get_atoms(),
                 weight_fun=lambda atom: atom.mass if atom.parent.id[0] != 'W' else 0))


    

    




(58.296333984624454, 15.48705585839803, 78.405295027957777)
(58.122611380926472, 15.751286500376127, 78.375370368859649)

In [8]:

    

my_center = np.ndarray((len(chain_names), 6))
for i, chain in enumerate(p53_1tup.get_chains()):
    x, y, z = get_center(chain.get_atoms())
    my_center[i, 0] = x
    my_center[i, 1] = y
    my_center[i, 2] = z
    x, y, z = get_center(chain.get_atoms(), weight_fun=lambda atom: atom.mass if atom.parent.id[0] != 'W' else 0)
    my_center[i, 3] = x
    my_center[i, 4] = y
    my_center[i, 5] = z
weights = pd.DataFrame(my_center, index=chain_names, columns=['X', 'Y', 'Z', 'X (Mass)', 'Y (Mass)', 'Z (Mass)'])
weights


    

    
Out[8]:






  

    

      

      
X
      
Y
      
Z
      
X (Mass)
      
Y (Mass)
      
Z (Mass)
    
  
  

    

      
E
      
49.727231
      
32.744879
      
81.253417
      
49.708513
      
32.759725
      
81.207395
    
    

      
F
      
51.982368
      
33.843370
      
81.578795
      
52.002223
      
33.820064
      
81.624394
    
    

      
A
      
72.990763
      
28.825429
      
56.714012
      
72.822668
      
28.810327
      
56.716117
    
    

      
B
      
67.810026
      
12.624435
      
88.656590
      
67.729100
      
12.724130
      
88.545659
    
    

      
C
      
38.221565
      
-5.010494
      
88.293141
      
38.169364
      
-4.915395
      
88.166711
    
  

In [9]:

    

#Pymol viz