Script distance check.py

From Bioinformatikpedia
Revision as of 20:42, 3 September 2013 by Gerkej (talk | contribs) (Created page with "<source lang="python"> #!/usr/bin/python import sys import os import re import numpy import math input=sys.argv[1]#contact.out in_pdb=sys.argv[2]#pdb file with actual coordina…")
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)

<source lang="python">

  1. !/usr/bin/python

import sys import os import re import numpy import math


input=sys.argv[1]#contact.out in_pdb=sys.argv[2]#pdb file with actual coordinates


residues=[] CN_dist=[]#[pos1, pos2, cn, state] state~TP or FP coordinates={}

  1. calculates euklidean distance between two atoms

def calc_dist(co1, co2):#dictionary with xyz

       p1=numpy.array((co1["x"],co1["y"],co1["z"]))
       p2=numpy.array((co2["x"],co2["y"],co2["z"]))
       dist=numpy.linalg.norm(p1-p2)
       return dist
  1. checks distance between any atom of two residues

def any_atom(atom1_list, atom2_list):

               for a1 in atom1_list:
                       for a2 in atom2_list:
                               dist=calc_dist(a1,a2)
                               if(dist<5.0):
                                       return "TP"
               return "FP"
  1. checks TP oor FP for all residue pairs

def all_dist(res):

       for i in res:#for every residue pair
               if(i[5]>1 ):
                       #print(i)
                       #print(coordinates.has_key(i[0]))
                       atoms1=coordinates[i[0]]#of all atoms of residue 1 (list of dictionarys)
                       atoms2=coordinates[i[2]]#of all atoms of residue 2 (list of dictionarys)
                       state=any_atom(atoms1, atoms2)
                       CN_dist.append([i[0],i[1],i[2],i[3],i[5],state])

def read_pdb():

       file=open(in_pdb, 'r')
       lines=file.readlines()
       for line in lines:
               if(re.match("^ATOM",line)):
                       info=line.split()
                       if(info[2]=="N"):#every new residue starts with N
                               res_co=[{"x":float(info[6]),"y":float(info[7]),"z":float(info[8])}] #list of coordinates of all atoms
                       else:
                               res_co.append({"x":float(info[6]),"y":float(info[7]),"z":float(info[8])})
                       #print(info)
                       coordinates[int(info[5])]=res_co #key:aa position
       file.close()
  1. info[position1, residue1, position2, residue2, MI, CN]

def read_input():

       file=open(input, 'r')
       lines=file.readlines()
       for line in lines:
               text=line.lstrip().rstrip('\n')
               info=text.split()
               info[0]=int(info[0])
               info[2]=int(info[2])
               info[4]=float(info[4])
               info[5]=float(info[5])
               residues.append(info)
       file.close()
  1. writes CN_dist into file

def make_output(a):

       file_name="corelations_%s"%(input)
       file=open(file_name, 'w')
       for i in a:
               file.write("%i %s %i %s %f %s\n"%(i[0],i[1],i[2],i[3],i[4],i[5]))
       file.close()


if __name__ == '__main__':

       read_input()
       read_pdb()
       all_dist(residues)
       make_output(CN_dist)


</source>