Source Code for Module Bio.PDB.PSEA

  1  # Copyright (C) 2006, Thomas Hamelryck (thamelry@binf.ku.dk) 
  2  # This code is part of the Biopython distribution and governed by its 
  3  # license.  Please see the LICENSE file that should have been included 
  4  # as part of this package. 
  5   
  6  """Wrappers for PSEA, a program for secondary structure assignment. 
  7   
  8  See this citation for P-SEA, PMID: 9183534 
  9   
 10  Labesse G, Colloc'h N, Pothier J, Mornon J-P:  P-SEA: a new efficient 
 11  assignment of secondary structure from C_alpha. 
 12  Comput Appl Biosci 1997 , 13:291-295 
 13   
 14  ftp://ftp.lmcp.jussieu.fr/pub/sincris/software/protein/p-sea/ 
 15  """ 
 16   
 17  import os 
 18   
 19  from Bio.PDB.Polypeptide import is_aa 
 20   
 21   
 22 -def run_psea(fname): 
 23      """Run PSEA and return output filename. 
 24   
 25      Note that this assumes the P-SEA binary is called "psea" and that it is 
 26      on the path. 
 27   
 28      Note that P-SEA will write an output file in the current directory using 
 29      the input filename with extension ".sea". 
 30   
 31      Note that P-SEA will write output to the terminal while run. 
 32      """ 
 33      os.system("psea "+fname) 
 34      last=fname.split("/")[-1] 
 35      base=last.split(".")[0] 
 36      return base+".sea" 
 37   
 38   
 39 -def psea(pname): 
 40      """Parse PSEA output file.""" 
 41      fname=run_psea(pname) 
 42      start=0 
 43      ss="" 
 44      fp=open(fname, 'r') 
 45      for l in fp.readlines(): 
 46          if l[0:6]==">p-sea": 
 47              start=1 
 48              continue 
 49          if not start: 
 50              continue 
 51          if l[0]=="\n": 
 52              break 
 53          ss=ss+l[0:-1] 
 54      fp.close() 
 55      return ss 
 56   
 57   
 58 -def psea2HEC(pseq): 
 59      """Translate PSEA secondary structure string into HEC.""" 
 60      seq=[] 
 61      for ss in pseq: 
 62          if ss=="a": 
 63              n="H" 
 64          elif ss=="b": 
 65              n="E" 
 66          elif ss=="c": 
 67              n="C" 
 68          seq.append(n) 
 69      return seq 
 70   
 71   
 72 -def annotate(m, ss_seq): 
 73      """Apply seconardary structure information to residues in model.""" 
 74      c=m.get_list()[0] 
 75      all=c.get_list() 
 76      residues=[] 
 77      # Now remove HOH etc. 
 78      for res in all: 
 79          if is_aa(res): 
 80              residues.append(res) 
 81      L=len(residues) 
 82      if not (L==len(ss_seq)): 
 83          raise ValueError("Length mismatch %i %i" % (L, len(ss_seq))) 
 84      for i in range(0, L): 
 85          residues[i].xtra["SS_PSEA"]=ss_seq[i] 
 86      #os.system("rm "+fname) 
 87   
 88   
 89 -class PSEA(object): 
 90 -    def __init__(self, model, filename): 
 91          ss_seq=psea(filename) 
 92          ss_seq=psea2HEC(ss_seq) 
 93          annotate(model, ss_seq) 
 94          self.ss_seq=ss_seq 
 95   
 96 -    def get_seq(self): 
 97          """ 
 98          Return secondary structure string. 
 99          """ 
100          return self.ss_seq 
101   
102   
103  if __name__=="__main__": 
104   
105      import sys 
106      from Bio.PDB import PDBParser 
107   
108      # Parse PDB file 
109      p=PDBParser() 
110      s=p.get_structure('X', sys.argv[1]) 
111   
112      # Annotate structure with PSEA sceondary structure info 
113      PSEA(s[0], sys.argv[1]) 
114