Source Code for Module Bio.motifs.jaspar

 1  from Bio.motifs import Motif, Instances 
 2  from Bio.Alphabet import IUPAC 
 3  from Bio.Seq import Seq 
 4   
 5   
 6 -def read(handle, format): 
 7      alphabet = IUPAC.unambiguous_dna 
 8      counts = {} 
 9      if format=="pfm": 
10          # reads the motif from Jaspar .pfm file 
11          letters = "ACGT" 
12          for letter, line in zip(letters, handle): 
13              words = line.split() 
14              #if there is a letter in the beginning, ignore it 
15              if words[0]==letter: 
16                  words = words[1:] 
17              counts[letter] = map(float, words) 
18          motif = Motif(alphabet, counts=counts) 
19      elif format=="sites": 
20          # reads the motif from Jaspar .sites file 
21          instances = [] 
22          for line in handle: 
23              if not line.startswith(">"): 
24                  break 
25              # line contains the header ">...." 
26              # now read the actual sequence 
27              line = handle.next() 
28              instance = "" 
29              for c in line.strip(): 
30                  if c==c.upper(): 
31                      instance += c 
32              instance = Seq(instance, alphabet) 
33              instances.append(instance) 
34          instances = Instances(instances, alphabet) 
35          motif = Motif(alphabet, instances=instances) 
36      else: 
37          raise ValueError("Unknown format %s" % format) 
38      motif.mask = "*"*motif.length 
39      return motif 
40   
41 -def write(motif): 
42      """Returns the pfm representation of the motif 
43      """ 
44      letters = "ACGT" 
45      counts = motif.counts 
46      lines = [] 
47      for letter in letters: 
48          terms = map(str, counts[letter]) 
49          line = "\t".join(terms) + "\n" 
50          lines.append(line) 
51      # Finished; glue the lines together 
52      text = "".join(lines) 
53      return text 
54