Source Code for Module Bio.Emboss.Primer3

  1  # Copyright 2008 Michiel de Hoon. 
  2  # Revisions copyright 2009 Leighton Pritchard. 
  3  # Revisions copyright 2010 Peter Cock. 
  4  # All rights reserved. 
  5  # This code is part of the Biopython distribution and governed by its 
  6  # license.  Please see the LICENSE file that should have been included 
  7  # as part of this package. 
  8  """Code to parse output from the EMBOSS eprimer3 program. 
  9   
 10  As elsewhere in Biopython there are two input functions, read and parse, 
 11  for single record output and multi-record output. For primer3, a single 
 12  record object is created for each target sequence and may contain 
 13  multiple primers. 
 14   
 15  i.e. If you ran eprimer3 with a single target sequence, use the read 
 16  function. If you ran eprimer3 with multiple targets, use the parse 
 17  function to iterate over the retsults. 
 18  """ 
 19   
 20  # --- primer3 
 21   
 22   
 23 -class Record(object): 
 24      """Represent information from a primer3 run finding primers. 
 25   
 26      Members: 
 27   
 28      primers  - list of Primer objects describing primer pairs for 
 29                 this target sequence. 
 30      comments - the comment line(s) for the record 
 31      """ 
 32 -    def __init__(self): 
 33          self.comments = "" 
 34          self.primers = [] 
 35   
 36   
 37 -class Primers(object): 
 38      """A primer set designed by Primer3. 
 39   
 40      Members: 
 41   
 42      size - length of product, note you can use len(primer) as an 
 43             alternative to primer.size 
 44   
 45      forward_seq 
 46      forward_start 
 47      forward_length 
 48      forward_tm 
 49      forward_gc 
 50   
 51      reverse_seq 
 52      reverse_start 
 53      reverse_length 
 54      reverse_tm 
 55      reverse_gc 
 56   
 57      internal_seq 
 58      internal_start 
 59      internal_length 
 60      internal_tm 
 61      internal_gc 
 62      """ 
 63 -    def __init__(self): 
 64          self.size = 0 
 65          self.forward_seq = "" 
 66          self.forward_start = 0 
 67          self.forward_length = 0 
 68          self.forward_tm = 0.0 
 69          self.forward_gc = 0.0 
 70          self.reverse_seq = "" 
 71          self.reverse_start = 0 
 72          self.reverse_length = 0 
 73          self.reverse_tm = 0.0 
 74          self.reverse_gc = 0.0 
 75          self.internal_seq = "" 
 76          self.internal_start = 0 
 77          self.internal_length = 0 
 78          self.internal_tm = 0.0 
 79          self.internal_gc = 0.0 
 80   
 81 -    def __len__(self): 
 82          """Length of the primer product (i.e. product size).""" 
 83          return self.size 
 84   
 85   
 86 -def parse(handle): 
 87      """Iterate over primer3 output as Bio.Emboss.Primer3.Record objects. 
 88      """ 
 89      # Skip blank lines at head of file 
 90      while True: 
 91          line = handle.readline() 
 92          if line.strip(): 
 93              break # Starting a record 
 94   
 95      # Read each record 
 96      record = None 
 97      primer = None 
 98      while True: 
 99          if line.startswith('# EPRIMER3') or line.startswith('# PRIMER3'): 
100              # Record data 
101              if record is not None: 
102                  yield record 
103              record = Record() 
104              record.comments += line 
105              primer = None 
106          elif line.startswith('#'): 
107              if line.strip() != '#                      Start  Len   Tm     GC%   Sequence': 
108                  record.comments += line 
109          elif not line.strip(): 
110              pass 
111          elif line[5:19]=="PRODUCT SIZE: ": 
112              primer = Primers() 
113              primer.size = int(line[19:]) 
114              record.primers.append(primer) 
115          elif line[5:19]=="FORWARD PRIMER": 
116              words = line.split() 
117              if not primer or primer.size==0: 
118                  primer = Primers() 
119                  record.primers.append(primer) 
120              primer.forward_start = int(words[2]) 
121              primer.forward_length = int(words[3]) 
122              primer.forward_tm = float(words[4]) 
123              primer.forward_gc = float(words[5]) 
124              primer.forward_seq = words[6] 
125          elif line[5:19]=="REVERSE PRIMER": 
126              words = line.split() 
127              if not primer or primer.size==0: 
128                  primer = Primers() 
129                  record.primers.append(primer) 
130              primer.reverse_start = int(words[2]) 
131              primer.reverse_length = int(words[3]) 
132              primer.reverse_tm = float(words[4]) 
133              primer.reverse_gc = float(words[5]) 
134              primer.reverse_seq = words[6] 
135          elif line[5:19]=="INTERNAL OLIGO": 
136              words = line.split() 
137              if not primer or primer.size==0: 
138                  primer = Primers() 
139                  record.primers.append(primer) 
140              primer.internal_start = int(words[2]) 
141              primer.internal_length = int(words[3]) 
142              primer.internal_tm = float(words[4]) 
143              primer.internal_gc = float(words[5]) 
144              try: 
145                  primer.internal_seq = words[6] 
146              except IndexError: # eprimer3 reports oligo without sequence 
147                  primer.internal_seq = '' 
148          try: 
149              line = handle.next() 
150          except StopIteration: 
151              break 
152      if record: 
153          yield record 
154   
155   
156 -def read(handle): 
157      """Parse primer3 output into a Bio.Emboss.Primer3.Record object. 
158   
159      This is for when there is one and only one target sequence. If 
160      designing primers for multiple sequences, use the parse function. 
161      """ 
162      iterator = parse(handle) 
163      try: 
164          first = iterator.next() 
165      except StopIteration: 
166          raise ValueError("No records found in handle") 
167      try: 
168          second = iterator.next() 
169      except StopIteration: 
170          second = None 
171      if second is not None: 
172          raise ValueError("More than one record found in handle") 
173      return first 
174