Harvard:Biophysics 101/2007/Notebook:Christopher Nabel/2007-2-6

Homework Due February 6

Here is my revision of the code assigned on February 1:

   #!/usr/bin/env python

  from Bio import GenBank, Seq

  # We need to import the Translation module from Bio.seq

  from Bio.Seq import Seq,translate

  # We can create a GenBank object that will parse a raw record
  # This facilitates extracting specific information from the sequences
  record_parser = GenBank.FeatureParser()

  # NCBIDictionary is an interface to Genbank
  ncbi_dict = GenBank.NCBIDictionary('nucleotide', 'genbank', parser = record_parser)

  # If you pass NCBIDictionary a GenBank id, it will download that record
  parsed_record = ncbi_dict['42740729']

  print "GenBank id:", parsed_record.id

  # Extract the sequence from the parsed_record
  s = parsed_record.seq.tostring()
  print "total sequence length:", len(s)

  max_repeat = 9

  print "method 1"
  for i in range(max_repeat):
    substr = ''.join(['T' for n in range(i+1)]) #note A changed to T
    print substr, s.count(substr)

  print "\nmethod 2"
  for i in range(max_repeat):
    substr = ''.join(['T' for n in range(i+1)]) # again, A changed to T
    count = 0
    pos = s.find(substr,0)
    while not pos == -1:
        count = count + 1
        pos = s.find(substr,pos+1)
    print substr, count

  # Translate the DNA to a protein sequence and give the length

  gp = translate(s)

 
  print "The translated sequence for Ebola Zaire is %s" % gp
  print "disclaimer: this translation starts before the open reading frame"
  print "The length for this sequence is", len (gp)

  # Print the raw record without parsing the subsets of data

  ncbi_dict = GenBank.NCBIDictionary('nucleotide', 'genbank')
  unparsed_record = ncbi_dict['42740729']
  print "Raw Record:"
  print unparsed_record

back to my page