Harvard:Biophysics 101/2007/Notebook:Shawn Liu/2007-2-6

#!/usr/bin/env python

from Bio import GenBank, Seq
from Bio.Seq import 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['U94340']

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)])
    print substr, s.count(substr)

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

# Protein Translation
my_protein = translate(s)
print "protein translation:"
print my_protein
print "its length is:", len(my_protein)

# Raw record
print "\nraw record (hold tight while we find it...)"
ncbi_dict_raw = GenBank.NCBIDictionary('nucleotide', 'genbank')
raw_record = ncbi_dict_raw['U94340']
print raw_record

print '*' * 50
print 'Shawn Liu.  Biophysics 101.  7 February 2007.\n'