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


 * 1) !/usr/bin/env python

from Bio import GenBank, Seq from Bio.Seq import translate

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

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

parsed_record = ncbi_dict['U94340']
 * 1) If you pass NCBIDictionary a GenBank id, it will download that record

print "GenBank id:", parsed_record.id

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

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

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

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
 * 1) Raw record

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