Harvard:Biophysics 101/Notebook ZS/2007-2-6/2607 kaiC 1.py

#!/usr/bin/env python from Bio import GenBank, Seq # 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['23957787'] 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(['A' for n in range(i+1)]) print substr, s.count(substr) print "\nmethod 2" for i in range(max_repeat): substr = ''.join(['A' 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