Harvard:Biophysics 101/2007/Notebook:Michael Wang/2007-2-1

Feburary 1

#!/usr/bin/env python
from Bio.Seq import translate
from Bio import GenBank, Seq
import sys

#user defines which array element to pick
array_position = int(sys.argv[-1])
print "Retrieving entry number ",array_position

#Creates a non-parsed library of genes with search terms Xenopus and notch
search_terms = "Xenopus AND notch"
gi_list = GenBank.search_for(search_terms)
print "Searching for", search_terms, "entries"
print gi_list
print "Done searching"
print "Entry ",array_position
ncbi_dict_alpha = GenBank.NCBIDictionary('nucleotide', 'genbank')

#prints the raw entry
print ncbi_dict_alpha[gi_list[0]]

# 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[gi_list[0]]
print parsed_record
print "GenBank id:", parsed_record.id

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

#Translating the raw sequence
my_protein = translate(s)
print "translated sequence:", my_protein

max_repeat = 9

print "multiple T analysis"
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