Submitted Files

001

import sys, fasta

002

003

REGIONSIZE = 10000

004

BPLOOKFOR = 'GC'

005

006

# load the file

007

header, sequence = fasta.loadSingle(sys.argv[1])

008

009

def percentage(region, lookFor):

010

'''

011

    calculates the percentage of the sequence made up of lookFor

012

'''

013

    count = 0

014

015

    # iterate over each letter in the sequence, incrementing count if

016

    # it is in lookFor

017

    for letter in region:

018

        if letter in lookFor:

019

            count += 1

020

021

    # return the percentage of this region

022

    return float(count)/len(region)

023

024

# compute the number of regions

025

regions = (len(sequence)/REGIONSIZE) + 1

026

027

regionList = []

028

029

# for each region, get the sequence cooresponding to this region, and

030

# print the result

031

for x in range(regions):

032

    currentRegion = sequence[x * REGIONSIZE : (x + 1) * REGIONSIZE]

033

    regionList.append(currentRegion)

034

print percentage(currentRegion, BPLOOKFOR)

Annotation Demo