Harvard:Biophysics 101/2007/Notebook:HRH/2007-2-8

Assigned on Feb 6, 2007

Script in progress:

 #!/usr/bin/env python
 
 # Hetmann Hsieh
 # Assignment 2 
 # 2/8/07 
 
import random

# make a list of values for each 
tally = [0 for i in range(11)]

# Generate the random 10-mer of H's and T's

for i in range(10000):
    coinflip = ''.join([random.choice(['H','T']) for n in range (10)])
    
    # Use this loop to tally up instances of each k-mer (from 2 to 10)
    for k in range(2,11):
        # store a k-mer of H's
        H = ''.join(['H' for n in range(k)])
        Hcount = 0
        pos = coinflip.find(H,0)
        while not pos == -1:
            Hcount = Hcount + 1
            pos = coinflip.find(H,pos+1)

        # Update the tally for this k-mer
        tally[k] = tally[k] + Hcount

    # Use this loop to tally up instances of each k-mer (from 2 to 10)
    for k in range(2,11):
        # store a k-mer of T's
        Tcount = 0
        T = ''.join(['T' for n in range(k)])
        pos = coinflip.find(T,0)
        while not pos == -1:
            Tcount = Tcount + 1
            pos = coinflip.find(T,pos+1)

        # Update the tally for this k-mer
        tally[k] = tally[k] + Hcount

# print out the results
for i in range(2,11):
    print i, tally[i]

Output:

2 22791
3 10172
4 4412
5 1860
6 792
7 336
8 147
9 66
10 28