simulate_reads.py

import random

def shotgun(iterable, size=12):
    """ """
    start = random.choice(range(0, len(iterable)-size))
    return(start, iterable[start:start+size])

def paired_end(iterable, read_size=10, gap_size=15):
    """ """
    start = random.choice(range(0, len(iterable)-(read_size+gap_size)))
    first_read = iterable[start:start+read_size]
    second_read =iterable[start+read_size+gap_size: start+read_size+gap_size+read_size]
    return start, first_read + gap_size*"-" + second_read


sentence = """
It has not escaped our notice that the specific pairing we have postulated immediately suggests a possible copying mechanism for the genetic material.
""".strip()

def main():
    sequencing_run = [paired_end(sentence, 12) for i in range(25)]
    print sentence
    for index, chunk in sorted(sequencing_run):
        sread = []
        for space in range(index):
            sread.append(" ")
        sread.append(chunk)
        print"".join(sread)

if __name__ == '__main__':
    main()