生成20个随机的文件, 由于没有用到hash名字,文件名有可能会重复
每个文件中有30-50条序列
每条序列的长度为70-120个碱基import os
import random
import string
print (dir(string))
letter = string.ascii_letters
os.chdir("D:\\")
bases = {1:"A", 2:"T", 3:"C", 4:"G"}
## Test random module , get random DNA base
Nth = random.randint(1,4)
print (bases[Nth])
## Create random DNA sequences
for i in range(20):
Number_of_Seq = random.randint(30,50)
filename = letter[i]
with open("Sequences"+filename + \
str(Number_of_Seq)+ ".fasta", "w") as file_output:
for j in range(Number_of_Seq):
each_Seq=""
Rand_len = random.randint(70,120)
for k in range(Rand_len):
Nth = random.randint(1,4)
each_Seq += bases[Nth]
file_output.write(">seq_"+str(Number_of_Seq)+ \
"_"+str(Rand_len)+"\n")
file_output.write(each_Seq+"\n")