Mar-01-2018, 06:03 AM
I need to generate permutation of some words (A T G C ) actually nucleotides for di-composition (eg AA AT AG AC), tri-composition (AAA AAT AAC AAG), tetra, penta etc (one at a time) and then check in the other file that contains sequences with some values the count of occurrences of each permutation. I generated the permutation list. Now I need to loop through the sequences only (splitting the sequences from values) for counting each of the permutation generated above and get the output in new file. But I'm getting the answer for only one sequence and not for the other sequences.
Logic of the programme i tried to follow is :
Generate the permutations of ATCG in a file1 (e.g. AT AG AC AA ...)
Read the generated file1 and sequence#value file (DNA_seq_val.txt)
Read the sequences and separate the sequences form values
Loop through the sequences for the permutations and print their occurrence with values (each separated with comma) in results file.
Input test file= DNA_seq_val.txt AAAATTTT#99
CCCCGGGG#77
ATATATCGCGCG#88
*Output I got is --
2,0,0,1,0,0,0,0,0,0,0,0,0,0,0,2,99 AAAATTTT
77 CCCCGGGG
88 ATATATCGCGCG
Output Needed is
2,0,0,1,0,0,0,0,0,0,0,0,0,0,0,2,99 AAAATTTT
x,x,x,x,x,x,x,x,x,x,x,x,x,x,x,x,77 CCCCGGGGx
x,x,x,x,x,x,x,x,x,x,x,x,x,x,x,x,88 ATATATCGCGCG
(where x= corresponding counts as in first line)
my code is below:
Logic of the programme i tried to follow is :
Generate the permutations of ATCG in a file1 (e.g. AT AG AC AA ...)
Read the generated file1 and sequence#value file (DNA_seq_val.txt)
Read the sequences and separate the sequences form values
Loop through the sequences for the permutations and print their occurrence with values (each separated with comma) in results file.
Input test file= DNA_seq_val.txt AAAATTTT#99
CCCCGGGG#77
ATATATCGCGCG#88
*Output I got is --
2,0,0,1,0,0,0,0,0,0,0,0,0,0,0,2,99 AAAATTTT
77 CCCCGGGG
88 ATATATCGCGCG
Output Needed is
2,0,0,1,0,0,0,0,0,0,0,0,0,0,0,2,99 AAAATTTT
x,x,x,x,x,x,x,x,x,x,x,x,x,x,x,x,77 CCCCGGGGx
x,x,x,x,x,x,x,x,x,x,x,x,x,x,x,x,88 ATATATCGCGCG
(where x= corresponding counts as in first line)
my code is below:
from itertools import product
import os
f2 = open('TRYYY', 'a')
#********Generate the permutations start********
per = product('ACGT', repeat=2) # ATGC =nucleotides; 2= for di ntd(replace 2 with 3 fir tri ntds and so on)
f = open('myfile', 'w')
p = ""
for p in per:
p = "".join(p)
f.write(p + "\n")
f.close()
#********Generate the permutations ENDS********
with open('DNA_seq_val.txt', 'r+') as SEQ, open('myfile', 'r+') as TET: #open two files
SEQ_lines = sum(1 for line in open('DNA_seq_val.txt')) #count lines in sequences file
#print (SEQ_lines)
compo_lines = sum(1 for line in open('myfile')) #count lines in composition
#print (compo_lines)
for lines in SEQ:
line,val1 = lines.split("#")
val2 = val1.rstrip('\n')
val = str(val2)
line = line.rstrip('\n')
length =len(line)
#print (line)
#print (val)
LIN = line, val
#print (LIN)
newstr = "".join((line))
print (newstr)
#while True: # infinte loop
for PER in TET:
#print (line)
PER = PER.rstrip('\n')
length2 =len(PER)
#print (length2)
#print (line)
# print (PER)
C_PER = str(line.count(PER))
# print (C_PER)
for R in C_PER:
R1 = "".join(R)
f2.write(R1+ ",")
f2.write(val,)
f2.write('\t')
f2.write(line)
f2.write('\n')
#exit()