Geek Answers Handbook

Reverse DNA chain padding using Python

I have a DNA sequence and would like to get the reverse complement to it using Python. It is located in one of the columns of the CSV file, and I would like to write the opposite complement to another column in the same file. The hard part is that there are several cells with something other than A, T, G, and C. I managed to get the opposite complement with this part of the code:

def complement(seq):
    complement = {'A': 'T', 'C': 'G', 'G': 'C', 'T': 'A'} 
    bases = list(seq) 
    bases = [complement[base] for base in bases] 
    return ''.join(bases)
    def reverse_complement(s):
        return complement(s[::-1])

    print "Reverse Complement:"
    print(reverse_complement("TCGGGCCC"))

However, when I try to find an item that is not in the add-ons dictionary using the code below, I just get the add-on to the latest database. This is not an iteration. I would like to know how I can fix this.

def complement(seq):
    complement = {'A': 'T', 'C': 'G', 'G': 'C', 'T': 'A'} 
    bases = list(seq) 
    for element in bases:
        if element not in complement:
            print element  
        letters = [complement[base] for base in element] 
        return ''.join(letters)
def reverse_complement(seq):
    return complement(seq[::-1])

print "Reverse Complement:"
print(reverse_complement("TCGGGCCCCX"))
+6
6

get , . ATGC ( -, ), , . , , , sni, ins.

alt_map = {'ins':'0'}
complement = {'A': 'T', 'C': 'G', 'G': 'C', 'T': 'A'} 

def reverse_complement(seq):    
    for k,v in alt_map.iteritems():
        seq = seq.replace(k,v)
    bases = list(seq) 
    bases = reversed([complement.get(base,base) for base in bases])
    bases = ''.join(bases)
    for k,v in alt_map.iteritems():
        bases = bases.replace(v,k)
    return bases

>>> seq = "TCGGinsGCCC"
>>> print "Reverse Complement:"
>>> print(reverse_complement(seq))
GGGCinsCCGA
+3

- , , Biopython. , "-", "*" ? , ? ?

, , , :

from Bio.Seq import Seq

seq = Seq("TCGGGCCC")

print seq.reverse_complement()
# GGGCCCGA

, :

print seq.complement()
print seq.transcribe()
print seq.translate()


AGCCCGGG
UCGGGCCC
SG

, . Biopython :

seq = Seq("TCGGGCCCX")
print seq.reverse_complement()
# XGGGCCCGA
+25

. , .

complement = {'A': 'T', 'C': 'G', 'G': 'C', 'T': 'A'}
seq = "TCGGGCCC"
reverse_complement = "".join(complement.get(base, base) for base in reversed(seq))
+15
import string
old_chars = "ACGT"
replace_chars = "TGCA"
tab = string.maketrans(old_chars,replace_chars)
print "AAAACCCGGT".translate(tab)[::-1]

= ACCGGGTTTT

+10
def ReverseComplement(Pattern):
    revcomp = []
    x = len(Pattern)
    for i in Pattern:
        x = x - 1
        revcomp.append(Pattern[x])
    return ''.join(revcomp)

# this if for the compliment 

def compliment(Nucleotide):
    comp = []
    for i in Nucleotide:
        if i == "T":
            comp.append("A")
        if i == "A":
            comp.append("T")
        if i == "G":
            comp.append("C")
        if i == "C":
            comp.append("G")

    return ''.join(comp)
0
source

Try the code below,

complement = {'A': 'T', 'C': 'G', 'G': 'C', 'T': 'A'}
seq = "TCGGGCCC"
reverse_complement = "".join(complement.get(base, base) for base in reversed(seq))
0
source

More articles:


All Articles