Pythonで塩基配列を相補鎖に変換[3パターン]

PythonでDNA、RNA配列を相補鎖に変換

状況によって使い分けれる3パターンのまとめ

best_choice.py

# 一番お手軽、biopythonを使う
# DNAでもRNAでも使える
from Bio.Seq import Seq

seq='ATGCatgc--Nn'
seq_c=str(Seq(seq).reverse_complement())

print(seq_c)
# nN--gcatGCAT

use_string_module.py

# あえてbiopythonを使わない
import string

# DNA
seq='ATGCatgc--Nn'
seq_c=seq.translate(str.maketrans('ATGCatgc', 'TACGtagc'))[::-1]  # python3

print(seq_c)
# nN--gcatGCAT

# RNAの場合
seq_c=seq.translate(str.maketrans('AUGCaugc', 'UACGuagc'))[::-1]  # python3

DIY.py

# どうしても自分でやりたい時
# DNA
def complement_dna(string):
    comp=''
    for char in string:
        if   char == 'A': comp += 'T'
        elif char == 'T': comp += 'A'
        elif char == 'G': comp += 'C'
        elif char == 'C': comp += 'G'
        elif char == 'a': comp += 't'
        elif char == 't': comp += 'a'
        elif char == 'g': comp += 'c'
        elif char == 'c': comp += 'g'
        else:             comp += char
    return comp[::-1]

seq='ATGCatgc--Nn'
seq_c=complement_dna(seq)

print(seq_c)
# nN--gcatGCAT

# RNAの場合
def complement_rna(string):
    comp=''
    for char in string:
        if   char == 'A': comp += 'U'
        elif char == 'U': comp += 'A'
        elif char == 'G': comp += 'C'
        elif char == 'C': comp += 'G'
        elif char == 'a': comp += 'u'
        elif char == 'u': comp += 'a'
        elif char == 'g': comp += 'c'
        elif char == 'c': comp += 'g'
        else:             comp += char
    return comp[::-1]

環境

Python 3.7.1
biopython 1.72