【Python小試】將核酸序列翻譯成氨基酸序列

三聯密碼表

gencode = {
    'ATA':'I', 'ATC':'I', 'ATT':'I', 'ATG':'M',
    'ACA':'T', 'ACC':'T', 'ACG':'T', 'ACT':'T',
    'AAC':'N', 'AAT':'N', 'AAA':'K', 'AAG':'K',
    'AGC':'S', 'AGT':'S', 'AGA':'R', 'AGG':'R',
    'CTA':'L', 'CTC':'L', 'CTG':'L', 'CTT':'L',
    'CCA':'P', 'CCC':'P', 'CCG':'P', 'CCT':'P',
    'CAC':'H', 'CAT':'H', 'CAA':'Q', 'CAG':'Q',
    'CGA':'R', 'CGC':'R', 'CGG':'R', 'CGT':'R',
    'GTA':'V', 'GTC':'V', 'GTG':'V', 'GTT':'V',
    'GCA':'A', 'GCC':'A', 'GCG':'A', 'GCT':'A',
    'GAC':'D', 'GAT':'D', 'GAA':'E', 'GAG':'E',
    'GGA':'G', 'GGC':'G', 'GGG':'G', 'GGT':'G',
    'TCA':'S', 'TCC':'S', 'TCG':'S', 'TCT':'S',
    'TTC':'F', 'TTT':'F', 'TTA':'L', 'TTG':'L',
    'TAC':'Y', 'TAT':'Y', 'TAA':'_', 'TAG':'_',
    'TGC':'C', 'TGT':'C', 'TGA':'_', 'TGG':'W'}

測試

dna = "ATGTTCGGTGATGCTACGTAACGT"

def translate(dna):
    amino_acid_sequence = ""
    for start in range(0,len(dna) - 2, 3):
        stop = start + 3
        codon = dna[start:stop]
        aa = gencode.get(codon.upper(),'X') #當指定鍵的值不存在時，返回X
        amino_acid_sequence = amino_acid_sequence + aa
    return(amino_acid_sequence)

print(translate(dna))

#用assert斷言一個表達式，為 false時觸發異常
# input sequence is easy
assert(translate_dna("ATGTTCGGT")) == "MFG"

# input sequence has incomplete codons at the end
assert(translate_dna("ATCGATCGAT")) == "IDR"

# input sequence contains N
assert(translate_dna("ACGANCGAT")) == "TXD"

結果

MFGDAT_R