dna.py

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



def protein_translation:
    "This function translates DNA into proteins" #define the function necessary for the translation
    
    with open ("cDNA_sequences.csv","r") as dna:
    	for line in dna:
        	name, seq = line.rstrip("\n").split(",") #remove end of line character and split  at the commas