counting_gc_content

#This program intends to read fast files with different gene sequences and give the GC content of each one of them 


def counting_nucleotides(sequence):#This general purpose function counts the nucleotides in a string looking for G, C, A and T
    
    sequence = sequence.upper() #defining the dictionary and the nucleotide list for the next loop
    
    dic_nuc = {'C' : 0, 'G' : 0 , 'A': 0, 'T' : 0}
    list_nuc = ['C', 'G', 'A', 'T']
    
    i = 0 #this loop updates our dictionary with the nucleotide counting
    while i < len(list_nuc): 
        dic_nuc[f'{list_nuc[i]}'] = sequence.count(f'{list_nuc[i]}')
        i += 1
    return dic_nuc

def comp_gc_content(sequence_counting): #this function receives a counting nucleotide dictionary 
	
	gc_content = (sequence_counting['C'] + sequence_counting['G'])/(sequence_counting['C'] + sequence_counting['G'] + sequence_counting['T'] + sequence_counting['A']) 
			
	return gc_content




dir_pathway = input('Type the file pathway. If it is already on this program file, just type <filename.txt>: ') #asking the user for the .txt file pathway 
txt = open(f"{dir_pathway}", 'r')
txt_file = txt.read()

txt_strip = txt_file.split('>')
txt_strip = txt_strip[1:]



txt_list = [] #here the script splits the first \n (after que FASTA id), splitting these 2 informations 
i = 0 
for el in range (len(txt_strip)):
	txt_list.append((txt_strip[i].split('\n',1)))
	i += 1 
	
print(txt_list)

id_gc_content = [] #put it inside a loop

i = 0
for ls in txt_list: #in this part the script puts side by side, in a list, the FASTA ID followed by the gc content. 
 
	dic_nuc = counting_nucleotides(txt_list[i][1])
	print(dic_nuc)
	id_gc_content.append(txt_list[i][0])
	id_gc_content.append(round(comp_gc_content(dic_nuc)*100,4))
	i += 1

print(id_gc_content)

txt.close()