6_mers

print("Введите бактерию")
bacterion = input()
seq = whole_seq(f"{bacterion}_fasta")
ORF_start = []
minus = []
pseudo_check = []
with open(f"{bacterion}_gb", mode = "r") as data:
  line = data.readline()
  while line!="":
    while not line.startswith("     gene") and line != "":
      line = data.readline()
    if line!= "":
      pseudo = line
      pseudo_check.append(pseudo)
      pseudo = data.readline()
      while pseudo.startswith("       "):
        pseudo_check.append(pseudo)
        pseudo = data.readline()
      if pseudo_check != []:
        pseudo_check = "".join(pseudo_check)
      if pseudo_check.find("pseudo") < 0:
        line = line.split()
        if line[1].find("join") < 0:
          if line[1].startswith("complement"):
            ORF_start.append(int(line[1][11:].split("..")[0]))
          else:
            ORF_start.append(int(line[1].split("..")[0]))
    line = data.readline()
    pseudo_check = []
Six_mer = {}
Mers = []
index = 0
for i in ORF_start:
  minus.append(seq[i-21:i-1]) # на этом этапе имеем список всех нужных участков длиной 20 п.н.
  for j in range(0,14,1):
    if minus[index][j:j+6] in Six_mer:
      Six_mer[minus[index][j:j+6]] +=1
    else:
      Six_mer[minus[index][j:j+6]] = 1
      Mers.append(minus[index][j:j+6])
  index += 1
Mers.sort()
with open(f"Six_mer_{bacterion}.txt",mode = "w") as result:
  for i in Mers:
    print (f"{i}\t{Six_mer[i]}", file=result)