def generating_theoretical_spectrum_cyclic_peptide(peptide):
mass_table = read_mass_table("integer_mass_table.txt")
# =============================================================================
# a = range(57, 201, 1)
# mass_table = {}
# for i in a:
# mass_table[chr(i)] = int(i)
# =============================================================================
subpeptides = [peptide]
#in order to easily process cylce, we double peptide
peptide *= 2
for i in range(0, int(len(peptide) / 2) ):
for j in range(1, int(len(peptide) / 2)):
subpeptides.append(peptide[i:i+j])
spectrum = [0]
#print(subpeptides)
for subpeptide in subpeptides:
mass = 0
for acid in subpeptide:
mass += mass_table[acid]
spectrum.append(mass)
return spectrum
def counting_peptides_with_given_mass(m):
# we know the smallest mass is 57 for G, so the length of linear peptides
# will be less than int(m/57)
# On the other hand, the largest mass is 186 for W, so the length will be
# greater than int(m/186)
# so the interval of length is [int(m/186), int(m/57)]
mass_table = read_mass_table("integer_mass_table.txt")
mass_table.pop("I")
mass_table.pop("K")
peptides = [""]
count = 0
mass_list = [0]
for i in range(int(m / 57)):
print(i)
peptides_new = []
mass_list_new = []
for j in range(len(peptides)):
for amino in mass_table:
new_peptide = peptides[j] + amino
new_peptide_mass = mass_list[j] + mass_table[amino]
#if i >= int(m / 186) - 1:
if new_peptide_mass == m:
count += 1
continue
elif new_peptide_mass + 57 > m:
continue
peptides_new.append(new_peptide)
mass_list_new.append(new_peptide_mass)
mass_list = mass_list_new
peptides = peptides_new
return count
def cyclopeptide_sequencing(spectrum):
mass_table = read_mass_table("integer_mass_table.txt")
one_k_mer = spectrum_consistent(spectrum, mass_table.copy())
peptides = one_k_mer.copy()
for i in range(int(max(spectrum) / 57)):
new_peptides = []
for peptide in peptides:
for j in one_k_mer:
new_peptides.append(peptide + j)
peptides_temp = []
for new_peptide in new_peptides:
new_peptide_spectrum = generating_theoretical_spectrum_linear_peptide(
new_peptide)
#if max(new_peptide_spectrum.values()) == max(spectrum):
if spectrum_consistent_bool(spectrum, new_peptide_spectrum):
peptides_temp.append(new_peptide)
if len(peptides_temp) != 0:
peptides = peptides_temp
peptides = set(peptides)
print(sorted(peptides))
cyclopeptide_spectrum = []
for i in peptides:
s = []
for j in i:
s.append(str(mass_table[j]))
cyclopeptide_spectrum.append("-".join(s))
return set(cyclopeptide_spectrum)
def generating_theoretical_spectrum_linear_peptide(peptide):
mass_table = read_mass_table("integer_mass_table.txt")
subpeptides = []
#in order to easily process cylce, we double peptide
i = 0
for i in range(0, int(len(peptide))):
for j in range(1, int(len(peptide)) - i + 1):
subpeptides.append(peptide[i:i + j])
spectrum = []
for subpeptide in subpeptides:
mass = 0
for acid in subpeptide:
mass += mass_table[acid]
spectrum.append(mass)
return spectrum