def test_find_subsequence():
string = "ATACGCTTGCT"
substring = "GCT"
main_seq = seq.NucleotideSequence(string)
sub_seq = seq.NucleotideSequence(substring)
matches = seq.find_subsequence(main_seq, sub_seq)
assert list(matches) == [4,8]
# :mod:`biotite.sequence.io.fastq` subpackage.
#
# Alternatively, a sequence can also be loaded from GenBank or GenPept
# files, using the :class:`GenBankFile` class (more on this later).
#
# Sequence search
# ---------------
#
# A sequence can be searched for the position of a subsequence or a
# specific symbol:
import biotite.sequence as seq
main_seq = seq.NucleotideSequence("ACCGTATCAAGTATTG")
sub_seq = seq.NucleotideSequence("TAT")
print("Occurences of 'TAT':", seq.find_subsequence(main_seq, sub_seq))
print("Occurences of 'C':", seq.find_symbol(main_seq, "C"))
########################################################################
# Sequence alignments
# -------------------
#
# .. currentmodule:: biotite.sequence.align
#
# When comparing two (or more) sequences, usually an alignment needs
# to be performed. Two kinds of algorithms need to be distinguished
# here:
# Heuristic algorithms do not guarantee to yield the optimal alignment,
# but instead they are very fast. On the other hand, there are
# algorithms that calculate the optimal (maximum similarity score)
# alignment, but are quite slow.
def RLFP(gene):
#The cutting sequances. Notice that this is only two restriction enzymes
#for forward and backward translation
gene = ''.join(gene.split()) #removing the spaces
gene = seq.NucleotideSequence(gene)
cut_TaqI = seq.NucleotideSequence("CGA")
cut_TaqI_rev = seq.NucleotideSequence("AGCT")
cut_HpaII = seq.NucleotideSequence("CGG")
cut_HpaII_rev = seq.NucleotideSequence("GGCT")
#finding the indexes
find_TaqI = list(seq.find_subsequence(gene, cut_TaqI))
find_TaqI_rev = list(seq.find_subsequence(gene, cut_TaqI_rev))
find_HpaII = list(seq.find_subsequence(gene, cut_HpaII))
find_HpaII_rev = list(seq.find_subsequence(gene, cut_HpaII_rev))
#lenghts of the cuts
#for Taqi
passed_cut_TaqI = [] #list of the indexs that have the cut before it
Taqi_length = [] #final length
for i in find_TaqI:
if gene[i - 1] == "T":
passed_cut_TaqI.append(i)
for i in passed_cut_TaqI:
if i != passed_cut_TaqI[0]:
if i != passed_cut_TaqI[-1]:
Taqi_length.append(i -
passed_cut_TaqI[passed_cut_TaqI.index(i) -
1])
else:
Taqi_length.append(len(gene) - i)
else:
Taqi_length.append(i)
#------------------------------------------------------------------------------------------------
#for Taqi reverse
passed_cut_TaqI_rev = [] #list of the indexs that have the cut before it
TaqI_rev_length = [] #final length
for i in find_TaqI_rev:
if i != find_TaqI_rev[0]:
if i != find_TaqI_rev[-1]:
TaqI_rev_length.append(i -
find_TaqI_rev[find_TaqI_rev.index(i) -
1])
else:
TaqI_rev_length.append(len(gene) - i)
else:
TaqI_rev_length.append(i)
#------------------------------------------------------------------------------------------------
#for HpaII
passed_cut_HpaII = [] #list of the indexs that have the cut before it
HpaII_length = [] #final length
for i in find_HpaII:
if gene[i - 1] == "C":
passed_cut_HpaII.append(i)
for i in passed_cut_HpaII:
if i != passed_cut_HpaII[0]:
if i != passed_cut_HpaII[-1]:
HpaII_length.append(
i - passed_cut_HpaII[passed_cut_HpaII.index(i) - 1])
else:
HpaII_length.append(len(gene) - i)
else:
HpaII_length.append(i)
#------------------------------------------------------------------------------------------------
#for HpaII_rev
passed_cut_HpaII_rev = [] #list of the indexs that hae the cut before it
HpaII_rev_length = [] #final length
for i in find_HpaII_rev:
if i != find_HpaII_rev[0]:
if i != find_HpaII_rev[-1]:
HpaII_rev_length.append(
i - find_HpaII_rev[find_HpaII_rev.index(i) - 1])
else:
HpaII_rev_length.append(len(gene) - i)
else:
HpaII_rev_length.append(i)
#---------------------------------------------------------------------------------------------
#building the histograms
pwd = os.getcwd()
plt.hist(Taqi_length, bins=500, facecolor='blue', alpha=0.5)
plt.ylabel("Number of strands")
plt.xlabel('length of strands')
plt.savefig(pwd + '/static/images/RLFP_Taqi_length.png', dpi=200)
plt.hist(TaqI_rev_length, bins=500, facecolor='blue', alpha=0.5)
plt.savefig(pwd + '/static/images/RLFP_TaqI_rev_length.png', dpi=200)
plt.hist(HpaII_length, bins=500, facecolor='blue', alpha=0.5)
plt.savefig(pwd + '/static/images/RLFP_HpaII_length.png', dpi=200)
plt.hist(HpaII_rev_length, bins=500, facecolor='blue', alpha=0.5)
plt.savefig(pwd + '/static/images/HpaII_rev_length.png', dpi=200)
session['valid_seq'] = True
