StephenFordham

import re

DNA = 'GAGCGCTAGCCAAA'
match = re.search(pattern='AAA', string=DNA)
# match = re.search('AAA', 'DNA')
print(match)

<re.Match object; span=(11, 14), match='AAA'>

StephenFordham

import re
DNA = 'GAGCGCTAGCCAAA'
if re.search('AAA', DNA):
    print("Tri-nucleotide found!")

#console output
# Tri-nucleotide found!

StephenFordham

import re
DNA = 'GAGCGCTAGCCAAA'
match = re.search('AAA', DNA)

print(match.start())
#11
print(match.end())
#14
print(match.span())
# (11,14)

StephenFordham

DNA = 'ATCGACCGGGTTT'
if re.search('CCGGG', DNA) or re.search('CCCGG', DNA):
    print('Restriction enzyme found!')

if re.search('CC(G|C)GG', DNA):
    print('Restriction enzyme found!')

StephenFordham

open_reading_frame = 'AUG.*(AA|AG|GA)'

StephenFordham

inframe_open_reading_frame = 'AUG(...)*U(AA|AG|GA)' 

StephenFordham

N_glycosylation_pattern = 'N[^P][ST][^P]'

StephenFordham

import re

N_glycosylation_pattern = 'N[^P][ST][^P]'
# putting a caret ^ at the start of the group will negate it
# and match any character that is not in that group

Protein_seq = 'YHWKYELIQNNSNEFC'

if re.search(N_glycosylation_pattern, Protein_seq):
    print("N-glycosylation site motif found")

StephenFordham

htt_pattern = '(CAG|CAA){18,}'

# just like with substrings we can leave out the lower and upper limits
# here, we will match the pattern 18 or more times

StephenFordham

import re

htt_pattern = '(CAG|CAA){18,}'
htt_mRNA = open('C:/Users/apsciuser/Downloads/htt_gene.fasta').read()
match = re.findall(htt_pattern, htt_mRNA)
print("The number of polyQ repeats found are: " + str(len(match)))

# Console output
# The number of polyQ repeats found are: 1