def CDS_markup(Search_Query):
#Take the search term and search database for corresponding information
Database_Result = dbapi.dict_entries(Search_Query)
if Database_Result == False:
print(
'Please enter valid search value for either accession, location, gene_id or protein_id'
)
p = re.compile(r'(\d+)..(\d+),?')
CDS = Database_Result['cds']
it = p.finditer(CDS)
start_end_list = [(int(match.group(1)), int(match.group(2)))
for match in it]
DNA_seq = Database_Result['dna_seq']
#Mark up the sequence with < > to locate start and end of CDS regions
DNA_list = list(DNA_seq)
offset = 0
for start, end in start_end_list:
DNA_list.insert((start - 1) + offset, "<")
offset += 1
DNA_list.insert((end - 1) + offset, ">")
offset += 1
DNA_str = ""
for elem in DNA_list:
DNA_str += elem
return (DNA_str)
def codon_freq(Search_Query):
'''this function takes a user search query and will return a dictionary of codon
usage frequencies from the DNA seq.
param: user search query The search format must be in a string
return: dictionary of codons and their frequencies '''
Database_Result = dbapi.dict_entries(Search_Query)
if Database_Result == False:
print(
'Please enter valid search value for either accession, location, gene_id or protein_id'
)
DNA_seq = Database_Result['dna_seq']
#create a list of DNA seq split into groups of 3 non-overlapping nucleotides
p5 = re.compile(r'\w\w\w')
codon = p5.findall(DNA_seq)
#Create a dictionary of codons and populate with the frequency of each codon
codon_dict = {}
for elem in codon:
if elem in codon_dict:
codon_dict[elem] += 1
else:
codon_dict[elem] = 1
return (codon_dict)
def search_RE(Search_Query, RE_name):
amb = IUPACAmbiguousDNA()
Database_Result = dbapi.dict_entries(Search_Query)
if Database_Result == False:
return (
'Please enter valid search value for either accession, location, gene_id or protein_id'
)
DNA_seq = Database_Result['dna_seq']
DNASeq = Seq(DNA_seq, amb)
if RE_name == 'EcoRI':
EcoRI = Restriction.EcoRI.search(DNASeq)
if EcoRI == []:
print('There are no EcoRI restriction sites in this DNA sequence')
else:
return 'The location sites for EcoRI are', EcoRI
elif RE_name == 'BamHI':
BamHI = Restriction.BamHI.search(DNASeq)
if BamHI == []:
print('There are no BamHI restriction sites in this DNA sequence')
else:
return 'The location sites for BamHI are', BamHI
elif RE_name == 'BsuRI':
BsuRI = Restriction.BsuRI.search(DNASeq)
if BsuRI == []:
print('There are no BsuRI restriction sites in this DNA sequence')
else:
return 'The location sites for BsuRI are', BsuRI
else:
print('search_RE function error: invalid RE name')
def search_db(Search_Query):
'''will search DB for query value, either accession, gene_id, location or protein_id and return a dictionary with the search outcome
param: nil - an input prompt will appear to insert a value
return: a dictionary of all raw DB information'''
Database_Result = dbapi.dict_entries(Search_Query)
return (Database_Result)
def codon_freq(Search_Query):
Database_Result = dbapi.dict_entries(Search_Query)
if Database_Result == False:
print(
'Please enter valid search value for either accession, location, gene_id or protein_id'
)
DNA_seq = Database_Result['dna_seq']
#create a list of DNA seq split into groups of 3 non-overlapping nucleotides
p5 = re.compile(r'\w\w\w')
codon = p5.findall(DNA_seq)
#Create a dictionary of codons and populate with the frequency of each codon
codon_dict = {}
for elem in codon:
if elem in codon_dict:
codon_dict[elem] += 1
else:
codon_dict[elem] = 1
return (codon_dict)
def search_RE(Search_Query, RE_name):
'''takes a restriction enzyme name and will search the gene DNA sequence
and return the location of the restriction enzyme.
param RE_name: the name of the restriction enzyme you want to search
either EcoRI, BamHI or BsuRI. The search format must be in
a string.
returns: a list of the location of the searched enzyme in the sequence '''
amb = IUPACAmbiguousDNA()
Database_Result = dbapi.dict_entries(Search_Query)
if Database_Result == False:
return (
'Please enter valid search value for either accession, location, gene_id or protein_id'
)
DNA_seq = Database_Result['dna_seq']
DNASeq = Seq(DNA_seq, amb)
if RE_name == 'EcoRI':
EcoRI = Restriction.EcoRI.search(DNASeq)
if EcoRI == []:
print('There are no EcoRI restriction sites in this DNA sequence')
else:
return 'The location sites for EcoRI are', EcoRI
elif RE_name == 'BamHI':
BamHI = Restriction.BamHI.search(DNASeq)
if BamHI == []:
print('There are no BamHI restriction sites in this DNA sequence')
else:
return 'The location sites for BamHI are', BamHI
elif RE_name == 'BsuRI':
BsuRI = Restriction.BsuRI.search(DNASeq)
if BsuRI == []:
print('There are no BsuRI restriction sites in this DNA sequence')
else:
return 'The location sites for BsuRI are', BsuRI
else:
print('search_RE function error: invalid RE name')
def CDS_markup(Search_Query):
'''This function will take a DNA sequence, identify CDS sites and produce a marked up sequence
that identifies one or more CDS sites in the DNA sequence.
param: user search query. The search format must be in a string
return: marked up sequence in string format
'''
#Take the search term and search database for corresponding information
Database_Result = dbapi.dict_entries(Search_Query)
if Database_Result == False:
print(
'Please enter valid search value for either accession, location, gene_id or protein_id'
)
p = re.compile(r'(\d+)..(\d+),?')
CDS = Database_Result['cds']
it = p.finditer(CDS)
start_end_list = [(int(match.group(1)), int(match.group(2)))
for match in it]
DNA_seq = Database_Result['dna_seq']
#Mark up the sequence with < > to locate start and end of CDS regions
DNA_list = list(DNA_seq)
offset = 0
for start, end in start_end_list:
DNA_list.insert((start - 1) + offset, "<")
offset += 1
DNA_list.insert((end - 1) + offset, ">")
offset += 1
DNA_str = ""
for elem in DNA_list:
DNA_str += elem
return (DNA_str)
def search_db(Search_Query):
Database_Result = dbapi.dict_entries(Search_Query)
return (Database_Result)