def merge_file(namefile_1, namefile_2, new_namefile):
file1 = FileUtils.open_text_r(namefile_1)
file2 = FileUtils.open_text_r(namefile_2)
new_file = FileUtils.open_text_a(new_namefile)
text_1 = file1.read()
text_2 = file2.read()
new_file.write(text_1)
new_file.write(text_2)
new_file.close()
def read_file(namefile):
f = FileUtils.open_text_r(namefile)
listfile = []
for line in f:
item = line.strip()
listfile.append(item)
return listfile
def change_header(path_input_file, path_ouptut_file, source=1, type_id=1):
file_input = FileUtils.open_text_r(path_input_file)
seq_file = file_input.read()
file_output = FileUtils.open_text_a(path_ouptut_file)
# Warning: Check that the file have the '>' char only at beginning of header lines and not in other points
# otherwise the split will occur in an incorrect way!
seq_file_list = seq_file.split('>')[1:]
for seq in seq_file_list:
lines = seq.split('\n')
header = lines[0]
Logger.get_instance().info(header)
# Ensembl
if source == 1:
new_header = '>' + header.split('|')[2] + '\n' # see Note
# Uniprot
elif source == 2:
diff_header = header.split(' ')[0]
# AC
if type_id == 1:
new_header = '>' + diff_header.split('|')[1] + '\n'
# ID
elif type_id == 2:
new_header = '>' + diff_header.split('|')[2] + '\n'
fasta = new_header + '\n'.join(lines[1:])
file_output.write(fasta)
file_output.close()
def output_reading(filename):
input_file = FileUtils.open_text_r(filename)
text_file = []
lines = input_file.readlines()
string = ''
for n, line in enumerate(lines):
if line[0:1] == '>' and n == 0:
string += line[1:]
elif line[0:1] != '>' and n != 0:
string += line
elif line[0:1] == '>' and n != 0:
# append in string format the output of one protein
text_file.append(string)
# reset the string variable and add the header
string = ''
string += line[1:]
else:
Logger.get_instance().warning(' Check this line : ' + line)
text_file.append(string)
return text_file
def domain_all_protein(domain_region_file):
file_domain = FileUtils.open_text_r(domain_region_file)
# Importation of Dictionary
dict_domain = pickle.load(file_domain)
return dict_domain
def domain_one_protein(domain_region_file, protname):
file_domain = FileUtils.open_text_r(domain_region_file)
# Importation of Dictionary
dict_domain = pickle.load(file_domain)
if protname in dict_domain:
domain_prot = dict_domain[protname]
return domain_prot
else:
Logger.get_instance().debug(" Protein without domains " + protname)
return []
def get_header(seq_obj, header_identifier=None, text=True):
if text == False:
fasta = FileUtils.open_text_r(seq_obj)
elif text == True:
fasta = seq_obj
HEADER = []
for line in fasta:
if line[0:1] == '>':
line = line.strip()
HEADER.append(line)
if header_identifier == None:
return HEADER
else:
for item in HEADER:
if header_identifier in item:
return item
def get_seq(seq_obj, header_identifier, text=True):
if text == False:
fasta = FileUtils.open_text_r(seq_obj)
elif text == True:
fasta = seq_obj
seq = ''
flag = 0
for n, line in enumerate(fasta):
line = line.strip()
if line[0:1] == '>' and flag == 0:
if header_identifier in line:
flag = 1
elif line[0:1] != '>' and flag == 1:
seq+=line
elif line[0:1] == '>' and flag == 1:
finalseq = seq
flag = 2
finalseq = seq
# The replace function is used in order to remove the star because the Ensembl sequences
# show the star at the end of sequence but if the sequences doesn't show the start anything happens
return finalseq.replace('*','')
def split_seq(file_sequences_path, path_output, start_header, end_header):
# Through the subprocess method the grep unix command gets the header of fasta file
#
header_dataset = subp.check_output(['grep', '>', file_sequences_path])
header = header_dataset.split('\n')
file_seq = FileUtils.open_text_r(file_sequences_path)
seq_obj = file_seq.readlines()
for i, term in enumerate(header):
prot = term[start_header:end_header]
Logger.get_instance().info(str(i + 1) + ' ' + prot)
# extraction of sequence from fasta file
prot_seq = InfoFasta.get_seq(seq_obj, prot)
# writing of sequence in a fasta file
fasta_seq = SeqToFasta.give_fasta(term, prot_seq)
file_out = FileUtils.open_text_w(path_output + prot + '.fasta')
file_out.write(fasta_seq)
file_out.close()