def make_dictionary(self):
Logger.get_instance().info(
" Creation of a dictionary for novel gene of dataset 2\
The dictionary structure is : \n \
{gene = [ isoform1, isoform2,...isoformN]}")
self.path_home = Constants.PATH_HOME
self.path_input_file = self.path_home + PropertyManager.get_instance(
).get_property(DataConstants.DOWNLOAD_DICTIONARY_INPUT_FILE_PROPERTY,
True)
self.dictionary_output_path = self.path_home + PropertyManager.get_instance(
).get_property(DataConstants.DOWNLOAD_DICTIONARY_OUTPUT_PATH_PROPERTY,
True)
self.output_file_path = self.dictionary_output_path + PropertyManager.get_instance(
).get_property(DataConstants.DOWNLOAD_DICTIONARY_FILE_OUTPUT_PROPERTY,
True)
dict_identifier = InfoFasta.make_dictionary(self.path_input_file)
self.dict_file = FileUtils.open_text_w(self.output_file_path)
pickle.dump(dict_identifier, self.dict_file)
Logger.get_instance().info(
" The creation of a dictionary is completed \n\n")
def dictionary_identifier(self):
Logger.get_instance().info(
" Creation of a dictionary for novel gene of dataset 2\
The dictionary structure is : \n \
{gene = [ isoform1, isoform2,...isoformN]}")
self.ensembl_path_output = Constants.PATH_HOME + PropertyManager.get_instance(
).get_property(DataConstants.ENSEMBL_OUTPUT_PATH_SEQUENCE_PROPERTY,
True)
self.ensembl_output_dataset2 = self.ensembl_path_output + PropertyManager.get_instance(
).get_property(DataConstants.ENSEMBL_FILE_SEQUENCES_2_PROPERTY, True)
self.dictionary_output = Constants.PATH_HOME + PropertyManager.get_instance(
).get_property(DataConstants.DICTIONARY_PATH_OUTPUT_PROPERTY, True)
self.dictionary_namefile = self.dictionary_output + PropertyManager.get_instance(
).get_property(DataConstants.DICTIONARY_NAME_FILE_PROPERTY, True)
dict_identifier = InfoFasta.make_dictionary(
self.ensembl_output_dataset2)
file_dict = FileUtils.open_text_w(self.dictionary_namefile)
pickle.dump(dict_identifier, file_dict)
Logger.get_instance().info(
" The creation of a dictionary for novel gene in dataset 2 is completed \n\n"
)
def iupred_analysis(self, fastafile, prot):
self.fastafile = fastafile
self.prot = prot
# Calling of IUPred command
iupred_out = subp.check_output([self.iupred_path+"iupred", self.fastafile, "long"])
# Prediction output file ( Prediction_protname.txt)
pred_file = FileUtils.open_text_w(self.path_output+'IUPred_' + self.prot + '.txt')
index_prediction = iupred_out.index('Prediction output')
iupred_out = iupred_out[index_prediction:]
iupred_out_list = iupred_out.split('\n')
new_iupred_out = []
new_iupred_out.append(iupred_out_list[0])
new_iupred_out.append(iupred_out_list[1])
for line in iupred_out_list[2:]:
new_line = []
for item in line.split(' '):
if item != '':
new_line.append(item)
new_line_string = '\t'.join(new_line)
new_iupred_out.append(new_line_string)
final_out = '\n'.join(new_iupred_out)
pred_file.write(final_out)
pred_file.close()
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()
def anchor_analysis(self, fastafile, motifslist, prot):
# Calling of anchor command
# anchor out contains the anchor output in text format
anchor_out = subp.check_output([
"perl", self.anchor_path + 'anchor.pl', fastafile, "-m", motifslist
])
# Definition of the section index of anchor output in order to get a specific section of anchor output
# Thereby in the next step it will be possible to write these sections in some file
index_bind_reg = anchor_out.index('Predicted binding regions')
index_motifs = anchor_out.index('Motifs')
index_pred_profile = anchor_out.index('Prediction profile output')
# The Anchor output can lack filtered regions section
if 'Filtered regions' in anchor_out:
index_filt_reg = anchor_out.index('Filtered regions')
else:
index_filt_reg = index_motifs
# ===============================================================================
# Files writing
# ===============================================================================
#
# Prediction binding regions file ( PBR_protname.txt)
# This section selects the Prediction binding region of anchor output
# The PBR section is split in lines and the '#\t' character is removed
#
pbr_out = anchor_out[index_bind_reg:index_filt_reg]
pbr_out_list = pbr_out.split('\n')
pbr = [line[2:] for line in pbr_out_list if line[0:2] == '#\t']
#
# When a protein lacks predicting binding region in the output file is written "None" then
# If the predicting binding regions are not in pbr_out the file writing is skipped
#
if 'None' in pbr_out:
Logger.get_instance().info(
"This protein doesn't contain predicted binding region (" +
prot + ')')
pass
elif 'None' not in pbr_out:
new_pbr_out = [line.replace(' ', '') for line in pbr]
pbr_file = FileUtils.open_text_w(self.path_output + 'PBR_' + prot +
'.txt')
pbr_file.write('\n'.join(new_pbr_out))
pbr_file.close()
#
# Found Motifs file (FMotifs_protname.txt)
#
fmotifs_out = anchor_out[index_motifs:index_pred_profile]
fmotifs_out_list = fmotifs_out.split('\n')
fmotifs = [line[2:] for line in fmotifs_out_list if line[0:2] == '#\t']
#
# When a protein lacks Motif in the output file is written "None" then
# If the Motif are not in fmotif_out the file writing is skipped
#
if 'None' in fmotifs_out:
Logger.get_instance().info(
"This protein doesn't contain any motifs (" + prot + ')')
pass
elif 'None' not in pbr_out:
new_fmotifs = [line.replace(' ', '') for line in fmotifs]
fmotifs_file = FileUtils.open_text_w(self.path_output +
'FMotifs_' + prot + '.txt')
fmotifs_file.write('\n'.join(new_fmotifs))
fmotifs_file.close()
#
# Prediction profile output (Pred_protname.txt)
# This section is always present in anchor output
#
pred_file = FileUtils.open_text_w(self.path_output + 'Pred_' + prot +
'.txt')
pred_out = anchor_out[index_pred_profile:]
string = '# Columns:\n# 1 - Amino acid number\n# 2 -\
One letter code\n# 3 - ANCHOR probability value\n# 4 - ANCHOR output\n#'
pred_out = pred_out.replace(string, '')
pred_out_list = pred_out.split('\n')
new_pred_out = [line.replace(' ', '') for line in pred_out_list]
final_out = '\n'.join(new_pred_out)
pred_file.write(final_out)
pred_file.close()