def get_column(table, index, start=None, end=None):
# Indexes check
if index > len(table[0]):
Logger.get_instance().error(" TableWrapper.get_column : the column index is greater then column number of table\n")
raise ParsingFileException(" TableWrapper.get_column : the column index is greater then column number of table\n")
if start != None and end != None:
if start == end:
Logger.get_instance().error(" TableWrapper.get_column : start and end indexes can't be equal\n")
raise ParsingFileException(" TableWrapper.get_column : start and end indexes can't be equal\n")
elif start > end:
Logger.get_instance().error(" TableWrapper.get_column : start index can't be greater than end index\n")
raise ParsingFileException(" TableWrapper.get_column : start index can't be greater than end index\n")
else:
Logger.get_instance().debug(" TableWrapper.get_column : start and end indexes are correct\n" +'start: '+str(start)+ ', end: '+str(end))
elif start != None and end == None:
Logger.get_instance().debug(" TableWrapper.get_column : start and end indexes are correct\n" +'start: '+str(start)+ ', end: '+str(end))
# in according to combination of index, start and end indexes the method returns
# a specific column
if start == None and end == None:
columns = zip(*table)
return list(columns[index])
elif start != None and end != None:
columns = zip(*table)
return list(columns[index][start:end])
elif start != None and end == None:
columns = zip(*table)
return list(columns[index][start:])
elif start == None and end != None:
columns = zip(*table)
return list(columns[index][0:end])
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 iupred_motifs(self):
Logger.get_instance().info( " .....Start of IUPred motifs analysis.....\n")
self.iupred_folder = self.path_home + PropertyManager.get_instance().get_property( DataConstants.MOTIFS_IUPRED_FOLDER_PROPERTY,True)
# Iupred Analysis at threshold value of 0.4
Timer.get_instance().step(" Start of IUPred motifs analysis - threshold = 0.4 \n")
self.threshold_1 = Constants.MOTIFS_THRESHOLD_1
self.output_folder_1 = self.path_home + PropertyManager.get_instance().get_property( DataConstants.MOTIFS_IUP_OUTPUT_FOLDER_1_PROPERTY, True)
GlobalOverlapRegionAnalysis.iupred_overlap_analysis(self.protein_list,self.iupred_folder, self.output_folder_1, self.threshold_1,
self.motif_folder,self.domain_region_file)
Timer.get_instance().step(" End of IUPred motifs analysis - threshold = 0.4 \n")
# Iupred Analysis at threshold value of 0.5
Timer.get_instance().step(" Start of IUPred motifs analysis - threshold = 0.5 \n")
self.threshold_2 = Constants.MOTIFS_THRESHOLD_2
self.output_folder_2 = self.path_home + PropertyManager.get_instance().get_property( DataConstants.MOTIFS_IUP_OUTPUT_FOLDER_2_PROPERTY, True)
GlobalOverlapRegionAnalysis.iupred_overlap_analysis(self.protein_list,self.iupred_folder, self.output_folder_2, self.threshold_2,
self.motif_folder,self.domain_region_file)
Timer.get_instance().step(" End of IUPred motifs analysis - threshold = 0.5 \n")
Logger.get_instance().info( " .....End of IUPred motifs analysis.....\n")
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 overlap_file_write(table_tool, output_folder, protein, toolname):
dict_filename = Constants.DICT_FILE_OUTPUT
filename_slim_region = dict_filename[toolname][
0] + protein + Constants.EXTENSION_TXT_FILE
filename_doamin_region = dict_filename[toolname][
1] + protein + Constants.EXTENSION_TXT_FILE
filepath_slim = output_folder + filename_slim_region
filepath_domain = output_folder + filename_doamin_region
title_slim_region = [[
Constants.SLIM_NAME, Constants.SLIM_REGION_COUNTER,
Constants.START_SLIM_REGION, Constants.END_SLIM_REGION,
Constants.TOOLNAME, Constants.TOOLNAME_REGION_COUNTER,
Constants.START_TOOL_REGION, Constants.END_TOOL_REGION,
Constants.OVERLAP_OUTCOME, Constants.OVERLAP_LENGTH
]]
table_slim_region = title_slim_region + table_tool[0]
table_domain_region = table_tool[1]
if table_tool[0] != []:
FileWriter.write_table(filepath_slim, table_slim_region)
else:
Logger.get_instance().debug(" The slim overlap file " +
filename_slim_region +
" has not been written")
if table_tool[1] != []:
FileWriter.write_table(filepath_domain, table_domain_region)
else:
Logger.get_instance().debug(" The domain overlap file " +
filename_doamin_region +
" has not been written\n\n")
def disordp_region(directory, disordp_file, protname):
filepath = directory + disordp_file
# the information about disordbp bind are memorized in a file containing information of many proteins
# this command allows to select the output information about one only protein (protname)
output_proteins = DisoRDPbind.output_reading(filepath)
proteins = [ line.split('\n')[0] for line in output_proteins]
if protname in proteins:
prot_selected = [ line for line in output_proteins if line.split('\n')[0]==protname ]
if 'WARNING:' in prot_selected[0]:
Logger.get_instance().warning( " This protein contains >=10000 residues\
(DisoRBDbind cannot predict the proteins with size >=10000) " + protname)
disordp_region_table = []
else:
# extraction of disordp regions
# the information are memorized in a table
dict_info = DisoRDPbind.fraction_calculation(prot_selected[0])
key_dictionary = Constants.KEY_DISORDP
# Table containing the anchor regions
disordp_table = dict_info[key_dictionary]
disordp_region_table = [ [int(line[2]), int(line[3])] for line in disordp_table]
else:
Logger.get_instance().warning(' This protein is not in DisoRDPbind prediction \
(DisoRBDbind cannot predict the proteins with size of 4 amino acids) ' + protname)
disordp_region_table = []
return disordp_region_table
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 read_properties(self, file_path):
Logger.get_instance().info("Reading properties from file : " +
file_path)
config_parser = ConfigParser()
config_parser.read(file_path)
for section in config_parser.sections():
options = config_parser.options(section)
for option in options:
try:
option = option.lower()
self.propertiesDict[option] = config_parser.get(
section, option)
if self.propertiesDict[option] == None:
raise RbpmotifException(
"PropertyManager.readProperties : Wrong property definition for key = "
+ option + " in section " + section + " of file " +
file_path)
except:
raise RbpmotifException(
"PropertyManager.readProperties : Abnormal property definition for key = "
+ option + " in section " + section + " of file " +
file_path)
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 delete_file(namefile):
try:
os.remove(namefile)
Logger.get_instance().info(" This file has been removed: " +
namefile)
except OSError:
Logger.get_instance().info(" Cannot remove : " + namefile)
def stop_chrono(self, message):
current_time = time.time()
step_duration = current_time - self.lastTime
total_duration = current_time - self.start_time
Logger.get_instance().info ( "Step duration : " + Timer.format_duration( step_duration))
Logger.get_instance().info ( "\n\nSTOP CHRONO : " + message + ". Total duration " + Timer.format_duration(total_duration))
self.lastTime = 0
self.start_time = 0
def del_column(table, index):
if index > len(table[0]):
Logger.get_instance().error(" TableWrapper.get_column : the column index is greater then column number of table\n")
raise ParsingFileException(" TableWrapper.get_column : the column index is greater then column number of table\n")
new_table = []
for row in table:
row.pop(index)
new_table.append(row)
return new_table
def open_text_a(path):
try:
file_handle = open(path, 'a')
except IOError as detail:
Logger.get_instance().critical\
("IOError: Unable to open " + path + " : " + str(detail))
exit()
return file_handle
def open_text_r(path):
try:
file_handle = open(path, 'r')
except IOError as ioe:
Logger.get_instance().critical\
("FileUtils.open_text_r : IOError: Unable to open '" + path + "' : " + str(ioe))
raise RbpmotifException(
"Unable to open file '" + path + "' : " + str(ioe), ioe)
return file_handle
def make_iupred_file(input_path, output_path, th_1, th_2, num_aa, dataset_type):
# initialization of file names
file_name_1 = dataset_type + '_IupredTable' + '_t1_'+ str(th_1) + '_t2_' + str(th_2) + '.txt'
file_name_2 = dataset_type + '_IupredRegion_' + str(th_1) + '.txt'
file_name_3 = dataset_type + '_IupredRegion_' + str(th_2) + '.txt'
num_aa_string = '('+ str(num_aa) +' AA)'
# Files opening and title string writing
file_1 = FileUtils.open_text_a(output_path + file_name_1)
file_2 = FileUtils.open_text_a(output_path + file_name_2)
file_3 = FileUtils.open_text_a(output_path + file_name_3)
header_file_table = ['Protein', 'Fraction '+ str(th_1), 'Fraction ' + str(th_2), 'Region N.' + num_aa_string +'th_'+ str(th_1) , 'Region N.'+ num_aa_string +'th_'+ str(th_2)]
header_file_region = ['Protein', 'N', 'Start', 'End', 'Region length']
header_string_table = '\t'.join(header_file_table)
header_file_region = '\t'.join(header_file_region)
file_1.write(header_string_table + '\n')
file_2.write(header_file_region + '\n')
file_3.write(header_file_region + '\n')
# This command allows to taken the file names of protein that you want analyze
list_file = subp.check_output(['ls', input_path])
list_file = list_file.split('\n')
if '' in list_file:
list_file.remove('')
# This section performs the iupred_string_info method (that calls also iupred_info method)
# for each protein file in list_file and simultaneously appends into files the output results
# in a tab format
for i, pred_file in enumerate(list_file):
i += 1
prot_id = pred_file.split('.')[0].split('_')[1]
Logger.get_instance().info( str(i) + ' ' + prot_id)
namefile = input_path + pred_file
out_string = Iupred.iupred_string_info(namefile, prot_id, th_1, th_2, num_aa)
string_file_1 = out_string[0]
string_file_2 = out_string[1]
string_file_3 = out_string[2]
file_1.write(string_file_1 + '\n')
file_2.write(string_file_2 + '\n')
file_3.write(string_file_3 + '\n')
file_1.close()
file_2.close()
file_3.close()
def check_length(feature, expected_length=None):
length = len(feature)
if expected_length is not None:
if length == expected_length:
Logger.get_instance().info(
" The length of dataset feature is that you expected\n")
else:
Logger.get_instance().info(
" The length of dataset feature isn't that you expected\n")
else:
pass
return length
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 global_anchor_analysis(file_motifs, input_folder, output_path):
# Description of execution
Logger.get_instance().info('Starting of Anchor Analysis')
# The list file is provided calling a unix command
try:
LIST_FILE = subp.check_output(['ls', input_folder])
LIST_FILE = LIST_FILE.split('\n')
if '' in LIST_FILE:
LIST_FILE.remove('')
for fastafile in LIST_FILE:
prot = fastafile.split('.fasta')[0]
Logger.get_instance().info(' Anchor Analysis: ' + prot)
file_input = input_folder + fastafile
# Anchor tool
A = Anchor(output_path)
A.anchor_analysis(file_input, file_motifs, prot)
except CalledProcessError as cpe:
Logger.get_instance().error(
'Anchor.global_anchor_analysis: Unable to execute listing of files in '
+ input_folder)
raise RbpmotifException(
'Anchor.global_anchor_analysis: Unable to execute listing of files in '
+ input_folder, cpe)
Logger.get_instance().info(" End of Anchor Analysis")
def whole_procedure():
dataset_type = PropertyManager.get_instance().get_property( DataConstants.MOTIFS_DATASET_TYPE_PROPERTY, True)
# start chrono
Timer.get_instance().start_chrono()
Logger.get_instance().info(" ........Start of " + dataset_type + " Motifs Analysis.....\n ")
motifs = MotifsAnalysis()
motifs.iupred_motifs()
motifs.anchor_motifs()
motifs.disordp_motifs()
Timer.get_instance().stop_chrono(" End of " + dataset_type + " Motifs Analysis")
def isoform_sequences(self):
Logger.get_instance().info(
" Starting the random selection of isoforms with same length \n")
Logger.get_instance().info(
" The following headers are the proteins randomly selected \n")
self.path_output_longest = Constants.PATH_HOME + PropertyManager.get_instance(
).get_property(DataConstants.LONGEST_PATH_OUTPUT_PROPERTY, True)
self.path_file_isoform = self.path_output_longest + PropertyManager.get_instance(
).get_property(DataConstants.ISOFORM_FILE_PROPERTY, True)
self.path_file_selected_isoform = self.path_output_longest + PropertyManager.get_instance(
).get_property(DataConstants.RANDOM_ISOFORM_SEQ_PROPERTY, True)
# The headers of a Isoform fasta file are taken by InfoFasta class
# You make sure that the arg text is equal to False because the input object is a file and not a list
self.headers = InfoFasta.get_header(self.path_file_isoform, text=False)
# Extraction of genes form headers line
# This vector contains double gene because the file contains some isoform of the same gene
gene_isoform = []
for header in self.headers:
gene = header[1:16]
gene_isoform.append(gene)
# gene set creation
unique_gene = set(gene_isoform)
# This for loop flows on the unique gene
#
random_header = []
old_num_isoform = 0
for gene in unique_gene:
# For each gene counts how many isoform has
num_isoform = gene_isoform.count(gene)
item = range(0, num_isoform)
# Select one isoform randomly
sel = random.choice(item)
# The header selected randomly are stored in array
random_header.append(self.headers[old_num_isoform:old_num_isoform +
num_isoform][sel])
old_num_isoform = old_num_isoform + num_isoform
self.file_random_seq = FileUtils.open_text_a(
self.path_file_selected_isoform)
# The sequences corresponding to header selected are extracted from isoform file
for header in random_header:
Logger.get_instance().info('Header selected : ' + header)
identifier = header[33:48]
sequence = InfoFasta.get_seq(self.path_file_isoform, identifier)
fasta_seq = SeqToFasta.give_fasta(header, sequence)
self.file_random_seq.write(fasta_seq)
Logger.get_instance().info(" End of selection random sequences \n ")
def make_dictionary(namefile):
headers = InfoFasta.get_header(namefile)
dict_header = {}
for line in headers:
line = line[1:]
ids = line.split('|')
if len(ids) != 2:
if ids[0] in dict_header:
dict_header[ids[0]].append(ids[2])
else:
dict_header[ids[0]] = [ids[2]]
else:
Logger.get_instance().info( " This gene has a protein sequence unavailable : " + line)
pass
return dict_header
def anchor_motifs(self):
Logger.get_instance().info( " .....Start of IUPred motifs analysis.....\n")
self.anchor_folder = self.path_home + PropertyManager.get_instance().get_property( DataConstants.MOTIFS_ANCHOR_FOLDER_PROPERTY, True)
self.anchor_output_folder = self.path_home + PropertyManager.get_instance().get_property( DataConstants.MOTIFS_ANCHOR_OUTPUT_FOLDER_PROPERTY, True)
Timer.get_instance().step(" Start of ANCHOR motifs analysis \n")
GlobalOverlapRegionAnalysis.anchor_overlap_analysis(self.protein_list,self.anchor_folder,self.anchor_output_folder,
self.motif_folder,self.domain_region_file)
Timer.get_instance().step(" End of IUPred motifs analysis \n")
Logger.get_instance().info( " .....End of ANCHOR motifs analysis.....\n")
def whole_procedure():
# start chrono
Timer.get_instance().start_chrono()
Logger.get_instance().info("Start of the sequences extraction.....\n ")
D = DownloadEnsemblSeq()
#D.download_product_gene_seq()
#D.make_dictionary()
#D.get_longest_seq()
#D.isoform_sequences()
#D.merger_sequences()
Timer.get_instance().stop_chrono(' End of the sequences extraction')
def split_dataset(self):
Logger.get_instance().info( " Division of Dataset in many fasta file each containing one protein sequence")
self.path_home = Constants.PATH_HOME
self.split_path_input = self.path_home + PropertyManager.get_instance().get_property( DataConstants.SPLIT_PATH_INPUT_PROPERTY, True)
self.split_file_fasta = self.split_path_input + PropertyManager.get_instance().get_property( DataConstants.SPLIT_DATASET_PROPERTY, True)
self.split_path_output = Constants.PATH_HOME + PropertyManager.get_instance().get_property( DataConstants.SPLIT_PATH_OUTPUT_PROPERTY, True)
self.split_start_index = PropertyManager.get_instance().get_property( DataConstants.SPLIT_START_HEADER_PROPERTY, True)
self.split_end_index = PropertyManager.get_instance().get_property( DataConstants.SPLIT_END_HEADER_PROPERTY, True)
SplitSeq.split_seq( self.split_file_fasta, self.split_path_output, int(self.split_start_index), int(self.split_end_index))
Logger.get_instance().info( " The dataset has been split in many fasta files ")
def whole_procedure():
# start chrono
Timer.get_instance().start_chrono()
Logger.get_instance().info("Start of Disorder Analysis.....\n ")
disorder = DisorderAnalysis()
#disorder.change_header()
#disorder.split_dataset()
#disorder.anchor_analysis()
#disorder.iupred_analysis()
#disorder.analysis_tools_output()
#disorder.disordpbind_analysis()
#disorder.particular_analysis()
Timer.get_instance().stop_chrono(' End of Disorder Analysis')
def make_disordp_file(input_path, output_path, binding_partner, num_aa,
dataset_type):
# initialization of file names
file_name_1 = dataset_type + '_DisoRDPbindTable.txt'
file_name_2 = dataset_type + '_DisoRDPbindRegion.txt'
num_aa_string = '(' + str(num_aa) + ' AA)'
# Files opening and title string writing
file_1 = FileUtils.open_text_a(output_path + file_name_1)
file_2 = FileUtils.open_text_a(output_path + file_name_2)
header_file_table = [
'Protein', 'Fraction ', 'Region N.' + num_aa_string
]
header_file_region = ['Protein', 'N', 'Start', 'End', 'Region length']
header_string_table = '\t'.join(header_file_table)
header_file_region = '\t'.join(header_file_region)
file_1.write(header_string_table + '\n')
file_2.write(header_file_region + '\n')
# Reading of DisoRDPbind output file
protein_output_list = DisoRDPbind.output_reading(input_path)
for n, output in enumerate(protein_output_list):
if 'WARNING:' in output:
prot = output.split('\n')[0]
Logger.get_instance().warning(
str(n + 1) + "\n This protein contains >=10000 residues\
(DisoRBDbind cannot predict the proteins with size >=10000) " + prot)
else:
Logger.get_instance().info(str(n + 1))
results = DisoRDPbind.disordp_string_info(
output, binding_partner, num_aa)
string_file_1 = results[0]
string_file_2 = results[1]
file_1.write(string_file_1 + '\n')
file_2.write(string_file_2 + '\n')
file_1.close()
file_2.close()
def disordp_motifs(self):
Logger.get_instance().info( " .....Start of DisoRDPbind motifs analysis.....\n")
self.disordp_folder = self.path_home + PropertyManager.get_instance().get_property( DataConstants.MOTIFS_DISORDP_FOLDER_PROPERTY, True)
self.disordp_output_folder = self.path_home + PropertyManager.get_instance().get_property( DataConstants.MOTIFS_DISORDP_OUTPUT_FOLDER_PROPERTY, True)
self.filename = PropertyManager.get_instance().get_property( DataConstants.MOTIFS_DISORDP_FILE_PROPERTY,True)
Timer.get_instance().step(" Start of DisoRDPbind motifs analysis \n")
GlobalOverlapRegionAnalysis.disordp_overlap_analysis(self.protein_list, self.disordp_folder, self.filename, self.motif_folder,
self.domain_region_file,self.disordp_output_folder)
Timer.get_instance().step(" End of DisoRDPbind motifs analysis \n")
Logger.get_instance().info( " .....End of DisoRDPbind motifs analysis.....\n")
def inv_column(table, index1, index2):
if index1 > len(table[0]) or index2 > len(table[0]):
Logger.get_instance().error(" TableWrapper.get_column : the column index is greater then column number of table\n")
raise ParsingFileException(" TableWrapper.get_column : the column index is greater then column number of table\n")
new_columns = []
new_table = []
num = len(table[0])
for i in range(num):
if i != index1 and i != index2:
new_columns.append(TableWrapper.get_column(table,i))
elif i == index1:
new_columns.append(TableWrapper.get_column(table, index2))
elif i == index2:
new_columns.append(TableWrapper.get_column(table, index1))
for item in zip(*new_columns):
item = list(item)
new_table.append(item)
return new_table
def anchor_overlap_analysis(protein_list, anchor_folder, output_folder,
motif_folder, domain_region_file):
toolname = Constants.ANCHOR_TOOL
for num, protein in enumerate(protein_list):
prot_counter = num + 1
result = math.fmod(prot_counter, 100)
if result == 0.0:
Logger.get_instance().info(' ' + str(prot_counter) +
"th Protein analyzed: " + protein)
# This line takes the iupred region of a protein
anchor_region = OverlapMotifsRegions.anchor_region(
anchor_folder, protein)
table_anchor = OverlapMotifsRegions.overlap_analysis(
protein, anchor_region, toolname, motif_folder,
domain_region_file)
# table Writing
GlobalOverlapRegionAnalysis.overlap_file_write(
table_anchor, output_folder, protein, toolname)
def download_product_gene_seq(self):
Logger.get_instance().info(
" Start of sequences download from Ensembl..")
self.path_home = Constants.PATH_HOME
self.gene_list_input = self.path_home + PropertyManager.get_instance(
).get_property(DataConstants.DOWNLOAD_ENSEMBL_FILE_INPUT_LIST_PROPERTY,
True)
self.ensembl_seq_output = self.path_home + PropertyManager.get_instance(
).get_property(DataConstants.DOWNLOAD_ENSEMBL_FILE_OUPUT_SEQ_PROPERTY,
True)
self.type_query = PropertyManager.get_instance().get_property(
DataConstants.DOWNLOAD_ENSEMBL_TYPE_QUERY_PROPERTY, True)
Ensembl.list_get_seq(self.gene_list_input,
int(self.type_query),
path_output=self.ensembl_seq_output)
Logger.get_instance().info(" End of sequences download from Ensembl..")
