def populate_combobox_process_type(self):
'''
Populate data in "combobox_process_type".
'''
# clear the value selected in the combobox
self.wrapper_process_type.set('')
# initialize the process type list
process_type_list = []
# get the dictionary of TOA configuration.
toa_config_dict = xtoa.get_toa_config_dict()
# get the process type list
subdir_list = [
subdir for subdir in os.listdir(toa_config_dict['RESULT_DIR'])
if os.path.isdir(
os.path.join(toa_config_dict['RESULT_DIR'], subdir))
]
for subdir in subdir_list:
process_type_list.append(subdir)
# check if there are any process type
if process_type_list == []:
message = 'There is not any run.'
tkinter.messagebox.showwarning(
f'{xlib.get_short_project_name()} - {self.head}', message)
return
# load the names of process types
self.combobox_process_type['values'] = sorted(process_type_list)
def input_result_dataset_id(experiment_id, app_list):
'''
Input a result dataset identification.
'''
# initialize the control variable
OK = True
# get the dictionary of TOA configuration.
toa_config_dict = xtoa.get_toa_config_dict()
# initialize the result dataset identification
result_dataset_id = ''
# initialize the result dataset list
result_dataset_id_list = []
# get the result dataset identifications of the experiment
experiment_dir = f'''{toa_config_dict['RESULT_DIR']}/{experiment_id}'''
subdir_list = sorted([
subdir for subdir in os.listdir(experiment_dir)
if os.path.isdir(os.path.join(experiment_dir, subdir))
])
for subdir in subdir_list:
for app in app_list:
if app == xlib.get_all_applications_selected_code(
) or subdir.startswith(app):
result_dataset_id_list.append(subdir)
break
# print the result dataset identifications in the clusters
if result_dataset_id_list != []:
result_dataset_id_list_text = str(result_dataset_id_list).strip(
'[]').replace('\'', '')
print(
f'dataset ids existing in {experiment_id}: {result_dataset_id_list_text} ...'
)
else:
OK = False
# input and check the result dataset identification
if OK:
while result_dataset_id == '':
result_dataset_id = input('... Enter the dataset id: ')
if result_dataset_id not in result_dataset_id_list:
print(f'*** ERROR: {result_dataset_id} does not exist.')
result_dataset_id = ''
# return the result dataset identification
return result_dataset_id
def form_view_result_log():
'''
View the log of an experiment/process result.
'''
# initialize the control variable
OK = True
# print the header
clib.clear_screen()
clib.print_headers_with_environment(
'Logs - View an experiment/process result log')
# get the experiment identification
if OK:
experiment_id = cinputs.input_experiment_id()
if experiment_id == '':
print('WARNING: There is not any experiment/process data.')
OK = False
# get the result_dataset identification
if OK:
result_dataset_id = cinputs.input_result_dataset_id(
experiment_id, xlib.get_all_applications_selected_code())
if result_dataset_id == '':
print(
f'WARNING: The experiment/process {experiment_id} does not have result datasets.'
)
OK = False
# get the dictionary of TOA configuration.
if OK:
toa_config_dict = xtoa.get_toa_config_dict()
# get the log file name and build local and cluster paths
if OK:
log_file = f'{toa_config_dict["RESULT_DIR"]}/{experiment_id}/{result_dataset_id}/{xlib.get_run_log_file()}'
# view the log file
if OK:
text = 'Logs - View an experiment/process log'
OK = clib.view_file(log_file, text)
# show continuation message
input('Press [Intro] to continue ...')
def input_experiment_id():
'''
Input an experiment/process identification.
'''
# initialize the control variable
OK = True
# initialize the experiment/process identification
experiment_id = ''
# initialize the experiment/process identification list
experiment_id_list = []
# get the dictionary of TOA configuration.
toa_config_dict = xtoa.get_toa_config_dict()
# get the experiment/process identifications
subdir_list = [
subdir for subdir in os.listdir(toa_config_dict['RESULT_DIR'])
if os.path.isdir(os.path.join(toa_config_dict['RESULT_DIR'], subdir))
]
for subdir in subdir_list:
experiment_id_list.append(subdir)
# print the experiment/process identifications in the clusters
if experiment_id_list != []:
experiment_id_list_text = str(experiment_id_list).strip('[]').replace(
'\'', '')
print(
f'Experiment/process ids existing: {experiment_id_list_text} ...')
else:
OK = False
# input and check the experiment/process identification
if OK:
while experiment_id == '':
experiment_id = input('... Enter the experiment/process id: ')
if experiment_id not in experiment_id_list:
print(f'*** ERROR: {experiment_id} does not exist.')
experiment_id = ''
# return the experiment/process identification
return experiment_id
def execute(self, event=None):
'''
Execute the list the result logs in the cluster.
'''
# if "button_execute" is disabled, exit function
if str(self.button_execute['state']) == 'disabled':
return
# check inputs
OK = self.check_inputs()
if not OK:
message = 'Some input values are not OK.'
tkinter.messagebox.showerror(
f'{xlib.get_short_project_name()} - {self.head}', message)
# get the dictionary of TOA configuration.
if OK:
toa_config_dict = xtoa.get_toa_config_dict()
# get the run dictionary
if OK:
process_type_dir = f'{toa_config_dict["RESULT_DIR"]}/{self.wrapper_process_type.get()}'
subdir_list = [
subdir for subdir in os.listdir(process_type_dir)
if os.path.isdir(os.path.join(process_type_dir, subdir))
]
result_dataset_dict = {}
for subdir in subdir_list:
result_dataset_id = subdir
try:
pattern = r'^(.+)\-(.+)\-(.+)$'
mo = re.search(pattern, result_dataset_id)
bioinfo_app_code = mo.group(1).strip()
yymmdd = mo.group(2)
hhmmss = mo.group(3)
date = f'20{yymmdd[:2]}-{yymmdd[2:4]}-{yymmdd[4:]}'
time = f'{hhmmss[:2]}:{hhmmss[2:4]}:{hhmmss[4:]}'
except:
bioinfo_app_code = 'xxx'
date = '0000-00-00'
time = '00:00:00'
if result_dataset_id.startswith(xlib.get_blastplus_code() +
'-'):
bioinfo_app_name = xlib.get_blastplus_name()
elif result_dataset_id.startswith(xlib.get_diamond_code() +
'-'):
bioinfo_app_name = xlib.get_diamond_name()
elif result_dataset_id.startswith(
xlib.get_entrez_direct_code() + '-'):
bioinfo_app_name = xlib.get_entrez_direct_name()
elif result_dataset_id.startswith(xlib.get_miniconda3_code() +
'-'):
bioinfo_app_name = xlib.get_miniconda3_name()
elif result_dataset_id.startswith(xlib.get_r_code() + '-'):
bioinfo_app_name = xlib.get_r_name()
elif result_dataset_id.startswith(
xlib.get_toa_process_download_basic_data_code() + '-'):
bioinfo_app_name = xlib.get_toa_process_download_basic_data_name(
)
elif result_dataset_id.startswith(
xlib.get_toa_process_download_dicots_04_code() + '-'):
bioinfo_app_name = xlib.get_toa_process_download_dicots_04_name(
)
elif result_dataset_id.startswith(
xlib.get_toa_process_download_gene_code() + '-'):
bioinfo_app_name = xlib.get_toa_process_download_gene_name(
)
elif result_dataset_id.startswith(
xlib.get_toa_process_download_go_code() + '-'):
bioinfo_app_name = xlib.get_toa_process_download_go_name()
elif result_dataset_id.startswith(
xlib.get_toa_process_download_gymno_01_code() + '-'):
bioinfo_app_name = xlib.get_toa_process_download_gymno_01_name(
)
elif result_dataset_id.startswith(
xlib.get_toa_process_download_interpro_code() + '-'):
bioinfo_app_name = xlib.get_toa_process_download_interpro_name(
)
elif result_dataset_id.startswith(
xlib.get_toa_process_download_monocots_04_code() +
'-'):
bioinfo_app_name = xlib.get_toa_process_download_monocots_04_name(
)
elif result_dataset_id.startswith(
xlib.get_toa_process_download_taxonomy_code() + '-'):
bioinfo_app_name = xlib.get_toa_process_download_taxonomy_name(
)
elif result_dataset_id.startswith(
xlib.
get_toa_process_gilist_viridiplantae_nucleotide_gi_code(
) + '-'):
bioinfo_app_name = xlib.get_toa_process_gilist_viridiplantae_nucleotide_gi_name(
)
elif result_dataset_id.startswith(
xlib.
get_toa_process_gilist_viridiplantae_protein_gi_code()
+ '-'):
bioinfo_app_name = xlib.get_toa_process_gilist_viridiplantae_protein_gi_name(
)
elif result_dataset_id.startswith(
xlib.get_toa_process_load_basic_data_code() + '-'):
bioinfo_app_name = xlib.get_toa_process_load_basic_data_name(
)
elif result_dataset_id.startswith(
xlib.get_toa_process_load_dicots_04_code() + '-'):
bioinfo_app_name = xlib.get_toa_process_load_dicots_04_name(
)
elif result_dataset_id.startswith(
xlib.get_toa_process_load_gene_code() + '-'):
bioinfo_app_name = xlib.get_toa_process_load_gene_name()
elif result_dataset_id.startswith(
xlib.get_toa_process_load_go_code() + '-'):
bioinfo_app_name = xlib.get_toa_process_load_go_name()
elif result_dataset_id.startswith(
xlib.get_toa_process_load_gymno_01_code() + '-'):
bioinfo_app_name = xlib.get_toa_process_load_gymno_01_name(
)
elif result_dataset_id.startswith(
xlib.get_toa_process_load_interpro_code() + '-'):
bioinfo_app_name = xlib.get_toa_process_load_interpro_name(
)
elif result_dataset_id.startswith(
xlib.get_toa_process_load_monocots_04_code() + '-'):
bioinfo_app_name = xlib.get_toa_process_load_monocots_04_name(
)
elif result_dataset_id.startswith(
xlib.get_toa_process_merge_annotations_code() + '-'):
bioinfo_app_name = xlib.get_toa_process_merge_annotations_name(
)
elif result_dataset_id.startswith(
xlib.get_toa_process_nr_blastplus_db_code() + '-'):
bioinfo_app_name = xlib.get_toa_process_nr_blastplus_db_name(
)
elif result_dataset_id.startswith(
xlib.get_toa_process_nr_diamond_db_code() + '-'):
bioinfo_app_name = xlib.get_toa_process_nr_diamond_db_name(
)
elif result_dataset_id.startswith(
xlib.get_toa_process_nt_blastplus_db_code() + '-'):
bioinfo_app_name = xlib.get_toa_process_nt_blastplus_db_name(
)
elif result_dataset_id.startswith(
xlib.get_toa_process_pipeline_aminoacid_code() + '-'):
bioinfo_app_name = xlib.get_toa_process_pipeline_aminoacid_name(
)
elif result_dataset_id.startswith(
xlib.get_toa_process_pipeline_nucleotide_code() + '-'):
bioinfo_app_name = xlib.get_toa_process_pipeline_nucleotide_name(
)
elif result_dataset_id.startswith(
xlib.get_toa_process_proteome_dicots_04_code() + '-'):
bioinfo_app_name = xlib.get_toa_process_proteome_dicots_04_name(
)
elif result_dataset_id.startswith(
xlib.get_toa_process_proteome_gymno_01_code() + '-'):
bioinfo_app_name = xlib.get_toa_process_proteome_gymno_01_name(
)
elif result_dataset_id.startswith(
xlib.get_toa_process_proteome_monocots_04_code() +
'-'):
bioinfo_app_name = xlib.get_toa_process_proteome_monocots_04_name(
)
elif result_dataset_id.startswith(
xlib.get_toa_process_proteome_refseq_plant_code() +
'-'):
bioinfo_app_name = xlib.get_toa_process_proteome_refseq_plant_name(
)
elif result_dataset_id.startswith(
xlib.get_toa_process_rebuild_toa_database_code() +
'-'):
bioinfo_app_name = xlib.get_get_toa_process_rebuild_toa_database_name(
)
elif result_dataset_id.startswith(
xlib.get_toa_process_recreate_toa_database_code() +
'-'):
bioinfo_app_name = xlib.get_get_toa_process_recreate_toa_database_name(
)
elif result_dataset_id.startswith(
xlib.get_transdecoder_code() + '-'):
bioinfo_app_name = xlib.get_transdecoder_name()
else:
bioinfo_app_name = 'xxx'
status_ok = os.path.isfile(
xlib.get_status_ok(os.path.join(process_type_dir, subdir)))
status_wrong = os.path.isfile(
xlib.get_status_wrong(
os.path.join(process_type_dir, subdir)))
if status_ok and not status_wrong:
status = 'OK'
elif not status_ok and status_wrong:
status = 'wrong'
elif not status_ok and not status_wrong:
status = 'not finished'
elif status_ok and status_wrong:
status = 'undetermined'
key = f'{bioinfo_app_name}-{result_dataset_id}'
result_dataset_dict[key] = {
'process_type': self.wrapper_process_type.get(),
'bioinfo_app': bioinfo_app_name,
'result_dataset_id': result_dataset_id,
'date': date,
'time': time,
'status': status
}
# check if there are any nodes running
if OK:
if result_dataset_dict == {}:
message = 'There is not any run.'
tkinter.messagebox.showwarning(
f'{xlib.get_short_project_name()} - {self.head}', message)
# build the data list
if OK:
data_list = [
'process_type', 'bioinfo_app', 'result_dataset_id', 'date',
'time', 'status'
]
# build the data dictionary
if OK:
data_dict = {}
data_dict['process_type'] = {
'text': 'Process type',
'width': 180,
'alignment': 'left'
}
data_dict['bioinfo_app'] = {
'text': 'Bioinfo app / Utility',
'width': 340,
'alignment': 'left'
}
data_dict['result_dataset_id'] = {
'text': 'Result dataset',
'width': 225,
'alignment': 'left'
}
data_dict['date'] = {
'text': 'Date',
'width': 95,
'alignment': 'right'
}
data_dict['time'] = {
'text': 'Time',
'width': 75,
'alignment': 'right'
}
data_dict['status'] = {
'text': 'Status',
'width': 90,
'alignment': 'left'
}
# create the dialog Table to show the nodes running
if OK:
dialog_table = gdialogs.DialogTable(
self,
f'Runs in {xlib.get_result_dir()}/{self.wrapper_process_type.get()}',
400, 1030, data_list, data_dict, result_dataset_dict,
sorted(result_dataset_dict.keys()), 'view_result_logs',
['revisar'])
self.wait_window(dialog_table)
# close the form
if OK:
self.close()
def form_view_phylogenic_data_frecuency(stats_code):
'''
View the frecuency distribution of phylogenic data.
'''
# initialize the control variable
OK = True
# assign the text of the "name"
if stats_code == 'species':
name = 'Species - Frequency distribution'
elif stats_code == 'family':
name = 'Family - Frequency distribution'
elif stats_code == 'phylum':
name = 'Phylum - Frequency distribution'
elif stats_code == 'namespace':
name = 'GO - Frequency distribution per namespace'
# print the header
clib.clear_screen()
clib.print_headers_with_environment(f'Statistics - {name} data')
# get the pipeline dataset identification
app_list = [
xlib.get_toa_process_pipeline_nucleotide_code(),
xlib.get_toa_process_pipeline_aminoacid_code(),
xlib.get_toa_process_merge_annotations_code()
]
pipeline_dataset_id = cinputs.input_result_dataset_id(
xlib.get_toa_result_pipeline_dir(), app_list)
if pipeline_dataset_id == '':
print(
'WARNING: There are not any annotation pipeline result datasets.')
OK = False
# build distribution dictionary
if OK:
# initialize the distribution dictionary
distribution_dict = {}
# get the dictionary of TOA configuration
toa_config_dict = xtoa.get_toa_config_dict()
# get the statistics file path
stats_file = f'{toa_config_dict["RESULT_DIR"]}/{xlib.get_toa_result_pipeline_dir()}/{pipeline_dataset_id}/{toa_config_dict["STATS_SUBDIR_NAME"]}/{stats_code}-{toa_config_dict["STATS_BASE_NAME"]}.csv'
# open the statistics file
if stats_file.endswith('.gz'):
try:
stats_file_id = gzip.open(stats_file,
mode='rt',
encoding='iso-8859-1',
newline='\n')
except Exception as e:
raise xlib.ProgramException('F002', stats_file)
else:
try:
stats_file_id = open(stats_file,
mode='r',
encoding='iso-8859-1',
newline='\n')
except Exception as e:
raise xlib.ProgramException('F001', stats_file)
# initialize the record counter
record_counter = 0
# initialize the header record control
header_record = True
# read the first record
record = stats_file_id.readline()
# while there are records
while record != '':
# add 1 to the record counter
record_counter += 1
# process the header record
if header_record:
header_record = False
# process data records
else:
# extract data
# record format: "stats_code_id";"all_count";"first_hsp_count";"min_evalue_count"
data_list = []
begin = 0
for end in [i for i, chr in enumerate(record) if chr == ';']:
data_list.append(record[begin:end].strip('"'))
begin = end + 1
data_list.append(record[begin:].strip('\n').strip('"'))
try:
id = data_list[0]
all_count = data_list[1]
first_hsp_count = data_list[2]
min_evalue_count = data_list[3]
except Exception as e:
raise xlib.ProgramException('F006',
os.path.basename(stats_file),
record_counter)
# add dato to the dictionary
distribution_dict[id] = {
'id': id,
'all_count': all_count,
'first_hsp_count': first_hsp_count,
'min_evalue_count': min_evalue_count
}
# read the next record
record = stats_file_id.readline()
# print the distribution
if OK:
print(xlib.get_separator())
if distribution_dict == {}:
print('*** WARNING: There is not any distribution.')
else:
# set data width
id_width = 50
all_count_width = 11
first_hsp_count_width = 11
min_evalue_count_width = 11
# set line template
line_template = '{0:' + str(id_width) + '} {1:' + str(
all_count_width) + '} {2:' + str(
first_hsp_count_width) + '} {3:' + str(
min_evalue_count_width) + '}'
# print header
print(
line_template.format(stats_code.capitalize(), 'All',
'First HSP', 'Min e-value'))
print(
line_template.format('=' * id_width, '=' * all_count_width,
'=' * first_hsp_count_width,
'=' * min_evalue_count_width))
# print detail lines
for key in sorted(distribution_dict.keys()):
print(
line_template.format(
distribution_dict[key]['id'],
distribution_dict[key]['all_count'],
distribution_dict[key]['first_hsp_count'],
distribution_dict[key]['min_evalue_count']))
# show continuation message
print(xlib.get_separator())
input('Press [Intro] to continue ...')
def form_view_dataset_data_frecuency():
'''
View the frecuency distribution of annotation dataset data.
'''
# initialize the control variable
OK = True
# print the header
clib.clear_screen()
clib.print_headers_with_environment(
'Statistics - Annotation datasets - Frequency distribution data')
# get the pipeline dataset identification
app_list = [
xlib.get_toa_process_pipeline_nucleotide_code(),
xlib.get_toa_process_pipeline_aminoacid_code()
]
pipeline_dataset_id = cinputs.input_result_dataset_id(
xlib.get_toa_result_pipeline_dir(), app_list)
if pipeline_dataset_id == '':
print(
'WARNING: There are not any annotation pipeline result datasets.')
OK = False
# build distribution dictionary
if OK:
# initialize the distribution dictionary
distribution_dict = {}
# get the dictionary of TOA configuration
toa_config_dict = xtoa.get_toa_config_dict()
# get the statistics file path
stats_file = f'{toa_config_dict["RESULT_DIR"]}/{xlib.get_toa_result_pipeline_dir()}/{pipeline_dataset_id}/{toa_config_dict["STATS_SUBDIR_NAME"]}/dataset-{toa_config_dict["STATS_BASE_NAME"]}.csv'
# open the statistics file
if stats_file.endswith('.gz'):
try:
stats_file_id = gzip.open(stats_file,
mode='rt',
encoding='iso-8859-1',
newline='\n')
except Exception as e:
raise xlib.ProgramException('F002', stats_file)
else:
try:
stats_file_id = open(stats_file,
mode='r',
encoding='iso-8859-1',
newline='\n')
except Exception as e:
raise xlib.ProgramException('F001', stats_file)
# initialize the record counter
record_counter = 0
# initialize the header record control
header_record = True
# read the first record
record = stats_file_id.readline()
# while there are records
while record != '':
# add 1 to the record counter
record_counter += 1
# process the header record
if header_record:
header_record = False
# process data records
else:
# extract data
# record format: "dataset_name";"annotated_seq_count";"remained_seq_count"
data_list = []
begin = 0
for end in [i for i, chr in enumerate(record) if chr == ';']:
data_list.append(record[begin:end].strip('"'))
begin = end + 1
data_list.append(record[begin:].strip('\n').strip('"'))
try:
dataset_name = data_list[0]
annotated_seq_count = data_list[1]
remained_seq_count = data_list[2]
except Exception as e:
raise xlib.ProgramException('F006',
os.path.basename(stats_file),
record_counter)
# add dato to the dictionary
distribution_dict[record_counter] = {
'dataset_name': dataset_name,
'annotated_seq_count': annotated_seq_count,
'remained_seq_count': remained_seq_count
}
# read the next record
record = stats_file_id.readline()
# print the distribution
if OK:
print(xlib.get_separator())
if distribution_dict == {}:
print('*** WARNING: There is not any distribution.')
else:
# set data width
dataset_name_width = 19
annotated_seq_count_width = 14
remained_seq_count_width = 14
# set line template
line_template = '{0:' + str(dataset_name_width) + '} {1:' + str(
annotated_seq_count_width) + '} {2:' + str(
remained_seq_count_width) + '}'
# print header
print(
line_template.format('Dataset', 'Annotated seqs',
'Remained seqs'))
print(
line_template.format('=' * dataset_name_width,
'=' * annotated_seq_count_width,
'=' * remained_seq_count_width))
# print detail lines
for key in sorted(distribution_dict.keys()):
print(
line_template.format(
distribution_dict[key]['dataset_name'],
distribution_dict[key]['annotated_seq_count'],
distribution_dict[key]['remained_seq_count']))
# show continuation message
print(xlib.get_separator())
input('Press [Intro] to continue ...')
def form_view_x_per_y_data(stats_code):
'''
View the x per y data.
'''
# initialize the control variable
OK = True
# assign the text of the "name"
if stats_code == 'hit_per_hsp':
name = '# HITs per # HSPs'
elif stats_code == 'seq_per_go':
name = '# sequences per # GO terms'
elif stats_code == 'seq_per_ec':
name = '# sequences per # EC ids'
elif stats_code == 'seq_per_interpro':
name = '# sequences per # InterPro ids'
elif stats_code == 'seq_per_kegg':
name = '# sequences per # KEGG ids'
elif stats_code == 'seq_per_mapman':
name = '# sequences per # MapMan ids'
elif stats_code == 'seq_per_metacyc':
name = '# sequences per # MetaCyc ids'
# print the header
clib.clear_screen()
clib.print_headers_with_environment(f'Statistics - {name} data')
# get the pipeline dataset identification
if stats_code == 'hit_per_hsp':
app_list = [
xlib.get_toa_process_pipeline_nucleotide_code(),
xlib.get_toa_process_pipeline_aminoacid_code()
]
else:
app_list = [
xlib.get_toa_process_pipeline_nucleotide_code(),
xlib.get_toa_process_pipeline_aminoacid_code(),
xlib.get_toa_process_merge_annotations_code()
]
pipeline_dataset_id = cinputs.input_result_dataset_id(
xlib.get_toa_result_pipeline_dir(), app_list)
if pipeline_dataset_id == '':
print(
'WARNING: There are not any annotation pipeline result datasets.')
OK = False
# build distribution dictionary
if OK:
# initialize the distribution dictionary
distribution_dict = {}
# get the dictionary of TOA configuration
toa_config_dict = xtoa.get_toa_config_dict()
# get the statistics file path
stats_file = f'{toa_config_dict["RESULT_DIR"]}/{xlib.get_toa_result_pipeline_dir()}/{pipeline_dataset_id}/{toa_config_dict["STATS_SUBDIR_NAME"]}/{stats_code}-{toa_config_dict["STATS_BASE_NAME"]}.csv'
# open the statistics file
if stats_file.endswith('.gz'):
try:
stats_file_id = gzip.open(stats_file,
mode='rt',
encoding='iso-8859-1',
newline='\n')
except Exception as e:
raise xlib.ProgramException('F002', stats_file)
else:
try:
stats_file_id = open(stats_file,
mode='r',
encoding='iso-8859-1',
newline='\n')
except Exception as e:
raise xlib.ProgramException('F001', stats_file)
# initialize the record counter
record_counter = 0
# initialize the header record control
header_record = True
# read the first record
record = stats_file_id.readline()
# while there are records
while record != '':
# add 1 to the record counter
record_counter += 1
# process the header record
if header_record:
header_record = False
# process data records
else:
# extract data
# record format: "x_count";"y_count"
data_list = []
begin = 0
for end in [i for i, chr in enumerate(record) if chr == ';']:
data_list.append(record[begin:end].strip('"'))
begin = end + 1
data_list.append(record[begin:].strip('\n').strip('"'))
try:
x_count = data_list[0]
y_count = data_list[1]
except Exception as e:
raise xlib.ProgramException('F006',
os.path.basename(stats_file),
record_counter)
# add dato to the dictionary
distribution_dict[record_counter] = {
'x_count': x_count,
'y_count': y_count
}
# read the next record
record = stats_file_id.readline()
# print the distribution
if OK:
print(xlib.get_separator())
if distribution_dict == {}:
print('*** WARNING: There is not any stats data.')
else:
# set data width
x_count_width = 15
y_count_width = 15
# set line template
line_template = '{0:' + str(x_count_width) + '} {1:' + str(
y_count_width) + '}'
# print header
if stats_code == 'hit_per_hsp':
print(line_template.format('# HSPs', '# HITs'))
elif stats_code == 'seq_per_go':
print(line_template.format('# GO terms', '# sequences'))
elif stats_code == 'seq_per_ec':
print(line_template.format('# EC ids', '# sequences'))
elif stats_code == 'seq_per_interpro':
print(line_template.format('# InterPro ids', '# sequences'))
elif stats_code == 'seq_per_kegg':
print(line_template.format('# KEGG ids', '# sequences'))
elif stats_code == 'seq_per_mapman':
print(line_template.format('# MapMan ids', '# sequences'))
elif stats_code == 'seq_per_metacyc':
print(line_template.format('# MetaCyc ids', '# sequences'))
print(
line_template.format('=' * x_count_width, '=' * y_count_width))
# print detail lines
for key in sorted(distribution_dict.keys()):
print(
line_template.format(distribution_dict[key]['x_count'],
distribution_dict[key]['y_count']))
# show continuation message
print(xlib.get_separator())
input('Press [Intro] to continue ...')
def form_list_results_logs():
'''
List the processes of an experiment in the cluster.
'''
# initialize the control variable
OK = True
# print the header
clib.clear_screen()
clib.print_headers_with_environment('Logs - List result logs')
# get experiment identification
experiment_id = cinputs.input_experiment_id()
if experiment_id == '':
print('WARNING: There is not any experiment/process run.')
OK = False
# get the dictionary of TOA configuration.
if OK:
toa_config_dict = xtoa.get_toa_config_dict()
# get the result dataset list of the experiment
if OK:
experiment_dir = f'{toa_config_dict["RESULT_DIR"]}/{experiment_id}'
subdir_list = [
subdir for subdir in os.listdir(experiment_dir)
if os.path.isdir(os.path.join(experiment_dir, subdir))
]
result_dataset_id_list = []
for subdir in subdir_list:
result_dataset_id_list.append(subdir)
# print the result dataset identification list of the experiment
if OK:
print(xlib.get_separator())
if result_dataset_id_list == []:
print(
f'*** WARNING: There is not any result dataset of the experiment/process {experiment_id}.'
)
else:
result_dataset_id_list.sort()
# set data width
result_dataset_width = 25
bioinfo_app_width = 25
# set line template
line_template = '{0:' + str(
result_dataset_width) + '} {1:' + str(
bioinfo_app_width) + '}'
# print header
print(
line_template.format('Result dataset',
'Bioinfo app / Utility'))
print(
line_template.format('=' * result_dataset_width,
'=' * bioinfo_app_width))
# print detail lines
for result_dataset_id in result_dataset_id_list:
if result_dataset_id.startswith(xlib.get_blastplus_code() +
'-'):
bioinfo_app_name = xlib.get_blastplus_name()
elif result_dataset_id.startswith(xlib.get_diamond_code() +
'-'):
bioinfo_app_name = xlib.get_diamond_name()
elif result_dataset_id.startswith(
xlib.get_entrez_direct_code() + '-'):
bioinfo_app_name = xlib.get_entrez_direct_name()
elif result_dataset_id.startswith(xlib.get_miniconda3_code() +
'-'):
bioinfo_app_name = xlib.get_miniconda3_name()
elif result_dataset_id.startswith(xlib.get_r_code() + '-'):
bioinfo_app_name = xlib.get_r_name()
elif result_dataset_id.startswith(
xlib.get_toa_process_download_basic_data_code() + '-'):
bioinfo_app_name = xlib.get_toa_process_download_basic_data_name(
)
elif result_dataset_id.startswith(
xlib.get_toa_process_download_dicots_04_code() + '-'):
bioinfo_app_name = xlib.get_toa_process_download_dicots_04_name(
)
elif result_dataset_id.startswith(
xlib.get_toa_process_download_gene_code() + '-'):
bioinfo_app_name = xlib.get_toa_process_download_gene_name(
)
elif result_dataset_id.startswith(
xlib.get_toa_process_download_go_code() + '-'):
bioinfo_app_name = xlib.get_toa_process_download_go_name()
elif result_dataset_id.startswith(
xlib.get_toa_process_download_gymno_01_code() + '-'):
bioinfo_app_name = xlib.get_toa_process_download_gymno_01_name(
)
elif result_dataset_id.startswith(
xlib.get_toa_process_download_interpro_code() + '-'):
bioinfo_app_name = xlib.get_toa_process_download_interpro_name(
)
elif result_dataset_id.startswith(
xlib.get_toa_process_download_monocots_04_code() +
'-'):
bioinfo_app_name = xlib.get_toa_process_download_monocots_04_name(
)
elif result_dataset_id.startswith(
xlib.get_toa_process_download_taxonomy_code() + '-'):
bioinfo_app_name = xlib.get_toa_process_download_taxonomy_name(
)
elif result_dataset_id.startswith(
xlib.
get_toa_process_gilist_viridiplantae_nucleotide_gi_code(
) + '-'):
bioinfo_app_name = xlib.get_toa_process_gilist_viridiplantae_nucleotide_gi_name(
)
elif result_dataset_id.startswith(
xlib.
get_toa_process_gilist_viridiplantae_protein_gi_code()
+ '-'):
bioinfo_app_name = xlib.get_toa_process_gilist_viridiplantae_protein_gi_name(
)
elif result_dataset_id.startswith(
xlib.get_toa_process_load_basic_data_code() + '-'):
bioinfo_app_name = xlib.get_toa_process_load_basic_data_name(
)
elif result_dataset_id.startswith(
xlib.get_toa_process_load_dicots_04_code() + '-'):
bioinfo_app_name = xlib.get_toa_process_load_dicots_04_name(
)
elif result_dataset_id.startswith(
xlib.get_toa_process_load_gene_code() + '-'):
bioinfo_app_name = xlib.get_toa_process_load_gene_name()
elif result_dataset_id.startswith(
xlib.get_toa_process_load_go_code() + '-'):
bioinfo_app_name = xlib.get_toa_process_load_go_name()
elif result_dataset_id.startswith(
xlib.get_toa_process_load_gymno_01_code() + '-'):
bioinfo_app_name = xlib.get_toa_process_load_gymno_01_name(
)
elif result_dataset_id.startswith(
xlib.get_toa_process_load_interpro_code() + '-'):
bioinfo_app_name = xlib.get_toa_process_load_interpro_name(
)
elif result_dataset_id.startswith(
xlib.get_toa_process_load_monocots_04_code() + '-'):
bioinfo_app_name = xlib.get_toa_process_load_monocots_04_name(
)
elif result_dataset_id.startswith(
xlib.get_toa_process_merge_annotations_code() + '-'):
bioinfo_app_name = xlib.get_toa_process_merge_annotations_name(
)
elif result_dataset_id.startswith(
xlib.get_toa_process_nr_blastplus_db_code() + '-'):
bioinfo_app_name = xlib.get_toa_process_nr_blastplus_db_name(
)
elif result_dataset_id.startswith(
xlib.get_toa_process_nr_diamond_db_code() + '-'):
bioinfo_app_name = xlib.get_toa_process_nr_diamond_db_name(
)
elif result_dataset_id.startswith(
xlib.get_toa_process_nt_blastplus_db_code() + '-'):
bioinfo_app_name = xlib.get_toa_process_nt_blastplus_db_name(
)
elif result_dataset_id.startswith(
xlib.get_toa_process_pipeline_aminoacid_code() + '-'):
bioinfo_app_name = xlib.get_toa_process_pipeline_aminoacid_name(
)
elif result_dataset_id.startswith(
xlib.get_toa_process_pipeline_nucleotide_code() + '-'):
bioinfo_app_name = xlib.get_toa_process_pipeline_nucleotide_name(
)
elif result_dataset_id.startswith(
xlib.get_toa_process_proteome_dicots_04_code() + '-'):
bioinfo_app_name = xlib.get_toa_process_proteome_dicots_04_name(
)
elif result_dataset_id.startswith(
xlib.get_toa_process_proteome_gymno_01_code() + '-'):
bioinfo_app_name = xlib.get_toa_process_proteome_gymno_01_name(
)
elif result_dataset_id.startswith(
xlib.get_toa_process_proteome_monocots_04_code() +
'-'):
bioinfo_app_name = xlib.get_toa_process_proteome_monocots_04_name(
)
elif result_dataset_id.startswith(
xlib.get_toa_process_proteome_refseq_plant_code() +
'-'):
bioinfo_app_name = xlib.get_toa_process_proteome_refseq_plant_name(
)
elif result_dataset_id.startswith(
xlib.get_toa_process_rebuild_toa_database_code() +
'-'):
bioinfo_app_name = xlib.get_get_toa_process_rebuild_toa_database_name(
)
elif result_dataset_id.startswith(
xlib.get_toa_process_recreate_toa_database_code() +
'-'):
bioinfo_app_name = xlib.get_get_toa_process_recreate_toa_database_name(
)
elif result_dataset_id.startswith(
xlib.get_transdecoder_code() + '-'):
bioinfo_app_name = xlib.get_transdecoder_name()
else:
bioinfo_app_name = 'xxx'
print(line_template.format(result_dataset_id,
bioinfo_app_name))
# show continuation message
print(xlib.get_separator())
input('Press [Intro] to continue ...')