def form_edit_pipeline_config_file(pipeline_type):
'''
Edit a pipeline config file to change the parameters of each process.
'''
# initialize the control variable
OK = True
# set the pipeline name
if pipeline_type == xlib.get_toa_process_pipeline_nucleotide_code():
name = xlib.get_toa_process_pipeline_nucleotide_name()
elif pipeline_type == xlib.get_toa_process_pipeline_aminoacid_code():
name = xlib.get_toa_process_pipeline_aminoacid_name()
elif pipeline_type == xlib.get_toa_process_merge_annotations_code():
name = xlib.get_toa_process_merge_annotations_name()
# print the header
clib.clear_screen()
clib.print_headers_with_environment(f'{name} - Edit config file')
# get the config file
if pipeline_type == xlib.get_toa_process_pipeline_nucleotide_code():
config_file = xtoa.get_nucleotide_pipeline_config_file()
elif pipeline_type == xlib.get_toa_process_pipeline_aminoacid_code():
config_file = xtoa.get_aminoacid_pipeline_config_file()
elif pipeline_type == xlib.get_toa_process_merge_annotations_code():
config_file = xtoa.get_annotation_merger_config_file()
# edit the read transfer config file
print(xlib.get_separator())
print(f'Editing the {name} config file ...')
command = f'{xlib.get_editor()} {config_file}'
rc = subprocess.call(command, shell=True)
if rc != 0:
print(f'*** ERROR: RC {rc} in command -> {command}')
OK = False
# check the config file
if OK:
print(xlib.get_separator())
print(f'Checking the {name} config file ...')
if pipeline_type == xlib.get_toa_process_pipeline_nucleotide_code():
(OK, error_list) = xtoa.check_pipeline_config_file(pipeline_type,
strict=False)
elif pipeline_type == xlib.get_toa_process_pipeline_aminoacid_code():
(OK, error_list) = xtoa.check_pipeline_config_file(pipeline_type,
strict=False)
elif pipeline_type == xlib.get_toa_process_merge_annotations_code():
(OK, error_list) = xtoa.check_annotation_merger_config_file(
strict=False)
if OK:
print('The file is OK.')
else:
print()
for error in error_list:
print(error)
# show continuation message
print(xlib.get_separator())
input('Press [Intro] to continue ...')
def form_run_pipeline_process(pipeline_type):
'''
Run a pipeline process with the parameters in the corresponding config file.
'''
# initialize the control variable
OK = True
# set the pipeline name
if pipeline_type == xlib.get_toa_process_pipeline_nucleotide_code():
name = xlib.get_toa_process_pipeline_nucleotide_name()
elif pipeline_type == xlib.get_toa_process_pipeline_aminoacid_code():
name = xlib.get_toa_process_pipeline_aminoacid_name()
elif pipeline_type == xlib.get_toa_process_merge_annotations_code():
name = xlib.get_toa_process_merge_annotations_name()
# print the header
clib.clear_screen()
clib.print_headers_with_environment(f'{name} - Run process')
# confirm the process run
if OK:
print(xlib.get_separator())
OK = clib.confirm_action(f'The {name} process is going to be run.')
# run the process
if OK:
if pipeline_type == xlib.get_toa_process_pipeline_nucleotide_code():
devstdout = xlib.DevStdOut(xtoa.run_pipeline_process.__name__)
OK = xtoa.run_pipeline_process(pipeline_type,
devstdout,
function=None)
elif pipeline_type == xlib.get_toa_process_pipeline_aminoacid_code():
devstdout = xlib.DevStdOut(xtoa.run_pipeline_process.__name__)
OK = xtoa.run_pipeline_process(pipeline_type,
devstdout,
function=None)
elif pipeline_type == xlib.get_toa_process_merge_annotations_code():
devstdout = xlib.DevStdOut(
xtoa.run_annotation_merger_process.__name__)
OK = xtoa.run_annotation_merger_process(devstdout, function=None)
# show continuation message
print(xlib.get_separator())
input('Press [Intro] to continue ...')
def build_menu_toa_nucleotide_pipeline():
'''
Build the menu Nucleotide pipeline.
'''
while True:
# print headers
clib.clear_screen()
clib.print_headers_with_environment(f'{xlib.get_toa_name()} {xlib.get_toa_process_pipeline_nucleotide_name()}')
# print the menu options
print( 'Options:')
print()
print( ' 1. Recreate config file')
print( ' 2. Edit config file')
print()
print( ' 3. Run pipeline')
print( ' 4. Restart pipeline')
print()
print( ' X. Return to menu Pipelines')
print()
# get the selected option
option = input('Input the selected option: ').upper()
# process the selected option
if option == '1':
ctoa.form_recreate_pipeline_config_file(xlib.get_toa_process_pipeline_nucleotide_code())
elif option == '2':
ctoa.form_edit_pipeline_config_file(xlib.get_toa_process_pipeline_nucleotide_code())
elif option == '3':
ctoa.form_run_pipeline_process(xlib.get_toa_process_pipeline_nucleotide_code())
elif option == '4':
ctoa.form_restart_pipeline_process(xlib.get_toa_process_pipeline_nucleotide_code())
elif option == 'X':
break
def form_restart_pipeline_process(pipeline_type):
'''
Restart a pipeline process from the last step ended OK.
'''
# initialize the control variable
OK = True
# set the pipeline name
if pipeline_type == xlib.get_toa_process_pipeline_nucleotide_code():
name = xlib.get_toa_process_pipeline_nucleotide_name()
elif pipeline_type == xlib.get_toa_process_pipeline_aminoacid_code():
name = xlib.get_toa_process_pipeline_aminoacid_name()
# print the header
clib.clear_screen()
clib.print_headers_with_environment(f'{name} - Run process')
# get the pipeline dataset identification
app_list = [pipeline_type]
pipeline_dataset_id = cinputs.input_result_dataset_id(
xlib.get_toa_result_pipeline_dir(), app_list)
if pipeline_dataset_id == '':
print(f'WARNING: There are not any {pipeline_type} result datasets.')
OK = False
# confirm the process run
if OK:
print(xlib.get_separator())
OK = clib.confirm_action(f'The {name} process is going to be run.')
# run the process
if OK:
devstdout = xlib.DevStdOut(xtoa.restart_pipeline_process.__name__)
OK = xtoa.restart_pipeline_process(pipeline_type,
pipeline_dataset_id,
devstdout,
function=None)
# show continuation message
print(xlib.get_separator())
input('Press [Intro] to continue ...')
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 get_result_dataset_dict(cluster_name, experiment_id, status, passed_connection, ssh_client):
'''
Get a dictionary with the result datasets of an experiment in the cluster.
'''
# initialize the control variable and the error list
OK = True
error_list = []
# get the result directory in the cluster
cluster_result_dir = xlib.get_cluster_result_dir()
# initialize the dictionary of the result datasets
result_dataset_dict = {}
# create the SSH client connection
if not passed_connection:
(OK, error_list, ssh_client) = xssh.create_ssh_client_connection(cluster_name)
# check the result directory is created
if OK:
command = '[ -d {0} ] && echo RC=0 || echo RC=1'.format(cluster_result_dir)
(OK, stdout, stderr) = xssh.execute_cluster_command(ssh_client, command)
if stdout[len(stdout) - 1] != 'RC=0':
error_list.append('*** ERROR: There is not any volume mounted in the result directory.\n')
error_list.append('You have to link a volume in the mounting point {0} for the cluster {1}.\n'.format(cluster_result_dir, cluster_name))
OK = False
# get the dictionary of the result datasets
if OK:
if status == 'uncompressed':
command = 'cd {0}/{1}; for list in `ls`; do ls -ld $list | grep -v ^- > /dev/null && echo $list; done;'.format(cluster_result_dir, experiment_id)
elif status == 'compressed':
command = 'cd {0}/{1}; for list in `ls`; do ls -ld $list | grep -v ^d > /dev/null && echo $list; done;'.format(cluster_result_dir, experiment_id)
(OK, stdout, stderr) = xssh.execute_cluster_command(ssh_client, command)
if OK:
if status == 'uncompressed':
input_pattern = '{0}-(.+)-(.+)'
output_pattern = '{0} ({1} {2})'
elif status == 'compressed':
input_pattern = '{0}-(.+)-(.+).tar.gz'
output_pattern = '{0} ({1} {2}) [compressed]'
for line in stdout:
line = line.rstrip('\n')
if line != 'lost+found':
result_dataset_id = line
if result_dataset_id.startswith(xlib.get_bowtie2_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_bowtie2_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_bowtie2_name(), date, time)
elif result_dataset_id.startswith(xlib.get_busco_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_busco_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_busco_name(), date, time)
elif result_dataset_id.startswith(xlib.get_cd_hit_est_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_cd_hit_est_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_cd_hit_est_name(), date, time)
elif result_dataset_id.startswith(xlib.get_cutadapt_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_cutadapt_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_cutadapt_name(), date, time)
elif result_dataset_id.startswith(xlib.get_cuffdiff_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_cuffdiff_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_cuffdiff_name(), date, time)
elif result_dataset_id.startswith(xlib.get_cufflinks_cuffmerge_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_cufflinks_cuffmerge_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_cufflinks_cuffmerge_name(), date, time)
elif result_dataset_id.startswith(xlib.get_cuffnorm_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_cuffnorm_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_cuffnorm_name(), date, time)
elif result_dataset_id.startswith(xlib.get_cuffquant_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_cuffquant_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_cuffquant_name(), date, time)
elif result_dataset_id.startswith(xlib.get_ddradseq_simulation_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_ddradseq_simulation_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_ddradseq_simulation_name(), date, time)
elif result_dataset_id.startswith(xlib.get_fastqc_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_fastqc_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_fastqc_name(), date, time)
elif result_dataset_id.startswith(xlib.get_ggtrinity_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_ggtrinity_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_ggtrinity_name(), date, time)
elif result_dataset_id.startswith(xlib.get_gmap_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_gmap_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_gmap_name(), date, time)
elif result_dataset_id.startswith(xlib.get_gsnap_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_gsnap_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_gsnap_name(), date, time)
elif result_dataset_id.startswith(xlib.get_gzip_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_gzip_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_gzip_name(), date, time)
elif result_dataset_id.startswith(xlib.get_hisat2_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_hisat2_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_hisat2_name(), date, time)
elif result_dataset_id.startswith(xlib.get_htseq_count_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_htseq_count_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_htseq_count_name(), date, time)
elif result_dataset_id.startswith(xlib.get_insilico_read_normalization_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_insilico_read_normalization_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_insilico_read_normalization_name(), date, time)
elif result_dataset_id.startswith(xlib.get_ipyrad_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_ipyrad_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_ipyrad_name(), date, time)
elif result_dataset_id.startswith(xlib.get_kallisto_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_kallisto_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_kallisto_name(), date, time)
elif result_dataset_id.startswith(xlib.get_quast_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_quast_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_quast_name(), date, time)
elif result_dataset_id.startswith(xlib.get_ref_eval_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_ref_eval_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_ref_eval_name(), date, time)
elif result_dataset_id.startswith(xlib.get_rnaquast_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_rnaquast_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_rnaquast_name(), date, time)
elif result_dataset_id.startswith(xlib.get_rsem_eval_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_rsem_eval_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_rsem_eval_name(), date, time)
elif result_dataset_id.startswith(xlib.get_rsitesearch_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_rsitesearch_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_rsitesearch_name(), date, time)
elif result_dataset_id.startswith(xlib.get_soapdenovo2_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_soapdenovo2_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_soapdenovo2_name(), date, time)
elif result_dataset_id.startswith(xlib.get_soapdenovotrans_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_soapdenovotrans_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_soapdenovotrans_name(), date, time)
elif result_dataset_id.startswith(xlib.get_star_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_star_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_star_name(), date, time)
elif result_dataset_id.startswith(xlib.get_starcode_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_starcode_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_starcode_name(), date, time)
elif result_dataset_id.startswith(xlib.get_toa_process_pipeline_aminoacid_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_toa_process_pipeline_aminoacid_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_toa_process_pipeline_aminoacid_name(), date, time)
elif result_dataset_id.startswith(xlib.get_toa_process_pipeline_nucleotide_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_toa_process_pipeline_nucleotide_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_toa_process_pipeline_nucleotide_name(), date, time)
elif result_dataset_id.startswith(xlib.get_tophat_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_tophat_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_tophat_name(), date, time)
elif result_dataset_id.startswith(xlib.get_transabyss_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_transabyss_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_transabyss_name(), date, time)
elif result_dataset_id.startswith(xlib.get_transcript_filter_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_transcript_filter_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_transcript_filter_name(), date, time)
elif result_dataset_id.startswith(xlib.get_transcriptome_blastx_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_transcriptome_blastx_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_transcriptome_blastx_name(), date, time)
elif result_dataset_id.startswith(xlib.get_transrate_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_transrate_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_transrate_name(), date, time)
elif result_dataset_id.startswith(xlib.get_trimmomatic_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_trimmomatic_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_trimmomatic_name(), date, time)
elif result_dataset_id.startswith(xlib.get_trinity_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_trinity_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_trinity_name(), date, time)
else:
result_dataset_name = result_dataset_id
result_dataset_dict[result_dataset_id] = {'result_dataset_id': result_dataset_id, 'result_dataset_name': result_dataset_name}
# close the SSH client connection
if OK and not passed_connection:
xssh.close_ssh_client_connection(ssh_client)
# return the control variable, error list and dictionary of the result datasets
return (OK, error_list, result_dataset_dict)
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_recreate_annotation_merger_config_file():
'''
Recreate the annotation merger config file.
'''
# initialize the control variable
OK = True
# print the header
clib.clear_screen()
clib.print_headers_with_environment(
f'{xlib.get_toa_process_merge_annotations_name()} - Recreate config file'
)
# get the identification of the first pipeline dataset
app_list = [
xlib.get_toa_process_pipeline_nucleotide_code(),
xlib.get_toa_process_pipeline_aminoacid_code(),
xlib.get_toa_process_merge_annotations_code()
]
print('First pipeline ...')
pipeline_dataset_id_1 = cinputs.input_result_dataset_id(
xlib.get_toa_result_pipeline_dir(), app_list)
if pipeline_dataset_id_1 == '':
print('WARNING: There are not any pipeline datasets.')
OK = False
# get the identification of the second pipeline dataset
app_list = [
xlib.get_toa_process_pipeline_nucleotide_code(),
xlib.get_toa_process_pipeline_aminoacid_code(),
xlib.get_toa_process_merge_annotations_code()
]
print('Second pipeline ...')
pipeline_dataset_id_2 = cinputs.input_result_dataset_id(
xlib.get_toa_result_pipeline_dir(), app_list)
if pipeline_dataset_id_2 == '':
print('WARNING: There are not any pipeline datasets.')
OK = False
elif pipeline_dataset_id_1 == pipeline_dataset_id_2:
print('ERROR: The first pipeline dataset is equal to the second one.')
OK = False
# get the merger operation
if OK:
merger_operation = cinputs.input_code(
text='Merger operation',
code_list=xlib.get_annotation_merger_operation_code_list(),
default_code=None).upper()
# recreate the pipeline config file
if OK:
# confirm the creation of the config file
print(xlib.get_separator())
OK = clib.confirm_action(
f'The file {xtoa.get_annotation_merger_config_file()} is going to be recreated. The previous files will be lost.'
)
# recreate the config file
if OK:
(OK, error_list) = xtoa.create_annotation_merger_config_file(
pipeline_dataset_id_1, pipeline_dataset_id_2, merger_operation)
if OK:
print('The file is recreated.')
else:
for error in error_list:
print(error)
# show continuation message
print(xlib.get_separator())
input('Press [Intro] to continue ...')
def form_recreate_pipeline_config_file(pipeline_type):
'''
Recreate a pipeline config file.
'''
# initialize the control variable
OK = True
# set the pipeline name
if pipeline_type == xlib.get_toa_process_pipeline_nucleotide_code():
name = xlib.get_toa_process_pipeline_nucleotide_name()
elif pipeline_type == xlib.get_toa_process_pipeline_aminoacid_code():
name = xlib.get_toa_process_pipeline_aminoacid_name()
# set the config file
if pipeline_type == xlib.get_toa_process_pipeline_nucleotide_code():
config_file = xtoa.get_nucleotide_pipeline_config_file()
elif pipeline_type == xlib.get_toa_process_pipeline_aminoacid_code():
config_file = xtoa.get_aminoacid_pipeline_config_file()
# print the header
clib.clear_screen()
clib.print_headers_with_environment(f'{name} - Recreate config file')
print(xlib.get_separator())
# get the transcriptome directory
transcriptome_dir = ''
while transcriptome_dir == '':
transcriptome_dir = input('Enter transcriptome directory: ')
if not os.path.isdir(transcriptome_dir):
print(f'***ERROR: The directory {transcriptome_dir} is not valid.')
transcriptome_dir = ''
# get the transcriptome file
transcriptome_file = ''
while transcriptome_file == '':
transcriptome_file = input('Enter transcriptome file: ')
print(f'transcriptome_file: {transcriptome_file}')
if not os.path.isfile(f'{transcriptome_dir}/{transcriptome_file}'):
print(f'***ERROR: The file {transcriptome_file} is not valid.')
transcriptome_file = ''
# get the database list
if OK:
# nucleotide pipelines
if pipeline_type == xlib.get_toa_process_pipeline_nucleotide_code():
database_list = cinputs.input_database_list(
xtoa.get_nucleotide_annotation_database_code_list(), 'nt')
# amino acid pipelines
elif pipeline_type == xlib.get_toa_process_pipeline_aminoacid_code():
database_list = cinputs.input_database_list(
xtoa.get_aminoacid_annotation_database_code_list(), 'nr')
# recreate the pipeline config file
if OK:
# confirm the creation of the config file
print(xlib.get_separator())
OK = clib.confirm_action(
f'The file {config_file} is going to be recreated. The previous files will be lost.'
)
# recreate the config file
if OK:
(OK, error_list) = xtoa.create_pipeline_config_file(
pipeline_type, transcriptome_dir, transcriptome_file,
database_list)
if OK:
print('The file is recreated.')
else:
for error in error_list:
print(error)
# show continuation message
print(xlib.get_separator())
input('Press [Intro] to continue ...')
def form_list_cluster_experiment_processes():
'''
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 experiment processes in the cluster')
# get the cluster name
print(xlib.get_separator())
if xec2.get_running_cluster_list(only_environment_cluster=True,
volume_creator_included=False) != []:
cluster_name = cinputs.input_cluster_name(
volume_creator_included=False, help=True)
else:
print('WARNING: There is not any running cluster.')
OK = False
# create the SSH client connection
if OK:
(OK, error_list,
ssh_client) = xssh.create_ssh_client_connection(cluster_name)
for error in error_list:
print(error)
# get experiment identification
if OK:
experiment_id = cinputs.input_experiment_id(ssh_client, help=True)
if experiment_id == '':
print(
f'WARNING: The cluster {cluster_name} does not have experiment data.'
)
OK = False
# get the result dataset list of the experiment
if OK:
command = f'cd {xlib.get_cluster_result_dir()}/{experiment_id}; for list in `ls`; do ls -ld $list | grep -v ^- > /dev/null && echo $list; done;'
(OK, stdout, _) = xssh.execute_cluster_command(ssh_client, command)
if OK:
result_dataset_id_list = []
for line in stdout:
line = line.rstrip('\n')
if line != 'lost+found':
result_dataset_id_list.append(line)
# 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 {experiment_id}.'
)
else:
result_dataset_id_list.sort()
# set data width
result_dataset_width = 30
bioinfo_app_width = 25
# set line
line = '{0:' + str(result_dataset_width) + '} {1:' + str(
bioinfo_app_width) + '}'
# print header
print(line.format('Result dataset', 'Bioinfo app / Utility'))
print(
line.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_bedtools_code() +
'-'):
bioinfo_app_name = xlib.get_bedtools_name()
elif result_dataset_id.startswith(xlib.get_blastplus_code() +
'-'):
bioinfo_app_name = xlib.get_blastplus_name()
elif result_dataset_id.startswith(xlib.get_bcftools_code() +
'-'):
bioinfo_app_name = xlib.get_bcftools_name()
elif result_dataset_id.startswith(xlib.get_bowtie2_code() +
'-'):
bioinfo_app_name = xlib.get_bowtie2_name()
elif result_dataset_id.startswith(xlib.get_busco_code() + '-'):
bioinfo_app_name = xlib.get_busco_name()
elif result_dataset_id.startswith(xlib.get_cd_hit_code() +
'-'):
bioinfo_app_name = xlib.get_cd_hit_name()
elif result_dataset_id.startswith(xlib.get_cd_hit_est_code() +
'-'):
bioinfo_app_name = xlib.get_cd_hit_est_name()
elif result_dataset_id.startswith(xlib.get_cuffdiff_code() +
'-'):
bioinfo_app_name = xlib.get_cuffdiff_name()
elif result_dataset_id.startswith(xlib.get_cufflinks_code() +
'-'):
bioinfo_app_name = xlib.get_cufflinks_name()
elif result_dataset_id.startswith(
xlib.get_cufflinks_cuffmerge_code() + '-'):
bioinfo_app_name = xlib.get_cufflinks_cuffmerge_name()
elif result_dataset_id.startswith(xlib.get_cuffnorm_code() +
'-'):
bioinfo_app_name = xlib.get_cuffnorm_name()
elif result_dataset_id.startswith(xlib.get_cuffquant_code() +
'-'):
bioinfo_app_name = xlib.get_cuffquant_name()
elif result_dataset_id.startswith(xlib.get_cutadapt_code() +
'-'):
bioinfo_app_name = xlib.get_cutadapt_name()
elif result_dataset_id.startswith(
xlib.get_ddradseq_simulation_code() + '-'):
bioinfo_app_name = xlib.get_ddradseq_simulation_name()
elif result_dataset_id.startswith(
xlib.get_ddradseqtools_code() + '-'):
bioinfo_app_name = xlib.get_ddradseqtools_name()
elif result_dataset_id.startswith(xlib.get_detonate_code() +
'-'):
bioinfo_app_name = xlib.get_detonate_name()
elif result_dataset_id.startswith(xlib.get_diamond_code() +
'-'):
bioinfo_app_name = xlib.get_diamond_name()
elif result_dataset_id.startswith(xlib.get_emboss_code() +
'-'):
bioinfo_app_name = xlib.get_emboss_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_express_code() +
'-'):
bioinfo_app_name = xlib.get_express_name()
elif result_dataset_id.startswith(xlib.get_fastqc_code() +
'-'):
bioinfo_app_name = xlib.get_fastqc_name()
elif result_dataset_id.startswith(xlib.get_ggtrinity_code() +
'-'):
bioinfo_app_name = xlib.get_ggtrinity_name()
elif result_dataset_id.startswith(xlib.get_gmap_gsnap_code() +
'-'):
bioinfo_app_name = xlib.get_gmap_gsnap_name()
elif result_dataset_id.startswith(xlib.get_gmap_code() + '-'):
bioinfo_app_name = xlib.get_gmap_name()
elif result_dataset_id.startswith(xlib.get_gsnap_code() + '-'):
bioinfo_app_name = xlib.get_gsnap_name()
elif result_dataset_id.startswith(xlib.get_gzip_code() + '-'):
bioinfo_app_name = xlib.get_gzip_name()
elif result_dataset_id.startswith(xlib.get_hisat2_code() +
'-'):
bioinfo_app_name = xlib.get_hisat2_name()
elif result_dataset_id.startswith(xlib.get_htseq_code() + '-'):
bioinfo_app_name = xlib.get_htseq_name()
elif result_dataset_id.startswith(xlib.get_htseq_count_code() +
'-'):
bioinfo_app_name = xlib.get_htseq_count_name()
elif result_dataset_id.startswith(
xlib.get_insilico_read_normalization_code() + '-'):
bioinfo_app_name = xlib.get_insilico_read_normalization_name(
)
elif result_dataset_id.startswith(xlib.get_ipyrad_code() +
'-'):
bioinfo_app_name = xlib.get_ipyrad_name()
elif result_dataset_id.startswith(xlib.get_kallisto_code() +
'-'):
bioinfo_app_name = xlib.get_kallisto_name()
elif result_dataset_id.startswith(xlib.get_miniconda3_code() +
'-'):
bioinfo_app_name = xlib.get_miniconda3_name()
elif result_dataset_id.startswith(xlib.get_ngshelper_code() +
'-'):
bioinfo_app_name = xlib.get_ngshelper_name()
elif result_dataset_id.startswith(xlib.get_quast_code() + '-'):
bioinfo_app_name = xlib.get_quast_name()
elif result_dataset_id.startswith(xlib.get_r_code() + '-'):
bioinfo_app_name = xlib.get_r_name()
elif result_dataset_id.startswith(xlib.get_raddesigner_code() +
'-'):
bioinfo_app_name = xlib.get_raddesigner_name()
elif result_dataset_id.startswith(xlib.get_ref_eval_code() +
'-'):
bioinfo_app_name = xlib.get_ref_eval_name()
elif result_dataset_id.startswith(xlib.get_rnaquast_code() +
'-'):
bioinfo_app_name = xlib.get_rnaquast_name()
elif result_dataset_id.startswith(xlib.get_rsem_code() + '-'):
bioinfo_app_name = xlib.get_rsem_name()
elif result_dataset_id.startswith(xlib.get_rsem_eval_code() +
'-'):
bioinfo_app_name = xlib.get_rsem_eval_name()
elif result_dataset_id.startswith(xlib.get_rsitesearch_code() +
'-'):
bioinfo_app_name = xlib.get_rsitesearch_name()
elif result_dataset_id.startswith(xlib.get_samtools_code() +
'-'):
bioinfo_app_name = xlib.get_samtools_name()
elif result_dataset_id.startswith(xlib.get_soapdenovo2_code() +
'-'):
bioinfo_app_name = xlib.get_soapdenovo2_name()
elif result_dataset_id.startswith(
xlib.get_soapdenovotrans_code() + '-'):
bioinfo_app_name = xlib.get_soapdenovotrans_name()
elif result_dataset_id.startswith(xlib.get_star_code() + '-'):
bioinfo_app_name = xlib.get_star_name()
elif result_dataset_id.startswith(xlib.get_starcode_code() +
'-'):
bioinfo_app_name = xlib.get_starcode_name()
elif result_dataset_id.startswith(xlib.get_toa_code() + '-'):
bioinfo_app_name = xlib.get_toa_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_tophat_code() +
'-'):
bioinfo_app_name = xlib.get_tophat_name()
elif result_dataset_id.startswith(xlib.get_transabyss_code() +
'-'):
bioinfo_app_name = xlib.get_transabyss_name()
elif result_dataset_id.startswith(
xlib.get_transcript_filter_code() + '-'):
bioinfo_app_name = xlib.get_transcript_filter_name()
elif result_dataset_id.startswith(
xlib.get_transcriptome_blastx_code() + '-'):
bioinfo_app_name = xlib.get_transcriptome_blastx_name()
elif result_dataset_id.startswith(
xlib.get_transdecoder_code() + '-'):
bioinfo_app_name = xlib.get_transdecoder_name()
elif result_dataset_id.startswith(xlib.get_transrate_code() +
'-'):
bioinfo_app_name = xlib.get_transrate_name()
elif result_dataset_id.startswith(xlib.get_trimmomatic_code() +
'-'):
bioinfo_app_name = xlib.get_trimmomatic_name()
elif result_dataset_id.startswith(xlib.get_trinity_code() +
'-'):
bioinfo_app_name = xlib.get_trinity_name()
elif result_dataset_id.startswith(
xlib.get_variant_calling_code() + '-'):
bioinfo_app_name = xlib.get_variant_calling_name()
elif result_dataset_id.startswith(xlib.get_vcftools_code() +
'-'):
bioinfo_app_name = xlib.get_vcftools_name()
elif result_dataset_id.startswith(
xlib.get_vcftools_perl_libraries_code() + '-'):
bioinfo_app_name = xlib.get_vcftools_perl_libraries_name()
elif result_dataset_id.startswith(xlib.get_vsearch_code() +
'-'):
bioinfo_app_name = xlib.get_vsearch_name()
else:
bioinfo_app_name = 'xxx'
print(line.format(result_dataset_id, bioinfo_app_name))
# close the SSH client connection
if OK:
xssh.close_ssh_client_connection(ssh_client)
# 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 ...')