def populate_combobox_experiment_id(self):
'''
Populate data in "combobox_experiment_id".
'''
# clear the value selected in the combobox
self.wrapper_experiment_id.set('')
# initialize the experiment identification list
experiment_id_list = []
# get the experiment identifications
command = 'ls {0}'.format(xlib.get_cluster_result_dir())
(OK, stdout, stderr) = xssh.execute_cluster_command(self.ssh_client, command)
if OK:
for line in stdout:
line = line.rstrip('\n')
if line != 'lost+found':
experiment_id_list.append(line)
# verify if there are any experimment identifications
if experiment_id_list == []:
message = 'The cluster has not experiment data.'
tkinter.messagebox.showwarning('{0} - {1}'.format(xlib.get_project_name(), self.head), message)
return
# load the names of clusters which are running in the combobox
self.combobox_experiment_id['values'] = experiment_id_list
def create_gmap_config_file(experiment_id='exp001', reference_dataset_id='NONE', reference_file='NONE', assembly_dataset_id='sdnt-170101-235959', assembly_type='CONTIGS'):
'''
Create GMAP config file with the default options. It is necessary
update the options in each run.
'''
# initialize the control variable and the error list
OK = True
error_list = []
# set the app
if assembly_dataset_id.startswith(xlib.get_soapdenovotrans_code()):
assembly_software = xlib.get_soapdenovotrans_code()
elif assembly_dataset_id.startswith(xlib.get_transabyss_code()):
assembly_software = xlib.get_transabyss_code()
elif assembly_dataset_id.startswith(xlib.get_trinity_code()):
assembly_software = xlib.get_trinity_code()
elif assembly_dataset_id.startswith(xlib.get_star_code()):
assembly_software = xlib.get_star_code()
elif assembly_dataset_id.startswith(xlib.get_cd_hit_est_code()):
assembly_software = xlib.get_cd_hit_est_code()
elif assembly_dataset_id.startswith(xlib.get_transcript_filter_code()):
assembly_software = xlib.get_transcript_filter_code()
# create the GMAP config file and write the default options
try:
if not os.path.exists(os.path.dirname(get_gmap_config_file())):
os.makedirs(os.path.dirname(get_gmap_config_file()))
with open(get_gmap_config_file(), mode='w', encoding='utf8') as file_id:
file_id.write('{0}\n'.format('# You must review the information of this file and update the values with the corresponding ones to the current run.'))
file_id.write('{0}\n'.format('#'))
file_id.write('{0}\n'.format('# The reference file must be located in the cluster directory {0}/experiment_id/reference_dataset_id'.format(xlib.get_cluster_reference_dir())))
file_id.write('{0}\n'.format('# The assembly files must be located in the cluster directory {0}/experiment_id/assembly_dataset_id'.format(xlib.get_cluster_result_dir())))
file_id.write('{0}\n'.format('# The experiment_id, reference_dataset_id, reference_file and assembly_dataset_id are fixed in the identification section.'))
file_id.write('{0}\n'.format('#'))
file_id.write('{0}\n'.format('# You can consult the parameters of GMAP and their meaning in http://research-pub.gene.com/gmap/.'))
file_id.write('{0}\n'.format('#'))
file_id.write('{0}\n'.format('# In section "GMAP parameters", the key "other_parameters" allows you to input additional parameters in the format:'))
file_id.write('{0}\n'.format('#'))
file_id.write('{0}\n'.format('# other_parameters = --parameter-1[=value-1][; --parameter-2[=value-2][; ...; --parameter-n[=value-n]]]'))
file_id.write('{0}\n'.format('#'))
file_id.write('{0}\n'.format('# parameter-i is a parameter name of GMAP and value-i a valid value of parameter-i, e.g.'))
file_id.write('{0}\n'.format('#'))
file_id.write('{0}\n'.format('# other_parameters = --no-chimeras; --canonical-mode=2'))
file_id.write('{0}\n'.format(''))
file_id.write('{0}\n'.format('# This section has the information identifies the experiment.'))
file_id.write('{0}\n'.format('[identification]'))
file_id.write('{0:<50} {1}\n'.format('experiment_id = {0}'.format(experiment_id), '# experiment identification'))
file_id.write('{0:<50} {1}\n'.format('reference_dataset_id = {0}'.format(reference_dataset_id), '# reference dataset identification or NONE'))
file_id.write('{0:<50} {1}\n'.format('reference_file = {0}'.format(reference_file), '# reference file name or NONE'))
file_id.write('{0:<50} {1}\n'.format('assembly_software = {0}'.format(assembly_software), '# assembly software: {0} ({1}) or {2} ({3}) or {4} ({5}) or {6} ({7}) or {8} ({9}) or {10} ({11})'.format(xlib.get_soapdenovotrans_code(), xlib.get_soapdenovotrans_name(), xlib.get_transabyss_code(), xlib.get_transabyss_name(), xlib.get_trinity_code(), xlib.get_trinity_name(), xlib.get_star_code(), xlib.get_star_name(), xlib.get_cd_hit_est_code(), xlib.get_cd_hit_est_name(), xlib.get_transcript_filter_code(), xlib.get_transcript_filter_name())))
file_id.write('{0:<50} {1}\n'.format('assembly_dataset_id = {0}'.format(assembly_dataset_id), '# assembly dataset identification'))
file_id.write('{0:<50} {1}\n'.format('assembly_type = {0}'.format(assembly_type), '# CONTIGS or SCAFFOLDS in {0}; NONE in {1}, {2}, {3}, {4} and {5}'.format(xlib.get_soapdenovotrans_name(), xlib.get_transabyss_name(), xlib.get_trinity_name(), xlib.get_star_name(), xlib.get_cd_hit_est_name(), xlib.get_transcript_filter_name())))
file_id.write('{0}\n'.format(''))
file_id.write('{0}\n'.format('# This section has the information to set the GMAP parameters'))
file_id.write('{0}\n'.format('[GMAP parameters]'))
file_id.write('{0:<50} {1}\n'.format('threads = 2', '# number of threads for use'))
file_id.write('{0:<50} {1}\n'.format('kmer = NONE', '# kmer size to use in genome database or NONE (the program will find the highest available kmer size in the genome database)'))
file_id.write('{0:<50} {1}\n'.format('sampling = NONE', '# Sampling to use in genome database or NONE (the program will find the smallest available sampling value in the genome database within selected k-mer size)'))
file_id.write('{0:<50} {1}\n'.format('input-buffer-size = 1000', '# size of input buffer'))
file_id.write('{0:<50} {1}\n'.format('output-buffer-size = 1000', '# size of buffer size in queries for output thread'))
file_id.write('{0:<50} {1}\n'.format('prunelevel = 0', '# pruning level: 0 (no pruning) or 1 (poor seqs) or 2 (repetitive seqs) or 3 (poor and repetitive)'))
file_id.write('{0:<50} {1}\n'.format('format = COMPRESS', '# format for output: COMPRESS or SUMMARY or ALIGN or PLS or GFF3_GENE or SPLICESITES or INTRONS or MAP_EXONS or MAP_RANGES or COORDS'))
file_id.write('{0:<50} {1}\n'.format('other_parameters = NONE', '# additional parameters to the previous ones or NONE'))
except:
error_list.append('*** ERROR: The file {0} can not be recreated'.format(get_gmap_config_file()))
OK = False
# return the control variable and the error list
return (OK, error_list)
def create_cd_hit_est_config_file(experiment_id='exp001',
assembly_dataset_id='sdnt-170101-235959',
assembly_type='CONTIGS'):
'''
Create CD-HIT-EST config file with the default options. It is necessary
update the options in each run.
'''
# initialize the control variable and the error list
OK = True
error_list = []
# set the assembly software
if assembly_dataset_id.startswith(xlib.get_soapdenovotrans_code()):
assembly_software = xlib.get_soapdenovotrans_code()
elif assembly_dataset_id.startswith(xlib.get_transabyss_code()):
assembly_software = xlib.get_transabyss_code()
elif assembly_dataset_id.startswith(xlib.get_trinity_code()):
assembly_software = xlib.get_trinity_code()
elif assembly_dataset_id.startswith(xlib.get_star_code()):
assembly_software = xlib.get_star_code()
elif assembly_dataset_id.startswith(xlib.get_cd_hit_est_code()):
assembly_software = xlib.get_cd_hit_est_code()
elif assembly_dataset_id.startswith(xlib.get_transcript_filter_code()):
assembly_software = xlib.get_transcript_filter_code()
# create the CD-HIT-EST config file and write the default options
try:
if not os.path.exists(os.path.dirname(get_cd_hit_est_config_file())):
os.makedirs(os.path.dirname(get_cd_hit_est_config_file()))
with open(get_cd_hit_est_config_file(), mode='w',
encoding='utf8') as file_id:
file_id.write('{0}\n'.format(
'# You must review the information of this file and update the values with the corresponding ones to the current run.'
))
file_id.write('{0}\n'.format('#'))
file_id.write('{0}\n'.format(
'# The assembly files must be located in the cluster directory {0}/experiment_id/assembly_dataset_id'
.format(xlib.get_cluster_result_dir())))
file_id.write('{0}\n'.format(
'# The experiment_id and assembly_dataset_id names are fixed in the identification section.'
))
file_id.write('{0}\n'.format('#'))
file_id.write('{0}\n'.format(
'# You can consult the parameters of CD-HIT-EST (CD-HIT package) and their meaning in http://weizhong-lab.ucsd.edu/cd-hit/.'
))
file_id.write('{0}\n'.format('#'))
file_id.write('{0}\n'.format(
'# In section "CD-HIT-EST parameters", the key "other_parameters" allows you to input additional parameters in the format:'
))
file_id.write('{0}\n'.format('#'))
file_id.write('{0}\n'.format(
'# other_parameters = --parameter-1[=value-1][; --parameter-2[=value-2][; ...; --parameter-n[=value-n]]]'
))
file_id.write('{0}\n'.format('#'))
file_id.write('{0}\n'.format(
'# parameter-i is a parameter name of CD-HIT-EST and value-i a valid value of parameter-i, e.g.'
))
file_id.write('{0}\n'.format('#'))
file_id.write(
'{0}\n'.format('# other_parameters = --aS=0.9; --U=10'))
file_id.write('{0}\n'.format(''))
file_id.write('{0}\n'.format(
'# This section has the information identifies the assembly result dataset.'
))
file_id.write('{0}\n'.format('[identification]'))
file_id.write('{0:<50} {1}\n'.format(
'experiment_id = {0}'.format(experiment_id),
'# experiment identification'))
file_id.write('{0:<50} {1}\n'.format(
'assembly_software = {0}'.format(assembly_software),
'# assembly software: {0} ({1}) or {2} ({3}) or {4} ({5}) or {6} ({7}) or {8} ({9}) or {10} ({11})'
.format(xlib.get_soapdenovotrans_code(),
xlib.get_soapdenovotrans_name(),
xlib.get_transabyss_code(), xlib.get_transabyss_name(),
xlib.get_trinity_code(), xlib.get_trinity_name(),
xlib.get_star_code(), xlib.get_star_name(),
xlib.get_cd_hit_est_code(), xlib.get_cd_hit_est_name(),
xlib.get_transcript_filter_code(),
xlib.get_transcript_filter_name())))
file_id.write('{0:<50} {1}\n'.format(
'assembly_dataset_id = {0}'.format(assembly_dataset_id),
'# assembly dataset identification'))
file_id.write('{0:<50} {1}\n'.format(
'assembly_type = {0}'.format(assembly_type),
'# CONTIGS or SCAFFOLDS in {0}; NONE in {1}, {2}, {3}, {4} and {5}'
.format(xlib.get_soapdenovotrans_name(),
xlib.get_transabyss_name(), xlib.get_trinity_name(),
xlib.get_star_name(), xlib.get_cd_hit_est_name(),
xlib.get_transcript_filter_name())))
file_id.write('{0}\n'.format(''))
file_id.write('{0}\n'.format(
'# This section has the information to set the CD-HIT-EST parameters'
))
file_id.write('{0}\n'.format('[CD-HIT-EST parameters]'))
file_id.write('{0:<50} {1}\n'.format(
'threads = 2',
'# number of threads for use; with 0, all CPUs will be used'))
file_id.write('{0:<50} {1}\n'.format(
'memory_limit = 800',
'# memory limit (in MB) for the program; 0 for unlimitted'))
file_id.write('{0:<50} {1}\n'.format(
'seq_identity_threshold = 0.9',
'# sequence identity threshold'))
file_id.write('{0:<50} {1}\n'.format('word_length = 5',
'# word length'))
file_id.write('{0:<50} {1}\n'.format(
'mask = NX',
'# masking letters (e.g. -mask NX, to mask out both "N" and "X")'
))
file_id.write('{0:<50} {1}\n'.format(
'match = 2', '# matching score (1 for T-U and N-N)'))
file_id.write('{0:<50} {1}\n'.format('mismatch = -2',
'# mismatching score'))
file_id.write('{0:<50} {1}\n'.format(
'other_parameters = NONE',
'# additional parameters to the previous ones or NONE'))
except:
error_list.append(
'*** ERROR: The file {0} can not be recreated'.format(
get_cd_hit_est_config_file()))
OK = False
# return the control variable and the error list
return (OK, error_list)
def download_result_dataset(cluster_name, log, function=None):
'''
Download the result dataset of a run from the cluster.
'''
# initialize the control variable
OK = True
# get the read transfer config file
result_transfer_config_file = get_result_transfer_config_file()
# warn that the log window must not be closed
if not isinstance(log, xlib.DevStdOut):
log.write('This process might take several minutes. Do not close this window, please wait!\n')
# get and validate the result transfer config file
log.write('{0}\n'.format(xlib.get_separator()))
log.write('The result transfer config file is been validating ...\n')
if validate_result_transfer_config_file(strict=True):
log.write('The config file is OK.\n')
else:
log.write('*** ERROR: The result transfer config file is not valid.\n')
log.write('Please correct this file or recreate the config files.\n')
OK = False
# create the SSH client connection
if OK:
(OK, error_list, ssh_client) = xssh.create_ssh_client_connection(cluster_name, 'master')
for error in error_list:
log.write('{0}\n'.format(error))
# create the SSH transport connection
if OK:
(OK, error_list, ssh_transport) = xssh.create_ssh_transport_connection(cluster_name, 'master')
for error in error_list:
log.write('{0}\n'.format(error))
# create the SFTP client
if OK:
sftp_client = xssh.create_sftp_client(ssh_transport)
# get the options dictionary
if OK:
result_transfer_options_dict = xlib.get_option_dict(result_transfer_config_file)
# download the result dataset
if OK:
# get the sections list
sections_list = []
for section in result_transfer_options_dict.keys():
sections_list.append(section)
sections_list.sort()
# get the experiment identification, run identification and local directory from the section "identification"
experiment_id = result_transfer_options_dict['identification']['experiment_id']
result_dataset_id = result_transfer_options_dict['identification']['result_dataset_id']
status = result_transfer_options_dict['identification']['status'].lower()
local_dir = result_transfer_options_dict['identification']['local_dir']
# download files when the status is uncompressed
if status == 'uncompressed':
# for each section "file-n"
for section in sections_list:
# verify than the section identification is like file-n
if re.match('^file-[0-9]+$', section):
# get the dataset subdirectory and file name
dataset_subdirectory = result_transfer_options_dict[section]['dataset_subdirectory']
file_name = result_transfer_options_dict[section]['file_name']
# verify if the dataset subdirectory is created
pathlib.Path(os.path.normpath('{0}/{1}'.format(local_dir, dataset_subdirectory))).mkdir(parents=True, exist_ok=True)
# assign the cluster path and local path
cluster_path = '{0}/{1}/{2}/{3}/{4}'.format(xlib.get_cluster_result_dir(), experiment_id, result_dataset_id, dataset_subdirectory, file_name)
local_path = os.path.normpath('{0}/{1}/{2}'.format(local_dir, dataset_subdirectory, file_name))
# download the result file from the cluster
log.write('{0}\n'.format(xlib.get_separator()))
log.write('Downloading the file {0} to {1} ...\n'.format(cluster_path, local_dir))
(OK, error_list) = xssh.get_file(sftp_client, cluster_path, local_path)
if OK:
log.write('The file has been downloaded.\n')
else:
for error in error_list:
log.write('{0}\n'.format(error))
break
# download files when the status is compressed
elif status == 'compressed':
# assign the cluster path and local path
cluster_path = '{0}/{1}/{2}'.format(xlib.get_cluster_result_dir(), experiment_id, result_dataset_id)
local_path = '{0}/{1}'.format(local_dir, result_dataset_id)
# download the result file from the cluster
log.write('{0}\n'.format(xlib.get_separator()))
log.write('Downloading the file {0} to {1} ...\n'.format(cluster_path, local_dir))
(OK, error_list) = xssh.get_file(sftp_client, cluster_path, local_path)
if OK:
log.write('The file has been downloaded.\n')
else:
for error in error_list:
log.write('{0}\n'.format(error))
# close the SSH transport connection
if OK:
xssh.close_ssh_transport_connection(ssh_transport)
# close the SSH client connection
if OK:
xssh.close_ssh_client_connection(ssh_client)
# warn that the log window can be closed
if not isinstance(log, xlib.DevStdOut):
log.write('{0}\n'.format(xlib.get_separator()))
log.write('You can close this window now.\n')
# execute final function
if function is not None:
function()
# return the control variable
return OK
def create_result_transfer_config_file(experiment_id='exp001', result_dataset_id='trinity-160629-151313', status='uncompressed', selected_file_list=['./Trinity.fasta'], local_dir='./results'):
'''
Create o recreate the result transfer config file.
'''
# initialize the control variable and the error list
OK = True
error_list = []
# get the result transfer config file path
result_transfer_config_file = get_result_transfer_config_file()
# create the result transfer config file to download result files of a run
try:
if not os.path.exists(os.path.dirname(result_transfer_config_file)):
os.makedirs(os.path.dirname(result_transfer_config_file))
with open(result_transfer_config_file, mode='w', encoding='utf8') as file_id:
file_id.write('{0}\n'.format('# You must review the information of this file and update the values with the corresponding ones to the current transfer.'))
file_id.write('{0}\n'.format('# The files will be copied from the cluster directory {0}/experiment_id/result_dataset_id.'.format(xlib.get_cluster_result_dir())))
file_id.write('{0}\n'.format(''))
file_id.write('{0}\n'.format('# This section has the information identifies the experiment.'))
file_id.write('{0}\n'.format('[identification]'))
file_id.write('{0:<50} {1}\n'.format('experiment_id = {0}'.format(experiment_id), '# experiment identification'))
file_id.write('{0:<50} {1}\n'.format('result_dataset_id = {0}'.format(result_dataset_id), '# run identification'))
file_id.write('{0:<50} {1}\n'.format('status = {0}'.format(status), '# result dataset status (it must be always {0})'.format(status)))
file_id.write('{0:<50} {1}\n'.format('local_dir = {0}'.format(local_dir), '# local path where the file will be download'))
if status == 'uncompressed':
for i in range(len(selected_file_list)):
file_id.write('{0}\n'.format(''))
if i == 0:
file_id.write('{0}\n'.format('# This section has the information of the first result file.'))
file_id.write('{0}\n'.format('[file-{0}]'.format(i + 1)))
file_id.write('{0:<50} {1}\n'.format('dataset_subdirectory = {0}'.format(os.path.dirname(selected_file_list[i])), '# subdirectory of result dataset'))
file_id.write('{0:<50} {1}\n'.format('file_name = {0}'.format(os.path.basename(selected_file_list[i])), '# result file name'))
if i == 0:
file_id.write('{0}\n'.format(''))
file_id.write('{0}\n'.format('# If there are more files, you must repeat the section file-1 with the data of each file.'))
file_id.write('{0}\n'.format('# The section identification must be library-n (n is an integer not repeated)'))
except:
error_list.append('*** ERROR: The file {0} can not be created'.format(result_transfer_config_file))
OK = False
# return the control variable and the error list
return (OK, error_list)
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, 'master')
# verify 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 must link a volume in the mounting point {0} for the template {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_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_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_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_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_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_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_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 create_quast_config_file(experiment_id='exp001', reference_dataset_id='NONE', reference_file='NONE', assembly_dataset_id='sdnt-170101-235959', assembly_type='CONTIGS'):
'''
Create QUAST config file with the default options. It is necessary
update the options in each run.
'''
# initialize the control variable and the error list
OK = True
error_list = []
# set the app
if assembly_dataset_id.startswith(xlib.get_soapdenovotrans_code()):
assembly_software = xlib.get_soapdenovotrans_code()
elif assembly_dataset_id.startswith(xlib.get_transabyss_code()):
assembly_software = xlib.get_transabyss_code()
elif assembly_dataset_id.startswith(xlib.get_trinity_code()):
assembly_software = xlib.get_trinity_code()
elif assembly_dataset_id.startswith(xlib.get_star_code()):
assembly_software = xlib.get_star_code()
elif assembly_dataset_id.startswith(xlib.get_cd_hit_est_code()):
assembly_software = xlib.get_cd_hit_est_code()
elif assembly_dataset_id.startswith(xlib.get_transcript_filter_code()):
assembly_software = xlib.get_transcript_filter_code()
# create the QUAST config file and write the default options
try:
if not os.path.exists(os.path.dirname(get_quast_config_file())):
os.makedirs(os.path.dirname(get_quast_config_file()))
with open(get_quast_config_file(), mode='w', encoding='utf8') as file_id:
file_id.write('{0}\n'.format('# You must review the information of this file and update the values with the corresponding ones to the current run.'))
file_id.write('{0}\n'.format('#'))
file_id.write('{0}\n'.format('# The reference file must be located in the cluster directory {0}/experiment_id/reference_dataset_id'.format(xlib.get_cluster_reference_dir())))
file_id.write('{0}\n'.format('# The assembly files must be located in the cluster directory {0}/experiment_id/assembly_dataset_id'.format(xlib.get_cluster_result_dir())))
file_id.write('{0}\n'.format('# The experiment_id, reference_dataset_id, reference_file and assembly_dataset_id are fixed in the identification section.'))
file_id.write('{0}\n'.format('#'))
file_id.write('{0}\n'.format('# You can consult the parameters of QUAST and their meaning in http://quast.sourceforge.net/quast.html.'))
file_id.write('{0}\n'.format(''))
file_id.write('{0}\n'.format('# This section has the information identifies the experiment.'))
file_id.write('{0}\n'.format('[identification]'))
file_id.write('{0:<50} {1}\n'.format('experiment_id = {0}'.format(experiment_id), '# experiment identification'))
file_id.write('{0:<50} {1}\n'.format('reference_dataset_id = {0}'.format(reference_dataset_id), '# reference dataset identification or NONE'))
file_id.write('{0:<50} {1}\n'.format('reference_file = {0}'.format(reference_file), '# reference file name or NONE'))
file_id.write('{0:<50} {1}\n'.format('assembly_software = {0}'.format(assembly_software), '# assembly software: {0} ({1}) or {2} ({3}) or {4} ({5}) or {6} ({7}) or {8} ({9}) or {10} ({11})'.format(xlib.get_soapdenovotrans_code(), xlib.get_soapdenovotrans_name(), xlib.get_transabyss_code(), xlib.get_transabyss_name(), xlib.get_trinity_code(), xlib.get_trinity_name(), xlib.get_star_code(), xlib.get_star_name(), xlib.get_cd_hit_est_code(), xlib.get_cd_hit_est_name(), xlib.get_transcript_filter_code(), xlib.get_transcript_filter_name())))
file_id.write('{0:<50} {1}\n'.format('assembly_dataset_id = {0}'.format(assembly_dataset_id), '# assembly dataset identification'))
file_id.write('{0:<50} {1}\n'.format('assembly_type = {0}'.format(assembly_type), '# CONTIGS or SCAFFOLDS in {0}; NONE in {1}, {2}, {3}, {4} and {5}'.format(xlib.get_soapdenovotrans_name(), xlib.get_transabyss_name(), xlib.get_trinity_name(), xlib.get_star_name(), xlib.get_cd_hit_est_name(), xlib.get_transcript_filter_name())))
file_id.write('{0}\n'.format(''))
file_id.write('{0}\n'.format('# This section has the information to set the QUAST parameters'))
file_id.write('{0}\n'.format('[QUAST parameters]'))
file_id.write('{0:<50} {1}\n'.format('threads = 2', '# number of threads for use'))
except:
error_list.append('*** ERROR: The file {0} can not be recreated'.format(get_quast_config_file()))
OK = False
# return the control variable and the error list
return (OK, error_list)
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(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, 'master')
for error in error_list:
log.write('{0}\n'.format(error))
# get experiment identification
if OK:
experiment_id = cinputs.input_experiment_id(ssh_client, help=True)
if experiment_id == '':
print('WARNING: The cluster {0} has not experiment data.'.format(cluster_name))
OK = False
# get the result dataset list of the experiment
if OK:
command = 'cd {0}/{1}; for list in `ls`; do ls -ld $list | grep -v ^- > /dev/null && echo $list; done;'.format(xlib.get_cluster_result_dir(), experiment_id)
(OK, stdout, stderr) = 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('*** WARNING: There is not any result dataset of the experiment {0}.'.format(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_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_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_est_name()
elif result_dataset_id.startswith(xlib.get_cd_hit_code()+'-'):
bioinfo_app_name = xlib.get_cd_hit_est_name()
elif result_dataset_id.startswith(xlib.get_detonate_code()+'-'):
bioinfo_app_name = xlib.get_detonate_name()
elif result_dataset_id.startswith(xlib.get_emboss_code()+'-'):
bioinfo_app_name = xlib.get_emboss_name()
elif result_dataset_id.startswith(xlib.get_fastqc_code()+'-'):
bioinfo_app_name = xlib.get_fastqc_name()
elif result_dataset_id.startswith(xlib.get_gmap_code()+'-'):
bioinfo_app_name = xlib.get_gmap_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_gzip_code()+'-'):
bioinfo_app_name = xlib.get_gzip_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_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_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_samtools_code()+'-'):
bioinfo_app_name = xlib.get_samtools_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_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_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()
else:
bioinfo_app_name = 'xxx'
print(line_template.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 create_busco_config_file(experiment_id='exp001', assembly_dataset_id='sdnt-170101-235959', assembly_type='CONTIGS'):
'''
Create BUSCO config file with the default options. It is necessary
update the options in each run.
'''
# initialize the control variable and the error list
OK = True
error_list = []
# set the assembly software
if assembly_dataset_id.startswith(xlib.get_soapdenovotrans_code()):
assembly_software = xlib.get_soapdenovotrans_code()
elif assembly_dataset_id.startswith(xlib.get_transabyss_code()):
assembly_software = xlib.get_transabyss_code()
elif assembly_dataset_id.startswith(xlib.get_trinity_code()):
assembly_software = xlib.get_trinity_code()
elif assembly_dataset_id.startswith(xlib.get_star_code()):
assembly_software = xlib.get_star_code()
elif assembly_dataset_id.startswith(xlib.get_cd_hit_est_code()):
assembly_software = xlib.get_cd_hit_est_code()
elif assembly_dataset_id.startswith(xlib.get_transcript_filter_code()):
assembly_software = xlib.get_transcript_filter_code()
# create the BUSCO config file and write the default options
try:
if not os.path.exists(os.path.dirname(get_busco_config_file())):
os.makedirs(os.path.dirname(get_busco_config_file()))
with open(get_busco_config_file(), mode='w', encoding='utf8') as file_id:
file_id.write('{0}\n'.format('# You must review the information of this file and update the values with the corresponding ones to the current run.'))
file_id.write('{0}\n'.format('#'))
file_id.write('{0}\n'.format('# The reference file must be located in the cluster directory {0}/experiment_id/reference_dataset_id'.format(xlib.get_cluster_reference_dir())))
file_id.write('{0}\n'.format('# The assembly files must be located in the cluster directory {0}/experiment_id/assembly_dataset_id'.format(xlib.get_cluster_result_dir())))
file_id.write('{0}\n'.format('# The experiment_id and assembly_dataset_id names are fixed in the identification section.'))
file_id.write('{0}\n'.format('#'))
file_id.write('{0}\n'.format('# In section "BUSCO parameters", the key "augustus_options" allows you to input additional August parameters in the format:'))
file_id.write('{0}\n'.format('#'))
file_id.write('{0}\n'.format('# augustus_options = --parameter-1[=value-1][; --parameter-2[=value-2][; ...; --parameter-n[=value-n]]]'))
file_id.write('{0}\n'.format('#'))
file_id.write('{0}\n'.format('# parameter-i is a parameter name of Augustus and value-i a valid value of parameter-i, e.g.'))
file_id.write('{0}\n'.format('#'))
file_id.write('{0}\n'.format('# augustus_options = --translation_table=6 --progress=true)'))
file_id.write('{0}\n'.format('#'))
file_id.write('{0}\n'.format('# You can consult the parameters of BUSCO and their meaning in http://busco.ezlab.org/.'))
file_id.write('{0}\n'.format('# and August ones in http://bioinf.uni-greifswald.de/augustus/.'))
file_id.write('{0}\n'.format(''))
file_id.write('{0}\n'.format('# This section has the information identifies the experiment.'))
file_id.write('{0}\n'.format('[identification]'))
file_id.write('{0:<50} {1}\n'.format('experiment_id = {0}'.format(experiment_id), '# experiment identification'))
file_id.write('{0:<50} {1}\n'.format('assembly_software = {0}'.format(assembly_software), '# assembly software: {0} ({1}) or {2} ({3}) or {4} ({5}) or {6} ({7}) or {8} ({9}) or {10} ({11})'.format(xlib.get_soapdenovotrans_code(), xlib.get_soapdenovotrans_name(), xlib.get_transabyss_code(), xlib.get_transabyss_name(), xlib.get_trinity_code(), xlib.get_trinity_name(), xlib.get_star_code(), xlib.get_star_name(), xlib.get_cd_hit_est_code(), xlib.get_cd_hit_est_name(), xlib.get_transcript_filter_code(), xlib.get_transcript_filter_name())))
file_id.write('{0:<50} {1}\n'.format('assembly_dataset_id = {0}'.format(assembly_dataset_id), '# assembly dataset identification'))
file_id.write('{0:<50} {1}\n'.format('assembly_type = {0}'.format(assembly_type), '# CONTIGS or SCAFFOLDS in {0}; NONE in {1}, {2}, {3}, {4} and {5}'.format(xlib.get_soapdenovotrans_name(), xlib.get_transabyss_name(), xlib.get_trinity_name(), xlib.get_star_name(), xlib.get_cd_hit_est_name(), xlib.get_transcript_filter_name())))
file_id.write('{0}\n'.format(''))
file_id.write('{0}\n'.format('# This section has the information to set the BUSCO parameters'))
file_id.write('{0}\n'.format('[BUSCO parameters]'))
file_id.write('{0:<50} {1}\n'.format('ncpu = 2', '# number of threads/cores for use'))
file_id.write('{0:<50} {1}\n'.format('lineage_data = embryophyta_odb9', '# value to find the lineage data url in BUSCO web (e.g. embryophyta -> http://busco.ezlab.org/v2/datasets/embryophyta_odb9.tar.gz)'))
file_id.write('{0:<50} {1}\n'.format('mode = tran', '# geno (genome assemblies, DNA) or tran (transcriptome assemblies, DNA) or prot (annotated gene sets, proteins)'))
file_id.write('{0:<50} {1}\n'.format('evalue = 1e-03', '# E-value cutoff for BLAST searches'))
file_id.write('{0:<50} {1}\n'.format('limit = 3', '# number of candidate regions to consider'))
file_id.write('{0:<50} {1}\n'.format('species = NONE', '# identifier of existing Augustus species gene finding parameters or NONE'))
file_id.write('{0:<50} {1}\n'.format('long = NO', '# Augustus optimization mode for self-training: YES or NO'))
file_id.write('{0:<50} {1}\n'.format('augustus_options = NONE', '# additional parameters to August or NONE'))
except:
error_list.append('*** ERROR: The file {0} can not be recreated'.format(get_busco_config_file()))
OK = False
# return the control variable and the error list
return (OK, error_list)
def execute(self, event=None):
'''
Execute the list the result logs in the cluster.
'''
# validate inputs
OK = self.validate_inputs()
if not OK:
message = 'Some input values are not OK.'
tkinter.messagebox.showerror('{0} - {1}'.format(xlib.get_project_name(), self.head), message)
# get the run dictionary of the experiment
if OK:
# -- command = 'ls {0}/{1}'.format(xlib.get_cluster_result_dir(), self.wrapper_experiment_id.get())
command = 'cd {0}/{1}; for list in `ls`; do ls -ld $list | grep -v ^- > /dev/null && echo $list; done;'.format(xlib.get_cluster_result_dir(), self.wrapper_experiment_id.get())
(OK, stdout, stderr) = xssh.execute_cluster_command(self.ssh_client, command)
if OK:
result_dataset_dict = {}
for line in stdout:
line = line.rstrip('\n')
if line != 'lost+found':
result_dataset_id = line
try:
pattern = r'^(.+)\-(.+)\-(.+)$'
mo = re.search(pattern, result_dataset_id)
bioinfo_app_code = mo.group(1).strip()
yymmdd = mo.group(2)
hhmmss = mo.group(3)
date = '20{0}-{1}-{2}'.format(yymmdd[:2], yymmdd[2:4], yymmdd[4:])
time = '{0}:{1}:{2}'.format(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_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_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_detonate_code()+'-'):
bioinfo_app_name = xlib.get_detonate_name()
elif result_dataset_id.startswith(xlib.get_emboss_code()+'-'):
bioinfo_app_name = xlib.get_emboss_name()
elif result_dataset_id.startswith(xlib.get_fastqc_code()+'-'):
bioinfo_app_name = xlib.get_fastqc_name()
elif result_dataset_id.startswith(xlib.get_gmap_code()+'-'):
bioinfo_app_name = xlib.get_gmap_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_gzip_code()+'-'):
bioinfo_app_name = xlib.get_gzip_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_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_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_samtools_code()+'-'):
bioinfo_app_name = xlib.get_samtools_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_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_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()
else:
bioinfo_app_name = 'xxx'
result_dataset_dict[result_dataset_id] = {'experiment_id': self.wrapper_experiment_id.get(), 'result_dataset_id': result_dataset_id, 'bioinfo_app': bioinfo_app_name, 'date': date, 'time': time}
# verify if there are any nodes running
if OK:
if result_dataset_dict == {}:
message = 'There is not any run.'
tkinter.messagebox.showwarning('{0} - {1}'.format(xlib.get_project_name(), self.head), message)
# build the data list
if OK:
data_list = ['experiment_id', 'result_dataset_id', 'bioinfo_app', 'date', 'time']
# build the data dictionary
if OK:
data_dict = {}
data_dict['experiment_id']= {'text': 'Experiment id. / Process', 'width': 200, 'aligment': 'left'}
data_dict['result_dataset_id'] = {'text': 'Result dataset', 'width': 200, 'aligment': 'left'}
data_dict['bioinfo_app'] = {'text': 'Bioinfo app / Utility', 'width': 200, 'aligment': 'left'}
data_dict['date'] = {'text': 'Date', 'width': 80, 'aligment': 'right'}
data_dict['time'] = {'text': 'Time', 'width': 80, 'aligment': 'right'}
# create the dialog Table to show the nodes running
if OK:
dialog_table = gdialogs.DialogTable(self, 'Experiment runs in {0}/{1}'.format(xlib.get_cluster_result_dir(), self.wrapper_experiment_id.get()), 400, 900, data_list, data_dict, result_dataset_dict, 'view_result_logs', [self.wrapper_cluster_name.get()])
self.wait_window(dialog_table)
# close the form
if OK:
self.close()