def __init__(self, main, app):
'''
Execute actions correspending to the creation of a "FormInstallBioinfoApp" instance.
'''
# save initial parameters in instance variables
self.main = main
self.root = main.root
self.container = main.container
self.app_code = app
# call the init method of the parent class
tkinter.Frame.__init__(self, self.container)
# set cursor to show busy status
self.root.config(cursor='watch')
self.root.update()
# set the software name
if self.app_code == xlib.get_blastplus_code():
self.app_name = xlib.get_blastplus_name()
elif self.app_code == xlib.get_diamond_code():
self.app_name = xlib.get_diamond_name()
elif self.app_code == xlib.get_entrez_direct_code():
self.app_name = xlib.get_entrez_direct_name()
elif self.app_code == xlib.get_miniconda3_code():
self.app_name = xlib.get_miniconda3_name()
elif self.app_code == xlib.get_r_code():
self.app_name = xlib.get_r_name()
elif self.app_code == xlib.get_transdecoder_code():
self.app_name = xlib.get_transdecoder_name()
# assign the text of the "head"
self.head = f'{self.app_name} - Install software'
# create the wrappers to track changes in the inputs
pass
# build the graphical user interface
self.build_gui()
# load initial data in inputs
self.initialize_inputs()
# set cursor to show normal status
self.root.config(cursor='')
self.root.update()
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 build_gmap_process_script(cluster_name, current_run_dir):
'''
Build the current GMAP process script.
'''
# initialize the control variable and the error list
OK = True
error_list = []
# get the GMAP option dictionary
gmap_option_dict = xlib.get_option_dict(get_gmap_config_file())
# get the options
experiment_id = gmap_option_dict['identification']['experiment_id']
reference_dataset_id = gmap_option_dict['identification']['reference_dataset_id']
reference_file = gmap_option_dict['identification']['reference_file']
assembly_software = gmap_option_dict['identification']['assembly_software']
assembly_dataset_id = gmap_option_dict['identification']['assembly_dataset_id']
assembly_type = gmap_option_dict['identification']['assembly_type']
threads = gmap_option_dict['GMAP parameters']['threads']
kmer = gmap_option_dict['GMAP parameters']['kmer']
sampling = gmap_option_dict['GMAP parameters']['sampling']
input_buffer_size = gmap_option_dict['GMAP parameters']['input-buffer-size']
output_buffer_size = gmap_option_dict['GMAP parameters']['output-buffer-size']
prunelevel = gmap_option_dict['GMAP parameters']['prunelevel']
format = gmap_option_dict['GMAP parameters']['format']
other_parameters = gmap_option_dict['GMAP parameters']['other_parameters']
# set the cluster reference dataset directory
cluster_reference_dataset_dir = xlib.get_cluster_reference_dataset_dir(reference_dataset_id)
# set the cluster reference file
cluster_reference_file = xlib.get_cluster_reference_file(reference_dataset_id, reference_file)
# set the GMAP database name
reference_file_name, reference_file_extension = os.path.splitext(reference_file)
gmap_database = '{0}-gmap_database'.format(reference_file_name)
# set the transcriptome file path
if assembly_software == xlib.get_soapdenovotrans_code():
if assembly_type.upper() == 'CONTIGS':
transcriptome_file = '{0}/{1}-{2}.contig'.format(xlib.get_cluster_experiment_result_dataset_dir(experiment_id, assembly_dataset_id), experiment_id, assembly_dataset_id)
elif assembly_type.upper() == 'SCAFFOLDS':
transcriptome_file = '{0}/{1}-{2}.scafSeq'.format(xlib.get_cluster_experiment_result_dataset_dir(experiment_id, assembly_dataset_id), experiment_id, assembly_dataset_id)
elif assembly_software == xlib.get_transabyss_code():
transcriptome_file = '{0}/transabyss-final.fa'.format(xlib.get_cluster_experiment_result_dataset_dir(experiment_id, assembly_dataset_id))
elif assembly_software == xlib.get_trinity_code():
transcriptome_file = '{0}/Trinity.fasta'.format(xlib.get_cluster_experiment_result_dataset_dir(experiment_id, assembly_dataset_id))
elif assembly_software == xlib.get_star_code():
transcriptome_file = '{0}/Trinity-GG.fasta'.format(xlib.get_cluster_experiment_result_dataset_dir(experiment_id, assembly_dataset_id))
elif assembly_software == xlib.get_cd_hit_est_code():
transcriptome_file = '{0}/clustered-transcriptome.fasta'.format(xlib.get_cluster_experiment_result_dataset_dir(experiment_id, assembly_dataset_id))
elif assembly_software == xlib.get_transcript_filter_code():
transcriptome_file = '{0}/filtered-transcriptome.fasta'.format(xlib.get_cluster_experiment_result_dataset_dir(experiment_id, assembly_dataset_id))
# set the output file path
output_file = 'gmap_output_{0}.txt'.format(format.lower())
# get the GMAP process script name
gmap_process_script = get_gmap_process_script()
# write the GMAP process script
try:
if not os.path.exists(os.path.dirname(gmap_process_script)):
os.makedirs(os.path.dirname(gmap_process_script))
with open(gmap_process_script, mode='w', encoding='utf8', newline='\n') as file_id:
file_id.write('{0}\n'.format('#!/bin/bash'))
file_id.write('{0}\n'.format('#-------------------------------------------------------------------------------'))
file_id.write('{0}\n'.format('GMAP_GSNAP_PATH={0}/{1}/envs/{2}/bin'.format(xlib.get_cluster_app_dir(), xlib.get_miniconda3_name(), xlib.get_gmap_gsnap_bioconda_code())))
file_id.write('{0}\n'.format('PATH=$GMAP_GSNAP_PATH:$PATH'))
file_id.write('{0}\n'.format('SEP="#########################################"'))
file_id.write('{0}\n'.format('cd {0}/{1}/bin'.format(xlib.get_cluster_app_dir(), xlib.get_miniconda3_name())))
file_id.write('{0}\n'.format('source activate {0}'.format(xlib.get_gmap_gsnap_bioconda_code())))
file_id.write('{0}\n'.format('#-------------------------------------------------------------------------------'))
file_id.write('{0}\n'.format('function init'))
file_id.write('{0}\n'.format('{'))
file_id.write('{0}\n'.format(' INIT_DATETIME=`date --utc +%s`'))
file_id.write('{0}\n'.format(' FORMATTED_INIT_DATETIME=`date --date="@$INIT_DATETIME" "+%Y-%m-%d %H:%M:%S"`'))
file_id.write('{0}\n'.format(' echo "$SEP"'))
file_id.write('{0}\n'.format(' echo "Script started in node $HOSTNAME of cluster {0} at $FORMATTED_INIT_DATETIME UTC."'.format(cluster_name)))
file_id.write('{0}\n'.format('}'))
file_id.write('{0}\n'.format('#-------------------------------------------------------------------------------'))
file_id.write('{0}\n'.format('function build_gmap_database'))
file_id.write('{0}\n'.format('{'))
file_id.write('{0}\n'.format(' cd {0}'.format(current_run_dir)))
file_id.write('{0}\n'.format(' echo "$SEP"'))
file_id.write('{0}\n'.format(' /usr/bin/time \\'))
file_id.write('{0}\n'.format(' --format="$SEP\\nElapsed real time (s): %e\\nCPU time in kernel mode (s): %S\\nCPU time in user mode (s): %U\\nPercentage of CPU: %P\\nMaximum resident set size(Kb): %M\\nAverage total memory use (Kb):%K" \\'))
file_id.write('{0}\n'.format(' gmap_build \\'))
file_id.write('{0}\n'.format(' --dir={0}\\'.format(cluster_reference_dataset_dir)))
file_id.write('{0}\n'.format(' --db={0}\\'.format(gmap_database)))
if kmer.upper() != 'NONE':
file_id.write('{0}\n'.format(' --kmer={0} \\'.format(kmer)))
file_id.write('{0}\n'.format(' {0}'.format(cluster_reference_file)))
file_id.write('{0}\n'.format('}'))
file_id.write('{0}\n'.format('#-------------------------------------------------------------------------------'))
file_id.write('{0}\n'.format('function run_gmap_process'))
file_id.write('{0}\n'.format('{'))
file_id.write('{0}\n'.format(' cd {0}'.format(current_run_dir)))
file_id.write('{0}\n'.format(' echo "$SEP"'))
file_id.write('{0}\n'.format(' gmap --version'))
file_id.write('{0}\n'.format(' echo "$SEP"'))
file_id.write('{0}\n'.format(' /usr/bin/time \\'))
file_id.write('{0}\n'.format(' --format="$SEP\\nElapsed real time (s): %e\\nCPU time in kernel mode (s): %S\\nCPU time in user mode (s): %U\\nPercentage of CPU: %P\\nMaximum resident set size(Kb): %M\\nAverage total memory use (Kb):%K" \\'))
file_id.write('{0}\n'.format(' gmap \\'))
file_id.write('{0}\n'.format(' --nthreads={0} \\'.format(threads)))
file_id.write('{0}\n'.format(' --dir={0} \\'.format(cluster_reference_dataset_dir)))
file_id.write('{0}\n'.format(' --db={0} \\'.format(gmap_database)))
if kmer.upper() != 'NONE':
file_id.write('{0}\n'.format(' --kmer={0} \\'.format(kmer)))
if sampling.upper() != 'NONE':
file_id.write('{0}\n'.format(' --sampling={0} \\'.format(sampling)))
file_id.write('{0}\n'.format(' --input-buffer-size={0} \\'.format(input_buffer_size)))
file_id.write('{0}\n'.format(' --output-buffer-size={0} \\'.format(output_buffer_size)))
file_id.write('{0}\n'.format(' --prunelevel={0} \\'.format(prunelevel)))
if format.upper() == 'COMPRESS':
file_id.write('{0}\n'.format(' --compress \\'))
elif format.upper() == 'SUMMARY':
file_id.write('{0}\n'.format(' --summary \\'))
elif format.upper() == 'ALIGN':
file_id.write('{0}\n'.format(' --align \\'))
else:
file_id.write('{0}\n'.format(' --format={0} \\'.format(format.lower())))
file_id.write('{0}\n'.format(' --ordered \\'))
file_id.write('{0}\n'.format(' --nofails \\'))
if other_parameters.upper() != 'NONE':
parameter_list = [x.strip() for x in other_parameters.split(';')]
for i in range(len(parameter_list)):
if parameter_list[i].find('=') > 0:
pattern = r'^--(.+)=(.+)$'
mo = re.search(pattern, parameter_list[i])
parameter_name = mo.group(1).strip()
parameter_value = mo.group(2).strip()
file_id.write('{0}\n'.format(' --{0}={1} \\'.format(parameter_name, parameter_value)))
else:
pattern = r'^--(.+)$'
mo = re.search(pattern, parameter_list[i])
parameter_name = mo.group(1).strip()
file_id.write('{0}\n'.format(' --{0} \\'.format(parameter_name)))
file_id.write('{0}\n'.format(' {0} \\'.format(transcriptome_file)))
file_id.write('{0}\n'.format(' > {0}'.format(output_file)))
file_id.write('{0}\n'.format(' RC=$?'))
file_id.write('{0}\n'.format(' if [ $RC -ne 0 ]; then manage_error gmap $RC; fi'))
file_id.write('{0}\n'.format('}'))
file_id.write('{0}\n'.format('#-------------------------------------------------------------------------------'))
file_id.write('{0}\n'.format('function end'))
file_id.write('{0}\n'.format('{'))
file_id.write('{0}\n'.format(' END_DATETIME=`date --utc +%s`'))
file_id.write('{0}\n'.format(' FORMATTED_END_DATETIME=`date --date="@$END_DATETIME" "+%Y-%m-%d %H:%M:%S"`'))
file_id.write('{0}\n'.format(' calculate_duration'))
file_id.write('{0}\n'.format(' echo "$SEP"'))
file_id.write('{0}\n'.format(' echo "Script ended OK at $FORMATTED_END_DATETIME UTC with a run duration of $DURATION s ($FORMATTED_DURATION)."'))
file_id.write('{0}\n'.format(' echo "$SEP"'))
file_id.write('{0}\n'.format(' RECIPIENT={0}'.format(xconfiguration.get_contact_data())))
file_id.write('{0}\n'.format(' SUBJECT="{0}: {1} process"'.format(xlib.get_project_name(), xlib.get_gmap_name())))
file_id.write('{0}\n'.format(' MESSAGE="The {0} process in node $HOSTNAME of cluster {1} ended OK at $FORMATTED_END_DATETIME with a run duration of $DURATION s ($FORMATTED_DURATION). Please review its log.<br/><br/>Regards,<br/>GI Genetica, Fisiologia e Historia Forestal<br/>Dpto. Sistemas y Recursos Naturales<br/>ETSI Montes, Forestal y del Medio Natural<br/>Universidad Politecnica de Madrid<br/>https://github.com/ggfhf/"'.format(xlib.get_gmap_name(), cluster_name)))
file_id.write('{0}\n'.format(' mail --append "Content-type: text/html;" --subject "$SUBJECT" "$RECIPIENT" <<< "$MESSAGE"'))
file_id.write('{0}\n'.format(' exit 0'))
file_id.write('{0}\n'.format('}'))
file_id.write('{0}\n'.format('#-------------------------------------------------------------------------------'))
file_id.write('{0}\n'.format('function manage_error'))
file_id.write('{0}\n'.format('{'))
file_id.write('{0}\n'.format(' END_DATETIME=`date --utc +%s`'))
file_id.write('{0}\n'.format(' FORMATTED_END_DATETIME=`date --date="@$END_DATETIME" "+%Y-%m-%d %H:%M:%S"`'))
file_id.write('{0}\n'.format(' calculate_duration'))
file_id.write('{0}\n'.format(' echo "$SEP"'))
file_id.write('{0}\n'.format(' echo "ERROR: $1 returned error $2"'))
file_id.write('{0}\n'.format(' echo "Script ended WRONG at $FORMATTED_END_DATETIME UTC with a run duration of $DURATION s ($FORMATTED_DURATION)."'))
file_id.write('{0}\n'.format(' echo "$SEP"'))
file_id.write('{0}\n'.format(' RECIPIENT={0}'.format(xconfiguration.get_contact_data())))
file_id.write('{0}\n'.format(' SUBJECT="{0}: {1} process"'.format(xlib.get_project_name(), xlib.get_gmap_name())))
file_id.write('{0}\n'.format(' MESSAGE="The {0} process in node $HOSTNAME of cluster {1} ended WRONG at $FORMATTED_END_DATETIME with a run duration of $DURATION s ($FORMATTED_DURATION). Please review its log.<br/><br/>Regards,<br/>GI Genetica, Fisiologia e Historia Forestal<br/>Dpto. Sistemas y Recursos Naturales<br/>ETSI Montes, Forestal y del Medio Natural<br/>Universidad Politecnica de Madrid<br/>https://github.com/ggfhf/"'.format(xlib.get_gmap_name(), cluster_name)))
file_id.write('{0}\n'.format(' mail --append "Content-type: text/html;" --subject "$SUBJECT" "$RECIPIENT" <<< "$MESSAGE"'))
file_id.write('{0}\n'.format(' exit 3'))
file_id.write('{0}\n'.format('}'))
file_id.write('{0}\n'.format('#-------------------------------------------------------------------------------'))
file_id.write('{0}\n'.format('function calculate_duration'))
file_id.write('{0}\n'.format('{'))
file_id.write('{0}\n'.format(' DURATION=`expr $END_DATETIME - $INIT_DATETIME`'))
file_id.write('{0}\n'.format(' HH=`expr $DURATION / 3600`'))
file_id.write('{0}\n'.format(' MM=`expr $DURATION % 3600 / 60`'))
file_id.write('{0}\n'.format(' SS=`expr $DURATION % 60`'))
file_id.write('{0}\n'.format(' FORMATTED_DURATION=`printf "%03d:%02d:%02d\\n" $HH $MM $SS`'))
file_id.write('{0}\n'.format('}'))
file_id.write('{0}\n'.format('#-------------------------------------------------------------------------------'))
file_id.write('{0}\n'.format('init'))
file_id.write('{0}\n'.format('build_gmap_database'))
file_id.write('{0}\n'.format('run_gmap_process'))
file_id.write('{0}\n'.format('end'))
except:
error_list.append('*** ERROR: The file {0} can not be created'.format(gmap_process_script))
OK = False
# return the control variable and the error list
return (OK, error_list)
def build_cd_hit_est_process_script(cluster_name, current_run_dir):
'''
Build the current CD-HIT-EST process script.
'''
# initialize the control variable and the error list
OK = True
error_list = []
# get the option dictionary
cd_hit_est_option_dict = xlib.get_option_dict(get_cd_hit_est_config_file())
# get the options
experiment_id = cd_hit_est_option_dict['identification']['experiment_id']
assembly_software = cd_hit_est_option_dict['identification'][
'assembly_software']
assembly_dataset_id = cd_hit_est_option_dict['identification'][
'assembly_dataset_id']
assembly_type = cd_hit_est_option_dict['identification']['assembly_type']
threads = cd_hit_est_option_dict['CD-HIT-EST parameters']['threads']
memory_limit = cd_hit_est_option_dict['CD-HIT-EST parameters'][
'memory_limit']
seq_identity_threshold = cd_hit_est_option_dict['CD-HIT-EST parameters'][
'seq_identity_threshold']
word_length = cd_hit_est_option_dict['CD-HIT-EST parameters'][
'word_length']
mask = cd_hit_est_option_dict['CD-HIT-EST parameters']['mask']
match = cd_hit_est_option_dict['CD-HIT-EST parameters']['match']
mismatch = cd_hit_est_option_dict['CD-HIT-EST parameters']['mismatch']
other_parameters = cd_hit_est_option_dict['CD-HIT-EST parameters'][
'other_parameters']
# set the transcriptome file path
if assembly_software == xlib.get_soapdenovotrans_code():
if assembly_type == 'CONTIGS':
transcriptome_file = '{0}/{1}-{2}.contig'.format(
xlib.get_cluster_experiment_result_dataset_dir(
experiment_id, assembly_dataset_id), experiment_id,
assembly_dataset_id)
elif assembly_type == 'SCAFFOLDS':
transcriptome_file = '{0}/{1}-{2}.scafSeq'.format(
xlib.get_cluster_experiment_result_dataset_dir(
experiment_id, assembly_dataset_id), experiment_id,
assembly_dataset_id)
elif assembly_software == xlib.get_transabyss_code():
transcriptome_file = '{0}/transabyss-final.fa'.format(
xlib.get_cluster_experiment_result_dataset_dir(
experiment_id, assembly_dataset_id))
elif assembly_software == xlib.get_trinity_code():
transcriptome_file = '{0}/Trinity.fasta'.format(
xlib.get_cluster_experiment_result_dataset_dir(
experiment_id, assembly_dataset_id))
elif assembly_software == xlib.get_star_code():
transcriptome_file = '{0}/Trinity-GG.fasta'.format(
xlib.get_cluster_experiment_result_dataset_dir(
experiment_id, assembly_dataset_id))
elif assembly_software == xlib.get_cd_hit_est_code():
transcriptome_file = '{0}/clustered-transcriptome.fasta'.format(
xlib.get_cluster_experiment_result_dataset_dir(
experiment_id, assembly_dataset_id))
elif assembly_software == xlib.get_transcript_filter_code():
transcriptome_file = '{0}/filtered-transcriptome.fasta'.format(
xlib.get_cluster_experiment_result_dataset_dir(
experiment_id, assembly_dataset_id))
# set the output file path
if OK:
output_file = '{0}/clustered-transcriptome.fasta'.format(
current_run_dir)
# write the CD-HIT-EST process script
try:
if not os.path.exists(os.path.dirname(
get_cd_hit_est_process_script())):
os.makedirs(os.path.dirname(get_cd_hit_est_process_script()))
with open(get_cd_hit_est_process_script(),
mode='w',
encoding='utf8',
newline='\n') as file_id:
file_id.write('{0}\n'.format('#!/bin/bash'))
file_id.write('{0}\n'.format(
'#-------------------------------------------------------------------------------'
))
file_id.write('{0}\n'.format(
'CDHIT_PATH={0}/{1}/envs/{2}/bin'.format(
xlib.get_cluster_app_dir(), xlib.get_miniconda3_name(),
xlib.get_cd_hit_bioconda_code())))
file_id.write('{0}\n'.format('PATH=$CDHIT_PATH:$PATH'))
file_id.write('{0}\n'.format(
'SEP="#########################################"'))
file_id.write('{0}\n'.format('cd {0}/{1}/bin'.format(
xlib.get_cluster_app_dir(), xlib.get_miniconda3_name())))
file_id.write('{0}\n'.format('source activate {0}'.format(
xlib.get_cd_hit_bioconda_code())))
file_id.write('{0}\n'.format(
'#-------------------------------------------------------------------------------'
))
file_id.write('{0}\n'.format('function init'))
file_id.write('{0}\n'.format('{'))
file_id.write('{0}\n'.format(' INIT_DATETIME=`date --utc +%s`'))
file_id.write('{0}\n'.format(
' FORMATTED_INIT_DATETIME=`date --date="@$INIT_DATETIME" "+%Y-%m-%d %H:%M:%S"`'
))
file_id.write('{0}\n'.format(' echo "$SEP"'))
file_id.write('{0}\n'.format(
' echo "Script started in node $HOSTNAME of cluster {0} at $FORMATTED_INIT_DATETIME UTC."'
.format(cluster_name)))
file_id.write('{0}\n'.format('}'))
file_id.write('{0}\n'.format(
'#-------------------------------------------------------------------------------'
))
file_id.write('{0}\n'.format('function run_cd_hit_est_process'))
file_id.write('{0}\n'.format('{'))
file_id.write('{0}\n'.format(' cd {0}'.format(current_run_dir)))
file_id.write('{0}\n'.format(' echo "$SEP"'))
file_id.write('{0}\n'.format(
' echo "Running {0} process ..."'.format(
xlib.get_cd_hit_est_name())))
file_id.write('{0}\n'.format(' /usr/bin/time \\'))
file_id.write('{0}\n'.format(
' --format="$SEP\\nElapsed real time (s): %e\\nCPU time in kernel mode (s): %S\\nCPU time in user mode (s): %U\\nPercentage of CPU: %P\\nMaximum resident set size(Kb): %M\\nAverage total memory use (Kb):%K" \\'
))
file_id.write('{0}\n'.format(' cd-hit-est \\'))
file_id.write('{0}\n'.format(
' -T {0} \\'.format(threads)))
file_id.write('{0}\n'.format(
' -M {0} \\'.format(memory_limit)))
file_id.write('{0}\n'.format(
' -i {0} \\'.format(transcriptome_file)))
file_id.write('{0}\n'.format(
' -c {0} \\'.format(seq_identity_threshold)))
file_id.write('{0}\n'.format(
' -n {0} \\'.format(word_length)))
file_id.write('{0}\n'.format(
' -mask {0} \\'.format(mask)))
file_id.write('{0}\n'.format(
' -match {0} \\'.format(match)))
file_id.write('{0}\n'.format(
' -mismatch {0} \\'.format(mismatch)))
if other_parameters.upper() == 'NONE':
file_id.write('{0}\n'.format(
' -o {0}'.format(output_file)))
else:
file_id.write('{0}\n'.format(
' -o {0} \\'.format(output_file)))
parameter_list = [
x.strip() for x in other_parameters.split(';')
]
for i in range(len(parameter_list)):
if parameter_list[i].find('=') > 0:
pattern = r'^--(.+)=(.+)$'
mo = re.search(pattern, parameter_list[i])
parameter_name = mo.group(1).strip()
parameter_value = mo.group(2).strip()
if i < len(parameter_list) - 1:
file_id.write('{0}\n'.format(
' -{0} {1} \\'.format(
parameter_name, parameter_value)))
else:
file_id.write('{0}\n'.format(
' -{0} {1}'.format(
parameter_name, parameter_value)))
else:
pattern = r'^--(.+)$'
mo = re.search(pattern, parameter_list[i])
parameter_name = mo.group(1).strip()
if i < len(parameter_list):
file_id.write('{0}\n'.format(
' -{0} \\'.format(parameter_name)))
else:
file_id.write('{0}\n'.format(
' -{0}'.format(parameter_name)))
i += 1
file_id.write('{0}\n'.format(' RC=$?'))
file_id.write('{0}\n'.format(
' if [ $RC -ne 0 ]; then manage_error cd-hit-est $RC; fi'))
file_id.write('{0}\n'.format('}'))
file_id.write('{0}\n'.format(
'#-------------------------------------------------------------------------------'
))
file_id.write('{0}\n'.format('function end'))
file_id.write('{0}\n'.format('{'))
file_id.write('{0}\n'.format(' END_DATETIME=`date --utc +%s`'))
file_id.write('{0}\n'.format(
' FORMATTED_END_DATETIME=`date --date="@$END_DATETIME" "+%Y-%m-%d %H:%M:%S"`'
))
file_id.write('{0}\n'.format(' calculate_duration'))
file_id.write('{0}\n'.format(' echo "$SEP"'))
file_id.write('{0}\n'.format(
' echo "Script ended OK at $FORMATTED_END_DATETIME UTC with a run duration of $DURATION s ($FORMATTED_DURATION)."'
))
file_id.write('{0}\n'.format(' echo "$SEP"'))
file_id.write('{0}\n'.format(' RECIPIENT={0}'.format(
xconfiguration.get_contact_data())))
file_id.write('{0}\n'.format(
' SUBJECT="{0}: {1} process"'.format(
xlib.get_project_name(), xlib.get_cd_hit_est_name())))
file_id.write('{0}\n'.format(
' MESSAGE="The {0} process in node $HOSTNAME of cluster {0} ended OK at $FORMATTED_END_DATETIME with a run duration of $DURATION s ($FORMATTED_DURATION). Please review its log.<br/><br/>Regards,<br/>GI Genetica, Fisiologia e Historia Forestal<br/>Dpto. Sistemas y Recursos Naturales<br/>ETSI Montes, Forestal y del Medio Natural<br/>Universidad Politecnica de Madrid<br/>https://github.com/ggfhf/"'
.format(xlib.get_rsem_eval_name(), cluster_name)))
file_id.write('{0}\n'.format(
' mail --append "Content-type: text/html;" --subject "$SUBJECT" "$RECIPIENT" <<< "$MESSAGE"'
))
file_id.write('{0}\n'.format(' exit 0'))
file_id.write('{0}\n'.format('}'))
file_id.write('{0}\n'.format(
'#-------------------------------------------------------------------------------'
))
file_id.write('{0}\n'.format('function manage_error'))
file_id.write('{0}\n'.format('{'))
file_id.write('{0}\n'.format(' END_DATETIME=`date --utc +%s`'))
file_id.write('{0}\n'.format(
' FORMATTED_END_DATETIME=`date --date="@$END_DATETIME" "+%Y-%m-%d %H:%M:%S"`'
))
file_id.write('{0}\n'.format(' calculate_duration'))
file_id.write('{0}\n'.format(' echo "$SEP"'))
file_id.write(
'{0}\n'.format(' echo "ERROR: $1 returned error $2"'))
file_id.write('{0}\n'.format(
' echo "Script ended WRONG at $FORMATTED_END_DATETIME UTC with a run duration of $DURATION s ($FORMATTED_DURATION)."'
))
file_id.write('{0}\n'.format(' echo "$SEP"'))
file_id.write('{0}\n'.format(' RECIPIENT={0}'.format(
xconfiguration.get_contact_data())))
file_id.write('{0}\n'.format(
' SUBJECT="{0}: {1} process"'.format(
xlib.get_project_name(), xlib.get_cd_hit_est_name())))
file_id.write('{0}\n'.format(
' MESSAGE="The {0} process in node $HOSTNAME of cluster {0} ended WRONG at $FORMATTED_END_DATETIME with a run duration of $DURATION s ($FORMATTED_DURATION). Please review its log.<br/><br/>Regards,<br/>GI Genetica, Fisiologia e Historia Forestal<br/>Dpto. Sistemas y Recursos Naturales<br/>ETSI Montes, Forestal y del Medio Natural<br/>Universidad Politecnica de Madrid<br/>https://github.com/ggfhf/"'
.format(xlib.get_rsem_eval_name(), cluster_name)))
file_id.write('{0}\n'.format(
' mail --append "Content-type: text/html;" --subject "$SUBJECT" "$RECIPIENT" <<< "$MESSAGE"'
))
file_id.write('{0}\n'.format(' exit 3'))
file_id.write('{0}\n'.format('}'))
file_id.write('{0}\n'.format(
'#-------------------------------------------------------------------------------'
))
file_id.write('{0}\n'.format('function calculate_duration'))
file_id.write('{0}\n'.format('{'))
file_id.write('{0}\n'.format(
' DURATION=`expr $END_DATETIME - $INIT_DATETIME`'))
file_id.write('{0}\n'.format(' HH=`expr $DURATION / 3600`'))
file_id.write(
'{0}\n'.format(' MM=`expr $DURATION % 3600 / 60`'))
file_id.write('{0}\n'.format(' SS=`expr $DURATION % 60`'))
file_id.write('{0}\n'.format(
' FORMATTED_DURATION=`printf "%03d:%02d:%02d\\n" $HH $MM $SS`'
))
file_id.write('{0}\n'.format('}'))
file_id.write('{0}\n'.format(
'#-------------------------------------------------------------------------------'
))
file_id.write('{0}\n'.format('init'))
file_id.write('{0}\n'.format('run_cd_hit_est_process'))
file_id.write('{0}\n'.format('end'))
except:
error_list.append('*** ERROR: The file {0} can not be created'.format(
get_cd_hit_est_process_script()))
OK = False
# return the control variable and the error list
return (OK, error_list)
def build_fastqc_process_script(cluster_name, current_run_dir):
'''
Build the current FastQC process script.
'''
# initialize the control variable and the error list
OK = True
error_list = []
# get the FastQC option dictionary
fastqc_option_dict = xlib.get_option_dict(get_fastqc_config_file())
# get the options
experiment_id = fastqc_option_dict['identification']['experiment_id']
read_dataset_id = fastqc_option_dict['identification']['read_dataset_id']
threads = fastqc_option_dict['FastQC parameters']['threads']
# get the sections list
sections_list = []
for section in fastqc_option_dict.keys():
sections_list.append(section)
sections_list.sort()
# build the file name list
file_name_list = []
for section in sections_list:
# if the section identification is like library-n
if re.match('^file-[0-9]+$', section):
file_name = fastqc_option_dict[section]['file_name']
file_name_list.append(file_name)
# write the FastQC process script
try:
if not os.path.exists(os.path.dirname(get_fastqc_process_script())):
os.makedirs(os.path.dirname(get_fastqc_process_script()))
with open(get_fastqc_process_script(),
mode='w',
encoding='utf8',
newline='\n') as file_id:
file_id.write('{0}\n'.format('#!/bin/bash'))
file_id.write('{0}\n'.format(
'#-------------------------------------------------------------------------------'
))
file_id.write('{0}\n'.format(
'FASTQC_PATH={0}/{1}/envs/{2}/bin'.format(
xlib.get_cluster_app_dir(), xlib.get_miniconda3_name(),
xlib.get_fastqc_bioconda_code())))
file_id.write('{0}\n'.format('PATH=$FASTQC_PATH:$PATH'))
file_id.write('{0}\n'.format(
'SEP="#########################################"'))
file_id.write('{0}\n'.format('cd {0}/{1}/bin'.format(
xlib.get_cluster_app_dir(), xlib.get_miniconda3_name())))
file_id.write('{0}\n'.format('source activate {0}'.format(
xlib.get_fastqc_bioconda_code())))
file_id.write('{0}\n'.format(
'#-------------------------------------------------------------------------------'
))
file_id.write('{0}\n'.format('function init'))
file_id.write('{0}\n'.format('{'))
file_id.write('{0}\n'.format(' INIT_DATETIME=`date --utc +%s`'))
file_id.write('{0}\n'.format(
' FORMATTED_INIT_DATETIME=`date --date="@$INIT_DATETIME" "+%Y-%m-%d %H:%M:%S"`'
))
file_id.write('{0}\n'.format(' echo "$SEP"'))
file_id.write('{0}\n'.format(
' echo "Script started in node $HOSTNAME of cluster {0} at $FORMATTED_INIT_DATETIME UTC."'
.format(cluster_name)))
file_id.write('{0}\n'.format('}'))
file_id.write('{0}\n'.format(
'#-------------------------------------------------------------------------------'
))
file_id.write('{0}\n'.format('function run_fastqc_process'))
file_id.write('{0}\n'.format('{'))
file_id.write('{0}\n'.format(' cd {0}'.format(current_run_dir)))
file_id.write('{0}\n'.format(' echo "$SEP"'))
file_id.write('{0}\n'.format(' fastqc --version'))
for file_name in file_name_list:
file_id.write('{0}\n'.format(' echo "$SEP"'))
file_id.write('{0}\n'.format(' /usr/bin/time \\'))
file_id.write('{0}\n'.format(
' --format="$SEP\\nElapsed real time (s): %e\\nCPU time in kernel mode (s): %S\\nCPU time in user mode (s): %U\\nPercentage of CPU: %P\\nMaximum resident set size(Kb): %M\\nAverage total memory use (Kb):%K" \\'
))
file_id.write('{0}\n'.format(' fastqc \\'))
file_id.write('{0}\n'.format(' {0} \\'.format(
xlib.get_cluster_read_file(experiment_id, read_dataset_id,
file_name))))
file_id.write('{0}\n'.format(
' --threads={0} \\'.format(threads)))
file_id.write('{0}\n'.format(
' --outdir={0}'.format(current_run_dir)))
file_id.write('{0}\n'.format(' RC=$?'))
file_id.write('{0}\n'.format(
' if [ $RC -ne 0 ]; then manage_error fastqc $RC; fi'))
file_id.write('{0}\n'.format('}'))
file_id.write('{0}\n'.format(
'#-------------------------------------------------------------------------------'
))
file_id.write('{0}\n'.format('function end'))
file_id.write('{0}\n'.format('{'))
file_id.write('{0}\n'.format(' END_DATETIME=`date --utc +%s`'))
file_id.write('{0}\n'.format(
' FORMATTED_END_DATETIME=`date --date="@$END_DATETIME" "+%Y-%m-%d %H:%M:%S"`'
))
file_id.write('{0}\n'.format(' calculate_duration'))
file_id.write('{0}\n'.format(' echo "$SEP"'))
file_id.write('{0}\n'.format(
' echo "Script ended OK at $FORMATTED_END_DATETIME UTC with a run duration of $DURATION s ($FORMATTED_DURATION)."'
))
file_id.write('{0}\n'.format(' echo "$SEP"'))
file_id.write('{0}\n'.format(' RECIPIENT={0}'.format(
xconfiguration.get_contact_data())))
file_id.write('{0}\n'.format(
' SUBJECT="{0}: {1} process"'.format(
xlib.get_project_name(), xlib.get_fastqc_name())))
file_id.write('{0}\n'.format(
' MESSAGE="The {0} process in node $HOSTNAME of cluster {1} ended OK at $FORMATTED_END_DATETIME with a run duration of $DURATION s ($FORMATTED_DURATION). Please review its log.<br/><br/>Regards,<br/>GI Genetica, Fisiologia e Historia Forestal<br/>Dpto. Sistemas y Recursos Naturales<br/>ETSI Montes, Forestal y del Medio Natural<br/>Universidad Politecnica de Madrid<br/>https://github.com/ggfhf/"'
.format(xlib.get_fastqc_name(), cluster_name)))
file_id.write('{0}\n'.format(
' mail --append "Content-type: text/html;" --subject "$SUBJECT" "$RECIPIENT" <<< "$MESSAGE"'
))
file_id.write('{0}\n'.format(' exit 0'))
file_id.write('{0}\n'.format('}'))
file_id.write('{0}\n'.format(
'#-------------------------------------------------------------------------------'
))
file_id.write('{0}\n'.format('function manage_error'))
file_id.write('{0}\n'.format('{'))
file_id.write('{0}\n'.format(' END_DATETIME=`date --utc +%s`'))
file_id.write('{0}\n'.format(
' FORMATTED_END_DATETIME=`date --date="@$END_DATETIME" "+%Y-%m-%d %H:%M:%S"`'
))
file_id.write('{0}\n'.format(' calculate_duration'))
file_id.write('{0}\n'.format(' echo "$SEP"'))
file_id.write(
'{0}\n'.format(' echo "ERROR: $1 returned error $2"'))
file_id.write('{0}\n'.format(
' echo "Script ended WRONG at $FORMATTED_END_DATETIME UTC with a run duration of $DURATION s ($FORMATTED_DURATION)."'
))
file_id.write('{0}\n'.format(' echo "$SEP"'))
file_id.write('{0}\n'.format(' RECIPIENT={0}'.format(
xconfiguration.get_contact_data())))
file_id.write('{0}\n'.format(
' SUBJECT="{0}: {1} process"'.format(
xlib.get_project_name(), xlib.get_fastqc_name())))
file_id.write('{0}\n'.format(
' MESSAGE="The {0} process in node $HOSTNAME of cluster {1} ended WRONG at $FORMATTED_END_DATETIME with a run duration of $DURATION s ($FORMATTED_DURATION). Please review its log.<br/><br/>Regards,<br/>GI Genetica, Fisiologia e Historia Forestal<br/>Dpto. Sistemas y Recursos Naturales<br/>ETSI Montes, Forestal y del Medio Natural<br/>Universidad Politecnica de Madrid<br/>https://github.com/ggfhf/"'
.format(xlib.get_fastqc_name(), cluster_name)))
file_id.write('{0}\n'.format(
' mail --append "Content-type: text/html;" --subject "$SUBJECT" "$RECIPIENT" <<< "$MESSAGE"'
))
file_id.write('{0}\n'.format(' exit 3'))
file_id.write('{0}\n'.format('}'))
file_id.write('{0}\n'.format(
'#-------------------------------------------------------------------------------'
))
file_id.write('{0}\n'.format('function calculate_duration'))
file_id.write('{0}\n'.format('{'))
file_id.write('{0}\n'.format(
' DURATION=`expr $END_DATETIME - $INIT_DATETIME`'))
file_id.write('{0}\n'.format(' HH=`expr $DURATION / 3600`'))
file_id.write(
'{0}\n'.format(' MM=`expr $DURATION % 3600 / 60`'))
file_id.write('{0}\n'.format(' SS=`expr $DURATION % 60`'))
file_id.write('{0}\n'.format(
' FORMATTED_DURATION=`printf "%03d:%02d:%02d\\n" $HH $MM $SS`'
))
file_id.write('{0}\n'.format('}'))
file_id.write('{0}\n'.format(
'#-------------------------------------------------------------------------------'
))
file_id.write('{0}\n'.format('init'))
file_id.write('{0}\n'.format('run_fastqc_process'))
file_id.write('{0}\n'.format('end'))
except:
error_list.append('*** ERROR: The file {0} can not be created'.format(
get_fastqc_process_script()))
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 build_quast_process_script(cluster_name, current_run_dir):
'''
Build the current QUAST process script.
'''
# initialize the control variable and the error list
OK = True
error_list = []
# get the QUAST option dictionary
quast_option_dict = xlib.get_option_dict(get_quast_config_file())
# get the options
experiment_id = quast_option_dict['identification']['experiment_id']
reference_dataset_id = quast_option_dict['identification']['reference_dataset_id']
reference_file = quast_option_dict['identification']['reference_file']
assembly_software = quast_option_dict['identification']['assembly_software']
assembly_dataset_id = quast_option_dict['identification']['assembly_dataset_id']
assembly_type = quast_option_dict['identification']['assembly_type']
threads = quast_option_dict['QUAST parameters']['threads']
# set the reference file path
if reference_dataset_id.upper() != 'NONE':
reference_file_path = xlib.get_cluster_reference_file(reference_dataset_id, reference_file)
# set the transcriptome file path
if assembly_software == xlib.get_soapdenovotrans_code():
if assembly_type.upper() == 'CONTIGS':
transcriptome_file = '{0}/{1}-{2}.contig'.format(xlib.get_cluster_experiment_result_dataset_dir(experiment_id, assembly_dataset_id), experiment_id, assembly_dataset_id)
elif assembly_type.upper() == 'SCAFFOLDS':
transcriptome_file = '{0}/{1}-{2}.scafSeq'.format(xlib.get_cluster_experiment_result_dataset_dir(experiment_id, assembly_dataset_id), experiment_id, assembly_dataset_id)
elif assembly_software == xlib.get_transabyss_code():
transcriptome_file = '{0}/transabyss-final.fa'.format(xlib.get_cluster_experiment_result_dataset_dir(experiment_id, assembly_dataset_id))
elif assembly_software == xlib.get_trinity_code():
transcriptome_file = '{0}/Trinity.fasta'.format(xlib.get_cluster_experiment_result_dataset_dir(experiment_id, assembly_dataset_id))
elif assembly_software == xlib.get_star_code():
transcriptome_file = '{0}/Trinity-GG.fasta'.format(xlib.get_cluster_experiment_result_dataset_dir(experiment_id, assembly_dataset_id))
elif assembly_software == xlib.get_cd_hit_est_code():
transcriptome_file = '{0}/clustered-transcriptome.fasta'.format(xlib.get_cluster_experiment_result_dataset_dir(experiment_id, assembly_dataset_id))
elif assembly_software == xlib.get_transcript_filter_code():
transcriptome_file = '{0}/filtered-transcriptome.fasta'.format(xlib.get_cluster_experiment_result_dataset_dir(experiment_id, assembly_dataset_id))
# get the QUAST process script name
quast_process_script = get_quast_process_script()
# write the QUAST process script
try:
if not os.path.exists(os.path.dirname(quast_process_script)):
os.makedirs(os.path.dirname(quast_process_script))
with open(quast_process_script, mode='w', encoding='utf8', newline='\n') as file_id:
file_id.write('{0}\n'.format('#!/bin/bash'))
file_id.write('{0}\n'.format('#-------------------------------------------------------------------------------'))
file_id.write('{0}\n'.format('QUAST_PATH={0}/{1}/envs/{2}/bin'.format(xlib.get_cluster_app_dir(), xlib.get_miniconda3_name(), xlib.get_quast_bioconda_code())))
file_id.write('{0}\n'.format('PATH=$QUAST_PATH:$PATH'))
file_id.write('{0}\n'.format('SEP="#########################################"'))
file_id.write('{0}\n'.format('cd {0}/{1}/bin'.format(xlib.get_cluster_app_dir(), xlib.get_miniconda3_name())))
file_id.write('{0}\n'.format('source activate {0}'.format(xlib.get_quast_bioconda_code())))
file_id.write('{0}\n'.format('#-------------------------------------------------------------------------------'))
file_id.write('{0}\n'.format('function init'))
file_id.write('{0}\n'.format('{'))
file_id.write('{0}\n'.format(' INIT_DATETIME=`date --utc +%s`'))
file_id.write('{0}\n'.format(' FORMATTED_INIT_DATETIME=`date --date="@$INIT_DATETIME" "+%Y-%m-%d %H:%M:%S"`'))
file_id.write('{0}\n'.format(' echo "$SEP"'))
file_id.write('{0}\n'.format(' echo "Script started in node $HOSTNAME of cluster {0} at $FORMATTED_INIT_DATETIME UTC."'.format(cluster_name)))
file_id.write('{0}\n'.format('}'))
file_id.write('{0}\n'.format('#-------------------------------------------------------------------------------'))
file_id.write('{0}\n'.format('function run_quast_process'))
file_id.write('{0}\n'.format('{'))
file_id.write('{0}\n'.format(' cd {0}'.format(current_run_dir)))
file_id.write('{0}\n'.format(' echo "$SEP"'))
file_id.write('{0}\n'.format(' quast.py --version'))
file_id.write('{0}\n'.format(' echo "$SEP"'))
file_id.write('{0}\n'.format(' /usr/bin/time \\'))
file_id.write('{0}\n'.format(' --format="$SEP\\nElapsed real time (s): %e\\nCPU time in kernel mode (s): %S\\nCPU time in user mode (s): %U\\nPercentage of CPU: %P\\nMaximum resident set size(Kb): %M\\nAverage total memory use (Kb):%K" \\'))
file_id.write('{0}\n'.format(' quast.py \\'))
file_id.write('{0}\n'.format(' --threads {0} \\'.format(threads)))
file_id.write('{0}\n'.format(' --output-dir {0} \\'.format(current_run_dir)))
if reference_dataset_id.upper() != 'NONE':
file_id.write('{0}\n'.format(' -R {0} \\'.format(reference_file_path)))
if assembly_type.upper() == 'SCAFFOLDS':
file_id.write('{0}\n'.format(' --scaffolds \\'))
file_id.write('{0}\n'.format(' {0}'.format(transcriptome_file)))
file_id.write('{0}\n'.format(' RC=$?'))
file_id.write('{0}\n'.format(' if [ $RC -ne 0 ]; then manage_error quast.py $RC; fi'))
file_id.write('{0}\n'.format('}'))
file_id.write('{0}\n'.format('#-------------------------------------------------------------------------------'))
file_id.write('{0}\n'.format('function end'))
file_id.write('{0}\n'.format('{'))
file_id.write('{0}\n'.format(' END_DATETIME=`date --utc +%s`'))
file_id.write('{0}\n'.format(' FORMATTED_END_DATETIME=`date --date="@$END_DATETIME" "+%Y-%m-%d %H:%M:%S"`'))
file_id.write('{0}\n'.format(' calculate_duration'))
file_id.write('{0}\n'.format(' echo "$SEP"'))
file_id.write('{0}\n'.format(' echo "Script ended OK at $FORMATTED_END_DATETIME UTC with a run duration of $DURATION s ($FORMATTED_DURATION)."'))
file_id.write('{0}\n'.format(' echo "$SEP"'))
file_id.write('{0}\n'.format(' RECIPIENT={0}'.format(xconfiguration.get_contact_data())))
file_id.write('{0}\n'.format(' SUBJECT="{0}: {1} process"'.format(xlib.get_project_name(), xlib.get_quast_name())))
file_id.write('{0}\n'.format(' MESSAGE="The {0} process in node $HOSTNAME of cluster {1} ended OK at $FORMATTED_END_DATETIME with a run duration of $DURATION s ($FORMATTED_DURATION). Please review its log.<br/><br/>Regards,<br/>GI Genetica, Fisiologia e Historia Forestal<br/>Dpto. Sistemas y Recursos Naturales<br/>ETSI Montes, Forestal y del Medio Natural<br/>Universidad Politecnica de Madrid<br/>https://github.com/ggfhf/"'.format(xlib.get_quast_name(), cluster_name)))
file_id.write('{0}\n'.format(' mail --append "Content-type: text/html;" --subject "$SUBJECT" "$RECIPIENT" <<< "$MESSAGE"'))
file_id.write('{0}\n'.format(' exit 0'))
file_id.write('{0}\n'.format('}'))
file_id.write('{0}\n'.format('#-------------------------------------------------------------------------------'))
file_id.write('{0}\n'.format('function manage_error'))
file_id.write('{0}\n'.format('{'))
file_id.write('{0}\n'.format(' END_DATETIME=`date --utc +%s`'))
file_id.write('{0}\n'.format(' FORMATTED_END_DATETIME=`date --date="@$END_DATETIME" "+%Y-%m-%d %H:%M:%S"`'))
file_id.write('{0}\n'.format(' calculate_duration'))
file_id.write('{0}\n'.format(' echo "$SEP"'))
file_id.write('{0}\n'.format(' echo "ERROR: $1 returned error $2"'))
file_id.write('{0}\n'.format(' echo "Script ended WRONG at $FORMATTED_END_DATETIME UTC with a run duration of $DURATION s ($FORMATTED_DURATION)."'))
file_id.write('{0}\n'.format(' echo "$SEP"'))
file_id.write('{0}\n'.format(' RECIPIENT={0}'.format(xconfiguration.get_contact_data())))
file_id.write('{0}\n'.format(' SUBJECT="{0}: {1} process"'.format(xlib.get_project_name(), xlib.get_quast_name())))
file_id.write('{0}\n'.format(' MESSAGE="The {0} process in node $HOSTNAME of cluster {1} ended WRONG at $FORMATTED_END_DATETIME with a run duration of $DURATION s ($FORMATTED_DURATION). Please review its log.<br/><br/>Regards,<br/>GI Genetica, Fisiologia e Historia Forestal<br/>Dpto. Sistemas y Recursos Naturales<br/>ETSI Montes, Forestal y del Medio Natural<br/>Universidad Politecnica de Madrid<br/>https://github.com/ggfhf/"'.format(xlib.get_quast_name(), cluster_name)))
file_id.write('{0}\n'.format(' mail --append "Content-type: text/html;" --subject "$SUBJECT" "$RECIPIENT" <<< "$MESSAGE"'))
file_id.write('{0}\n'.format(' exit 3'))
file_id.write('{0}\n'.format('}'))
file_id.write('{0}\n'.format('#-------------------------------------------------------------------------------'))
file_id.write('{0}\n'.format('function calculate_duration'))
file_id.write('{0}\n'.format('{'))
file_id.write('{0}\n'.format(' DURATION=`expr $END_DATETIME - $INIT_DATETIME`'))
file_id.write('{0}\n'.format(' HH=`expr $DURATION / 3600`'))
file_id.write('{0}\n'.format(' MM=`expr $DURATION % 3600 / 60`'))
file_id.write('{0}\n'.format(' SS=`expr $DURATION % 60`'))
file_id.write('{0}\n'.format(' FORMATTED_DURATION=`printf "%03d:%02d:%02d\\n" $HH $MM $SS`'))
file_id.write('{0}\n'.format('}'))
file_id.write('{0}\n'.format('#-------------------------------------------------------------------------------'))
file_id.write('{0}\n'.format('init'))
file_id.write('{0}\n'.format('run_quast_process'))
file_id.write('{0}\n'.format('end'))
except:
error_list.append('*** ERROR: The file {0} can not be created'.format(quast_process_script))
OK = False
# return the control variable and the error list
return (OK, error_list)
def build_busco_process_script(cluster_name, current_run_dir):
'''
Build the current BUSCO process script.
'''
# initialize the control variable and the error list
OK = True
error_list = []
# get the BUSCO option dictionary
busco_option_dict = xlib.get_option_dict(get_busco_config_file())
# get the options
experiment_id = busco_option_dict['identification']['experiment_id']
assembly_software = busco_option_dict['identification']['assembly_software']
assembly_dataset_id = busco_option_dict['identification']['assembly_dataset_id']
assembly_type = busco_option_dict['identification']['assembly_type']
ncpu = busco_option_dict['BUSCO parameters']['ncpu']
lineage_data = busco_option_dict['BUSCO parameters']['lineage_data']
lineage_data_file = '{0}.tar.gz'.format(lineage_data)
lineage_data_url = 'http://busco.ezlab.org/v2/datasets/{0}'.format(lineage_data_file)
mode = busco_option_dict['BUSCO parameters']['mode'].lower()
evalue = busco_option_dict['BUSCO parameters']['evalue']
limit = busco_option_dict['BUSCO parameters']['limit']
species = busco_option_dict['BUSCO parameters']['species']
long = busco_option_dict['BUSCO parameters']['long'].upper()
augustus_options = busco_option_dict['BUSCO parameters']['augustus_options'].upper()
# set the transcriptome file path
if assembly_software == xlib.get_soapdenovotrans_code():
if assembly_type == 'CONTIGS':
transcriptome_file = '{0}/{1}-{2}.contig'.format(xlib.get_cluster_experiment_result_dataset_dir(experiment_id, assembly_dataset_id), experiment_id, assembly_dataset_id)
elif assembly_type == 'SCAFFOLDS':
transcriptome_file = '{0}/{1}-{2}.scafSeq'.format(xlib.get_cluster_experiment_result_dataset_dir(experiment_id, assembly_dataset_id), experiment_id, assembly_dataset_id)
elif assembly_software == xlib.get_transabyss_code():
transcriptome_file = '{0}/transabyss-final.fa'.format(xlib.get_cluster_experiment_result_dataset_dir(experiment_id, assembly_dataset_id))
elif assembly_software == xlib.get_trinity_code():
transcriptome_file = '{0}/Trinity.fasta'.format(xlib.get_cluster_experiment_result_dataset_dir(experiment_id, assembly_dataset_id))
elif assembly_software == xlib.get_star_code():
transcriptome_file = '{0}/Trinity-GG.fasta'.format(xlib.get_cluster_experiment_result_dataset_dir(experiment_id, assembly_dataset_id))
elif assembly_software == xlib.get_cd_hit_est_code():
transcriptome_file = '{0}/clustered-transcriptome.fasta'.format(xlib.get_cluster_experiment_result_dataset_dir(experiment_id, assembly_dataset_id))
elif assembly_software == xlib.get_transcript_filter_code():
transcriptome_file = '{0}/filtered-transcriptome.fasta'.format(xlib.get_cluster_experiment_result_dataset_dir(experiment_id, assembly_dataset_id))
# write the BUSCO process script
try:
if not os.path.exists(os.path.dirname(get_busco_process_script())):
os.makedirs(os.path.dirname(get_busco_process_script()))
with open(get_busco_process_script(), mode='w', encoding='utf8', newline='\n') as file_id:
file_id.write('{0}\n'.format('#!/bin/bash'))
file_id.write('{0}\n'.format('#-------------------------------------------------------------------------------'))
file_id.write('{0}\n'.format('BUSCO_PATH={0}/{1}/envs/{2}/bin'.format(xlib.get_cluster_app_dir(), xlib.get_miniconda3_name(), xlib.get_busco_bioconda_code())))
file_id.write('{0}\n'.format('export PATH=$BUSCO_PATH:$PATH'))
file_id.write('{0}\n'.format('SEP="#########################################"'))
file_id.write('{0}\n'.format('cd {0}/{1}/bin'.format(xlib.get_cluster_app_dir(), xlib.get_miniconda3_name())))
file_id.write('{0}\n'.format('source activate {0}'.format(xlib.get_busco_bioconda_code())))
file_id.write('{0}\n'.format('#-------------------------------------------------------------------------------'))
file_id.write('{0}\n'.format('function init'))
file_id.write('{0}\n'.format('{'))
file_id.write('{0}\n'.format(' INIT_DATETIME=`date --utc +%s`'))
file_id.write('{0}\n'.format(' FORMATTED_INIT_DATETIME=`date --date="@$INIT_DATETIME" "+%Y-%m-%d %H:%M:%S"`'))
file_id.write('{0}\n'.format(' echo "$SEP"'))
file_id.write('{0}\n'.format(' echo "Script started in node $HOSTNAME of cluster {0} at $FORMATTED_INIT_DATETIME UTC."'.format(cluster_name)))
file_id.write('{0}\n'.format('}'))
file_id.write('{0}\n'.format('#-------------------------------------------------------------------------------'))
file_id.write('{0}\n'.format('function download_lineage_data'))
file_id.write('{0}\n'.format('{'))
file_id.write('{0}\n'.format(' cd {0}'.format(current_run_dir)))
file_id.write('{0}\n'.format(' echo "$SEP"'))
file_id.write('{0}\n'.format(' echo "Downloading lineage data ..."'))
file_id.write('{0}\n'.format(' wget --quiet --output-document ./{0} {1}'.format(lineage_data_file, lineage_data_url)))
file_id.write('{0}\n'.format(' tar -xzvf ./{0}'.format(lineage_data_file)))
file_id.write('{0}\n'.format(' rm ./{0}'.format(lineage_data_file)))
file_id.write('{0}\n'.format('}'))
file_id.write('{0}\n'.format('#-------------------------------------------------------------------------------'))
file_id.write('{0}\n'.format('function run_busco_process'))
file_id.write('{0}\n'.format('{'))
file_id.write('{0}\n'.format(' cd {0}'.format(current_run_dir)))
file_id.write('{0}\n'.format(' echo "$SEP"'))
file_id.write('{0}\n'.format(' run_BUSCO.py --version'))
file_id.write('{0}\n'.format(' echo "$SEP"'))
file_id.write('{0}\n'.format(' /usr/bin/time \\'))
file_id.write('{0}\n'.format(' --format="$SEP\\nElapsed real time (s): %e\\nCPU time in kernel mode (s): %S\\nCPU time in user mode (s): %U\\nPercentage of CPU: %P\\nMaximum resident set size(Kb): %M\\nAverage total memory use (Kb):%K" \\'))
file_id.write('{0}\n'.format(' run_BUSCO.py \\'))
file_id.write('{0}\n'.format(' --cpu={0} \\'.format(ncpu)))
file_id.write('{0}\n'.format(' --lineage_path=./{0} \\'.format(lineage_data)))
file_id.write('{0}\n'.format(' --mode={0} \\'.format(mode)))
file_id.write('{0}\n'.format(' --evalue={0} \\'.format(evalue)))
file_id.write('{0}\n'.format(' --limit={0} \\'.format(limit)))
if species.upper() != 'NONE':
file_id.write('{0}\n'.format(' --species={0} \\'.format(species)))
if long == 'YES':
file_id.write('{0}\n'.format(' --long \\'))
if augustus_options.upper() != 'NONE':
file_id.write('{0}\n'.format(" --august_options='{0}' \\".format(augustus_options)))
file_id.write('{0}\n'.format(' --in={0} \\'.format(transcriptome_file)))
file_id.write('{0}\n'.format(' --out={0}'.format(os.path.basename(current_run_dir))))
file_id.write('{0}\n'.format(' RC=$?'))
file_id.write('{0}\n'.format(' if [ $RC -ne 0 ]; then manage_error run_BUSCO.py $RC; fi'))
file_id.write('{0}\n'.format('}'))
file_id.write('{0}\n'.format('#-------------------------------------------------------------------------------'))
file_id.write('{0}\n'.format('function end'))
file_id.write('{0}\n'.format('{'))
file_id.write('{0}\n'.format(' END_DATETIME=`date --utc +%s`'))
file_id.write('{0}\n'.format(' FORMATTED_END_DATETIME=`date --date="@$END_DATETIME" "+%Y-%m-%d %H:%M:%S"`'))
file_id.write('{0}\n'.format(' calculate_duration'))
file_id.write('{0}\n'.format(' echo "$SEP"'))
file_id.write('{0}\n'.format(' echo "Script ended OK at $FORMATTED_END_DATETIME UTC with a run duration of $DURATION s ($FORMATTED_DURATION)."'))
file_id.write('{0}\n'.format(' echo "$SEP"'))
file_id.write('{0}\n'.format(' RECIPIENT={0}'.format(xconfiguration.get_contact_data())))
file_id.write('{0}\n'.format(' SUBJECT="{0}: {1} process"'.format(xlib.get_project_name(), xlib.get_busco_name())))
file_id.write('{0}\n'.format(' MESSAGE="The {0} process in node $HOSTNAME of cluster {1} ended OK at $FORMATTED_END_DATETIME with a run duration of $DURATION s ($FORMATTED_DURATION). Please review its log.<br/><br/>Regards,<br/>GI Genetica, Fisiologia e Historia Forestal<br/>Dpto. Sistemas y Recursos Naturales<br/>ETSI Montes, Forestal y del Medio Natural<br/>Universidad Politecnica de Madrid<br/>https://github.com/ggfhf/"'.format(xlib.get_busco_name(), cluster_name)))
file_id.write('{0}\n'.format(' mail --append "Content-type: text/html;" --subject "$SUBJECT" "$RECIPIENT" <<< "$MESSAGE"'))
file_id.write('{0}\n'.format(' exit 0'))
file_id.write('{0}\n'.format('}'))
file_id.write('{0}\n'.format('#-------------------------------------------------------------------------------'))
file_id.write('{0}\n'.format('function manage_error'))
file_id.write('{0}\n'.format('{'))
file_id.write('{0}\n'.format(' END_DATETIME=`date --utc +%s`'))
file_id.write('{0}\n'.format(' FORMATTED_END_DATETIME=`date --date="@$END_DATETIME" "+%Y-%m-%d %H:%M:%S"`'))
file_id.write('{0}\n'.format(' calculate_duration'))
file_id.write('{0}\n'.format(' echo "$SEP"'))
file_id.write('{0}\n'.format(' echo "ERROR: $1 returned error $2"'))
file_id.write('{0}\n'.format(' echo "Script ended WRONG at $FORMATTED_END_DATETIME UTC with a run duration of $DURATION s ($FORMATTED_DURATION)."'))
file_id.write('{0}\n'.format(' echo "$SEP"'))
file_id.write('{0}\n'.format(' RECIPIENT={0}'.format(xconfiguration.get_contact_data())))
file_id.write('{0}\n'.format(' SUBJECT="{0}: {1} process"'.format(xlib.get_project_name(), xlib.get_busco_name())))
file_id.write('{0}\n'.format(' MESSAGE="The {0} process in node $HOSTNAME of cluster {1} ended WRONG at $FORMATTED_END_DATETIME with a run duration of $DURATION s ($FORMATTED_DURATION). Please review its log.<br/><br/>Regards,<br/>GI Genetica, Fisiologia e Historia Forestal<br/>Dpto. Sistemas y Recursos Naturales<br/>ETSI Montes, Forestal y del Medio Natural<br/>Universidad Politecnica de Madrid<br/>https://github.com/ggfhf/"'.format(xlib.get_busco_name(), cluster_name)))
file_id.write('{0}\n'.format(' mail --append "Content-type: text/html;" --subject "$SUBJECT" "$RECIPIENT" <<< "$MESSAGE"'))
file_id.write('{0}\n'.format(' exit 3'))
file_id.write('{0}\n'.format('}'))
file_id.write('{0}\n'.format('#-------------------------------------------------------------------------------'))
file_id.write('{0}\n'.format('function calculate_duration'))
file_id.write('{0}\n'.format('{'))
file_id.write('{0}\n'.format(' DURATION=`expr $END_DATETIME - $INIT_DATETIME`'))
file_id.write('{0}\n'.format(' HH=`expr $DURATION / 3600`'))
file_id.write('{0}\n'.format(' MM=`expr $DURATION % 3600 / 60`'))
file_id.write('{0}\n'.format(' SS=`expr $DURATION % 60`'))
file_id.write('{0}\n'.format(' FORMATTED_DURATION=`printf "%03d:%02d:%02d\\n" $HH $MM $SS`'))
file_id.write('{0}\n'.format('}'))
file_id.write('{0}\n'.format('#-------------------------------------------------------------------------------'))
file_id.write('{0}\n'.format('init'))
file_id.write('{0}\n'.format('download_lineage_data'))
file_id.write('{0}\n'.format('run_busco_process'))
file_id.write('{0}\n'.format('end'))
except:
error_list.append('*** ERROR: The file {0} can not be created'.format(get_busco_process_script()))
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()
def form_install_bioinfo_app(app_code):
'''
Install the bioinfo application software in the cluster.
'''
# initialize the control variable
OK = True
# set the bioinfo application name
if app_code == xlib.get_blastplus_code():
app_name = xlib.get_blastplus_name()
elif app_code == xlib.get_diamond_code():
app_name = xlib.get_diamond_name()
elif app_code == xlib.get_entrez_direct_code():
app_name = xlib.get_entrez_direct_name()
elif app_code == xlib.get_miniconda3_code():
app_name = xlib.get_miniconda3_name()
elif app_code == xlib.get_r_code():
app_name = xlib.get_r_name()
elif app_code == xlib.get_transdecoder_code():
app_name = xlib.get_transdecoder_name()
# print the header
clib.clear_screen()
clib.print_headers_with_environment(f'{app_name} - Install software')
# confirm the software installation
print(xlib.get_separator())
if app_code == xlib.get_miniconda3_code():
OK = clib.confirm_action(
f'{app_name} (Conda infrastructure) is going to be installed. All Conda packages previously installed will be lost and they have to be reinstalled.'
)
elif app_code == xlib.get_r_code():
OK = clib.confirm_action(
f'{app_name} and analysis packages are going to be installed. The previous version will be lost, if it exists.'
)
else:
OK = clib.confirm_action(
f'The {app_name} Conda package is going to be installed. The previous version will be lost, if it exists.'
)
# install the software
if OK:
# install the BLAST+ software
if app_code == xlib.get_blastplus_code():
# -- package_code_list = [(xlib.get_blastplus_conda_code(), 'last')]
package_code_list = [(xlib.get_blastplus_conda_code(), '2.9.0')]
devstdout = xlib.DevStdOut(
xbioinfoapp.install_conda_package_list.__name__)
OK = xbioinfoapp.install_conda_package_list(app_code,
app_name,
package_code_list,
devstdout,
function=None)
# install the DIAMOND software
elif app_code == xlib.get_diamond_code():
# -- package_code_list = [(xlib.get_diamond_conda_code(), 'last')]
package_code_list = [(xlib.get_diamond_conda_code(), '0.9.34')]
devstdout = xlib.DevStdOut(
xbioinfoapp.install_conda_package_list.__name__)
OK = xbioinfoapp.install_conda_package_list(app_code,
app_name,
package_code_list,
devstdout,
function=None)
# install the Entrez Direct software
elif app_code == xlib.get_entrez_direct_code():
package_code_list = [(xlib.get_entrez_direct_conda_code(), 'last')]
devstdout = xlib.DevStdOut(
xbioinfoapp.install_conda_package_list.__name__)
OK = xbioinfoapp.install_conda_package_list(app_code,
app_name,
package_code_list,
devstdout,
function=None)
# install the Miniconda3 software
elif app_code == xlib.get_miniconda3_code():
devstdout = xlib.DevStdOut(xbioinfoapp.install_miniconda3.__name__)
OK = xbioinfoapp.install_miniconda3(devstdout, function=None)
# install R and analysis packages
elif app_code == xlib.get_r_code():
devstdout = xlib.DevStdOut(xbioinfoapp.install_r.__name__)
OK = xbioinfoapp.install_r(devstdout, function=None)
# install the TransDecoder software
elif app_code == xlib.get_transdecoder_code():
package_code_list = [(xlib.get_transdecoder_conda_code(), 'last')]
devstdout = xlib.DevStdOut(
xbioinfoapp.install_conda_package_list.__name__)
OK = xbioinfoapp.install_conda_package_list(app_code,
app_name,
package_code_list,
devstdout,
function=None)
# 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 ...')