def get_alignment_software_code_list():
'''
Get the code list of "alignment_software".
'''
return [
xlib.get_bowtie2_code(),
xlib.get_gsnap_code(),
xlib.get_hisat2_code(),
xlib.get_star_code(),
xlib.get_tophat_code()
]
def create_htseq_count_config_file(
experiment_id='exp001',
reference_dataset_id='Athaliana',
annotation_file='Arabidopsis_thaliana.TAIR10.36.gtf',
alignment_dataset_id_list=[
'star-170101-235959', 'tophat-170101-235959'
]):
'''
Create htseq-count config file with the default options. It is necessary
update the options in each run.
'''
# initialize the control variable and the error list
OK = True
error_list = []
# create the htseq-count config file and write the default options
try:
if not os.path.exists(os.path.dirname(get_htseq_count_config_file())):
os.makedirs(os.path.dirname(get_htseq_count_config_file()))
with open(get_htseq_count_config_file(),
mode='w',
encoding='iso-8859-1',
newline='\n') as file_id:
file_id.write(
'# You must review the information of this file and update the values with the corresponding ones to the current run.\n'
)
file_id.write('#\n')
file_id.write(
f'# The reference and annotation files have to be located in the cluster directory {xlib.get_cluster_reference_dir()}/experiment_id/reference_dataset_id\n'
)
file_id.write(
'# The experiment_id, reference_dataset_id, and annotation_file names are fixed in the identification section.\n'
)
file_id.write(
f'# The alignment files have to be located in the cluster directory {xlib.get_cluster_result_dir()}/experiment_id/alignment_dataset_id\n'
)
file_id.write('#\n')
file_id.write(
'# You can consult the parameters of htseq_count and their meaning in "https://github.com/simon-anders/htseq".\n'
)
file_id.write('#\n')
file_id.write(
'# In section "htseq-count parameters", the key "other_parameters" allows you to input additional parameters in the format:\n'
)
file_id.write('#\n')
file_id.write(
'# other_parameters = --parameter-1[=value-1][; --parameter-2[=value-2][; ...; --parameter-n[=value-n]]]\n'
)
file_id.write('#\n')
file_id.write(
'# parameter-i is a parameter name of TopHat and value-i a valid value of parameter-i, e.g.\n'
)
file_id.write('#\n')
file_id.write(
'# other_parameters = --max-reads-in-buffer=30000000\n')
file_id.write('\n')
file_id.write(
'# This section has the information identifies the experiment.\n'
)
file_id.write('[identification]\n')
file_id.write('{0:<50} {1}\n'.format(
f'experiment_id = {experiment_id}',
'# experiment identification'))
file_id.write('{0:<50} {1}\n'.format(
f'reference_dataset_id = {reference_dataset_id}',
'# reference dataset identification'))
file_id.write('{0:<50} {1}\n'.format(
f'annotation_file = {annotation_file}',
'# reference annotation file name'))
for i in range(len(alignment_dataset_id_list)):
# set the alignment software
alignment_dataset_id = alignment_dataset_id_list[i]
if alignment_dataset_id.startswith(xlib.get_bowtie2_code()):
alignment_software = xlib.get_bowtie2_code()
elif alignment_dataset_id.startswith(xlib.get_gsnap_code()):
alignment_software = xlib.get_gsnap_code()
elif alignment_dataset_id.startswith(xlib.get_hisat2_code()):
alignment_software = xlib.get_hisat2_code()
elif alignment_dataset_id.startswith(xlib.get_star_code()):
alignment_software = xlib.get_star_code()
elif alignment_dataset_id.startswith(xlib.get_tophat_code()):
alignment_software = xlib.get_tophat_code()
# write the alignment dataset section
file_id.write('\n')
if i == 0:
file_id.write(
'# This section has the information of the first alignment dataset.\n'
)
file_id.write(f'[alignment-dataset-{i + 1}]\n')
file_id.write('{0:<50} {1}\n'.format(
f'alignment_software = {alignment_software}',
f'# alignment software: {get_alignment_software_code_list_text()}'
))
file_id.write('{0:<50} {1}\n'.format(
f'alignment_dataset_id = {alignment_dataset_id}',
'# alignment dataset identification'))
if i == 0:
file_id.write('\n')
file_id.write(
'# If there are more alignment datasets, you have to repeat the section alignment-dataset-1 with the data of each dataset.\n'
)
file_id.write(
'# The section identification has to be alignment-dataset-n (n is an integer not repeated)\n'
)
file_id.write('\n')
file_id.write(
'# This section has the information to set the htseq-count parameters\n'
)
file_id.write('[htseq-count parameters]\n')
file_id.write('{0:<50} {1}\n'.format('nprocesses = 4',
'# number of CPU for use'))
file_id.write('{0:<50} {1}\n'.format(
'stranded = YES',
f'# whether the data is from a strand-specific assay: {get_stranded_code_list_text()}'
))
file_id.write('{0:<50} {1}\n'.format(
'minaqual = 10',
'# skip all reads with MAPQ (5th column in BAM file) alignment quality lower than the given minimum value'
))
file_id.write('{0:<50} {1}\n'.format(
'type = exon',
'# feature type (3rd column in GTF file) to be used, all features of other type are ignored'
))
file_id.write('{0:<50} {1}\n'.format(
'idattr = gene_id',
'# GTF file feature id used to identity the counts in the output table'
))
file_id.write('{0:<50} {1}\n'.format(
'mode = UNION',
f'# mode to handle reads overlapping more than one feature: {get_mode_code_list_text()}'
))
file_id.write('{0:<50} {1}\n'.format(
'nonunique = NONE',
f'# Mode to handle reads that align to or are assigned to more than one feature in the overlap mode of choice: {get_nonunique_code_list_text()}'
))
file_id.write('{0:<50} {1}\n'.format(
'other_parameters = NONE',
'# additional parameters to the previous ones or NONE'))
except Exception as e:
error_list.append(f'*** EXCEPTION: "{e}".')
error_list.append(
f'*** ERROR: The file {get_htseq_count_config_file()} can not be recreated'
)
OK = False
# return the control variable and the error list
return (OK, error_list)
def create_express_config_file(experiment_id='exp001', assembly_dataset_id='sdnt-170101-235959', assembly_type='CONTIGS', alignment_dataset_id_list=['bowtie2-170101-235959']):
'''
Create eXpress config file with the default options. It is necessary
update the options in each run.
'''
# initialize the control variable and the error list
OK = True
error_list = []
# set the assembly software
if assembly_dataset_id.startswith(xlib.get_soapdenovotrans_code()):
assembly_software = xlib.get_soapdenovotrans_code()
elif assembly_dataset_id.startswith(xlib.get_transabyss_code()):
assembly_software = xlib.get_transabyss_code()
elif assembly_dataset_id.startswith(xlib.get_trinity_code()):
assembly_software = xlib.get_trinity_code()
elif assembly_dataset_id.startswith(xlib.get_ggtrinity_code()):
assembly_software = xlib.get_ggtrinity_code()
elif assembly_dataset_id.startswith(xlib.get_cd_hit_est_code()):
assembly_software = xlib.get_cd_hit_est_code()
elif assembly_dataset_id.startswith(xlib.get_transcript_filter_code()):
assembly_software = xlib.get_transcript_filter_code()
# create the eXpress config file and write the default options
try:
if not os.path.exists(os.path.dirname(get_express_config_file())):
os.makedirs(os.path.dirname(get_express_config_file()))
with open(get_express_config_file(), mode='w', encoding='iso-8859-1', newline='\n') as file_id:
file_id.write( '# You must review the information of this file and update the values with the corresponding ones to the current run.\n')
file_id.write( '#\n')
file_id.write(f'# The assembly files have to be located in the cluster directory {xlib.get_cluster_result_dir()}/experiment_id/assembly_dataset_id\n')
file_id.write(f'# The alignment file has to be located in the cluster directory {xlib.get_cluster_result_dir()}/experiment_id/alignment_dataset_id\n')
file_id.write( '# The experiment_id, assembly_dataset_id and alignment_dataset_id are fixed in the identification section.\n')
file_id.write( '#\n')
file_id.write( '# You can consult the parameters of eXpress and their meaning in "https://pachterlab.github.io/eXpress/".\n')
file_id.write( '#\n')
file_id.write( '# In section "eXpress parameters", the key "other_parameters" allows you to input additional parameters in the format:\n')
file_id.write( '#\n')
file_id.write( '# other_parameters = --parameter-1[=value-1][; --parameter-2[=value-2][; ...; --parameter-n[=value-n]]]\n')
file_id.write( '#\n')
file_id.write( '# parameter-i is a parameter name of Cufflinks and value-i a valid value of parameter-i, e.g.\n')
file_id.write( '#\n')
file_id.write( '# other_parameters = --calc-covar; --forget-param=0.6\n')
file_id.write( '\n')
file_id.write( '# This section has the information identifies the experiment.\n')
file_id.write( '[identification]\n')
file_id.write( '{0:<50} {1}\n'.format(f'experiment_id = {experiment_id}', '# experiment identification'))
file_id.write( '{0:<50} {1}\n'.format(f'assembly_software = {assembly_software}', f'# assembly software: {get_assembly_software_code_list_text()}'))
file_id.write( '{0:<50} {1}\n'.format(f'assembly_dataset_id = {assembly_dataset_id}', '# assembly dataset identification'))
file_id.write( '{0:<50} {1}\n'.format(f'assembly_type = {assembly_type}', f'# assembly type: CONTIGS or SCAFFOLDS in {xlib.get_soapdenovotrans_name()}; NONE in any other case'))
for i in range(len(alignment_dataset_id_list)):
# set the alignment software
alignment_dataset_id = alignment_dataset_id_list[i]
if alignment_dataset_id.startswith(xlib.get_bowtie2_code()):
alignment_software = xlib.get_bowtie2_code()
elif alignment_dataset_id.startswith(xlib.get_gsnap_code()):
alignment_software = xlib.get_gsnap_code()
# write the alignment dataset section
file_id.write( '\n')
if i == 0:
file_id.write( '# This section has the information of the first alignment dataset.\n')
file_id.write(f'[alignment-dataset-{i + 1}]\n')
file_id.write( '{0:<50} {1}\n'.format(f'alignment_software = {alignment_software}', f'# alignment software: {get_alignment_software_code_list_text()}'))
file_id.write( '{0:<50} {1}\n'.format(f'alignment_dataset_id = {alignment_dataset_id}', '# alignment dataset identification'))
if i == 0:
file_id.write( '\n')
file_id.write( '# If there are more alignment datasets, you have to repeat the section alignment-dataset-1 with the data of each dataset.\n')
file_id.write( '# The section identification has to be alignment-dataset-n (n is an integer not repeated)\n')
file_id.write( '\n')
file_id.write( '# This section has the information to set the eXpress parameters\n')
file_id.write( '[eXpress parameters]\n')
file_id.write( '{0:<50} {1}\n'.format( 'frag-len-mean = 200', '# mean fragment length'))
file_id.write( '{0:<50} {1}\n'.format( 'frag-len-stddev = 60', '# fragment length standard deviation'))
file_id.write( '{0:<50} {1}\n'.format( 'library_type = NONE', f'# library type: {get_library_type_code_list_text()}'))
file_id.write( '{0:<50} {1}\n'.format( 'max-indel-size = 0', '# maximum allowed size of a single indel'))
file_id.write( '{0:<50} {1}\n'.format( 'no-bias-correct = NO', f'# if YES, eXpress will not measure and account for sequence-specific biases: {get_no_bias_correct_code_list_text()}'))
file_id.write( '{0:<50} {1}\n'.format( 'no-error-model = NO', f'# if YES, eXpress will not measure and account for errors in alignments: {get_no_error_model_code_list_text()}'))
file_id.write( '{0:<50} {1}\n'.format( 'other_parameters = NONE', '# additional parameters to the previous ones or NONE'))
except Exception as e:
error_list.append(f'*** EXCEPTION: "{e}".')
error_list.append(f'*** ERROR: The file {get_express_config_file()} can not be recreated')
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 get_result_dataset_dict(cluster_name, experiment_id, status, passed_connection, ssh_client):
'''
Get a dictionary with the result datasets of an experiment in the cluster.
'''
# initialize the control variable and the error list
OK = True
error_list = []
# get the result directory in the cluster
cluster_result_dir = xlib.get_cluster_result_dir()
# initialize the dictionary of the result datasets
result_dataset_dict = {}
# create the SSH client connection
if not passed_connection:
(OK, error_list, ssh_client) = xssh.create_ssh_client_connection(cluster_name)
# check the result directory is created
if OK:
command = '[ -d {0} ] && echo RC=0 || echo RC=1'.format(cluster_result_dir)
(OK, stdout, stderr) = xssh.execute_cluster_command(ssh_client, command)
if stdout[len(stdout) - 1] != 'RC=0':
error_list.append('*** ERROR: There is not any volume mounted in the result directory.\n')
error_list.append('You have to link a volume in the mounting point {0} for the cluster {1}.\n'.format(cluster_result_dir, cluster_name))
OK = False
# get the dictionary of the result datasets
if OK:
if status == 'uncompressed':
command = 'cd {0}/{1}; for list in `ls`; do ls -ld $list | grep -v ^- > /dev/null && echo $list; done;'.format(cluster_result_dir, experiment_id)
elif status == 'compressed':
command = 'cd {0}/{1}; for list in `ls`; do ls -ld $list | grep -v ^d > /dev/null && echo $list; done;'.format(cluster_result_dir, experiment_id)
(OK, stdout, stderr) = xssh.execute_cluster_command(ssh_client, command)
if OK:
if status == 'uncompressed':
input_pattern = '{0}-(.+)-(.+)'
output_pattern = '{0} ({1} {2})'
elif status == 'compressed':
input_pattern = '{0}-(.+)-(.+).tar.gz'
output_pattern = '{0} ({1} {2}) [compressed]'
for line in stdout:
line = line.rstrip('\n')
if line != 'lost+found':
result_dataset_id = line
if result_dataset_id.startswith(xlib.get_bowtie2_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_bowtie2_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_bowtie2_name(), date, time)
elif result_dataset_id.startswith(xlib.get_busco_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_busco_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_busco_name(), date, time)
elif result_dataset_id.startswith(xlib.get_cd_hit_est_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_cd_hit_est_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_cd_hit_est_name(), date, time)
elif result_dataset_id.startswith(xlib.get_cutadapt_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_cutadapt_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_cutadapt_name(), date, time)
elif result_dataset_id.startswith(xlib.get_cuffdiff_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_cuffdiff_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_cuffdiff_name(), date, time)
elif result_dataset_id.startswith(xlib.get_cufflinks_cuffmerge_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_cufflinks_cuffmerge_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_cufflinks_cuffmerge_name(), date, time)
elif result_dataset_id.startswith(xlib.get_cuffnorm_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_cuffnorm_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_cuffnorm_name(), date, time)
elif result_dataset_id.startswith(xlib.get_cuffquant_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_cuffquant_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_cuffquant_name(), date, time)
elif result_dataset_id.startswith(xlib.get_ddradseq_simulation_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_ddradseq_simulation_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_ddradseq_simulation_name(), date, time)
elif result_dataset_id.startswith(xlib.get_fastqc_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_fastqc_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_fastqc_name(), date, time)
elif result_dataset_id.startswith(xlib.get_ggtrinity_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_ggtrinity_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_ggtrinity_name(), date, time)
elif result_dataset_id.startswith(xlib.get_gmap_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_gmap_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_gmap_name(), date, time)
elif result_dataset_id.startswith(xlib.get_gsnap_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_gsnap_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_gsnap_name(), date, time)
elif result_dataset_id.startswith(xlib.get_gzip_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_gzip_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_gzip_name(), date, time)
elif result_dataset_id.startswith(xlib.get_hisat2_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_hisat2_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_hisat2_name(), date, time)
elif result_dataset_id.startswith(xlib.get_htseq_count_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_htseq_count_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_htseq_count_name(), date, time)
elif result_dataset_id.startswith(xlib.get_insilico_read_normalization_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_insilico_read_normalization_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_insilico_read_normalization_name(), date, time)
elif result_dataset_id.startswith(xlib.get_ipyrad_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_ipyrad_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_ipyrad_name(), date, time)
elif result_dataset_id.startswith(xlib.get_kallisto_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_kallisto_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_kallisto_name(), date, time)
elif result_dataset_id.startswith(xlib.get_quast_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_quast_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_quast_name(), date, time)
elif result_dataset_id.startswith(xlib.get_ref_eval_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_ref_eval_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_ref_eval_name(), date, time)
elif result_dataset_id.startswith(xlib.get_rnaquast_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_rnaquast_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_rnaquast_name(), date, time)
elif result_dataset_id.startswith(xlib.get_rsem_eval_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_rsem_eval_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_rsem_eval_name(), date, time)
elif result_dataset_id.startswith(xlib.get_rsitesearch_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_rsitesearch_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_rsitesearch_name(), date, time)
elif result_dataset_id.startswith(xlib.get_soapdenovo2_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_soapdenovo2_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_soapdenovo2_name(), date, time)
elif result_dataset_id.startswith(xlib.get_soapdenovotrans_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_soapdenovotrans_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_soapdenovotrans_name(), date, time)
elif result_dataset_id.startswith(xlib.get_star_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_star_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_star_name(), date, time)
elif result_dataset_id.startswith(xlib.get_starcode_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_starcode_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_starcode_name(), date, time)
elif result_dataset_id.startswith(xlib.get_toa_process_pipeline_aminoacid_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_toa_process_pipeline_aminoacid_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_toa_process_pipeline_aminoacid_name(), date, time)
elif result_dataset_id.startswith(xlib.get_toa_process_pipeline_nucleotide_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_toa_process_pipeline_nucleotide_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_toa_process_pipeline_nucleotide_name(), date, time)
elif result_dataset_id.startswith(xlib.get_tophat_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_tophat_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_tophat_name(), date, time)
elif result_dataset_id.startswith(xlib.get_transabyss_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_transabyss_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_transabyss_name(), date, time)
elif result_dataset_id.startswith(xlib.get_transcript_filter_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_transcript_filter_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_transcript_filter_name(), date, time)
elif result_dataset_id.startswith(xlib.get_transcriptome_blastx_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_transcriptome_blastx_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_transcriptome_blastx_name(), date, time)
elif result_dataset_id.startswith(xlib.get_transrate_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_transrate_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_transrate_name(), date, time)
elif result_dataset_id.startswith(xlib.get_trimmomatic_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_trimmomatic_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_trimmomatic_name(), date, time)
elif result_dataset_id.startswith(xlib.get_trinity_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_trinity_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_trinity_name(), date, time)
else:
result_dataset_name = result_dataset_id
result_dataset_dict[result_dataset_id] = {'result_dataset_id': result_dataset_id, 'result_dataset_name': result_dataset_name}
# close the SSH client connection
if OK and not passed_connection:
xssh.close_ssh_client_connection(ssh_client)
# return the control variable, error list and dictionary of the result datasets
return (OK, error_list, result_dataset_dict)
def 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_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 ...')