def create_gmap_config_file(experiment_id='exp001', reference_dataset_id='NONE', reference_file='NONE', assembly_dataset_id='sdnt-170101-235959', assembly_type='CONTIGS'):
'''
Create GMAP config file with the default options. It is necessary
update the options in each run.
'''
# initialize the control variable and the error list
OK = True
error_list = []
# set the app
if assembly_dataset_id.startswith(xlib.get_soapdenovotrans_code()):
assembly_software = xlib.get_soapdenovotrans_code()
elif assembly_dataset_id.startswith(xlib.get_transabyss_code()):
assembly_software = xlib.get_transabyss_code()
elif assembly_dataset_id.startswith(xlib.get_trinity_code()):
assembly_software = xlib.get_trinity_code()
elif assembly_dataset_id.startswith(xlib.get_star_code()):
assembly_software = xlib.get_star_code()
elif assembly_dataset_id.startswith(xlib.get_cd_hit_est_code()):
assembly_software = xlib.get_cd_hit_est_code()
elif assembly_dataset_id.startswith(xlib.get_transcript_filter_code()):
assembly_software = xlib.get_transcript_filter_code()
# create the GMAP config file and write the default options
try:
if not os.path.exists(os.path.dirname(get_gmap_config_file())):
os.makedirs(os.path.dirname(get_gmap_config_file()))
with open(get_gmap_config_file(), mode='w', encoding='utf8') as file_id:
file_id.write('{0}\n'.format('# You must review the information of this file and update the values with the corresponding ones to the current run.'))
file_id.write('{0}\n'.format('#'))
file_id.write('{0}\n'.format('# The reference file must be located in the cluster directory {0}/experiment_id/reference_dataset_id'.format(xlib.get_cluster_reference_dir())))
file_id.write('{0}\n'.format('# The assembly files must be located in the cluster directory {0}/experiment_id/assembly_dataset_id'.format(xlib.get_cluster_result_dir())))
file_id.write('{0}\n'.format('# The experiment_id, reference_dataset_id, reference_file and assembly_dataset_id are fixed in the identification section.'))
file_id.write('{0}\n'.format('#'))
file_id.write('{0}\n'.format('# You can consult the parameters of GMAP and their meaning in http://research-pub.gene.com/gmap/.'))
file_id.write('{0}\n'.format('#'))
file_id.write('{0}\n'.format('# In section "GMAP parameters", the key "other_parameters" allows you to input additional parameters in the format:'))
file_id.write('{0}\n'.format('#'))
file_id.write('{0}\n'.format('# other_parameters = --parameter-1[=value-1][; --parameter-2[=value-2][; ...; --parameter-n[=value-n]]]'))
file_id.write('{0}\n'.format('#'))
file_id.write('{0}\n'.format('# parameter-i is a parameter name of GMAP and value-i a valid value of parameter-i, e.g.'))
file_id.write('{0}\n'.format('#'))
file_id.write('{0}\n'.format('# other_parameters = --no-chimeras; --canonical-mode=2'))
file_id.write('{0}\n'.format(''))
file_id.write('{0}\n'.format('# This section has the information identifies the experiment.'))
file_id.write('{0}\n'.format('[identification]'))
file_id.write('{0:<50} {1}\n'.format('experiment_id = {0}'.format(experiment_id), '# experiment identification'))
file_id.write('{0:<50} {1}\n'.format('reference_dataset_id = {0}'.format(reference_dataset_id), '# reference dataset identification or NONE'))
file_id.write('{0:<50} {1}\n'.format('reference_file = {0}'.format(reference_file), '# reference file name or NONE'))
file_id.write('{0:<50} {1}\n'.format('assembly_software = {0}'.format(assembly_software), '# assembly software: {0} ({1}) or {2} ({3}) or {4} ({5}) or {6} ({7}) or {8} ({9}) or {10} ({11})'.format(xlib.get_soapdenovotrans_code(), xlib.get_soapdenovotrans_name(), xlib.get_transabyss_code(), xlib.get_transabyss_name(), xlib.get_trinity_code(), xlib.get_trinity_name(), xlib.get_star_code(), xlib.get_star_name(), xlib.get_cd_hit_est_code(), xlib.get_cd_hit_est_name(), xlib.get_transcript_filter_code(), xlib.get_transcript_filter_name())))
file_id.write('{0:<50} {1}\n'.format('assembly_dataset_id = {0}'.format(assembly_dataset_id), '# assembly dataset identification'))
file_id.write('{0:<50} {1}\n'.format('assembly_type = {0}'.format(assembly_type), '# CONTIGS or SCAFFOLDS in {0}; NONE in {1}, {2}, {3}, {4} and {5}'.format(xlib.get_soapdenovotrans_name(), xlib.get_transabyss_name(), xlib.get_trinity_name(), xlib.get_star_name(), xlib.get_cd_hit_est_name(), xlib.get_transcript_filter_name())))
file_id.write('{0}\n'.format(''))
file_id.write('{0}\n'.format('# This section has the information to set the GMAP parameters'))
file_id.write('{0}\n'.format('[GMAP parameters]'))
file_id.write('{0:<50} {1}\n'.format('threads = 2', '# number of threads for use'))
file_id.write('{0:<50} {1}\n'.format('kmer = NONE', '# kmer size to use in genome database or NONE (the program will find the highest available kmer size in the genome database)'))
file_id.write('{0:<50} {1}\n'.format('sampling = NONE', '# Sampling to use in genome database or NONE (the program will find the smallest available sampling value in the genome database within selected k-mer size)'))
file_id.write('{0:<50} {1}\n'.format('input-buffer-size = 1000', '# size of input buffer'))
file_id.write('{0:<50} {1}\n'.format('output-buffer-size = 1000', '# size of buffer size in queries for output thread'))
file_id.write('{0:<50} {1}\n'.format('prunelevel = 0', '# pruning level: 0 (no pruning) or 1 (poor seqs) or 2 (repetitive seqs) or 3 (poor and repetitive)'))
file_id.write('{0:<50} {1}\n'.format('format = COMPRESS', '# format for output: COMPRESS or SUMMARY or ALIGN or PLS or GFF3_GENE or SPLICESITES or INTRONS or MAP_EXONS or MAP_RANGES or COORDS'))
file_id.write('{0:<50} {1}\n'.format('other_parameters = NONE', '# additional parameters to the previous ones or NONE'))
except:
error_list.append('*** ERROR: The file {0} can not be recreated'.format(get_gmap_config_file()))
OK = False
# return the control variable and the error list
return (OK, error_list)
def validate_cd_hit_est_config_file(strict):
'''
Validate the CD-HIT-EST config file of a run.
'''
# initialize the control variable and the error list
OK = True
error_list = []
# intitialize variable used when value is not found
not_found = '***NOTFOUND***'.upper()
# get the option dictionary
try:
cd_hit_est_option_dict = xlib.get_option_dict(
get_cd_hit_est_config_file())
except:
error_list.append('*** ERROR: The syntax is WRONG.')
OK = False
else:
# get the sections list
sections_list = []
for section in cd_hit_est_option_dict.keys():
sections_list.append(section)
sections_list.sort()
# check section "identification"
if 'identification' not in sections_list:
error_list.append(
'*** ERROR: the section "identification" is not found.')
OK = False
else:
# check section "identification" - key "experiment_id"
experiment_id = cd_hit_est_option_dict.get(
'identification', {}).get('experiment_id', not_found)
if experiment_id == not_found:
error_list.append(
'*** ERROR: the key "experiment_id" is not found in the section "identification".'
)
OK = False
# check section "identification" - key "assembly_software"
assembly_software = cd_hit_est_option_dict.get(
'identification', {}).get('assembly_software', not_found)
if assembly_software == not_found:
error_list.append(
'*** ERROR: the key "assembly_software" is not found in the section "identification".'
)
OK = False
elif assembly_software not in [
xlib.get_soapdenovotrans_code(),
xlib.get_transabyss_code(),
xlib.get_trinity_code(),
xlib.get_star_code(),
xlib.get_cd_hit_est_code(),
xlib.get_transcript_filter_code()
]:
error_list.append(
'*** ERROR: the key "assembly_software" value in the section "identification" must be {0} or {1} or {2} or {3} or {4} OR {5}.'
.format(xlib.get_soapdenovotrans_code(),
xlib.get_transabyss_code(),
xlib.get_trinity_code(), xlib.get_star_code(),
xlib.get_cd_hit_est_code(),
xlib.get_transcript_filter_code()))
OK = False
# check section "identification" - key "assembly_dataset_id"
assembly_dataset_id = cd_hit_est_option_dict.get(
'identification', {}).get('assembly_dataset_id', not_found)
if assembly_dataset_id == not_found:
error_list.append(
'*** ERROR: the key "assembly_dataset_id" is not found in the section "identification".'
)
OK = False
elif not assembly_dataset_id.startswith(
xlib.get_soapdenovotrans_code()
) and not assembly_dataset_id.startswith(xlib.get_transabyss_code(
)) and not assembly_dataset_id.startswith(xlib.get_trinity_code(
)) and not assembly_dataset_id.startswith(xlib.get_star_code(
)) and not assembly_dataset_id.startswith(xlib.get_cd_hit_est_code(
)) and not assembly_dataset_id.startswith(
xlib.get_transcript_filter_code()):
error_list.append(
'*** ERROR: the key "assembly_dataset_id" value is not a {0} nor {1} nor {2} nor {3} nor {4} nor {5} assembly.'
.format(xlib.get_soapdenovotrans_name(),
xlib.get_transabyss_name(),
xlib.get_trinity_name(), xlib.get_star_name(),
xlib.get_cd_hit_est_name(),
xlib.get_transcript_filter_code()))
OK = False
# check section "identification" - key "assembly_type"
assembly_type = cd_hit_est_option_dict.get(
'identification', {}).get('assembly_type', not_found)
if assembly_type == not_found:
error_list.append(
'*** ERROR: the key "assembly_type" is not found in the section "identification".'
)
OK = False
elif assembly_dataset_id.startswith(
xlib.get_soapdenovotrans_code()):
if assembly_type.upper() not in ['CONTIGS', 'SCAFFOLDS']:
error_list.append(
'*** ERROR: the key "assembly_type" must be "CONTIGS" or "SCAFFOLDS" when {0} is the assembly software.'
.format(xlib.get_soapdenovotrans_name()))
OK = False
elif assembly_dataset_id.startswith(xlib.get_transabyss_code(
)) or assembly_dataset_id.startswith(xlib.get_trinity_code(
)) or assembly_dataset_id.startswith(
xlib.get_star_code()) or assembly_dataset_id.startswith(
xlib.get_cd_hit_est_code(
)) or assembly_dataset_id.startswith(
xlib.get_transcript_filter_code()):
if assembly_type.upper() != 'NONE':
error_list.append(
'*** ERROR: the key "assembly_type" must be "NONE" when {0} or {1} or {2} or {3} or {4} is the assembly software.'
.format(xlib.get_transabyss_name(),
xlib.get_trinity_name(), xlib.get_star_name(),
xlib.get_cd_hit_est_name(),
xlib.get_transcript_filter_name()))
OK = False
# check section "CD-HIT-EST parameters"
if 'CD-HIT-EST parameters' not in sections_list:
error_list.append(
'*** ERROR: the section "CD-HIT-EST parameters" is not found.')
OK = False
else:
# check section "CD-HIT-EST parameters" - key "threads"
threads = cd_hit_est_option_dict.get('CD-HIT-EST parameters',
{}).get('threads', not_found)
if threads == not_found:
error_list.append(
'*** ERROR: the key "threads" is not found in the section "CD-HIT-EST parameters".'
)
OK = False
else:
try:
if int(threads) < 0:
error_list.append(
'*** ERROR: the key "threads" in the section "CD-HIT-EST parameters" must be an integer value greater or equal to 0.'
)
OK = False
except:
error_list.append(
'*** ERROR: the key "threads" in the section "CD-HIT-EST parameters" must be an integer value greater or equal to 0.'
)
OK = False
# check section "CD-HIT-EST parameters" - key "memory_limit"
memory_limit = cd_hit_est_option_dict.get(
'CD-HIT-EST parameters', {}).get('memory_limit', not_found)
if memory_limit == not_found:
error_list.append(
'*** ERROR: the key "memory_limit" is not found in the section "CD-HIT-EST parameters".'
)
OK = False
else:
try:
if int(memory_limit) < 0:
error_list.append(
'*** ERROR: the key "memory_limit" in the section "CD-HIT-EST parameters" must be an integer value greater or equal to 0.'
)
OK = False
except:
error_list.append(
'*** ERROR: the key "memory_limit" in the section "CD-HIT-EST parameters" must be an integer value greater or equal to 0.'
)
OK = False
# check section "CD-HIT-EST parameters" - key "seq_identity_threshold"
seq_identity_threshold = cd_hit_est_option_dict.get(
'CD-HIT-EST parameters', {}).get('seq_identity_threshold',
not_found)
if seq_identity_threshold == not_found:
error_list.append(
'*** ERROR: the key "seq_identity_threshold" is not found in the section "CD-HIT-EST parameters".'
)
OK = False
else:
try:
if float(seq_identity_threshold) < 0.0 or float(
seq_identity_threshold) > 1.0:
error_list.append(
'*** ERROR: the key "seq_identity_threshold" in the section "CD-HIT-EST parameters" must be a float value between 0.0 and 1.0.'
)
OK = False
except:
error_list.append(
'*** ERROR: the key "seq_identity_threshold" in the section "CD-HIT-EST parameters" must be a float value between 0.0 and 1.0.'
)
OK = False
# check section "CD-HIT-EST parameters" - key "word_length"
word_length = cd_hit_est_option_dict.get(
'CD-HIT-EST parameters', {}).get('word_length', not_found)
if word_length == not_found:
error_list.append(
'*** ERROR: the key "word_length" is not found in the section "CD-HIT-EST parameters".'
)
OK = False
else:
try:
if int(word_length) < 1:
error_list.append(
'*** ERROR: the key "word_length" in the section "CD-HIT-EST parameters" must be an integer value greater or equal to 1.'
)
OK = False
except:
error_list.append(
'*** ERROR: the key "word_length" in the section "CD-HIT-EST parameters" must be an integer value greater or equal to 1.'
)
OK = False
# check section "CD-HIT-EST parameters" - key "mask"
mask = cd_hit_est_option_dict.get('CD-HIT-EST parameters',
{}).get('mask',
not_found).upper()
if mask == not_found:
error_list.append(
'*** ERROR: the key "mask" is not found in the section "CD-HIT-EST parameters".'
)
OK = False
# check section "CD-HIT-EST parameters" - key "match"
match = cd_hit_est_option_dict.get('CD-HIT-EST parameters',
{}).get('match', not_found)
if match == not_found:
error_list.append(
'*** ERROR: the key "match" is not found in the section "CD-HIT-EST parameters".'
)
OK = False
else:
try:
int(match)
except:
error_list.append(
'*** ERROR: the key "match" in the section "CD-HIT-EST parameters" must be an integer value.'
)
OK = False
# check section "CD-HIT-EST parameters" - key "mismatch"
mismatch = cd_hit_est_option_dict.get('CD-HIT-EST parameters',
{}).get(
'mismatch', not_found)
if mismatch == not_found:
error_list.append(
'*** ERROR: the key "mismatch" is not found in the section "CD-HIT-EST parameters".'
)
OK = False
else:
try:
int(mismatch)
except:
error_list.append(
'*** ERROR: the key "match" in the section "CD-HIT-EST parameters" must be an integer value.'
)
OK = False
# check section "CD-HIT-EST parameters" - key "other_parameters"
not_allowed_parameters_list = [
'T', 'M', 'c', 'n', 'mask', 'match', 'mismatch'
]
other_parameters = cd_hit_est_option_dict.get(
'CD-HIT-EST parameters', {}).get('other_parameters', not_found)
if other_parameters == not_found:
error_list.append(
'*** ERROR: the key "other_parameters" is not found in the section "CD-HIT-EST parameters".'
)
OK = False
else:
if other_parameters.upper() != 'NONE':
parameter_list = [
x.strip() for x in other_parameters.split(';')
]
for parameter in parameter_list:
try:
if parameter.find('=') > 0:
pattern = r'^--(.+)=(.+)$'
mo = re.search(pattern, parameter)
parameter_name = mo.group(1).strip()
parameter_value = mo.group(2).strip()
else:
pattern = r'^--(.+)$'
mo = re.search(pattern, parameter)
parameter_name = mo.group(1).strip()
except:
error_list.append(
'*** ERROR: the value of the key "other_parameters" in the section "CD-HIT-EST parameters" must be NONE or a valid parameter list.'
)
OK = False
break
if parameter_name in not_allowed_parameters_list:
error_list.append(
'*** ERROR: the parameter {0} is not allowed in the key "other_parameters" of the section "CD-HIT-EST parameters" because it is controled by {1}.'
.format(parameter_name,
xlib.get_project_name()))
OK = False
# warn that the results config file is not valid if there are any errors
if not OK:
error_list.append(
'\nThe {0} config file is not valid. Please, correct this file or recreate it.'
.format(xlib.get_cd_hit_est_name()))
# return the control variable and the error list
return (OK, error_list)
def validate_gmap_config_file(strict):
'''
Validate the GMAP config file of a run.
'''
# initialize the control variable and the error list
OK = True
error_list = []
# intitialize variable used when value is not found
not_found = '***NOTFOUND***'.upper()
# get the option dictionary
try:
gmap_option_dict = xlib.get_option_dict(get_gmap_config_file())
except:
error_list.append('*** ERROR: The syntax is WRONG.')
OK = False
else:
# get the sections list
sections_list = []
for section in gmap_option_dict.keys():
sections_list.append(section)
sections_list.sort()
# check section "identification"
if 'identification' not in sections_list:
error_list.append('*** ERROR: the section "identification" is not found.')
OK = False
else:
# check section "identification" - key "experiment_id"
experiment_id = gmap_option_dict.get('identification', {}).get('experiment_id', not_found)
is_experiment_id_OK = True
if experiment_id == not_found:
error_list.append('*** ERROR: the key "experiment_id" is not found in the section "identification".')
is_experiment_id_OK = False
OK = False
# check section "identification" - key "reference_dataset_id"
reference_dataset_id = gmap_option_dict.get('identification', {}).get('reference_dataset_id', not_found)
is_reference_dataset_id_OK = True
if reference_dataset_id == not_found:
error_list.append('*** ERROR: the key "reference_dataset_id" is not found in the section "identification".')
is_reference_dataset_id_OK = False
OK = False
# check section "identification" - key "reference_file"
reference_file = gmap_option_dict.get('identification', {}).get('reference_file', not_found)
is_reference_file_OK = True
if reference_file == not_found:
error_list.append('*** ERROR: the key "reference_file" is not found in the section "identification".')
is_reference_file_OK = False
OK = False
# check section "identification" - key "assembly_software"
assembly_software = gmap_option_dict.get('identification', {}).get('assembly_software', not_found)
is_assembly_software_OK = True
if assembly_software == not_found:
error_list.append('*** ERROR: the key "assembly_software" is not found in the section "identification".')
is_assembly_software_OK = False
OK = False
elif assembly_software not in [xlib.get_soapdenovotrans_code(), xlib.get_transabyss_code(), xlib.get_trinity_code(), xlib.get_star_code(), xlib.get_cd_hit_est_code(), xlib.get_transcript_filter_code()]:
error_list.append('*** ERROR: the key "assembly_software" value in the section "identification" must be {0} or {1} or {2} or {3} or {4} OR {5}.'.format(xlib.get_soapdenovotrans_code(), xlib.get_transabyss_code(), xlib.get_trinity_code(), xlib.get_star_code(), xlib.get_cd_hit_est_code(), xlib.get_transcript_filter_code()))
is_assembly_software_OK = False
OK = False
# check section "identification" - key "assembly_dataset_id"
assembly_dataset_id = gmap_option_dict.get('identification', {}).get('assembly_dataset_id', not_found)
is_assembly_dataset_id_OK = True
if assembly_dataset_id == not_found:
error_list.append('*** ERROR: the key "assembly_dataset_id" is not found in the section "identification".')
is_assembly_dataset_id_OK = False
OK = False
elif not assembly_dataset_id.startswith(xlib.get_soapdenovotrans_code()) and not assembly_dataset_id.startswith(xlib.get_transabyss_code()) and not assembly_dataset_id.startswith(xlib.get_trinity_code()) and not assembly_dataset_id.startswith(xlib.get_star_code()) and not assembly_dataset_id.startswith(xlib.get_cd_hit_est_code()) and not assembly_dataset_id.startswith(xlib.get_transcript_filter_code()):
error_list.append('*** ERROR: the key "assembly_dataset_id" value is not a {0} nor {1} nor {2} nor {3} nor {4} nor {5} assembly.'.format(xlib.get_soapdenovotrans_name(), xlib.get_transabyss_name(), xlib.get_trinity_name(), xlib.get_star_name(), xlib.get_cd_hit_est_name(), xlib.get_transcript_filter_code()))
is_assembly_dataset_id_OK = False
OK = False
# check section "identification" - key "assembly_type"
assembly_type = gmap_option_dict.get('identification', {}).get('assembly_type', not_found)
is_assembly_type_OK = True
if assembly_type == not_found:
error_list.append('*** ERROR: the key "assembly_type" is not found in the section "identification".')
is_assembly_type_OK = False
OK = False
elif assembly_dataset_id.startswith(xlib.get_soapdenovotrans_code()):
if assembly_type.upper() not in ['CONTIGS', 'SCAFFOLDS']:
error_list.append('*** ERROR: the key "assembly_type" must be "CONTIGS" or "SCAFFOLDS" when {0} is the assembly software.'.format(xlib.get_soapdenovotrans_name()))
is_assembly_type_OK = False
OK = False
elif assembly_dataset_id.startswith(xlib.get_transabyss_code()) or assembly_dataset_id.startswith(xlib.get_trinity_code()) or assembly_dataset_id.startswith(xlib.get_star_code()) or assembly_dataset_id.startswith(xlib.get_cd_hit_est_code()) or assembly_dataset_id.startswith(xlib.get_transcript_filter_code()):
if assembly_type.upper() != 'NONE':
error_list.append('*** ERROR: the key "assembly_type" must be "NONE" when {0} or {1} or {2} or {3} or {4} is the assembly software.'.format(xlib.get_transabyss_name(), xlib.get_trinity_name(), xlib.get_star_name(), xlib.get_cd_hit_est_name(), xlib.get_transcript_filter_name()))
is_assembly_type_OK = False
OK = False
# check section "GMAP parameters"
if 'GMAP parameters' not in sections_list:
error_list.append('*** ERROR: the section "GMAP parameters" is not found.')
OK = False
else:
# check section "GMAP parameters" - key "threads"
threads = gmap_option_dict.get('GMAP parameters', {}).get('threads', not_found)
is_threads_OK = True
if threads == not_found:
error_list.append('*** ERROR: the key "threads" is not found in the section "GMAP parameters".')
is_threads_OK = False
OK = False
else:
try:
if int(threads) < 1:
error_list.append('*** ERROR: the key "threads" in the section "GMAP parameters" must be an integer value greater or equal to 1.')
is_threads_OK = False
OK = False
except:
error_list.append('*** ERROR: the key "threads" in the section "GMAP parameters" must be an integer value greater or equal to 1.')
is_threads_OK = False
OK = False
# check section "GMAP parameters" - key "kmer"
kmer = gmap_option_dict.get('GMAP parameters', {}).get('kmer', not_found)
is_kmer_OK = True
if kmer == not_found:
error_list.append('*** ERROR: the key "kmer" is not found in the section "GMAP parameters".')
is_kmer_OK = False
OK = False
else:
try:
if kmer.upper() != 'NONE' and (int(kmer) < 1 or int(kmer) > 16):
error_list.append('*** ERROR: the key "kmer" in the section "GMAP parameters" must be an integer value between 1 and 16 or NONE.')
is_kmer_OK = False
OK = False
except:
error_list.append('*** ERROR: the key "kmer" in the section "GMAP parameters" must be an integer value between 1 and 16 or NONE.')
is_kmer_OK = False
OK = False
# check section "GMAP parameters" - key "sampling"
sampling = gmap_option_dict.get('GMAP parameters', {}).get('sampling', not_found)
is_sampling_OK = True
if sampling == not_found:
error_list.append('*** ERROR: the key "sampling" is not found in the section "GMAP parameters".')
is_sampling_OK = False
OK = False
else:
try:
if sampling.upper() != 'NONE' and int(sampling) < 1:
error_list.append('*** ERROR: the key "sampling" in the section "GMAP parameters" must be an integer value greater or equal to 1 or NONE.')
is_sampling_OK = False
OK = False
except:
error_list.append('*** ERROR: the key "sampling" in the section "GMAP parameters" must be an integer value greater or equal to 1 or NONE.')
is_sampling_OK = False
OK = False
# check section "GMAP parameters" - key "input-buffer-size"
input_buffer_size = gmap_option_dict.get('GMAP parameters', {}).get('input-buffer-size', not_found)
is_input_buffer_size_OK = True
if input_buffer_size == not_found:
error_list.append('*** ERROR: the key "input-buffer-size" is not found in the section "GMAP parameters".')
is_input_buffer_size_OK = False
OK = False
else:
try:
if int(input_buffer_size) < 1:
error_list.append('*** ERROR: the key "input-buffer-size" in the section "GMAP parameters" must be an integer value greater or equal to 1.')
is_input_buffer_size_OK = False
OK = False
except:
error_list.append('*** ERROR: the key "input-buffer-size" in the section "GMAP parameters" must be an integer value greater or equal to 1.')
is_input_buffer_size_OK = False
OK = False
# check section "GMAP parameters" - key "output-buffer-size"
output_buffer_size = gmap_option_dict.get('GMAP parameters', {}).get('output-buffer-size', not_found)
is_output_buffer_size_OK = True
if output_buffer_size == not_found:
error_list.append('*** ERROR: the key "output-buffer-size" is not found in the section "GMAP parameters".')
is_output_buffer_size_OK = False
OK = False
else:
try:
if int(output_buffer_size) < 1:
error_list.append('*** ERROR: the key "output-buffer-size" in the section "GMAP parameters" must be an integer value greater or equal to 1.')
is_output_buffer_size_OK = False
OK = False
except:
error_list.append('*** ERROR: the key "output-buffer-size" in the section "GMAP parameters" must be an integer value greater or equal to 1.')
is_output_buffer_size_OK = False
OK = False
# check section "GMAP parameters" - key "prunelevel"
prunelevel = gmap_option_dict.get('GMAP parameters', {}).get('prunelevel', not_found)
is_prunelevel_OK = True
if prunelevel == not_found:
error_list.append('*** ERROR: the key "prunelevel" is not found in the section "GMAP parameters".')
is_prunelevel_OK = False
OK = False
else:
if prunelevel not in ['0', '1', '2', '3']:
error_list.append('*** ERROR: the key "prunelevel" in the section "GMAP parameters" must be 0 (no pruning) or 1 (poor seqs) or 2 (repetitive seqs) or 3 (poor and repetitive).')
is_prunelevel_OK = False
OK = False
# check section "GMAP parameters" - key "format"
format = gmap_option_dict.get('GMAP parameters', {}).get('format', not_found)
is_format_OK = True
if format == not_found:
error_list.append('*** ERROR: the key "format" is not found in the section "GMAP parameters".')
is_format_OK = False
OK = False
else:
if format.upper() not in ['COMPRESS', 'SUMMARY', 'ALIGN', 'PLS', 'GFF3_GENE', 'SPLICESITES', 'INTRONS', 'MAP_EXONS', 'MAP_RANGES', 'COORDS']:
error_list.append('*** ERROR: the key "format" in the section "GMAP parameters" must be COMPRESS or SUMMARY or ALIGN or PLS or GFF3_GENE or SPLICESITES or INTRONS or MAP_EXONS or MAP_RANGES or COORDS.')
is_format_OK = False
OK = False
# check section "GMAP parameters" - key "other_parameters"
not_allowed_parameters_list = ['nthreads', 'kmer', 'sampling', 'input-buffer-size', 'output-buffer-size', 'prunelevel', 'compress', 'summary', 'align', 'format' ]
other_parameters = gmap_option_dict.get('GMAP parameters', {}).get('other_parameters', not_found)
is_other_parameters_OK = True
if other_parameters == not_found:
error_list.append('*** ERROR: the key "other_parameters" is not found in the section "GMAP parameters".')
is_other_parameters_OK = False
OK = False
else:
if other_parameters.upper() != 'NONE':
parameter_list = [x.strip() for x in other_parameters.split(';')]
for parameter in parameter_list:
try:
if parameter.find('=') > 0:
pattern = r'^--(.+)=(.+)$'
mo = re.search(pattern, parameter)
parameter_name = mo.group(1).strip()
parameter_value = mo.group(2).strip()
else:
pattern = r'^--(.+)$'
mo = re.search(pattern, parameter)
parameter_name = mo.group(1).strip()
except:
error_list.append('*** ERROR: the value of the key "other_parameters" in the section "GMAP parameters" must be NONE or a valid parameter list.')
is_other_parameters_OK = False
OK = False
break
else:
if parameter_name in not_allowed_parameters_list:
error_list.append('*** ERROR: the parameter {0} is not allowed in the key "other_parameters" of the section "GMAP parameters" because it is controled by NGScloud.'.format(parameter_name))
is_other_parameters_OK = False
OK = False
# warn that the results config file is not valid if there are any errors
if not OK:
error_list.append('\nThe {0} config file is not valid. Please, correct this file or recreate it.'.format(xlib.get_gmap_name()))
# return the control variable and the error list
return (OK, error_list)
def get_result_dataset_dict(cluster_name, experiment_id, status, passed_connection, ssh_client):
'''
Get a dictionary with the result datasets of an experiment in the cluster.
'''
# initialize the control variable and the error list
OK = True
error_list = []
# get the result directory in the cluster
cluster_result_dir = xlib.get_cluster_result_dir()
# initialize the dictionary of the result datasets
result_dataset_dict = {}
# create the SSH client connection
if not passed_connection:
(OK, error_list, ssh_client) = xssh.create_ssh_client_connection(cluster_name, 'master')
# verify the result directory is created
if OK:
command = '[ -d {0} ] && echo RC=0 || echo RC=1'.format(cluster_result_dir)
(OK, stdout, stderr) = xssh.execute_cluster_command(ssh_client, command)
if stdout[len(stdout) - 1] != 'RC=0':
error_list.append('*** ERROR: There is not any volume mounted in the result directory.\n')
error_list.append('You must link a volume in the mounting point {0} for the template {1}.\n'.format(cluster_result_dir, cluster_name))
OK = False
# get the dictionary of the result datasets
if OK:
if status == 'uncompressed':
command = 'cd {0}/{1}; for list in `ls`; do ls -ld $list | grep -v ^- > /dev/null && echo $list; done;'.format(cluster_result_dir, experiment_id)
elif status == 'compressed':
command = 'cd {0}/{1}; for list in `ls`; do ls -ld $list | grep -v ^d > /dev/null && echo $list; done;'.format(cluster_result_dir, experiment_id)
(OK, stdout, stderr) = xssh.execute_cluster_command(ssh_client, command)
if OK:
if status == 'uncompressed':
input_pattern = '{0}-(.+)-(.+)'
output_pattern = '{0} ({1} {2})'
elif status == 'compressed':
input_pattern = '{0}-(.+)-(.+).tar.gz'
output_pattern = '{0} ({1} {2}) [compressed]'
for line in stdout:
line = line.rstrip('\n')
if line != 'lost+found':
result_dataset_id = line
if result_dataset_id.startswith(xlib.get_cd_hit_est_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_cd_hit_est_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_cd_hit_est_name(), date, time)
elif result_dataset_id.startswith(xlib.get_fastqc_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_fastqc_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_fastqc_name(), date, time)
elif result_dataset_id.startswith(xlib.get_gzip_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_gzip_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_gzip_name(), date, time)
elif result_dataset_id.startswith(xlib.get_insilico_read_normalization_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_insilico_read_normalization_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_insilico_read_normalization_name(), date, time)
elif result_dataset_id.startswith(xlib.get_quast_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_quast_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_quast_name(), date, time)
elif result_dataset_id.startswith(xlib.get_ref_eval_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_ref_eval_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_ref_eval_name(), date, time)
elif result_dataset_id.startswith(xlib.get_rnaquast_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_rnaquast_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_rnaquast_name(), date, time)
elif result_dataset_id.startswith(xlib.get_rsem_eval_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_rsem_eval_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_rsem_eval_name(), date, time)
elif result_dataset_id.startswith(xlib.get_soapdenovotrans_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_soapdenovotrans_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_soapdenovotrans_name(), date, time)
elif result_dataset_id.startswith(xlib.get_star_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_star_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_star_name(), date, time)
elif result_dataset_id.startswith(xlib.get_transabyss_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_transabyss_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_transabyss_name(), date, time)
elif result_dataset_id.startswith(xlib.get_transcript_filter_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_transcript_filter_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_transcript_filter_name(), date, time)
elif result_dataset_id.startswith(xlib.get_transcriptome_blastx_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_transcriptome_blastx_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_transcriptome_blastx_name(), date, time)
elif result_dataset_id.startswith(xlib.get_transrate_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_transrate_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_transrate_name(), date, time)
elif result_dataset_id.startswith(xlib.get_trimmomatic_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_trimmomatic_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_trimmomatic_name(), date, time)
elif result_dataset_id.startswith(xlib.get_trinity_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_trinity_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_trinity_name(), date, time)
else:
result_dataset_name = result_dataset_id
result_dataset_dict[result_dataset_id] = {'result_dataset_id': result_dataset_id, 'result_dataset_name': result_dataset_name}
# close the SSH client connection
if OK and not passed_connection:
xssh.close_ssh_client_connection(ssh_client)
# return the control variable, error list and dictionary of the result datasets
return (OK, error_list, result_dataset_dict)
def create_cd_hit_est_config_file(experiment_id='exp001',
assembly_dataset_id='sdnt-170101-235959',
assembly_type='CONTIGS'):
'''
Create CD-HIT-EST config file with the default options. It is necessary
update the options in each run.
'''
# initialize the control variable and the error list
OK = True
error_list = []
# set the assembly software
if assembly_dataset_id.startswith(xlib.get_soapdenovotrans_code()):
assembly_software = xlib.get_soapdenovotrans_code()
elif assembly_dataset_id.startswith(xlib.get_transabyss_code()):
assembly_software = xlib.get_transabyss_code()
elif assembly_dataset_id.startswith(xlib.get_trinity_code()):
assembly_software = xlib.get_trinity_code()
elif assembly_dataset_id.startswith(xlib.get_star_code()):
assembly_software = xlib.get_star_code()
elif assembly_dataset_id.startswith(xlib.get_cd_hit_est_code()):
assembly_software = xlib.get_cd_hit_est_code()
elif assembly_dataset_id.startswith(xlib.get_transcript_filter_code()):
assembly_software = xlib.get_transcript_filter_code()
# create the CD-HIT-EST config file and write the default options
try:
if not os.path.exists(os.path.dirname(get_cd_hit_est_config_file())):
os.makedirs(os.path.dirname(get_cd_hit_est_config_file()))
with open(get_cd_hit_est_config_file(), mode='w',
encoding='utf8') as file_id:
file_id.write('{0}\n'.format(
'# You must review the information of this file and update the values with the corresponding ones to the current run.'
))
file_id.write('{0}\n'.format('#'))
file_id.write('{0}\n'.format(
'# The assembly files must be located in the cluster directory {0}/experiment_id/assembly_dataset_id'
.format(xlib.get_cluster_result_dir())))
file_id.write('{0}\n'.format(
'# The experiment_id and assembly_dataset_id names are fixed in the identification section.'
))
file_id.write('{0}\n'.format('#'))
file_id.write('{0}\n'.format(
'# You can consult the parameters of CD-HIT-EST (CD-HIT package) and their meaning in http://weizhong-lab.ucsd.edu/cd-hit/.'
))
file_id.write('{0}\n'.format('#'))
file_id.write('{0}\n'.format(
'# In section "CD-HIT-EST parameters", the key "other_parameters" allows you to input additional parameters in the format:'
))
file_id.write('{0}\n'.format('#'))
file_id.write('{0}\n'.format(
'# other_parameters = --parameter-1[=value-1][; --parameter-2[=value-2][; ...; --parameter-n[=value-n]]]'
))
file_id.write('{0}\n'.format('#'))
file_id.write('{0}\n'.format(
'# parameter-i is a parameter name of CD-HIT-EST and value-i a valid value of parameter-i, e.g.'
))
file_id.write('{0}\n'.format('#'))
file_id.write(
'{0}\n'.format('# other_parameters = --aS=0.9; --U=10'))
file_id.write('{0}\n'.format(''))
file_id.write('{0}\n'.format(
'# This section has the information identifies the assembly result dataset.'
))
file_id.write('{0}\n'.format('[identification]'))
file_id.write('{0:<50} {1}\n'.format(
'experiment_id = {0}'.format(experiment_id),
'# experiment identification'))
file_id.write('{0:<50} {1}\n'.format(
'assembly_software = {0}'.format(assembly_software),
'# assembly software: {0} ({1}) or {2} ({3}) or {4} ({5}) or {6} ({7}) or {8} ({9}) or {10} ({11})'
.format(xlib.get_soapdenovotrans_code(),
xlib.get_soapdenovotrans_name(),
xlib.get_transabyss_code(), xlib.get_transabyss_name(),
xlib.get_trinity_code(), xlib.get_trinity_name(),
xlib.get_star_code(), xlib.get_star_name(),
xlib.get_cd_hit_est_code(), xlib.get_cd_hit_est_name(),
xlib.get_transcript_filter_code(),
xlib.get_transcript_filter_name())))
file_id.write('{0:<50} {1}\n'.format(
'assembly_dataset_id = {0}'.format(assembly_dataset_id),
'# assembly dataset identification'))
file_id.write('{0:<50} {1}\n'.format(
'assembly_type = {0}'.format(assembly_type),
'# CONTIGS or SCAFFOLDS in {0}; NONE in {1}, {2}, {3}, {4} and {5}'
.format(xlib.get_soapdenovotrans_name(),
xlib.get_transabyss_name(), xlib.get_trinity_name(),
xlib.get_star_name(), xlib.get_cd_hit_est_name(),
xlib.get_transcript_filter_name())))
file_id.write('{0}\n'.format(''))
file_id.write('{0}\n'.format(
'# This section has the information to set the CD-HIT-EST parameters'
))
file_id.write('{0}\n'.format('[CD-HIT-EST parameters]'))
file_id.write('{0:<50} {1}\n'.format(
'threads = 2',
'# number of threads for use; with 0, all CPUs will be used'))
file_id.write('{0:<50} {1}\n'.format(
'memory_limit = 800',
'# memory limit (in MB) for the program; 0 for unlimitted'))
file_id.write('{0:<50} {1}\n'.format(
'seq_identity_threshold = 0.9',
'# sequence identity threshold'))
file_id.write('{0:<50} {1}\n'.format('word_length = 5',
'# word length'))
file_id.write('{0:<50} {1}\n'.format(
'mask = NX',
'# masking letters (e.g. -mask NX, to mask out both "N" and "X")'
))
file_id.write('{0:<50} {1}\n'.format(
'match = 2', '# matching score (1 for T-U and N-N)'))
file_id.write('{0:<50} {1}\n'.format('mismatch = -2',
'# mismatching score'))
file_id.write('{0:<50} {1}\n'.format(
'other_parameters = NONE',
'# additional parameters to the previous ones or NONE'))
except:
error_list.append(
'*** ERROR: The file {0} can not be recreated'.format(
get_cd_hit_est_config_file()))
OK = False
# return the control variable and the error list
return (OK, error_list)
def validate_quast_config_file(strict):
'''
Validate the QUAST config file of a run.
'''
# initialize the control variable and the error list
OK = True
error_list = []
# intitialize variable used when value is not found
not_found = '***NOTFOUND***'.upper()
# get the option dictionary
try:
quast_option_dict = xlib.get_option_dict(get_quast_config_file())
except:
error_list.append('*** ERROR: The syntax is WRONG.')
OK = False
else:
# get the sections list
sections_list = []
for section in quast_option_dict.keys():
sections_list.append(section)
sections_list.sort()
# check section "identification"
if 'identification' not in sections_list:
error_list.append('*** ERROR: the section "identification" is not found.')
OK = False
else:
# check section "identification" - key "experiment_id"
experiment_id = quast_option_dict.get('identification', {}).get('experiment_id', not_found)
if experiment_id == not_found:
error_list.append('*** ERROR: the key "experiment_id" is not found in the section "identification".')
OK = False
# check section "identification" - key "reference_dataset_id"
reference_dataset_id = quast_option_dict.get('identification', {}).get('reference_dataset_id', not_found)
if reference_dataset_id == not_found:
error_list.append('*** ERROR: the key "reference_dataset_id" is not found in the section "identification".')
OK = False
# check section "identification" - key "reference_file"
reference_file = quast_option_dict.get('identification', {}).get('reference_file', not_found)
if reference_file == not_found:
error_list.append('*** ERROR: the key "reference_file" is not found in the section "identification".')
OK = False
# check section "identification" - key "assembly_software"
assembly_software = quast_option_dict.get('identification', {}).get('assembly_software', not_found)
if assembly_software == not_found:
error_list.append('*** ERROR: the key "assembly_software" is not found in the section "identification".')
OK = False
elif assembly_software not in [xlib.get_soapdenovotrans_code(), xlib.get_transabyss_code(), xlib.get_trinity_code(), xlib.get_star_code(), xlib.get_cd_hit_est_code(), xlib.get_transcript_filter_code()]:
error_list.append('*** ERROR: the key "assembly_software" value in the section "identification" must be {0} or {1} or {2} or {3} or {4} OR {5}.'.format(xlib.get_soapdenovotrans_code(), xlib.get_transabyss_code(), xlib.get_trinity_code(), xlib.get_star_code(), xlib.get_cd_hit_est_code(), xlib.get_transcript_filter_code()))
OK = False
# check section "identification" - key "assembly_dataset_id"
assembly_dataset_id = quast_option_dict.get('identification', {}).get('assembly_dataset_id', not_found)
if assembly_dataset_id == not_found:
error_list.append('*** ERROR: the key "assembly_dataset_id" is not found in the section "identification".')
OK = False
elif not assembly_dataset_id.startswith(xlib.get_soapdenovotrans_code()) and not assembly_dataset_id.startswith(xlib.get_transabyss_code()) and not assembly_dataset_id.startswith(xlib.get_trinity_code()) and not assembly_dataset_id.startswith(xlib.get_star_code()) and not assembly_dataset_id.startswith(xlib.get_cd_hit_est_code()) and not assembly_dataset_id.startswith(xlib.get_transcript_filter_code()):
error_list.append('*** ERROR: the key "assembly_dataset_id" value is not a {0} nor {1} nor {2} nor {3} nor {4} nor {5} assembly.'.format(xlib.get_soapdenovotrans_name(), xlib.get_transabyss_name(), xlib.get_trinity_name(), xlib.get_star_name(), xlib.get_cd_hit_est_name(), xlib.get_transcript_filter_code()))
OK = False
# check section "identification" - key "assembly_type"
assembly_type = quast_option_dict.get('identification', {}).get('assembly_type', not_found)
if assembly_type == not_found:
error_list.append('*** ERROR: the key "assembly_type" is not found in the section "identification".')
OK = False
elif assembly_dataset_id.startswith(xlib.get_soapdenovotrans_code()):
if assembly_type.upper() not in ['CONTIGS', 'SCAFFOLDS']:
error_list.append('*** ERROR: the key "assembly_type" must be "CONTIGS" or "SCAFFOLDS" when {0} is the assembly software.'.format(xlib.get_soapdenovotrans_name()))
OK = False
elif assembly_dataset_id.startswith(xlib.get_transabyss_code()) or assembly_dataset_id.startswith(xlib.get_trinity_code()) or assembly_dataset_id.startswith(xlib.get_star_code()) or assembly_dataset_id.startswith(xlib.get_cd_hit_est_code()) or assembly_dataset_id.startswith(xlib.get_transcript_filter_code()):
if assembly_type.upper() != 'NONE':
error_list.append('*** ERROR: the key "assembly_type" must be "NONE" when {0} or {1} or {2} or {3} or {4} is the assembly software.'.format(xlib.get_transabyss_name(), xlib.get_trinity_name(), xlib.get_star_name(), xlib.get_cd_hit_est_name(), xlib.get_transcript_filter_name()))
OK = False
# check section "QUAST parameters"
if 'QUAST parameters' not in sections_list:
error_list.append('*** ERROR: the section "QUAST parameters" is not found.')
OK = False
else:
# check section "QUAST parameters" - key "threads"
threads = quast_option_dict.get('QUAST parameters', {}).get('threads', not_found)
if threads == not_found:
error_list.append('*** ERROR: the key "threads" is not found in the section "QUAST parameters".')
OK = False
else:
try:
if int(threads) < 1:
error_list.append('*** ERROR: the key "threads" in the section "QUAST parameters" must be an integer value greater or equal to 1.')
OK = False
except:
error_list.append('*** ERROR: the key "threads" in the section "QUAST parameters" must be an integer value greater or equal to 1.')
OK = False
# warn that the results config file is not valid if there are any errors
if not OK:
error_list.append('\nThe {0} config file is not valid. Please, correct this file or recreate it.'.format(xlib.get_quast_name()))
# return the control variable and the error list
return (OK, error_list)
def create_quast_config_file(experiment_id='exp001', reference_dataset_id='NONE', reference_file='NONE', assembly_dataset_id='sdnt-170101-235959', assembly_type='CONTIGS'):
'''
Create QUAST config file with the default options. It is necessary
update the options in each run.
'''
# initialize the control variable and the error list
OK = True
error_list = []
# set the app
if assembly_dataset_id.startswith(xlib.get_soapdenovotrans_code()):
assembly_software = xlib.get_soapdenovotrans_code()
elif assembly_dataset_id.startswith(xlib.get_transabyss_code()):
assembly_software = xlib.get_transabyss_code()
elif assembly_dataset_id.startswith(xlib.get_trinity_code()):
assembly_software = xlib.get_trinity_code()
elif assembly_dataset_id.startswith(xlib.get_star_code()):
assembly_software = xlib.get_star_code()
elif assembly_dataset_id.startswith(xlib.get_cd_hit_est_code()):
assembly_software = xlib.get_cd_hit_est_code()
elif assembly_dataset_id.startswith(xlib.get_transcript_filter_code()):
assembly_software = xlib.get_transcript_filter_code()
# create the QUAST config file and write the default options
try:
if not os.path.exists(os.path.dirname(get_quast_config_file())):
os.makedirs(os.path.dirname(get_quast_config_file()))
with open(get_quast_config_file(), mode='w', encoding='utf8') as file_id:
file_id.write('{0}\n'.format('# You must review the information of this file and update the values with the corresponding ones to the current run.'))
file_id.write('{0}\n'.format('#'))
file_id.write('{0}\n'.format('# The reference file must be located in the cluster directory {0}/experiment_id/reference_dataset_id'.format(xlib.get_cluster_reference_dir())))
file_id.write('{0}\n'.format('# The assembly files must be located in the cluster directory {0}/experiment_id/assembly_dataset_id'.format(xlib.get_cluster_result_dir())))
file_id.write('{0}\n'.format('# The experiment_id, reference_dataset_id, reference_file and assembly_dataset_id are fixed in the identification section.'))
file_id.write('{0}\n'.format('#'))
file_id.write('{0}\n'.format('# You can consult the parameters of QUAST and their meaning in http://quast.sourceforge.net/quast.html.'))
file_id.write('{0}\n'.format(''))
file_id.write('{0}\n'.format('# This section has the information identifies the experiment.'))
file_id.write('{0}\n'.format('[identification]'))
file_id.write('{0:<50} {1}\n'.format('experiment_id = {0}'.format(experiment_id), '# experiment identification'))
file_id.write('{0:<50} {1}\n'.format('reference_dataset_id = {0}'.format(reference_dataset_id), '# reference dataset identification or NONE'))
file_id.write('{0:<50} {1}\n'.format('reference_file = {0}'.format(reference_file), '# reference file name or NONE'))
file_id.write('{0:<50} {1}\n'.format('assembly_software = {0}'.format(assembly_software), '# assembly software: {0} ({1}) or {2} ({3}) or {4} ({5}) or {6} ({7}) or {8} ({9}) or {10} ({11})'.format(xlib.get_soapdenovotrans_code(), xlib.get_soapdenovotrans_name(), xlib.get_transabyss_code(), xlib.get_transabyss_name(), xlib.get_trinity_code(), xlib.get_trinity_name(), xlib.get_star_code(), xlib.get_star_name(), xlib.get_cd_hit_est_code(), xlib.get_cd_hit_est_name(), xlib.get_transcript_filter_code(), xlib.get_transcript_filter_name())))
file_id.write('{0:<50} {1}\n'.format('assembly_dataset_id = {0}'.format(assembly_dataset_id), '# assembly dataset identification'))
file_id.write('{0:<50} {1}\n'.format('assembly_type = {0}'.format(assembly_type), '# CONTIGS or SCAFFOLDS in {0}; NONE in {1}, {2}, {3}, {4} and {5}'.format(xlib.get_soapdenovotrans_name(), xlib.get_transabyss_name(), xlib.get_trinity_name(), xlib.get_star_name(), xlib.get_cd_hit_est_name(), xlib.get_transcript_filter_name())))
file_id.write('{0}\n'.format(''))
file_id.write('{0}\n'.format('# This section has the information to set the QUAST parameters'))
file_id.write('{0}\n'.format('[QUAST parameters]'))
file_id.write('{0:<50} {1}\n'.format('threads = 2', '# number of threads for use'))
except:
error_list.append('*** ERROR: The file {0} can not be recreated'.format(get_quast_config_file()))
OK = False
# return the control variable and the error list
return (OK, error_list)
def form_list_cluster_experiment_processes():
'''
List the processes of an experiment in the cluster.
'''
# initialize the control variable
OK = True
# print the header
clib.clear_screen()
clib.print_headers_with_environment('Logs - List experiment processes in the cluster')
# get the cluster name
print(xlib.get_separator())
if xec2.get_running_cluster_list(volume_creator_included=False) != []:
cluster_name = cinputs.input_cluster_name(volume_creator_included=False, help=True)
else:
print('WARNING: There is not any running cluster.')
OK = False
# create the SSH client connection
if OK:
(OK, error_list, ssh_client) = xssh.create_ssh_client_connection(cluster_name, 'master')
for error in error_list:
log.write('{0}\n'.format(error))
# get experiment identification
if OK:
experiment_id = cinputs.input_experiment_id(ssh_client, help=True)
if experiment_id == '':
print('WARNING: The cluster {0} has not experiment data.'.format(cluster_name))
OK = False
# get the result dataset list of the experiment
if OK:
command = 'cd {0}/{1}; for list in `ls`; do ls -ld $list | grep -v ^- > /dev/null && echo $list; done;'.format(xlib.get_cluster_result_dir(), experiment_id)
(OK, stdout, stderr) = xssh.execute_cluster_command(ssh_client, command)
if OK:
result_dataset_id_list = []
for line in stdout:
line = line.rstrip('\n')
if line != 'lost+found':
result_dataset_id_list.append(line)
# print the result dataset identification list of the experiment
if OK:
print(xlib.get_separator())
if result_dataset_id_list == []:
print('*** WARNING: There is not any result dataset of the experiment {0}.'.format(experiment_id))
else:
result_dataset_id_list.sort()
# set data width
result_dataset_width = 25
bioinfo_app_width = 25
# set line template
line_template = '{0:' + str(result_dataset_width) + '} {1:' + str(bioinfo_app_width) + '}'
# print header
print(line_template.format('Result dataset', 'Bioinfo app / Utility'))
print(line_template.format('=' * result_dataset_width, '=' * bioinfo_app_width))
# print detail lines
for result_dataset_id in result_dataset_id_list:
if result_dataset_id.startswith(xlib.get_bedtools_code()+'-'):
bioinfo_app_name = xlib.get_bedtools_name()
elif result_dataset_id.startswith(xlib.get_blastplus_code()+'-'):
bioinfo_app_name = xlib.get_blastplus_name()
elif result_dataset_id.startswith(xlib.get_bowtie2_code()+'-'):
bioinfo_app_name = xlib.get_bowtie2_name()
elif result_dataset_id.startswith(xlib.get_busco_code()+'-'):
bioinfo_app_name = xlib.get_busco_name()
elif result_dataset_id.startswith(xlib.get_cd_hit_code()+'-'):
bioinfo_app_name = xlib.get_cd_hit_est_name()
elif result_dataset_id.startswith(xlib.get_cd_hit_code()+'-'):
bioinfo_app_name = xlib.get_cd_hit_est_name()
elif result_dataset_id.startswith(xlib.get_detonate_code()+'-'):
bioinfo_app_name = xlib.get_detonate_name()
elif result_dataset_id.startswith(xlib.get_emboss_code()+'-'):
bioinfo_app_name = xlib.get_emboss_name()
elif result_dataset_id.startswith(xlib.get_fastqc_code()+'-'):
bioinfo_app_name = xlib.get_fastqc_name()
elif result_dataset_id.startswith(xlib.get_gmap_code()+'-'):
bioinfo_app_name = xlib.get_gmap_name()
elif result_dataset_id.startswith(xlib.get_gmap_gsnap_code()+'-'):
bioinfo_app_name = xlib.get_gmap_gsnap_name()
elif result_dataset_id.startswith(xlib.get_gzip_code()+'-'):
bioinfo_app_name = xlib.get_gzip_name()
elif result_dataset_id.startswith(xlib.get_insilico_read_normalization_code()+'-'):
bioinfo_app_name = xlib.get_insilico_read_normalization_name()
elif result_dataset_id.startswith(xlib.get_miniconda3_code()+'-'):
bioinfo_app_name = xlib.get_miniconda3_name()
elif result_dataset_id.startswith(xlib.get_ngshelper_code()+'-'):
bioinfo_app_name = xlib.get_ngshelper_name()
elif result_dataset_id.startswith(xlib.get_quast_code()+'-'):
bioinfo_app_name = xlib.get_quast_name()
elif result_dataset_id.startswith(xlib.get_r_code()+'-'):
bioinfo_app_name = xlib.get_r_name()
elif result_dataset_id.startswith(xlib.get_ref_eval_code()+'-'):
bioinfo_app_name = xlib.get_ref_eval_name()
elif result_dataset_id.startswith(xlib.get_rnaquast_code()+'-'):
bioinfo_app_name = xlib.get_rnaquast_name()
elif result_dataset_id.startswith(xlib.get_rsem_code()+'-'):
bioinfo_app_name = xlib.get_rsem_name()
elif result_dataset_id.startswith(xlib.get_rsem_eval_code()+'-'):
bioinfo_app_name = xlib.get_rsem_eval_name()
elif result_dataset_id.startswith(xlib.get_samtools_code()+'-'):
bioinfo_app_name = xlib.get_samtools_name()
elif result_dataset_id.startswith(xlib.get_soapdenovotrans_code()+'-'):
bioinfo_app_name = xlib.get_soapdenovotrans_name()
elif result_dataset_id.startswith(xlib.get_star_code()+'-'):
bioinfo_app_name = xlib.get_star_name()
elif result_dataset_id.startswith(xlib.get_transabyss_code()+'-'):
bioinfo_app_name = xlib.get_transabyss_name()
elif result_dataset_id.startswith(xlib.get_transcript_filter_code()+'-'):
bioinfo_app_name = xlib.get_transcript_filter_name()
elif result_dataset_id.startswith(xlib.get_transcriptome_blastx_code()+'-'):
bioinfo_app_name = xlib.get_transcriptome_blastx_name()
elif result_dataset_id.startswith(xlib.get_transrate_code()+'-'):
bioinfo_app_name = xlib.get_transrate_name()
elif result_dataset_id.startswith(xlib.get_trimmomatic_code()+'-'):
bioinfo_app_name = xlib.get_trimmomatic_name()
elif result_dataset_id.startswith(xlib.get_trinity_code()+'-'):
bioinfo_app_name = xlib.get_trinity_name()
else:
bioinfo_app_name = 'xxx'
print(line_template.format(result_dataset_id, bioinfo_app_name))
# close the SSH client connection
if OK:
xssh.close_ssh_client_connection(ssh_client)
# show continuation message
print(xlib.get_separator())
input('Press [Intro] to continue ...')
def create_busco_config_file(experiment_id='exp001', assembly_dataset_id='sdnt-170101-235959', assembly_type='CONTIGS'):
'''
Create BUSCO config file with the default options. It is necessary
update the options in each run.
'''
# initialize the control variable and the error list
OK = True
error_list = []
# set the assembly software
if assembly_dataset_id.startswith(xlib.get_soapdenovotrans_code()):
assembly_software = xlib.get_soapdenovotrans_code()
elif assembly_dataset_id.startswith(xlib.get_transabyss_code()):
assembly_software = xlib.get_transabyss_code()
elif assembly_dataset_id.startswith(xlib.get_trinity_code()):
assembly_software = xlib.get_trinity_code()
elif assembly_dataset_id.startswith(xlib.get_star_code()):
assembly_software = xlib.get_star_code()
elif assembly_dataset_id.startswith(xlib.get_cd_hit_est_code()):
assembly_software = xlib.get_cd_hit_est_code()
elif assembly_dataset_id.startswith(xlib.get_transcript_filter_code()):
assembly_software = xlib.get_transcript_filter_code()
# create the BUSCO config file and write the default options
try:
if not os.path.exists(os.path.dirname(get_busco_config_file())):
os.makedirs(os.path.dirname(get_busco_config_file()))
with open(get_busco_config_file(), mode='w', encoding='utf8') as file_id:
file_id.write('{0}\n'.format('# You must review the information of this file and update the values with the corresponding ones to the current run.'))
file_id.write('{0}\n'.format('#'))
file_id.write('{0}\n'.format('# The reference file must be located in the cluster directory {0}/experiment_id/reference_dataset_id'.format(xlib.get_cluster_reference_dir())))
file_id.write('{0}\n'.format('# The assembly files must be located in the cluster directory {0}/experiment_id/assembly_dataset_id'.format(xlib.get_cluster_result_dir())))
file_id.write('{0}\n'.format('# The experiment_id and assembly_dataset_id names are fixed in the identification section.'))
file_id.write('{0}\n'.format('#'))
file_id.write('{0}\n'.format('# In section "BUSCO parameters", the key "augustus_options" allows you to input additional August parameters in the format:'))
file_id.write('{0}\n'.format('#'))
file_id.write('{0}\n'.format('# augustus_options = --parameter-1[=value-1][; --parameter-2[=value-2][; ...; --parameter-n[=value-n]]]'))
file_id.write('{0}\n'.format('#'))
file_id.write('{0}\n'.format('# parameter-i is a parameter name of Augustus and value-i a valid value of parameter-i, e.g.'))
file_id.write('{0}\n'.format('#'))
file_id.write('{0}\n'.format('# augustus_options = --translation_table=6 --progress=true)'))
file_id.write('{0}\n'.format('#'))
file_id.write('{0}\n'.format('# You can consult the parameters of BUSCO and their meaning in http://busco.ezlab.org/.'))
file_id.write('{0}\n'.format('# and August ones in http://bioinf.uni-greifswald.de/augustus/.'))
file_id.write('{0}\n'.format(''))
file_id.write('{0}\n'.format('# This section has the information identifies the experiment.'))
file_id.write('{0}\n'.format('[identification]'))
file_id.write('{0:<50} {1}\n'.format('experiment_id = {0}'.format(experiment_id), '# experiment identification'))
file_id.write('{0:<50} {1}\n'.format('assembly_software = {0}'.format(assembly_software), '# assembly software: {0} ({1}) or {2} ({3}) or {4} ({5}) or {6} ({7}) or {8} ({9}) or {10} ({11})'.format(xlib.get_soapdenovotrans_code(), xlib.get_soapdenovotrans_name(), xlib.get_transabyss_code(), xlib.get_transabyss_name(), xlib.get_trinity_code(), xlib.get_trinity_name(), xlib.get_star_code(), xlib.get_star_name(), xlib.get_cd_hit_est_code(), xlib.get_cd_hit_est_name(), xlib.get_transcript_filter_code(), xlib.get_transcript_filter_name())))
file_id.write('{0:<50} {1}\n'.format('assembly_dataset_id = {0}'.format(assembly_dataset_id), '# assembly dataset identification'))
file_id.write('{0:<50} {1}\n'.format('assembly_type = {0}'.format(assembly_type), '# CONTIGS or SCAFFOLDS in {0}; NONE in {1}, {2}, {3}, {4} and {5}'.format(xlib.get_soapdenovotrans_name(), xlib.get_transabyss_name(), xlib.get_trinity_name(), xlib.get_star_name(), xlib.get_cd_hit_est_name(), xlib.get_transcript_filter_name())))
file_id.write('{0}\n'.format(''))
file_id.write('{0}\n'.format('# This section has the information to set the BUSCO parameters'))
file_id.write('{0}\n'.format('[BUSCO parameters]'))
file_id.write('{0:<50} {1}\n'.format('ncpu = 2', '# number of threads/cores for use'))
file_id.write('{0:<50} {1}\n'.format('lineage_data = embryophyta_odb9', '# value to find the lineage data url in BUSCO web (e.g. embryophyta -> http://busco.ezlab.org/v2/datasets/embryophyta_odb9.tar.gz)'))
file_id.write('{0:<50} {1}\n'.format('mode = tran', '# geno (genome assemblies, DNA) or tran (transcriptome assemblies, DNA) or prot (annotated gene sets, proteins)'))
file_id.write('{0:<50} {1}\n'.format('evalue = 1e-03', '# E-value cutoff for BLAST searches'))
file_id.write('{0:<50} {1}\n'.format('limit = 3', '# number of candidate regions to consider'))
file_id.write('{0:<50} {1}\n'.format('species = NONE', '# identifier of existing Augustus species gene finding parameters or NONE'))
file_id.write('{0:<50} {1}\n'.format('long = NO', '# Augustus optimization mode for self-training: YES or NO'))
file_id.write('{0:<50} {1}\n'.format('augustus_options = NONE', '# additional parameters to August or NONE'))
except:
error_list.append('*** ERROR: The file {0} can not be recreated'.format(get_busco_config_file()))
OK = False
# return the control variable and the error list
return (OK, error_list)
def validate_busco_config_file(strict):
'''
Validate the BUSCO config file of a run.
'''
# initialize the control variable and the error list
OK = True
error_list = []
# intitialize variable used when value is not found
not_found = '***NOTFOUND***'.upper()
# get the option dictionary
try:
busco_option_dict = xlib.get_option_dict(get_busco_config_file())
except:
error_list.append('*** ERROR: The syntax is WRONG.')
OK = False
else:
# get the sections list
sections_list = []
for section in busco_option_dict.keys():
sections_list.append(section)
sections_list.sort()
# check section "identification"
if 'identification' not in sections_list:
error_list.append('*** ERROR: the section "identification" is not found.')
OK = False
else:
# check section "identification" - key "experiment_id"
experiment_id = busco_option_dict.get('identification', {}).get('experiment_id', not_found)
is_experiment_id_OK = True
if experiment_id == not_found:
error_list.append('*** ERROR: the key "experiment_id" is not found in the section "identification".')
is_experiment_id_OK = False
OK = False
# check section "identification" - key "assembly_software"
assembly_software = busco_option_dict.get('identification', {}).get('assembly_software', not_found)
is_assembly_software_OK = True
if assembly_software == not_found:
error_list.append('*** ERROR: the key "assembly_software" is not found in the section "identification".')
is_assembly_software_OK = False
OK = False
elif assembly_software not in [xlib.get_soapdenovotrans_code(), xlib.get_transabyss_code(), xlib.get_trinity_code(), xlib.get_star_code(), xlib.get_cd_hit_est_code(), xlib.get_transcript_filter_code()]:
error_list.append('*** ERROR: the key "assembly_software" value in the section "identification" must be {0} or {1} or {2} or {3} or {4} OR {5}.'.format(xlib.get_soapdenovotrans_code(), xlib.get_transabyss_code(), xlib.get_trinity_code(), xlib.get_star_code(), xlib.get_cd_hit_est_code(), xlib.get_transcript_filter_code()))
is_assembly_software_OK = False
OK = False
# check section "identification" - key "assembly_dataset_id"
assembly_dataset_id = busco_option_dict.get('identification', {}).get('assembly_dataset_id', not_found)
is_assembly_dataset_id_OK = True
if assembly_dataset_id == not_found:
error_list.append('*** ERROR: the key "assembly_dataset_id" is not found in the section "identification".')
is_assembly_dataset_id_OK = False
OK = False
elif not assembly_dataset_id.startswith(xlib.get_soapdenovotrans_code()) and not assembly_dataset_id.startswith(xlib.get_transabyss_code()) and not assembly_dataset_id.startswith(xlib.get_trinity_code()) and not assembly_dataset_id.startswith(xlib.get_star_code()) and not assembly_dataset_id.startswith(xlib.get_cd_hit_est_code()) and not assembly_dataset_id.startswith(xlib.get_transcript_filter_code()):
error_list.append('*** ERROR: the key "assembly_dataset_id" value is not a {0} nor {1} nor {2} nor {3} nor {4} nor {5} assembly.'.format(xlib.get_soapdenovotrans_name(), xlib.get_transabyss_name(), xlib.get_trinity_name(), xlib.get_star_name(), xlib.get_cd_hit_est_name(), xlib.get_transcript_filter_code()))
is_assembly_dataset_id_OK = False
OK = False
# check section "identification" - key "assembly_type"
assembly_type = busco_option_dict.get('identification', {}).get('assembly_type', not_found)
is_assembly_type_OK = True
if assembly_type == not_found:
error_list.append('*** ERROR: the key "assembly_type" is not found in the section "identification".')
is_assembly_type_OK = False
OK = False
elif assembly_dataset_id.startswith(xlib.get_soapdenovotrans_code()):
if assembly_type.upper() not in ['CONTIGS', 'SCAFFOLDS']:
error_list.append('*** ERROR: the key "assembly_type" must be "CONTIGS" or "SCAFFOLDS" when {0} is the assembly software.'.format(xlib.get_soapdenovotrans_name()))
is_assembly_type_OK = False
OK = False
elif assembly_dataset_id.startswith(xlib.get_transabyss_code()) or assembly_dataset_id.startswith(xlib.get_trinity_code()) or assembly_dataset_id.startswith(xlib.get_star_code()) or assembly_dataset_id.startswith(xlib.get_cd_hit_est_code()) or assembly_dataset_id.startswith(xlib.get_transcript_filter_code()):
if assembly_type.upper() != 'NONE':
error_list.append('*** ERROR: the key "assembly_type" must be "NONE" when {0} or {1} or {2} or {3} or {4} is the assembly software.'.format(xlib.get_transabyss_name(), xlib.get_trinity_name(), xlib.get_star_name(), xlib.get_cd_hit_est_name(), xlib.get_transcript_filter_name()))
is_assembly_type_OK = False
OK = False
# check section "BUSCO parameters"
if 'BUSCO parameters' not in sections_list:
error_list.append('*** ERROR: the section "BUSCO parameters" is not found.')
OK = False
else:
# check section "BUSCO parameters" - key "ncpu"
ncpu = busco_option_dict.get('BUSCO parameters', {}).get('ncpu', not_found)
is_ncpu_OK = True
if ncpu == not_found:
error_list.append('*** ERROR: the key "ncpu" is not found in the section "BUSCO parameters".')
is_ncpu_OK = False
OK = False
else:
try:
if int(ncpu) < 1:
error_list.append('*** ERROR: the key "ncpu" in the section "BUSCO parameters" must be an integer value greater or equal to 1.')
is_ncpu_OK = False
OK = False
except:
error_list.append('*** ERROR: the key "ncpu" in the section "BUSCO parameters" must be an integer value greater or equal to 1.')
is_ncpu_OK = False
OK = False
# check section "BUSCO parameters" - key "lineage_data"
lineage_data = busco_option_dict.get('BUSCO parameters', {}).get('lineage_data', not_found)
is_lineage_data_OK = True
if lineage_data == not_found:
error_list.append('*** ERROR: the key "lineage_data" is not found in the section "BUSCO parameters"')
is_lineage_data_OK = False
OK = False
# check section "BUSCO parameters" - key "mode"
mode = busco_option_dict.get('BUSCO parameters', {}).get('mode', not_found).lower()
is_mode_OK = True
if mode == not_found:
error_list.append('*** ERROR: the key "mode" is not found in the section "BUSCO parameters".')
is_mode_OK = False
OK = False
elif mode not in ['geno', 'tran', 'prot']:
error_list.append('*** ERROR: the key "mode" value in the section "BUSCO parameters" must be geno or tran or prot.')
is_mode_OK = False
OK = False
# check section "BUSCO parameters" - key "evalue"
evalue = busco_option_dict.get('BUSCO parameters', {}).get('evalue', not_found)
is_evalue_OK = True
if evalue == not_found:
error_list.append('*** ERROR: the key "evalue" is not found in the section "BUSCO parameters".')
is_evalue_OK = False
OK = False
else:
try:
if float(evalue) <= 0:
error_list.append('*** ERROR: the key "evalue" in the section "BUSCO parameters" must be a float value greater than 0.')
is_evalue_OK = False
OK = False
except:
error_list.append('*** ERROR: the key "evalue" in the section "BUSCO parameters" must be a float value greater than 0.')
is_evalue_OK = False
OK = False
# check section "BUSCO parameters" - key "limit"
limit = busco_option_dict.get('BUSCO parameters', {}).get('limit', not_found)
is_limit_OK = True
if limit == not_found:
error_list.append('*** ERROR: the key "limit" is not found in the section "BUSCO parameters".')
OK = False
else:
try:
if int(limit) < 1:
error_list.append('*** ERROR: the key "limit" in the section "BUSCO parameters" must be an integer value greater or equal to 1.')
is_limit_OK = False
OK = False
except:
error_list.append('*** ERROR: the key "limit" in the section "BUSCO parameters" must be an integer value greater or equal to 1.')
is_limit_OK = False
OK = False
# check section "BUSCO parameters" - key "species"
species = busco_option_dict.get('BUSCO parameters', {}).get('species', not_found)
is_species_OK = True
if species == not_found:
error_list.append('*** ERROR: the key "species" is not found in the section "BUSCO parameters"')
is_species_OK = False
OK = False
# check section "BUSCO parameters" - key "long"
long = busco_option_dict.get('BUSCO parameters', {}).get('long', not_found).upper()
is_long_OK = True
if long == not_found:
error_list.append('*** ERROR: the key "long" is not found in the section "BUSCO parameters".')
is_long_OK = False
OK = False
elif long not in ['YES', 'NO']:
error_list.append('*** ERROR: the key "long" value in the section "BUSCO parameters" must be YES or NO.')
is_long_OK = False
OK = False
# check section "BUSCO parameters" - key "augustus_options"
augustus_options = busco_option_dict.get('BUSCO parameters', {}).get('augustus_options', not_found)
is_augustus_options_OK = True
if augustus_options == not_found:
error_list.append('*** ERROR: the key "augustus_options" is not found in the section "BUSCO parameters".')
is_augustus_options_OK = False
OK = False
else:
if augustus_options.upper() != 'NONE':
parameter_list = [x.strip() for x in augustus_options.split(';')]
for parameter in parameter_list:
try:
if parameter.find('=') > 0:
pattern = r'^--(.+)=(.+)$'
mo = re.search(pattern, parameter)
parameter_name = mo.group(1).strip()
parameter_value = mo.group(2).strip()
else:
pattern = r'^--(.+)$'
mo = re.search(pattern, parameter)
parameter_name = mo.group(1).strip()
except:
error_list.append('*** ERROR: the value of the key "augustus_options" in the section "BUSCO parameters" must be NONE or a valid August parameter list.')
is_augustus_options_OK = False
OK = False
break
# warn that the results config file is not valid if there are any errors
if not OK:
error_list.append('\nThe {0} config file is not valid. Please, correct this file or recreate it.'.format(xlib.get_busco_name()))
# 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_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 ...')