def input_float(text,
default=None,
minimum=float(-sys.maxsize - 1),
maximum=float(sys.maxsize),
mne=0.0,
mxe=0.0):
'''
Input a float number.
'''
# initialize the number
literal = None
# input and check the float number
while literal is None:
if default is None:
literal = input(f'{text}: ')
else:
literal = input(f'{text} [{default}]: ')
if literal == '': literal = default
if not xlib.check_float(literal, minimum, maximum, mne, mxe):
print(f'*** ERROR: {literal} is not a valid value.')
literal = None
# return the float value
return float(literal)
def check_args(args):
'''
Verity the input arguments data.
'''
# initialize the control variable
OK = True
# check the assembly_software_code value
if args.assembly_software_code is None:
xlib.Message.print(
'error',
'*** The assembly software that generated the transcritpme file is not indicated in the input arguments.'
)
OK = False
elif args.assembly_software_code not in [
xlib.Const.AS_TRINITY_CODE, xlib.Const.AS_SOAPDENOVOTRANS_CODE,
xlib.Const.AS_GENERATED_BY_NGSCLOUD
]:
xlib.Message.print(
'error',
f'*** {args.assembly_software_code} is not a valid code of assembly software.'
)
OK = False
# check the transcriptome_file value
if args.transcriptome_file is None:
xlib.Message.print(
'error',
'*** A transcritpme file in Fasta format is not indicated in the input arguments.'
)
OK = False
elif not os.path.isfile(args.transcriptome_file):
xlib.Message.print(
'error', f'*** The file {args.transcriptome_file} does not exist.')
OK = False
# check the score_file value
if args.score_file is None:
xlib.Message.print(
'error',
'*** A score file where RSEM-EVAL (DETONATE package) saved the score of the transcriptome file is not indicated in the input arguments.'
)
OK = False
elif not os.path.isfile(args.score_file):
xlib.Message.print('error',
f'*** The file {args.score_file} does not exist.')
OK = False
# check the output_file value
if args.output_file is None:
xlib.Message.print(
'error',
'*** A output file where filtered transcripts will be saved is not indicated in the input arguments.'
)
OK = False
else:
try:
if not os.path.exists(os.path.dirname(args.output_file)):
os.makedirs(os.path.dirname(args.output_file))
except Exception as e:
xlib.Message.print(
'error',
f'*** The directory {os.path.dirname(args.output_file)} of the file {args.output_file} is not valid.'
)
OK = False
# check the minlen value
if args.minlen is None:
args.minlen = xlib.Const.DEFAULT_MINLEN
elif not xlib.check_int(args.minlen, minimum=1):
xlib.Message.print(
'error',
'*** The minlen has to be a integer number greater than 0.')
OK = False
else:
args.minlen = int(args.minlen)
# check the maxlen value
if args.maxlen is None:
args.maxlen = xlib.Const.DEFAULT_MAXLEN
elif not xlib.check_int(args.maxlen, minimum=1):
xlib.Message.print(
'error',
'*** The maxlen has to be a integer number greater than 0.')
OK = False
else:
args.maxlen = int(args.maxlen)
# check the minFPKM value
if args.minFPKM is None:
args.minFPKM = xlib.Const.DEFAULT_MINFPKM
elif not xlib.check_float(args.minFPKM, minimum=0.0):
print(
'*** FPKM has to be a float number greater than or equal to 0.0.')
OK = False
else:
args.minFPKM = float(args.minFPKM)
# check the minTPM value
if args.minTPM is None:
args.minTPM = xlib.Const.DEFAULT_MINTPM
elif not xlib.check_float(args.minTPM, minimum=0.0):
print(
'*** FPKM has to be a float number greater than or equal to 0.0.')
OK = False
else:
args.minTPM = float(args.minTPM)
# check "verbose"
if args.verbose is None:
args.verbose = xlib.Const.DEFAULT_VERBOSE
elif not xlib.check_code(
args.verbose, xlib.get_verbose_code_list(), case_sensitive=False):
xlib.Message.print(
'error',
f'*** verbose has to be {xlib.get_verbose_code_list_text()}.')
OK = False
if args.verbose.upper() == 'Y':
xlib.Message.set_verbose_status(True)
# check "trace"
if args.trace is None:
args.trace = xlib.Const.DEFAULT_TRACE
elif not xlib.check_code(
args.trace, xlib.get_trace_code_list(), case_sensitive=False):
xlib.Message.print(
'error', f'*** trace has to be {xlib.get_trace_code_list_text()}.')
OK = False
if args.trace.upper() == 'Y':
xlib.Message.set_trace_status(True)
# check if maxlen value is greater or equal than minlen value
if OK:
if args.maxlen < args.minlen:
xlib.Message.print(
'error',
'*** The maxlen value has to be greater than or equal to minlen.'
)
OK = False
# if there are errors, exit with exception
if not OK:
raise xlib.ProgramException('', 'P001')
def check_busco_config_file(strict):
'''
Check 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 Exception as e:
error_list.append(f'*** EXCEPTION: "{e}".')
error_list.append(
'*** ERROR: The option dictionary could not be built from the config file'
)
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)
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 = busco_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 not xlib.check_code(assembly_software,
get_assembly_software_code_list(),
case_sensitive=False):
error_list.append(
f'*** ERROR: the key "assembly_software" has to be {get_assembly_software_code_list_text()}.'
)
OK = False
# check section "identification" - key "assembly_dataset_id"
assembly_dataset_id = busco_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 xlib.check_startswith(assembly_dataset_id,
get_assembly_software_code_list(),
case_sensitive=True):
error_list.append(
f'*** ERROR: the key "assembly_dataset_id" has to start with {get_assembly_software_code_list_text()}.'
)
OK = False
# check section "identification" - key "assembly_type"
assembly_type = busco_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()) and assembly_type.upper() not in ['CONTIGS', 'SCAFFOLDS'] or \
not assembly_dataset_id.startswith(xlib.get_soapdenovotrans_code()) and assembly_type.upper() != 'NONE':
error_list.append(
f'*** ERROR: the key "assembly_type" has to be CONTIGS or SCAFFOLDS in {xlib.get_soapdenovotrans_name()} or NONE in any other case.'
)
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)
if ncpu == not_found:
error_list.append(
'*** ERROR: the key "ncpu" is not found in the section "BUSCO parameters".'
)
OK = False
elif not xlib.check_int(ncpu, minimum=1):
error_list.append(
'*** ERROR: the key "ncpu" has to be an integer number greater than or equal to 1.'
)
OK = False
# check section "BUSCO parameters" - key "lineage_data_url"
lineage_data_url = busco_option_dict.get(
'BUSCO parameters', {}).get('lineage_data_url', not_found)
if lineage_data_url == not_found:
error_list.append(
'*** ERROR: the key "lineage_data_url" is not found in the section "BUSCO parameters"'
)
OK = False
else:
try:
urllib.request.urlopen(lineage_data_url)
except Exception as e:
error_list.append(f'*** EXCEPTION: "{e}".')
error_list.append(
'*** ERROR: the key "lineage_data_url" has to be a reachable address.'
)
OK = False
# check section "BUSCO parameters" - key "mode"
mode = busco_option_dict.get('BUSCO parameters',
{}).get('mode', not_found)
if mode == not_found:
error_list.append(
'*** ERROR: the key "mode" is not found in the section "BUSCO parameters".'
)
OK = False
elif not xlib.check_code(
mode, get_mode_code_list(), case_sensitive=False):
error_list.append(
f'*** ERROR: the key "mode" has to be {get_mode_code_list_text()}.'
)
OK = False
# check section "BUSCO parameters" - key "evalue"
evalue = busco_option_dict.get('BUSCO parameters',
{}).get('evalue', not_found)
if evalue == not_found:
error_list.append(
'*** ERROR: the key "evalue" is not found in the section "BUSCO parameters".'
)
OK = False
elif not xlib.check_float(evalue, minimum=0., mne=1E-12):
error_list.append(
'*** ERROR: the key "evalue" has to be a float number greater than 0.'
)
OK = False
# check section "BUSCO parameters" - key "limit"
limit = busco_option_dict.get('BUSCO parameters',
{}).get('limit', not_found)
if limit == not_found:
error_list.append(
'*** ERROR: the key "limit" is not found in the section "BUSCO parameters".'
)
OK = False
elif not xlib.check_int(limit, minimum=1):
error_list.append(
'*** ERROR: the key "limit" has to be an integer number greater than or equal to 1.'
)
OK = False
# check section "BUSCO parameters" - key "species"
species = busco_option_dict.get('BUSCO parameters',
{}).get('species', not_found)
if species == not_found:
error_list.append(
'*** ERROR: the key "species" is not found in the section "BUSCO parameters"'
)
OK = False
# check section "BUSCO parameters" - key "long"
long = busco_option_dict.get('BUSCO parameters',
{}).get('long', not_found)
if long == not_found:
error_list.append(
'*** ERROR: the key "long" is not found in the section "BUSCO parameters".'
)
OK = False
elif not xlib.check_code(
long, get_long_code_list(), case_sensitive=False):
error_list.append(
f'*** ERROR: the key "long" has to be {get_long_code_list_text()}.'
)
OK = False
# check section "BUSCO parameters" - key "augustus_options"
augustus_options = busco_option_dict.get(
'BUSCO parameters', {}).get('augustus_options', not_found)
if augustus_options == not_found:
error_list.append(
'*** ERROR: the key "augustus_options" is not found in the section "BUSCO parameters".'
)
OK = False
elif augustus_options.upper() != 'NONE':
(OK, error_list2) = xlib.check_parameter_list(
augustus_options, "augustus_options", [])
error_list = error_list + error_list2
# warn that the results config file is not valid if there are any errors
if not OK:
error_list.append(
f'\nThe {xlib.get_busco_name()} config file is not valid. Please, correct this file or recreate it.'
)
# return the control variable and the error list
return (OK, error_list)
def check_args(args):
'''
Verity the input arguments.
'''
# initialize the control variable
OK = True
# check "fasta_file"
if args.fasta_file is None:
xlib.Message.print(
'error',
'*** The input FASTA file is not indicated in the input arguments.'
)
OK = False
elif not os.path.isfile(args.fasta_file):
xlib.Message.print('error',
f'*** The file {args.fasta_file} does not exist.')
OK = False
# check "output_file"
if args.output_file is None:
xlib.Message.print(
'error',
'*** The FASTA file with debased sequences is not indicated in the input arguments.'
)
OK = False
# check "fragmentation_probability"
if args.fragmentation_probability is None:
xlib.Message.print(
'error',
'*** The fragmentation probability is not indicated in the input arguments.'
)
OK = False
elif not xlib.check_float(args.fragmentation_probability,
minimum=xlib.Const.FRAGPROB_LOWEST,
maximum=xlib.Const.FRAGPROB_UPPEST):
xlib.Message.print(
'error',
f'The fragmentation probability has to be a float number between {xlib.Const.FRAGPROB_LOWEST} and {xlib.Const.FRAGPROB_UPPEST}.'
)
OK = False
else:
args.fragmentation_probability = float(args.fragmentation_probability)
# check "max_fragment_number"
if args.max_fragment_number is None:
xlib.Message.print(
'error',
'*** The maximum fragment number is not indicated in the input arguments.'
)
OK = False
elif not xlib.check_int(args.max_fragment_number,
minimum=xlib.Const.MAXFRAGNUM_LOWEST,
maximum=xlib.Const.MAXFRAGNUM_UPPEST):
xlib.Message.print(
'error',
f'The maximum fragment number has to be a integer number between {xlib.Const.MAXFRAGNUM_LOWEST} and {xlib.Const.MAXFRAGNUM_UPPEST}.'
)
OK = False
else:
args.max_fragment_number = int(args.max_fragment_number)
# check "max_end_shortening"
if args.max_end_shortening is None:
xlib.Message.print(
'error',
'*** The maximum shortening of a fragment end is not indicated in the input arguments.'
)
OK = False
elif not xlib.check_int(args.max_end_shortening,
minimum=xlib.Const.MAXSHORTENING_LOWEST,
maximum=xlib.Const.MAXSHORTENING_UPPEST):
xlib.Message.print(
'error',
f'The maximum shortening of a fragment end has to be a integer number between {xlib.Const.MAXSHORTENING_LOWEST} and {xlib.Const.MAXSHORTENING_UPPEST}.'
)
OK = False
else:
args.max_end_shortening = int(args.max_end_shortening)
# check "min_fragment_length"
if args.min_fragment_length is None:
xlib.Message.print(
'error',
'*** The minimum fragment length is not indicated in the input arguments.'
)
OK = False
elif not xlib.check_int(args.min_fragment_length, minimum=1):
xlib.Message.print(
'error',
'The minimum fragment length has to be a integer number greater than 0.'
)
OK = False
else:
args.min_fragment_length = int(args.min_fragment_length)
# check "mutation_probability"
if args.mutation_probability is None:
xlib.Message.print(
'error',
'*** The mutation probability is not indicated in the input arguments.'
)
OK = False
elif not xlib.check_float(args.mutation_probability,
minimum=xlib.Const.MUTPROB_LOWEST,
maximum=xlib.Const.MUTPROB_UPPEST):
xlib.Message.print(
'error',
f'The mutation probability has to be a float number between {xlib.Const.MUTPROB_LOWEST} and {xlib.Const.MUTPROB_UPPEST}'
)
OK = False
else:
args.mutation_probability = float(args.mutation_probability)
# check "max_mutation_number"
if args.max_mutation_number is None:
xlib.Message.print(
'error',
'*** The maximum mutation number is not indicated in the input arguments.'
)
OK = False
elif not xlib.check_int(args.max_mutation_number,
minimum=xlib.Const.MAXMUTNUM_LOWEST,
maximum=xlib.Const.MAXMUTNUM_UPPEST):
xlib.Message.print(
'error',
f'The maximum mutation number has to be a integer number between {xlib.Const.MAXMUTNUM_LOWEST} and {xlib.Const.MAXMUTNUM_UPPEST}.'
)
OK = False
else:
args.max_mutation_number = int(args.max_mutation_number)
# check "indel_probability"
if args.indel_probability is None:
xlib.Message.print(
'error',
'*** The insertion/deletion probability is not indicated in the input arguments.'
)
OK = False
elif not xlib.check_float(args.indel_probability,
minimum=xlib.Const.INDELPROB_LOWEST,
maximum=xlib.Const.INDELPROB_UPPEST):
xlib.Message.print(
'error',
f'The insertion/deletion probability has to be a float number between {xlib.Const.INDELPROB_LOWEST} and {xlib.Const.INDELPROB_UPPEST}.'
)
OK = False
else:
args.indel_probability = float(args.indel_probability)
# check "max_mutation_size"
if args.max_mutation_size is None:
xlib.Message.print(
'error',
'*** The maximum mutation size size is not indicated in the input arguments.'
)
OK = False
elif not xlib.check_int(args.max_mutation_size,
minimum=xlib.Const.MAXMUTSIZE_LOWEST,
maximum=xlib.Const.MAXMUTSIZE_UPPEST):
xlib.Message.print(
'error',
f'The maximum mutation size size has to be a integer number between {xlib.Const.MAXMUTSIZE_LOWEST} and {xlib.Const.MAXMUTSIZE_UPPEST}.'
)
OK = False
else:
args.max_mutation_size = int(args.max_mutation_size)
# check "verbose"
if args.verbose is None:
args.verbose = xlib.Const.DEFAULT_VERBOSE
elif args.verbose.upper() not in get_verbose_code_list():
xlib.Message.print(
'error', f'The verbose has to be {get_verbose_code_list_text()}.')
OK = False
if args.verbose.upper() == 'Y':
xlib.Message.set_verbose_status(True)
# check "trace"
if args.trace is None:
args.trace = xlib.Const.DEFAULT_TRACE
elif args.trace.upper() not in get_trace_code_list():
xlib.Message.print(
'error', f'The trace has to be {get_trace_code_list_text()}.')
OK = False
if args.trace.upper() == 'Y':
xlib.Message.set_trace_status(True)
# if there are errors, exit with exception
if not OK:
raise xlib.ProgramException('', 'P001')
def check_cd_hit_est_config_file(strict):
'''
check 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 Exception as e:
error_list.append(f'*** EXCEPTION: "{e}".')
error_list.append(
'*** ERROR: The option dictionary could not be built from the config file'
)
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 not xlib.check_code(assembly_software,
get_assembly_software_code_list(),
case_sensitive=False):
error_list.append(
f'*** ERROR: the key "assembly_software" has to be {get_assembly_software_code_list_text()}.'
)
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 xlib.check_startswith(assembly_dataset_id,
get_assembly_software_code_list(),
case_sensitive=True):
error_list.append(
f'*** ERROR: the key "assembly_dataset_id" has to start with {get_assembly_software_code_list_text()}.'
)
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()) and assembly_type.upper() not in ['CONTIGS', 'SCAFFOLDS'] or \
not assembly_dataset_id.startswith(xlib.get_soapdenovotrans_code()) and assembly_type.upper() != 'NONE':
error_list.append(
f'*** ERROR: the key "assembly_type" has to be CONTIGS or SCAFFOLDS in {xlib.get_soapdenovotrans_name()} or NONE in any other case.'
)
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
elif not xlib.check_int(threads, minimum=0):
error_list.append(
'*** ERROR: the key "threads" has to be an integer number greater than 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
elif not xlib.check_int(memory_limit, minimum=0):
error_list.append(
'*** ERROR: the key "memory_limit" has to be an integer number greater than 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
elif not xlib.check_float(
seq_identity_threshold, minimum=0., maximum=1.):
error_list.append(
'*** ERROR: the key "seq_identity_threshold" has to be a float number 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
elif not xlib.check_int(word_length, minimum=1):
error_list.append(
'*** ERROR: the key "word_length" has to be an integer number greater than 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)
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
elif not xlib.check_int(match):
error_list.append(
'*** ERROR: the key "match" has to be an integer number.')
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
elif not xlib.check_int(mismatch):
error_list.append(
'*** ERROR: the key "mismatch" has to be an integer number.'
)
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
elif other_parameters.upper() != 'NONE':
(OK, error_list2) = xlib.check_parameter_list(
other_parameters, "other_parameters",
not_allowed_parameters_list)
error_list = error_list + error_list2
# warn that the results config file is not valid if there are any errors
if not OK:
error_list.append(
f'\nThe {xlib.get_cd_hit_est_name()} config file is not valid. Please, correct this file or recreate it.'
)
# return the control variable and the error list
return (OK, error_list)
def check_args(args):
'''
Check the input arguments.
'''
# initialize the control variable
OK = True
# check "input_vcf_file"
if args.input_vcf_file is None:
xlib.Message.print(
'error',
'*** The VCF file is not indicated in the input arguments.')
OK = False
elif not os.path.isfile(args.input_vcf_file):
xlib.Message.print(
'error', f'*** The file {args.input_vcf_file} does not exist.')
OK = False
# check "sample_file"
if args.sample_file is None:
xlib.Message.print(
'error',
'*** The sample file is not indicated in the input arguments.')
OK = False
elif not os.path.isfile(args.sample_file):
xlib.Message.print('error',
f'*** The file {args.sample_file} does not exist.')
OK = False
# check "fix"
if args.fix is None:
xlib.Message.print('error',
'*** Fix is not indicated in the input arguments.')
OK = False
elif not xlib.check_code(
args.fix, xlib.get_fix_code_list(), case_sensitive=False):
xlib.Message.print(
'error', f'*** fix has to be {xlib.get_fix_code_list_text()}.')
OK = False
else:
args.fix = args.fix.upper()
# check "scenario"
if args.scenario is None:
xlib.Message.print(
'error',
'*** The scenario is not indicated in the input arguments.')
OK = False
elif not xlib.check_code(args.scenario,
xlib.get_scenario_code_list(),
case_sensitive=False):
xlib.Message.print(
'error',
f'*** The scenario has to be {xlib.get_scenario_code_list_text()}.'
)
OK = False
# check "min_aa_percentage"
if args.min_aa_percentage is None:
xlib.Message.print(
'error',
'*** The minimum percent of alternative alleles per species is not indicated in the input arguments.'
)
OK = False
elif not xlib.check_float(
args.min_aa_percentage, minimum=0.0, maximum=100.0):
xlib.Message.print(
'error',
'The minimum percent of alternative alleles per species has to be a float number between 0.0 and 100.0.'
)
OK = False
else:
args.min_aa_percentage = float(args.min_aa_percentage)
# check "min_md_imputation_percentage"
if args.min_md_imputation_percentage is None:
xlib.Message.print(
'error',
'*** The minimum percentage of missing data imputation to a new alternative allele per species is not indicated in the input arguments.'
)
OK = False
elif not xlib.check_float(
args.min_md_imputation_percentage, minimum=0.0, maximum=100.0):
xlib.Message.print(
'error',
'The minimum percentage of missing data imputation to a new alternative allele per species has to be a float number between 0.0 and 100.0.'
)
OK = False
else:
args.min_md_imputation_percentage = float(
args.min_md_imputation_percentage)
# check "imputed_md_id"
if args.imputed_md_id is None:
args.imputed_md_id = xlib.Const.DEFAULT_IMPUTED_MD_ID
# check "sp1_id"
if args.sp1_id is None:
xlib.Message.print(
'error',
'*** The identification of the first species is not indicated in the input arguments.'
)
OK = False
# check "sp1_max_md_percentage"
if args.sp1_max_md_percentage is None:
xlib.Message.print(
'error',
'*** The maximum percentage of missing data of the first species is not indicated in the input arguments.'
)
OK = False
elif not xlib.check_float(
args.sp1_max_md_percentage, minimum=0.0, maximum=100.0):
xlib.Message.print(
'error',
'The maximum percentage of missing data of the first species has to be a float number between 0.0 and 100.0.'
)
OK = False
else:
args.sp1_max_md_percentage = float(args.sp1_max_md_percentage)
# check "sp2_id"
if args.sp2_id is None:
xlib.Message.print(
'error',
'*** The identification of the second species is not indicated in the input arguments.'
)
OK = False
# check "sp2_max_md_percentage"
if args.sp2_max_md_percentage is None:
xlib.Message.print(
'error',
'*** The maximum percentage of missing data of the second species is not indicated in the input arguments.'
)
OK = False
elif not xlib.check_float(
args.sp2_max_md_percentage, minimum=0.0, maximum=100.0):
xlib.Message.print(
'error',
'The maximum percentage of missing data of the second species has to be a float number between 0.0 and 100.0.'
)
OK = False
else:
args.sp2_max_md_percentage = float(args.sp2_max_md_percentage)
# check "hybrid_id"
if args.hybrid_id is None:
args.hybrid_id = 'NONE'
# check "min_afr_percentage"
if args.min_afr_percentage is None:
xlib.Message.print(
'error',
'*** The minimum percentage of allele frequency per species is not indicated in the input arguments.'
)
OK = False
elif not xlib.check_float(
args.min_afr_percentage, minimum=0.0, maximum=100.0):
xlib.Message.print(
'error',
'The minimum percentage of allele frequency per species has to be a float number between 0.0 and 100.0.'
)
OK = False
else:
args.min_afr_percentage = float(args.min_afr_percentage)
# check "min_depth"
if args.min_depth is None:
args.min_depth = xlib.Const.DEFAULT_MIN_DEPTH
elif not xlib.check_int(args.min_depth, minimum=1):
xlib.Message.print(
'error',
'The minimum combined depth across samples has to be an integer number greater than or equal to 1.'
)
OK = False
else:
args.min_depth = int(args.min_depth)
# check "output_vcf_file"
if args.output_vcf_file is None:
xlib.Message.print(
'error',
'*** The output VCF file is not indicated in the input arguments.')
OK = False
# check "verbose"
if args.verbose is None:
args.verbose = xlib.Const.DEFAULT_VERBOSE
elif not xlib.check_code(
args.verbose, xlib.get_verbose_code_list(), case_sensitive=False):
xlib.Message.print(
'error',
f'*** verbose has to be {xlib.get_verbose_code_list_text()}.')
OK = False
if args.verbose.upper() == 'Y':
xlib.Message.set_verbose_status(True)
# check "trace"
if args.trace is None:
args.trace = xlib.Const.DEFAULT_TRACE
elif not xlib.check_code(
args.trace, xlib.get_trace_code_list(), case_sensitive=False):
xlib.Message.print(
'error', f'*** trace has to be {xlib.get_trace_code_list_text()}.')
OK = False
if args.trace.upper() == 'Y':
xlib.Message.set_trace_status(True)
# check "tvi_list"
if args.tvi_list is None or args.tvi_list == 'NONE':
args.tvi_list = []
else:
args.tvi_list = xlib.split_literal_to_string_list(args.tvi_list)
# check the identification set
if OK:
if args.sp1_id == args.sp2_id or \
args.hybrid_id is not None and (args.sp1_id == args.hybrid_id or args.sp2_id == args.hybrid_id):
xlib.Message.print('error',
'The identifications must be different.')
OK = False
# if there are errors, exit with exception
if not OK:
raise xlib.ProgramException('', 'P001')