def test_unused_protocol_fixer(self):
i_table_path = os.path.join(self._tmp_dir, 'BII-S-3', 'i_gilbert.txt')
fixer = utils.IsaTabFixer(i_table_path)
fixer.remove_unused_protocols()
with open('{}.fix'.format(i_table_path)) as fixed_i_fp:
investigation = isatab.load(fixed_i_fp)
study = investigation.studies[-1]
unused_protocol1 = \
study.get_prot('reverse transcription - standard procedure 5')
unused_protocol2 = \
study.get_prot('sequence analysis - standard procedure 7')
self.assertIsNone(unused_protocol1)
self.assertIsNone(unused_protocol2)
def test_replace_factor_with_source_characteristic(self):
fixer = utils.IsaTabFixer(os.path.join(self._tmp_dir, 's_BII-S-1.txt'))
fixer.replace_factor_with_source_characteristic('limiting nutrient')
expected_field_names = [
'Source Name', 'Factor Value[limiting nutrient]',
'Term Source REF', 'Term Accession Number',
'Characteristics[organism]', 'Term Source REF',
'Term Accession Number', 'Characteristics[strain]',
'Term Source REF', 'Term Accession Number',
'Characteristics[genotype]', 'Term Source REF',
'Term Accession Number', 'Protocol REF', 'Sample Name',
'Factor Value[rate]', 'Unit', 'Term Source REF',
'Term Accession Number'
]
with open(os.path.join(self._tmp_dir,
's_BII-S-1.txt')) as fixed_tab_fp:
actual_field_names = list(
map(lambda field_name: field_name.strip(),
next(fixed_tab_fp).split('\t')))
self.assertListEqual(actual_field_names, expected_field_names)
def test_fix_factor_two_args(self):
s_table_path = os.path.join(self._tmp_dir, 'BII-S-3', 's_BII-S-3.txt')
fixer = utils.IsaTabFixer(s_table_path)
fixer.fix_factor(
'dose', 'environmental material collection - standard procedure 1')
expected_field_names = [
'Source Name',
'Characteristics[organism]',
'Term Source REF', 'Term Accession Number',
'Characteristics[geographic location (country and/or sea,region)]',
'Term Source REF', 'Term Accession Number',
'Characteristics[geographic location (longitude)]',
'Unit', 'Term Source REF', 'Term Accession Number',
'Characteristics[geographic location (latitude)]',
'Unit', 'Term Source REF', 'Term Accession Number',
'Characteristics[chlorophyll a concentration]',
'Unit', 'Term Source REF', 'Term Accession Number',
'Characteristics[fucoxanthin concentration]',
'Unit', 'Term Source REF', 'Term Accession Number',
'Characteristics[peridinin concentration]',
'Unit', 'Term Source REF', 'Term Accession Number',
'Characteristics[butfucoxanthin concentration]',
'Unit', 'Term Source REF', 'Term Accession Number',
'Characteristics[hexfucoxanthin concentration]',
'Unit', 'Term Source REF', 'Term Accession Number',
'Characteristics[alloxanthin concentration]',
'Unit', 'Term Source REF', 'Term Accession Number',
'Characteristics[zeaxanthin concentration]',
'Unit', 'Term Source REF', 'Term Accession Number',
'Characteristics[lutein concentration]',
'Unit', 'Term Source REF', 'Term Accession Number',
'Characteristics[chl-c3 concentration]',
'Unit', 'Term Source REF', 'Term Accession Number',
'Characteristics[chl-c2 concentration]',
'Unit', 'Term Source REF', 'Term Accession Number',
'Characteristics[prasinoxanthin concentration]',
'Unit', 'Term Source REF', 'Term Accession Number',
'Characteristics[neoxanthin concentration]',
'Unit', 'Term Source REF', 'Term Accession Number',
'Characteristics[violaxanthin concentration]',
'Unit', 'Term Source REF', 'Term Accession Number',
'Characteristics[diadinoxanthin concentration]',
'Unit', 'Term Source REF', 'Term Accession Number',
'Characteristics[diatoxanthin concentration]',
'Unit', 'Term Source REF', 'Term Accession Number',
'Characteristics[divinyl-chl-b concentration]',
'Unit', 'Term Source REF', 'Term Accession Number',
'Characteristics[chl-b concentration]',
'Unit', 'Term Source REF', 'Term Accession Number',
'Characteristics[divinyl-chl-a concentration]',
'Unit', 'Term Source REF', 'Term Accession Number',
'Characteristics[chl-a concentration]',
'Unit', 'Term Source REF', 'Term Accession Number',
'Characteristics[BB carotene concentration]',
'Unit', 'Term Source REF', 'Term Accession Number',
'Characteristics[bacteria count]',
'Unit', 'Term Source REF', 'Term Accession Number',
'Characteristics[synechococcus count]',
'Unit', 'Term Source REF', 'Term Accession Number',
'Characteristics[small picoeukaryotes count]',
'Unit', 'Term Source REF', 'Term Accession Number',
'Characteristics[large picoeukaryotes count]',
'Unit', 'Term Source REF', 'Term Accession Number',
'Characteristics[nanoflagellates count]',
'Unit', 'Term Source REF', 'Term Accession Number',
'Characteristics[cryptophytes count]',
'Unit', 'Term Source REF', 'Term Accession Number',
'Characteristics[phosphate concentration]',
'Unit', 'Term Source REF', 'Term Accession Number',
'Characteristics[nitrate concentration]',
'Unit', 'Term Source REF', 'Term Accession Number',
'Characteristics[particulate organic nitrogen concentration]',
'Unit', 'Term Source REF', 'Term Accession Number',
'Characteristics[particulate organic carbon concentration]',
'Unit', 'Term Source REF', 'Term Accession Number',
'Characteristics[primary production depth integrated production to '
'3 m expressed_in mgC m-2 d-1]',
'Unit', 'Term Source REF', 'Term Accession Number',
'Characteristics[water salinity]',
'Unit', 'Term Source REF', 'Term Accession Number',
'Characteristics[fluorescence]',
'Term Source REF', 'Term Accession Number',
'Characteristics[water temperature at 3 meter depth]',
'Unit', 'Term Source REF', 'Term Accession Number',
'Protocol REF',
'Parameter Value[dose]',
'Term Source REF', 'Term Accession Number',
'Parameter Value[filter pore size]',
'Unit', 'Term Source REF', 'Term Accession Number',
'Sample Name',
'Factor Value[compound]',
'Term Source REF', 'Term Accession Number',
'Factor Value[collection time]',
'Term Source REF', 'Term Accession Number']
# check the columns got moved in the study file
with open(s_table_path + '.fix') as fixed_tab_fp:
actual_field_names = list(
map(lambda field_name: field_name.strip(),
next(fixed_tab_fp).split('\t')))
self.assertListEqual(actual_field_names, expected_field_names)
# check the param got added to protocol and factor removed from study
with open(os.path.dirname(
s_table_path) + '/i_Investigation.txt.fix') as fixed_i_fp:
investigation = isatab.load(fixed_i_fp)
study = investigation.studies[-1]
protocol = study.get_prot(
'environmental material collection - standard procedure 1')
param = protocol.get_param('dose')
self.assertIsNotNone(param)
factor = study.get_factor('dose')
self.assertIsNone(factor)
def test_fix_factor_one_arg(self):
s_table_path = os.path.join(self._tmp_dir, 'BII-S-3', 's_BII-S-3.txt')
fixer = utils.IsaTabFixer(s_table_path)
fixer.fix_factor('dose')
expected_field_names = [
'Source Name',
'Characteristics[dose]',
'Term Source REF', 'Term Accession Number',
'Characteristics[organism]',
'Term Source REF', 'Term Accession Number',
'Characteristics[geographic location (country and/or sea,region)]',
'Term Source REF', 'Term Accession Number',
'Characteristics[geographic location (longitude)]',
'Unit', 'Term Source REF', 'Term Accession Number',
'Characteristics[geographic location (latitude)]',
'Unit', 'Term Source REF', 'Term Accession Number',
'Characteristics[chlorophyll a concentration]',
'Unit', 'Term Source REF', 'Term Accession Number',
'Characteristics[fucoxanthin concentration]',
'Unit', 'Term Source REF', 'Term Accession Number',
'Characteristics[peridinin concentration]',
'Unit', 'Term Source REF', 'Term Accession Number',
'Characteristics[butfucoxanthin concentration]',
'Unit', 'Term Source REF', 'Term Accession Number',
'Characteristics[hexfucoxanthin concentration]',
'Unit', 'Term Source REF', 'Term Accession Number',
'Characteristics[alloxanthin concentration]',
'Unit', 'Term Source REF', 'Term Accession Number',
'Characteristics[zeaxanthin concentration]',
'Unit', 'Term Source REF', 'Term Accession Number',
'Characteristics[lutein concentration]',
'Unit', 'Term Source REF', 'Term Accession Number',
'Characteristics[chl-c3 concentration]',
'Unit', 'Term Source REF', 'Term Accession Number',
'Characteristics[chl-c2 concentration]',
'Unit', 'Term Source REF', 'Term Accession Number',
'Characteristics[prasinoxanthin concentration]',
'Unit', 'Term Source REF', 'Term Accession Number',
'Characteristics[neoxanthin concentration]',
'Unit', 'Term Source REF', 'Term Accession Number',
'Characteristics[violaxanthin concentration]',
'Unit', 'Term Source REF', 'Term Accession Number',
'Characteristics[diadinoxanthin concentration]',
'Unit', 'Term Source REF', 'Term Accession Number',
'Characteristics[diatoxanthin concentration]',
'Unit', 'Term Source REF', 'Term Accession Number',
'Characteristics[divinyl-chl-b concentration]',
'Unit', 'Term Source REF', 'Term Accession Number',
'Characteristics[chl-b concentration]',
'Unit', 'Term Source REF', 'Term Accession Number',
'Characteristics[divinyl-chl-a concentration]',
'Unit', 'Term Source REF', 'Term Accession Number',
'Characteristics[chl-a concentration]',
'Unit', 'Term Source REF', 'Term Accession Number',
'Characteristics[BB carotene concentration]',
'Unit', 'Term Source REF', 'Term Accession Number',
'Characteristics[bacteria count]',
'Unit', 'Term Source REF', 'Term Accession Number',
'Characteristics[synechococcus count]',
'Unit', 'Term Source REF', 'Term Accession Number',
'Characteristics[small picoeukaryotes count]',
'Unit', 'Term Source REF', 'Term Accession Number',
'Characteristics[large picoeukaryotes count]',
'Unit', 'Term Source REF', 'Term Accession Number',
'Characteristics[nanoflagellates count]',
'Unit', 'Term Source REF', 'Term Accession Number',
'Characteristics[cryptophytes count]',
'Unit', 'Term Source REF', 'Term Accession Number',
'Characteristics[phosphate concentration]',
'Unit', 'Term Source REF', 'Term Accession Number',
'Characteristics[nitrate concentration]',
'Unit', 'Term Source REF', 'Term Accession Number',
'Characteristics[particulate organic nitrogen concentration]',
'Unit', 'Term Source REF', 'Term Accession Number',
'Characteristics[particulate organic carbon concentration]',
'Unit', 'Term Source REF', 'Term Accession Number',
'Characteristics[primary production depth integrated production to '
'3 m expressed_in mgC m-2 d-1]',
'Unit', 'Term Source REF', 'Term Accession Number',
'Characteristics[water salinity]',
'Unit', 'Term Source REF', 'Term Accession Number',
'Characteristics[fluorescence]',
'Term Source REF', 'Term Accession Number',
'Characteristics[water temperature at 3 meter depth]',
'Unit', 'Term Source REF', 'Term Accession Number',
'Protocol REF',
'Parameter Value[filter pore size]',
'Unit', 'Term Source REF', 'Term Accession Number',
'Sample Name',
'Factor Value[compound]',
'Term Source REF', 'Term Accession Number',
'Factor Value[collection time]',
'Term Source REF', 'Term Accession Number']
with open(s_table_path) as fixed_tab_fp:
actual_field_names = list(
map(lambda field_name: field_name.strip(),
next(fixed_tab_fp).split('\t')))
self.assertListEqual(actual_field_names, expected_field_names)
