def test_extractNamesAndIntensities_single(self):
intensities_single = self.intensities_single
feature_dir = (current_dir +
"/test_data/FIA_MS_Data/features_AdditionalAdducts")
sequence_single = pd.read_csv(
current_dir + "/test_data/FIA_MS_Data/sequence_HumanSerum.csv",
sep=";")
sample_names_single = sequence_single["sample_group_name"].unique()
database_single = pd.read_csv(
current_dir + "/test_data/FIA_MS_Data/CHEMISTRY/HMDB_struct.tsv",
sep="\t",
header=None,
)
intensities_single_ = fia_ms.extractNamesAndIntensities(
feature_dir, sample_names_single, database_single)
self.assertEqual(len(intensities_single), len(intensities_single_))
self.assertEqual(len(intensities_single.columns),
len(intensities_single_.columns))
self.assertEqual(intensities_single, intensities_single_)
def test_extractNamesAndIntensities_standard(self):
intensities_standard = self.intensities_standard
feature_dir = (current_dir +
"/test_data/FIA_MS_Data/features_AdditionalAdducts")
sequence_standard = pd.read_csv(
current_dir + "/test_data/FIA_MS_Data/sequence_Standards.csv",
sep=";")
sample_names_standard = sequence_standard["sample_group_name"].unique()
database_standard = pd.read_csv(
current_dir +
"/test_data/FIA_MS_Data/CHEMISTRY/standard_mix_struct.tsv",
sep="\t",
header=None,
)
intensities_standard_ = fia_ms.extractNamesAndIntensities(
feature_dir, sample_names_standard, database_standard)
self.assertEqual(len(intensities_standard), len(intensities_standard_))
self.assertEqual(len(intensities_standard.columns),
len(intensities_standard_.columns))
self.assertEqual(intensities_standard, intensities_standard_)
def test_extractNamesAndIntensities_triplicates(self):
intensities_triplicates = self.intensities_triplicates
feature_dir = (current_dir +
"/test_data/FIA_MS_Data/features_AdditionalAdducts")
sequence_triplicates = pd.read_csv(
current_dir + "/test_data/FIA_MS_Data/sequence_EColi.csv", sep=";")
sample_names_triplicates = sequence_triplicates[
"sample_group_name"].unique()
database_triplicates = pd.read_csv(
current_dir +
"/test_data/FIA_MS_Data/CHEMISTRY/iJO1366_struct.tsv",
sep="\t",
header=None,
)
intensities_triplicates_ = fia_ms.extractNamesAndIntensities(
feature_dir, sample_names_triplicates, database_triplicates)
self.assertEqual(len(intensities_triplicates),
len(intensities_triplicates_))
self.assertEqual(
len(intensities_triplicates.columns),
len(intensities_triplicates_.columns),
)
self.assertEqual(intensities_triplicates, intensities_triplicates_)
sep=";")
sample_names_single = sequence_single["sample_group_name"].unique()
database_single = pd.read_csv(current_dir + "/../CHEMISTRY/HMDB_struct.tsv",
sep="\t",
header=None)
sequence_standard = pd.read_csv(current_dir + "/../sequence_Standards.csv",
sep=";")
sample_names_standard = sequence_standard["sample_group_name"].unique()
database_standard = pd.read_csv(
current_dir + "/../CHEMISTRY/standard_mix_struct.tsv",
sep="\t",
header=None,
)
# extractNamesAndIntensities, triplicates
intensities_triplicates = fia_ms.extractNamesAndIntensities(
feature_dir, sample_names_triplicates, database_triplicates)
intensities_single = fia_ms.extractNamesAndIntensities(feature_dir,
sample_names_single,
database_single)
intensities_standard = fia_ms.extractNamesAndIntensities(
feature_dir, sample_names_standard, database_standard)
# calculateMeanVarRSD
stats_triplicates = fia_ms.calculateMeanVarRSD(
intensities_triplicates,
sequence_triplicates.drop_duplicates(
["sample_group_name", "replicate_group_name"]),
min_reps=3,
)
stats_single = fia_ms.calculateMeanVarRSD(
intensities_single,