def test_is_empty_if_no_spectra(self):
m1 = Molecule(name='test', sum_formula="C1H2O3")
m1.save()
s1 = Standard(molecule=m1)
s1.save()
molecule_table, molecules_with_spectra = self.get_table_and_count()
self.assertEqual(len(molecule_table.rows), 1)
self.assertEqual(molecules_with_spectra, 0)
def test_get_mz(self):
m1 = Molecule(name='test', sum_formula="C1H2O3")
m1.save()
a1 = Adduct(nM=1, delta_formula='-H', charge=-1)
a1.save()
s1 = Standard(molecule=m1)
s1.save()
self.assertEqual(Standard.objects.all().count(), 1)
self.assertAlmostEqual(s1.molecule.get_mz(a1), 60.99311, places=4)
def test_is_not_empty_if_annotated(self):
m1 = Molecule(name='test', sum_formula="C1H2O3")
m1.save()
s1 = Standard(molecule=m1)
s1.save()
d1 = Dataset()
d1.save()
fs1 = FragmentationSpectrum(ms1_intensity=42, dataset=d1, standard=s1)
fs1.save()
molecule_table, molecules_with_spectra = self.get_table_and_count()
self.assertEqual(len(molecule_table.rows), 1)
self.assertEqual(molecules_with_spectra, 1)
def test_xic_and_standard_and_adduct(self):
# create some datasets
d1 = Dataset(name='Dataset1')
d1.save()
a1 = Adduct(nM=1, delta_formula='-H', charge=-1)
a1.save()
m1 = Molecule(name='TestMolecule1', sum_formula="C1H2O3")
m1.save()
s1 = Standard(molecule=m1, inventory_id="0")
s1.save()
# create some xics
x1 = Xic(mz=60.993, dataset=d1)
xic = [1.0, 2.0, 3.0, 4.0, 5.0]
x1.set_xic(xic)
x1.standard = s1
x1.adduct = a1
x1.save()
self.assertEqual(Xic.objects.all().count(), 1)
self.assertEqual(Dataset.objects.all().count(), 1)
self.assertEqual(Standard.objects.all().count(), 1)
# mass check
with self.assertRaises(ValueError):
x1.mz = 123.993
x1.save()
x1.check_mass()
def test_xic_mass_filter(self):
d1 = Dataset(name='dataset')
d1.save()
mz = 60.993
# three larger
Xic(mz=mz + 5., dataset=d1).save()
Xic(mz=mz + 10., dataset=d1).save()
Xic(mz=mz + 15., dataset=d1).save()
# three approx equal
Xic(mz=mz + 0.005, dataset=d1).save()
Xic(mz=mz + 0.0, dataset=d1).save()
Xic(mz=mz - 0.0015, dataset=d1).save()
# three smaller
Xic(mz=mz - 5., dataset=d1).save()
Xic(mz=mz - 10., dataset=d1).save()
Xic(mz=mz - 15., dataset=d1).save()
# three approx equal from another dataset
d2 = Dataset(name='dataset2')
d2.save()
Xic(mz=mz + 0.005, dataset=d2).save()
Xic(mz=mz + 0.0, dataset=d2).save()
Xic(mz=mz - 0.0015, dataset=d2).save()
self.assertEqual(Xic.objects.all().count(), 12)
xics = Xic.objects.all().filter(dataset=d1).filter(mz__gte=mz + 0.01).filter(mz__lte=mz - 0.01)
self.assertEqual(xics.objects.all().count(), 3)
def test_add_molecule(self):
m1 = Molecule(
name='test_molecule',
sum_formula='C1H2O3',
inchi_code="str",
solubility="none",
hmdb_id="000235",
chebi_id="123456",
lipidmaps_id="558855",
cas_id="789456",
pubchem_id="1235")
m1.save()
self.assertEqual(Molecule.objects.all().count(), 1)
self.assertAlmostEqual(m1.exact_mass, 62.00039, places=4)
def test_single(self):
m1 = Molecule(name='test', sum_formula="C1H2O3")
m1.save()
s1 = Standard(
inventory_id=0,
molecule=m1,
vendor="sigma",
vendor_cat="sig0001",
lot_num="#123456",
location="fridge",
purchase_date=datetime.datetime.now(),
)
s1.save()
standard_table = self.client.get('/inventory/').context['standard_list']
self.assertEqual(len(standard_table.rows), 1)
def test_add_standard(self):
m1 = Molecule(name='test', sum_formula="C1H2O3")
m1.save()
s1 = Standard(
inventory_id=0,
molecule=m1,
vendor="sigma",
vendor_cat="sig0001",
lot_num="#123456",
location="fridge",
purchase_date=datetime.datetime.now(),
)
s1.save()
self.assertEqual(s1.inventory_id, 0)
self.assertEqual(Standard.objects.all().count(), 1)
self.assertAlmostEqual(s1.molecule.exact_mass, 62.00039, places=4)
def test_add_xic(self):
m1 = Molecule(name='TestMolecule1', sum_formula="C1H2O3")
m1.save()
s1 = Standard(molecule=m1, inventory_id="0")
s1.save()
a1 = Adduct(nM=1, delta_formula='+H+K', charge=-2)
a1.save()
d1 = Dataset(name='Dataset1')
d1.save()
d1.standards_present.add(s1)
d1.adducts_present.add(a1)
x1 = Xic(mz='0.0', dataset=d1)
xic = [1.0, 2.0, 3.0, 4.0, 5.0]
x1.set_xic(xic)
x1.save()
self.assertEqual(Xic.objects.all().count(), 1)
np.testing.assert_array_almost_equal(xic, x1.xic)
def test_clean_db(self):
# clean should remove any molecules without a standard
m1 = Molecule(name="TestMolecule1", sum_formula="C1H2O3")
m1.save()
m2 = Molecule(name="TestMolecule2", sum_formula="C2H2O3")
m2.save()
s1 = Standard(molecule=m1, inventory_id="0")
s1.save()
clear_molecules_without_standard()
self.assertEqual(Molecule.objects.all().count(), 1)
def load_molecules(filename: str, dbname='#'):
'''### load molecules from fasta file
#### params:
- filename: Your file name
- dbname: Name of your data base
*returns* -> dict with molecules
'''
molecules = {}
with open(filename) as file:
lines = file.read()
molecules_str = lines.split('>')[1::]
for molecule_str in molecules_str:
mol_str = molecule_str.split('\n', 1)
mol_str[1] = mol_str[1].replace('\n', '')
ignorable_alleles = ['N', 'L', 'Q', 'S', 'A', 'C']
name = mol_str[0].split(' ')
if len(name) > 2:
name = name[1]
elif len(name) > 1:
name = name[0]
else:
name = name[0]
if any(name.endswith(allele) for allele in ignorable_alleles):
print('ignorated ', name)
continue
if name:
if name.find(':') > 2:
name = ':'.join(name.split(':', 2)[:2])
if any(subname in molecules for subname in name):
continue
else:
name = 'None'
mol = Molecule(dbname=dbname, name=name, seq=mol_str[1])
molecules[name] = mol
return molecules
def setUpTestData(cls):
d1 = Dataset(name='Dataset1')
d1.save()
m1 = Molecule(sum_formula='H2O')
m1.save()
m2 = Molecule(sum_formula='O2')
m2.save()
s1 = Standard(molecule=m1)
s1.save()
s2 = Standard(molecule=m1)
s2.save()
s3 = Standard(molecule=m2)
s3.save()
FragmentationSpectrum.objects.create(precursor_mz='123.456', spec_num=0, dataset=d1, standard=s1)
FragmentationSpectrum.objects.create(precursor_mz='123.45', spec_num=0, dataset=d1, standard=s2)
FragmentationSpectrum.objects.create(precursor_mz='123.4', spec_num=0, dataset=d1, standard=s3)
cls.m_onespectrum = m2
cls.m_twospectra = m1
def test_add_dataset(self):
# create standards
m1 = Molecule(name='TestMolecule1', sum_formula="C1H2O3")
m1.save()
m2 = Molecule(name='TestMolecule1', sum_formula="C2H2O3")
m2.save()
s1 = Standard(molecule=m1, inventory_id="0")
s1.save()
s2 = Standard(molecule=m2, inventory_id="1")
s2.save()
# create adduct
a1 = Adduct(nM=1, delta_formula='+H+K', charge=-2)
a1.save()
# create a dataset
d1 = Dataset(name='Dataset1')
d1.save()
d1.standards_present.add(s1)
d1.standards_present.add(s2)
d1.adducts_present.add(a1)
self.assertEqual(Dataset.objects.all().count(), 1)
self.assertEqual(Dataset.objects.all()[0].standards_present.count(), 2)
def add_batch_standard(metadata, csv_file):
"""
handle a csv fil of standards
header line should be "mcfid","name","formula", "inchi", "solubility", "vendor","vendor_id", "hmdb_id" , "chebi_id", "lipidmaps_id", "cas_id", "pubchem_id". "date","location","lot_num"
To Be Set:
### Standard
# mandatory
molecule = models.ForeignKey(Molecule, default=Molecule.objects.all().filter(name='DUMMY'))
MCFID = models.IntegerField(null=True, blank=True)# if blank MCFID == Standard.pk
# optional
vendor = models.TextField(null=True, blank=True)
vendor_cat = models.TextField(null=True, blank=True)
lot_num = models.TextField(null=True, blank=True)
location = models.TextField(null=True, blank=True)
purchase_date = models.DateField(null=True, blank=True)
If Not Existing:
### Molecule
# mandatory
name = models.TextField(default = "")
sum_formula = models.TextField(null=True)
pubchem_id = models.TextField(null=True, blank=True)
# Optional
inchi_code = models.TextField(default="")
exact_mass = models.FloatField(default=0.0)
solubility = models.TextField(null=True, blank=True)
# External reference numbers
hmdb_id = models.TextField(null=True, blank=True)
chebi_id = models.TextField(null=True, blank=True)
lipidmaps_id = models.TextField(null=True, blank=True)
cas_id = models.TextField(null=True, blank=True)
:param csv_file:
:return:
"""
error_list = []
df = pd.read_csv(csv_file, sep="\t", dtype=unicode)
logging.info( 'I read the file')
df.columns = [x.replace(" ", "_").lower() for x in df.columns]
logging.info("I replaced columns")
df = df.fillna("")
# df = df.applymap(to_unicode)
logging.info("Shape: {}".format(df.shape))
for row in df.iterrows():
logging.info("row: {}".format(row))
try:
# clean up input
entry = row[1]
if entry['formula'] == '':
raise ValueError('sum formula cannot be blank')
# for tag in entry.keys():
# if entry[tag] != "":
# entry[tag] = entry[tag].encode("utf8") # make strings safe
entry['id'] = ''.join([char for char in entry['id'] if char in ("0123456789")])
if entry['pubchem_id'] != "":
molecule = Molecule.objects.all().filter(pubchem_id=entry['pubchem_id'])
else:
molecule = Molecule.objects.all().filter(name__iexact=entry['name']) # filter lowercase
if molecule.exists():
molecule = molecule[0]
else:
molecule = Molecule(
name=entry["name"],
sum_formula=entry["formula"],
inchi_code=entry["inchi"],
solubility=entry["solubility"],
hmdb_id=entry["hmdb_id"],
chebi_id=entry["chebi_id"],
lipidmaps_id=entry["lipidmaps_id"],
cas_id=entry["cas_id"],
pubchem_id=entry["pubchem_id"],
)
logging.info("about to save " + molecule.name)
logging.info(molecule)
molecule.save()
logging.info("Successfully saved " + molecule.name)
s = Standard.objects.all().filter(inventory_id=entry['id'])
if s.exists(): # standard already added, overwrite
s = s[0]
else:
s = Standard(molecule=molecule)
s.save()
s.vendor = entry["vendor"]
s.vendor_cat = entry["vendor_id"]
s.lot_num = entry["lot_num"]
if entry["purchase_date"] != '':
s.purchase_date = dateutil.parser.parse(entry["purchase_date"], fuzzy=True)
s.save()
if entry["id"] == []:
s.inventory_id = s.pk
else:
s.inventory_id = entry['id']
s.save()
except:
error_list.append([entry['name'], sys.exc_info()[1]])
logging.warning("Failed for: {} with {}".format(entry['name'], sys.exc_info()[1]))
return error_list
