def test_targets_to_mols(self):
ret = targets_to_mols(
[resolve_target(x)[0]['target_chembl_id'] for x in ['POLK']])
serialiser = get_serializer('chembl_id')
self.assertTrue({
'CHEMBL6', 'CHEMBL25', 'CHEMBL10', 'CHEMBL30', 'CHEMBL50',
'CHEMBL71', 'CHEMBL28', 'CHEMBL66'
}.issubset(set(serialiser.serialize_line(ret).strip().split(','))))
ret = targets_to_mols(
[resolve_target(x)[0]['target_chembl_id'] for x in ['HERG']])
serialiser = get_serializer('smiles')
self.assertTrue({
'CN1C(=O)N(CC(=O)c2ccccc2)C(=O)c3c1nc(N4CCC[C@H](N)C4)n3CC=C(C)C',
'C[C@]12CCC(=O)C=C1CC[C@@H]3[C@@H]2CC[C@@]4(C)[C@H]3CC[C@@]4(O)C#C',
'CS(=O)(=O)N1CCC(CN([C@@H]2CC[C@@]3(CC3C2)c4cccc(c4)C#N)C(=O)Nc5ccc(F)c(F)c5)CC1',
'O=S(=O)(NCCCN1CCN(CC1)c2nsc3ccccc23)c4cccc5scnc45',
'Cl.CC(C)n1nc(C(=O)NCC2CCN(CCNS(=O)(=O)C)CC2)c3ccccc13',
'CC1CN(CC(=O)N[C@@H]2C3CC4CC2C[C@@](C4)(C3)C(=O)N)S(=O)(=O)N(C1)c5c(Cl)cc(Cl)cc5Cl',
'Oc1cccc2CC(CN3CCC4(CC3)CCc5ccccc45)NCc12',
'[O-][N+](=O)c1ccc(cc1)c2nc(c3ccc(F)cc3)c([nH]2)c4ccncc4'
}.issubset(set(serialiser.serialize_line(ret).strip().split())))
ret = targets_to_mols(
[resolve_target(x)[0]['target_chembl_id'] for x in ['CMKAR1']])
serialiser = get_serializer('inchi')
self.assertTrue({
'InChI=1S/C7H6O2/c8-7(9)6-4-2-1-3-5-6/h1-5H,(H,8,9)',
'InChI=1S/C11H7NS/c13-8-12-11-7-3-5-9-4-1-2-6-10(9)11/h1-7H',
'InChI=1S/CHCl3/c2-1(3)4/h1H',
'InChI=1S/H4N2/c1-2/h1-2H2',
'InChI=1S/C8H8N4/c9-11-8-7-4-2-1-3-6(7)5-10-12-8/h1-5H,9H2,(H,11,12)',
'InChI=1S/CH4N2O2/c2-1(4)3-5/h5H,(H3,2,3,4)',
'InChI=1S/CH3O5P/c2-1(3)7(4,5)6/h(H,2,3)(H2,4,5,6)',
'InChI=1S/C4H11NO3/c5-4(1-6,2-7)3-8/h6-8H,1-3,5H2',
'InChI=1S/C9H9Cl2N3O/c10-6-2-1-3-7(11)5(6)4-8(15)14-9(12)13/h1-3H,4H2,(H4,12,13,14,15)',
}.issubset(set(serialiser.serialize_line(ret).strip().split('\t'))))
ret = targets_to_mols([
resolve_target(x)[0]['target_chembl_id']
for x in ['ADRA2L1', 'VIPR1']
])
serialiser = get_serializer('inchi_key')
self.assertTrue({
'OELFLUMRDSZNSF-BRWVUGGUSA-N',
'KJPRLNWUNMBNBZ-QPJJXVBHSA-N',
'VEPKQEUBKLEPRA-UHFFFAOYSA-N',
'ACGUYXCXAPNIKK-UHFFFAOYSA-N',
'MVGSNCBCUWPVDA-MFOYZWKCSA-N',
'JZHXLYHEWUWHQL-LVYIWIAJSA-N',
'CUVBGWMAORETGV-UHFFFAOYSA-N',
'DVSMVUMYJDOPJQ-UHFFFAOYSA-N',
}.issubset(set(serialiser.serialize_line(ret).strip().split(','))))
def main():
options = get_options()
with open(options.input) if options.input else sys.stdin as in_f, \
open(options.output, 'w') if options.output else sys.stdout as out_f:
serializer_cls = get_serializer(options.format)
if not serializer_cls:
sys.stderr.write('Unsupported format', options.format)
return
if options.human:
serializer_cls.write_header(out_f)
for line in in_f:
name = line.strip()
if not name:
continue
resolved = None
try:
resolved = resolve(name, options.single)
except Exception as e:
pass
if options.parent:
resolved = get_parents(resolved)
out_f.write(
serializer_cls.serialize_line(resolved,
human=options.human,
name=name))
def test_inchi_serialiser(self):
serialiser = get_serializer('inchi')
mols = resolve('Vigamox')
buf = StringIO()
serialiser.write_header(buf)
buf.seek(0)
self.assertEqual(buf.read(), 'Name:\tInChI:\n')
self.assertEqual(
serialiser.serialize_line(mols),
'InChI=1S/C21H24FN3O4/c1-29-20-17-13(19(26)14(21(27)28)9-25(17)12-4-5-12)7-15(22)18(20)24-8-11'
'-3-2-6-23-16(11)10-24/h7,9,11-12,16,23H,2-6,8,10H2,1H3,(H,27,28)/t11-,16+/m0/s1\tInChI=1S/C21'
'H24FN3O4.ClH/c1-29-20-17-13(19(26)14(21(27)28)9-25(17)12-4-5-12)7-15(22)18(20)24-8-11-3-2-6-2'
'3-16(11)10-24;/h7,9,11-12,16,23H,2-6,8,10H2,1H3,(H,27,28);1H/t11-,16+;/m0./s1\n'
)
self.assertEqual(
serialiser.serialize_line(mols, human=True),
'InChI=1S/C21H24FN3O4/c1-29-20-17-13(19(26)14(21(27)28)9-25(17)12-4-5-12)7-15(22)18(20)24-8-11'
'-3-2-6-23-16(11)10-24/h7,9,11-12,16,23H,2-6,8,10H2,1H3,(H,27,28)/t11-,16+/m0/s1\tInChI=1S/C21'
'H24FN3O4.ClH/c1-29-20-17-13(19(26)14(21(27)28)9-25(17)12-4-5-12)7-15(22)18(20)24-8-11-3-2-6-2'
'3-16(11)10-24;/h7,9,11-12,16,23H,2-6,8,10H2,1H3,(H,27,28);1H/t11-,16+;/m0./s1\n'
)
self.assertEqual(
serialiser.serialize_line(mols, human=True, name='Vigamox'),
'Vigamox\tInChI=1S/C21H24FN3O4/c1-29-20-17-13(19(26)14(21(27)28)9-25(17)12-4-5-12)7-15(22)18(2'
'0)24-8-11-3-2-6-23-16(11)10-24/h7,9,11-12,16,23H,2-6,8,10H2,1H3,(H,27,28)/t11-,16+/m0/s1\tInC'
'hI=1S/C21H24FN3O4.ClH/c1-29-20-17-13(19(26)14(21(27)28)9-25(17)12-4-5-12)7-15(22)18(20)24-8-1'
'1-3-2-6-23-16(11)10-24;/h7,9,11-12,16,23H,2-6,8,10H2,1H3,(H,27,28);1H/t11-,16+;/m0./s1\n'
)
def main():
options = get_options()
with open(options.input) if options.input else sys.stdin as in_f, \
open(options.output, 'w') if options.output else sys.stdout as out_f:
serializer_cls = get_serializer(options.dest_format)
if not serializer_cls:
sys.stderr.write('Unsupported format', options.dest_format)
return
if options.human:
serializer_cls.write_header(out_f)
for line in in_f:
chunk = line.strip().split()[0]
identifiers = chunk.strip().split(',')
valid_identifiers = list()
for identifier in identifiers:
target = resolve_target(identifier)
if not target:
continue
valid_identifiers.append(target)
mols = targets_to_mols(valid_identifiers,
only_ids=(options.dest_format == 'chembl_id'),
include_parents=options.parent,
chunk_size=int(options.chunk))
out_f.write(serializer_cls.serialize_line(mols, human=options.human, name=','.join(valid_identifiers)))
def main():
options = get_options()
with open(options.input) if options.input else sys.stdin as in_f, \
open(options.output, 'w') if options.output else sys.stdout as out_f:
serializer_cls = get_serializer(options.format)
if not serializer_cls:
sys.stderr.write('Unsupported format', options.format)
return
if options.human:
serializer_cls.write_header(out_f)
for line in in_f:
name = line.strip()
if not name:
continue
resolved = None
try:
resolved = resolve(name, options.single)
except Exception as e:
pass
if options.parent:
resolved = get_parents(resolved)
out_f.write(serializer_cls.serialize_line(resolved, human=options.human, name=name))
def test_targets_to_mols(self):
ret = targets_to_mols([resolve_target(x)[0]['target_chembl_id'] for x in ['POLK']])
serialiser = get_serializer('chembl_id')
self.assertTrue({'CHEMBL6', 'CHEMBL25', 'CHEMBL10', 'CHEMBL30', 'CHEMBL50', 'CHEMBL71', 'CHEMBL28', 'CHEMBL66'
}.issubset(set(serialiser.serialize_line(ret).strip().split(','))))
ret = targets_to_mols([resolve_target(x)[0]['target_chembl_id'] for x in ['HERG']])
serialiser = get_serializer('smiles')
self.assertTrue({'CN1C(=O)N(CC(=O)c2ccccc2)C(=O)c3c1nc(N4CCC[C@H](N)C4)n3CC=C(C)C',
'C[C@]12CCC(=O)C=C1CC[C@@H]3[C@@H]2CC[C@@]4(C)[C@H]3CC[C@@]4(O)C#C',
'CS(=O)(=O)N1CCC(CN([C@@H]2CC[C@@]3(CC3C2)c4cccc(c4)C#N)C(=O)Nc5ccc(F)c(F)c5)CC1',
'O=S(=O)(NCCCN1CCN(CC1)c2nsc3ccccc23)c4cccc5scnc45',
'Cl.CC(C)n1nc(C(=O)NCC2CCN(CCNS(=O)(=O)C)CC2)c3ccccc13',
'CC1CN(CC(=O)N[C@@H]2C3CC4CC2C[C@@](C4)(C3)C(=O)N)S(=O)(=O)N(C1)c5c(Cl)cc(Cl)cc5Cl',
'Oc1cccc2CC(CN3CCC4(CC3)CCc5ccccc45)NCc12',
'[O-][N+](=O)c1ccc(cc1)c2nc(c3ccc(F)cc3)c([nH]2)c4ccncc4'
}.issubset(set(serialiser.serialize_line(ret).strip().split())))
ret = targets_to_mols([resolve_target(x)[0]['target_chembl_id'] for x in ['CMKAR1']])
serialiser = get_serializer('inchi')
self.assertTrue({
'InChI=1S/C7H6O2/c8-7(9)6-4-2-1-3-5-6/h1-5H,(H,8,9)',
'InChI=1S/C11H7NS/c13-8-12-11-7-3-5-9-4-1-2-6-10(9)11/h1-7H',
'InChI=1S/CHCl3/c2-1(3)4/h1H',
'InChI=1S/H4N2/c1-2/h1-2H2',
'InChI=1S/C8H8N4/c9-11-8-7-4-2-1-3-6(7)5-10-12-8/h1-5H,9H2,(H,11,12)',
'InChI=1S/CH4N2O2/c2-1(4)3-5/h5H,(H3,2,3,4)',
'InChI=1S/CH3O5P/c2-1(3)7(4,5)6/h(H,2,3)(H2,4,5,6)',
'InChI=1S/C4H11NO3/c5-4(1-6,2-7)3-8/h6-8H,1-3,5H2',
'InChI=1S/C9H9Cl2N3O/c10-6-2-1-3-7(11)5(6)4-8(15)14-9(12)13/h1-3H,4H2,(H4,12,13,14,15)',
}.issubset(set(serialiser.serialize_line(ret).strip().split('\t'))))
ret = targets_to_mols([resolve_target(x)[0]['target_chembl_id'] for x in ['ADRA2L1', 'VIPR1']])
serialiser = get_serializer('inchi_key')
self.assertTrue({
'OELFLUMRDSZNSF-BRWVUGGUSA-N',
'KJPRLNWUNMBNBZ-QPJJXVBHSA-N',
'VEPKQEUBKLEPRA-UHFFFAOYSA-N',
'ACGUYXCXAPNIKK-UHFFFAOYSA-N',
'MVGSNCBCUWPVDA-MFOYZWKCSA-N',
'JZHXLYHEWUWHQL-LVYIWIAJSA-N',
'CUVBGWMAORETGV-UHFFFAOYSA-N',
'DVSMVUMYJDOPJQ-UHFFFAOYSA-N',
}.issubset(set(serialiser.serialize_line(ret).strip().split(','))))
def test_sdf_serialiser(self):
serialiser = get_serializer('sdf')
mols = resolve('Vigamox')
buf = StringIO()
serialiser.write_header(buf)
buf.seek(0)
self.assertEqual(buf.read(), '')
self.assertEqual(serialiser.serialize_line(mols), sdf, serialiser.serialize_line(mols))
self.assertEqual(serialiser.serialize_line(mols, human=True), sdf)
self.assertEqual(serialiser.serialize_line(mols, human=True, name='Vigamox'), sdf)
serialiser = get_serializer('mol')
mols = resolve('Vigamox')
buf = StringIO()
serialiser.write_header(buf)
buf.seek(0)
self.assertEqual(buf.read(), '')
self.assertEqual(serialiser.serialize_line(mols), sdf, serialiser.serialize_line(mols))
self.assertEqual(serialiser.serialize_line(mols, human=True), sdf)
self.assertEqual(serialiser.serialize_line(mols, human=True, name='Vigamox'), sdf)
def test_chembl_id_serialiser(self):
serialiser = get_serializer('chembl_id')
mols = resolve('Vigamox')
buf = StringIO()
serialiser.write_header(buf)
buf.seek(0)
self.assertEqual(buf.read(), 'Name:\tChEMBL ID:\n')
self.assertEqual(serialiser.serialize_line(mols), 'CHEMBL32,CHEMBL1200735\n')
self.assertEqual(serialiser.serialize_line(mols, human=True), 'CHEMBL32,CHEMBL1200735\n')
self.assertEqual(serialiser.serialize_line(mols, human=True, name='Vigamox'),
'Vigamox\tCHEMBL32,CHEMBL1200735\n')
def test_chembl_key_serialiser(self):
serialiser = get_serializer('inchi_key')
mols = resolve('Vigamox')
buf = StringIO()
serialiser.write_header(buf)
buf.seek(0)
self.assertEqual(buf.read(), 'Name:\tInChI Key:\n')
self.assertEqual(serialiser.serialize_line(mols), 'FABPRXSRWADJSP-MEDUHNTESA-N,IDIIJJHBXUESQI-DFIJPDEKSA-N\n')
self.assertEqual(serialiser.serialize_line(mols, human=True),
'FABPRXSRWADJSP-MEDUHNTESA-N,IDIIJJHBXUESQI-DFIJPDEKSA-N\n')
self.assertEqual(serialiser.serialize_line(mols, human=True, name='Vigamox'),
'Vigamox\tFABPRXSRWADJSP-MEDUHNTESA-N,IDIIJJHBXUESQI-DFIJPDEKSA-N\n')
def test_mols_to_targets(self):
ret = mols_to_targets(['CHEMBL819'], organism='Escherichia coli')
serialiser = get_serializer('uniprot')
self.assertEqual(set(serialiser.serialize_line(ret).strip().split(',')), {'A1E3K9', 'P62593', 'P35695'})
ret = mols_to_targets(['CHEMBL819'], organism='Escherichia coli', include_parents=True)
serialiser = get_serializer('uniprot')
self.assertEqual(set(serialiser.serialize_line(ret).strip().split(',')),
{'A1E3K9', 'P62593', 'P35695', 'P00811'})
ret = mols_to_targets(['CHEMBL25', 'CHEMBL1'])
serialiser = get_serializer('gene_name')
self.assertTrue({'POLK', 'ADRA2RL2', 'CCR2', 'CHRM5', 'ADRA2L1', 'CMKAR1', 'PTPRC', 'HADH2', 'ITGAB', 'VIPR1'
}.issubset(set(serialiser.serialize_line(ret).strip().split(','))))
ret = mols_to_targets(['CHEMBL2', 'CHEMBL1737'])
serialiser = get_serializer('chembl_id')
targets_a = set(serialiser.serialize_line(ret).strip().split(','))
self.assertTrue({'CHEMBL213', 'CHEMBL1916', 'CHEMBL205', 'CHEMBL4071', 'CHEMBL1909043', 'CHEMBL2622',
}.issubset(targets_a))
ret = mols_to_targets(['CHEMBL2', 'CHEMBL1737'], only_ids=True)
serialiser = get_serializer('chembl_id')
targets_b = set(serialiser.serialize_line(ret).strip().split(','))
self.assertTrue({'CHEMBL213', 'CHEMBL1916', 'CHEMBL205', 'CHEMBL4071', 'CHEMBL1909043', 'CHEMBL2622',
}.issubset(targets_b))
self.assertEqual(targets_a, targets_b)
drugs = ['Viagra', 'Gleevec']
ret = mols_to_targets([resolve(x)[0]['molecule_chembl_id'] for x in drugs])
serialiser = get_serializer('uniprot')
self.assertTrue({'Q9BQI3', 'P00523', 'O15111', 'P22612', 'P25021', 'P16591', 'Q13153', 'Q8WXR4', 'P28564',
}.issubset(set(serialiser.serialize_line(ret).strip().split(','))))
def main():
similarity = new_client.similarity
options = get_options()
try:
threshold = int(options.threshold)
if threshold not in range(70, 101):
sys.stderr.write('Threshold should be an integer in range [70-100]')
return
threshold = str(threshold)
except:
sys.stderr.write('Threshold should be an integer in range [70-100]')
return
source_format = options.source_format.lower()
if source_format not in AVAILABLE_SOURCE_FORMATS:
sys.stderr.write('Unsupported source format', options.source_format)
return
inp = sys.stdin
if source_format == 'sdf':
with open(options.input) if options.input else sys.stdin as in_f:
options.input = None
inp = convert_to_smiles(in_f)
with open(options.input) if options.input else inp as in_f, \
open(options.output, 'w') if options.output else sys.stdout as out_f:
serializer_cls = get_serializer(options.dest_format)
if not serializer_cls:
sys.stderr.write('Unsupported format', options.dest_format)
return
if options.human:
serializer_cls.write_header(out_f)
for line in in_f:
if not line or line.lower().startswith('smiles'):
continue
chunk = line.strip().split()[0]
identifiers = chunk.strip().split(',')
valid_identifiers = list()
sim = list()
for identifier in identifiers:
if chembl_id_regex.match(identifier):
valid_identifiers.append(identifier)
sim.extend(list(similarity.filter(chembl_id=identifier, similarity=threshold)))
elif smiles_regex.match(identifier):
valid_identifiers.append(identifier)
sim.extend(list(similarity.filter(smiles=identifier, similarity=threshold)))
sim = list({v['molecule_chembl_id']: v for v in sim}.values())
out_f.write(serializer_cls.serialize_line(sim, human=options.human, name=','.join(valid_identifiers)))
def test_chembl_id_serialiser(self):
serialiser = get_serializer('chembl_id')
mols = resolve('Vigamox')
buf = StringIO()
serialiser.write_header(buf)
buf.seek(0)
self.assertEqual(buf.read(), 'Name:\tChEMBL ID:\n')
self.assertEqual(serialiser.serialize_line(mols),
'CHEMBL32,CHEMBL1200735\n')
self.assertEqual(serialiser.serialize_line(mols, human=True),
'CHEMBL32,CHEMBL1200735\n')
self.assertEqual(
serialiser.serialize_line(mols, human=True, name='Vigamox'),
'Vigamox\tCHEMBL32,CHEMBL1200735\n')
def test_sdf_serialiser(self):
serialiser = get_serializer('sdf')
mols = resolve('Vigamox')
buf = StringIO()
serialiser.write_header(buf)
buf.seek(0)
self.assertEqual(buf.read(), '')
self.assertEqual(serialiser.serialize_line(mols), sdf,
serialiser.serialize_line(mols))
self.assertEqual(serialiser.serialize_line(mols, human=True), sdf)
self.assertEqual(
serialiser.serialize_line(mols, human=True, name='Vigamox'), sdf)
serialiser = get_serializer('mol')
mols = resolve('Vigamox')
buf = StringIO()
serialiser.write_header(buf)
buf.seek(0)
self.assertEqual(buf.read(), '')
self.assertEqual(serialiser.serialize_line(mols), sdf,
serialiser.serialize_line(mols))
self.assertEqual(serialiser.serialize_line(mols, human=True), sdf)
self.assertEqual(
serialiser.serialize_line(mols, human=True, name='Vigamox'), sdf)
def test_smiles_serialiser(self):
serialiser = get_serializer('smi')
mols = resolve('Vigamox')
buf = StringIO()
serialiser.write_header(buf)
buf.seek(0)
self.assertEqual(buf.read(), 'SMILES Name\n')
self.assertEqual(serialiser.serialize_line(mols),
'COc1c(N2C[C@@H]3CCCN[C@@H]3C2)c(F)cc4C(=O)C(=CN(C5CC5)c14)C(=O)O\n'
'Cl.COc1c(N2C[C@@H]3CCCN[C@@H]3C2)c(F)cc4C(=O)C(=CN(C5CC5)c14)C(=O)O\n')
self.assertEqual(serialiser.serialize_line(mols, human=True),
'COc1c(N2C[C@@H]3CCCN[C@@H]3C2)c(F)cc4C(=O)C(=CN(C5CC5)c14)C(=O)O\n'
'Cl.COc1c(N2C[C@@H]3CCCN[C@@H]3C2)c(F)cc4C(=O)C(=CN(C5CC5)c14)C(=O)O\n')
self.assertEqual(serialiser.serialize_line(mols, human=True, name='Vigamox'),
'COc1c(N2C[C@@H]3CCCN[C@@H]3C2)c(F)cc4C(=O)C(=CN(C5CC5)c14)C(=O)O Vigamox\n'
'Cl.COc1c(N2C[C@@H]3CCCN[C@@H]3C2)c(F)cc4C(=O)C(=CN(C5CC5)c14)C(=O)O Vigamox\n')
def test_chembl_key_serialiser(self):
serialiser = get_serializer('inchi_key')
mols = resolve('Vigamox')
buf = StringIO()
serialiser.write_header(buf)
buf.seek(0)
self.assertEqual(buf.read(), 'Name:\tInChI Key:\n')
self.assertEqual(
serialiser.serialize_line(mols),
'FABPRXSRWADJSP-MEDUHNTESA-N,IDIIJJHBXUESQI-DFIJPDEKSA-N\n')
self.assertEqual(
serialiser.serialize_line(mols, human=True),
'FABPRXSRWADJSP-MEDUHNTESA-N,IDIIJJHBXUESQI-DFIJPDEKSA-N\n')
self.assertEqual(
serialiser.serialize_line(mols, human=True, name='Vigamox'),
'Vigamox\tFABPRXSRWADJSP-MEDUHNTESA-N,IDIIJJHBXUESQI-DFIJPDEKSA-N\n'
)
def main():
substructure = new_client.substructure
options = get_options()
source_format = options.source_format.lower()
if source_format not in AVAILABLE_SOURCE_FORMATS:
sys.stderr.write('Unsupported source format', options.source_format)
return
inp = sys.stdin
if source_format == 'sdf':
with open(options.input) if options.input else sys.stdin as in_f:
options.input = None
inp = convert_to_smiles(in_f)
with open(options.input) if options.input else inp as in_f, \
open(options.output, 'w') if options.output else sys.stdout as out_f:
serializer_cls = get_serializer(options.dest_format)
if not serializer_cls:
sys.stderr.write('Unsupported format', options.dest_format)
return
if options.human:
serializer_cls.write_header(out_f)
for line in in_f:
if not line or line.lower().startswith('smiles'):
continue
chunk = line.strip().split()[0]
identifiers = chunk.strip().split(',')
valid_identifiers = list()
sub = list()
for identifier in identifiers:
if chembl_id_regex.match(identifier):
valid_identifiers.append(identifier)
sub.extend(list(substructure.filter(chembl_id=identifier)))
elif smiles_regex.match(identifier):
valid_identifiers.append(identifier)
sub.extend(list(substructure.filter(smiles=identifier)))
sub = list({v['molecule_chembl_id']: v for v in sub}.values())
out_f.write(
serializer_cls.serialize_line(
sub, human=options.human,
name=','.join(valid_identifiers)))
def main():
substructure = new_client.substructure
options = get_options()
source_format = options.source_format.lower()
if source_format not in AVAILABLE_SOURCE_FORMATS:
sys.stderr.write('Unsupported source format', options.source_format)
return
inp = sys.stdin
if source_format == 'sdf':
with open(options.input) if options.input else sys.stdin as in_f:
options.input = None
inp = convert_to_smiles(in_f)
with open(options.input) if options.input else inp as in_f, \
open(options.output, 'w') if options.output else sys.stdout as out_f:
serializer_cls = get_serializer(options.dest_format)
if not serializer_cls:
sys.stderr.write('Unsupported format', options.dest_format)
return
if options.human:
serializer_cls.write_header(out_f)
for line in in_f:
if not line or line.lower().startswith('smiles'):
continue
chunk = line.strip().split()[0]
identifiers = chunk.strip().split(',')
valid_identifiers = list()
sub = list()
for identifier in identifiers:
if chembl_id_regex.match(identifier):
valid_identifiers.append(identifier)
sub.extend(list(substructure.filter(chembl_id=identifier)))
elif smiles_regex.match(identifier):
valid_identifiers.append(identifier)
sub.extend(list(substructure.filter(smiles=identifier)))
sub = list({v['molecule_chembl_id']: v for v in sub}.values())
out_f.write(serializer_cls.serialize_line(sub, human=options.human, name=','.join(valid_identifiers)))
def main():
options = get_options()
source_format = options.source_format.lower()
if source_format not in AVAILABLE_SOURCE_FORMATS:
sys.stderr.write('Unsupported source format', options.source_format)
return
inp = sys.stdin
if source_format == 'sdf':
with open(options.input) if options.input else sys.stdin as in_f:
options.input = None
inp = convert_to_smiles(in_f)
with open(options.input) if options.input else inp as in_f, \
open(options.output, 'w') if options.output else sys.stdout as out_f:
serializer_cls = get_serializer(options.dest_format)
if not serializer_cls:
sys.stderr.write('Unsupported format', options.dest_format)
return
if options.human:
serializer_cls.write_header(out_f)
for line in in_f:
if not line or line.lower().startswith('smiles'):
continue
chunk = line.strip().split()[0]
identifiers = chunk.strip().split(',')
valid_identifiers = list()
for identifier in identifiers:
if chembl_id_regex.match(identifier):
valid_identifiers.append(identifier)
elif smiles_regex.match(identifier):
valid_identifiers.extend([x['molecule_chembl_id'] for x in resolve(identifier)])
targets = mols_to_targets(valid_identifiers,
organism=options.organism,
only_ids=(options.dest_format == 'chembl_id'),
include_parents=options.parent,
chunk_size=int(options.chunk))
out_f.write(serializer_cls.serialize_line(targets, human=options.human, name=','.join(valid_identifiers)))
def test_inchi_serialiser(self):
serialiser = get_serializer('inchi')
mols = resolve('Vigamox')
buf = StringIO()
serialiser.write_header(buf)
buf.seek(0)
self.assertEqual(buf.read(), 'Name:\tInChI:\n')
self.assertEqual(serialiser.serialize_line(mols),
'InChI=1S/C21H24FN3O4/c1-29-20-17-13(19(26)14(21(27)28)9-25(17)12-4-5-12)7-15(22)18(20)24-8-11'
'-3-2-6-23-16(11)10-24/h7,9,11-12,16,23H,2-6,8,10H2,1H3,(H,27,28)/t11-,16+/m0/s1\tInChI=1S/C21'
'H24FN3O4.ClH/c1-29-20-17-13(19(26)14(21(27)28)9-25(17)12-4-5-12)7-15(22)18(20)24-8-11-3-2-6-2'
'3-16(11)10-24;/h7,9,11-12,16,23H,2-6,8,10H2,1H3,(H,27,28);1H/t11-,16+;/m0./s1\n')
self.assertEqual(serialiser.serialize_line(mols, human=True),
'InChI=1S/C21H24FN3O4/c1-29-20-17-13(19(26)14(21(27)28)9-25(17)12-4-5-12)7-15(22)18(20)24-8-11'
'-3-2-6-23-16(11)10-24/h7,9,11-12,16,23H,2-6,8,10H2,1H3,(H,27,28)/t11-,16+/m0/s1\tInChI=1S/C21'
'H24FN3O4.ClH/c1-29-20-17-13(19(26)14(21(27)28)9-25(17)12-4-5-12)7-15(22)18(20)24-8-11-3-2-6-2'
'3-16(11)10-24;/h7,9,11-12,16,23H,2-6,8,10H2,1H3,(H,27,28);1H/t11-,16+;/m0./s1\n')
self.assertEqual(serialiser.serialize_line(mols, human=True, name='Vigamox'),
'Vigamox\tInChI=1S/C21H24FN3O4/c1-29-20-17-13(19(26)14(21(27)28)9-25(17)12-4-5-12)7-15(22)18(2'
'0)24-8-11-3-2-6-23-16(11)10-24/h7,9,11-12,16,23H,2-6,8,10H2,1H3,(H,27,28)/t11-,16+/m0/s1\tInC'
'hI=1S/C21H24FN3O4.ClH/c1-29-20-17-13(19(26)14(21(27)28)9-25(17)12-4-5-12)7-15(22)18(20)24-8-1'
'1-3-2-6-23-16(11)10-24;/h7,9,11-12,16,23H,2-6,8,10H2,1H3,(H,27,28);1H/t11-,16+;/m0./s1\n')
def test_smiles_serialiser(self):
serialiser = get_serializer('smi')
mols = resolve('Vigamox')
buf = StringIO()
serialiser.write_header(buf)
buf.seek(0)
self.assertEqual(buf.read(), 'SMILES Name\n')
self.assertEqual(
serialiser.serialize_line(mols),
'COc1c(N2C[C@@H]3CCCN[C@@H]3C2)c(F)cc4C(=O)C(=CN(C5CC5)c14)C(=O)O\n'
'Cl.COc1c(N2C[C@@H]3CCCN[C@@H]3C2)c(F)cc4C(=O)C(=CN(C5CC5)c14)C(=O)O\n'
)
self.assertEqual(
serialiser.serialize_line(mols, human=True),
'COc1c(N2C[C@@H]3CCCN[C@@H]3C2)c(F)cc4C(=O)C(=CN(C5CC5)c14)C(=O)O\n'
'Cl.COc1c(N2C[C@@H]3CCCN[C@@H]3C2)c(F)cc4C(=O)C(=CN(C5CC5)c14)C(=O)O\n'
)
self.assertEqual(
serialiser.serialize_line(mols, human=True, name='Vigamox'),
'COc1c(N2C[C@@H]3CCCN[C@@H]3C2)c(F)cc4C(=O)C(=CN(C5CC5)c14)C(=O)O Vigamox\n'
'Cl.COc1c(N2C[C@@H]3CCCN[C@@H]3C2)c(F)cc4C(=O)C(=CN(C5CC5)c14)C(=O)O Vigamox\n'
)
def test_mols_to_targets(self):
ret = mols_to_targets(['CHEMBL819'], organism='Escherichia coli')
serialiser = get_serializer('uniprot')
self.assertEqual(
set(serialiser.serialize_line(ret).strip().split(',')),
{'A1E3K9', 'P62593', 'P35695'})
ret = mols_to_targets(['CHEMBL819'],
organism='Escherichia coli',
include_parents=True)
serialiser = get_serializer('uniprot')
self.assertEqual(
set(serialiser.serialize_line(ret).strip().split(',')),
{'A1E3K9', 'P62593', 'P35695', 'P00811'})
ret = mols_to_targets(['CHEMBL25', 'CHEMBL1'])
serialiser = get_serializer('gene_name')
self.assertTrue({
'POLK', 'ADRA2RL2', 'CCR2', 'CHRM5', 'ADRA2L1', 'CMKAR1', 'PTPRC',
'HADH2', 'ITGAB', 'VIPR1'
}.issubset(set(serialiser.serialize_line(ret).strip().split(','))))
ret = mols_to_targets(['CHEMBL2', 'CHEMBL1737'])
serialiser = get_serializer('chembl_id')
targets_a = set(serialiser.serialize_line(ret).strip().split(','))
self.assertTrue({
'CHEMBL213',
'CHEMBL1916',
'CHEMBL205',
'CHEMBL4071',
'CHEMBL1909043',
'CHEMBL2622',
}.issubset(targets_a))
ret = mols_to_targets(['CHEMBL2', 'CHEMBL1737'], only_ids=True)
serialiser = get_serializer('chembl_id')
targets_b = set(serialiser.serialize_line(ret).strip().split(','))
self.assertTrue({
'CHEMBL213',
'CHEMBL1916',
'CHEMBL205',
'CHEMBL4071',
'CHEMBL1909043',
'CHEMBL2622',
}.issubset(targets_b))
self.assertEqual(targets_a, targets_b)
drugs = ['Viagra', 'Gleevec']
ret = mols_to_targets(
[resolve(x)[0]['molecule_chembl_id'] for x in drugs])
serialiser = get_serializer('uniprot')
self.assertTrue({
'Q9BQI3',
'P00523',
'O15111',
'P22612',
'P25021',
'P16591',
'Q13153',
'Q8WXR4',
'P28564',
}.issubset(set(serialiser.serialize_line(ret).strip().split(','))))
def main():
similarity = new_client.similarity
options = get_options()
try:
threshold = int(options.threshold)
if threshold not in range(70, 101):
sys.stderr.write(
'Threshold should be an integer in range [70-100]')
return
threshold = str(threshold)
except:
sys.stderr.write('Threshold should be an integer in range [70-100]')
return
source_format = options.source_format.lower()
if source_format not in AVAILABLE_SOURCE_FORMATS:
sys.stderr.write('Unsupported source format', options.source_format)
return
inp = sys.stdin
if source_format == 'sdf':
with open(options.input) if options.input else sys.stdin as in_f:
options.input = None
inp = convert_to_smiles(in_f)
with open(options.input) if options.input else inp as in_f, \
open(options.output, 'w') if options.output else sys.stdout as out_f:
serializer_cls = get_serializer(options.dest_format)
if not serializer_cls:
sys.stderr.write('Unsupported format', options.dest_format)
return
if options.human:
serializer_cls.write_header(out_f)
for line in in_f:
if not line or line.lower().startswith('smiles'):
continue
chunk = line.strip().split()[0]
identifiers = chunk.strip().split(',')
valid_identifiers = list()
sim = list()
for identifier in identifiers:
if chembl_id_regex.match(identifier):
valid_identifiers.append(identifier)
sim.extend(
list(
similarity.filter(chembl_id=identifier,
similarity=threshold)))
elif smiles_regex.match(identifier):
valid_identifiers.append(identifier)
sim.extend(
list(
similarity.filter(smiles=identifier,
similarity=threshold)))
sim = list({v['molecule_chembl_id']: v for v in sim}.values())
out_f.write(
serializer_cls.serialize_line(
sim, human=options.human,
name=','.join(valid_identifiers)))