def main():
# Read in a SD or SMILES file - then write out into a specified directory
parser = argparse.ArgumentParser(
description=
"Convert a SMILES or SDFile to input for Astex Fragment network.")
parser.add_argument("--input")
parser.add_argument("--input_format", default="smi")
parser.add_argument("--base_dir")
parser.add_argument("--iso_flag", default=True)
args = parser.parse_args()
attrs = []
id = 0
mols = parse_mols(args.input, args.input_format)
for x in tqdm(mols):
if x is None:
continue
attr = Attr(
Chem.CanonSmiles(Chem.MolToSmiles(x, isomericSmiles=True)),
["EM", x.GetProp("_Name")],
)
attrs.append(attr)
id += 1
if not os.path.isdir(args.base_dir):
os.mkdir(args.base_dir)
# Build the network
node_holder = NodeHolder(iso_flag=args.iso_flag)
node_holder = build_network(attrs, node_holder)
# Write the data out
write_data(args.base_dir, node_holder, attrs)
def process_smiles(smiles, id='1', recurse=True, no_output=False, verbosity=0):
attrs = []
# print("Original SMILES: " + args.smiles)
# mol = Chem.MolFromSmiles(args.smiles)
# if args.standardize:
# mol = standardize(mol)
# print("Standardized SMILES: " + Chem.MolToSmiles(mol))
# smiles = Chem.CanonSmiles(Chem.MolToSmiles(mol, isomericSmiles=True))
# print("Canonical SMILES: " + smiles)
attr = Attr(smiles, ["EM", id])
attrs.append(attr)
# Build the network
node_holder = NodeHolder(iso_flag=False)
max_frags = 0
# print("Recurse:",recurse)
node_holder = build_network(attrs,
node_holder,
max_frags,
smiles,
verbosity,
recurse=recurse)
# Write the data out
if not no_output:
for node in node_holder.get_nodes():
print(str(node))
for edge in node_holder.get_edges():
print(str(edge))
for attr in attrs:
print(str(attr))
print("Number of nodes: " + str(len(node_holder.get_nodes())) +
" edges: " + str(len(node_holder.get_edges())))
def main():
# Read in a SD or SMILES file - then write out into a specified directory
parser = argparse.ArgumentParser(
description=
"Convert a SMILES or SDFile to input for Astex Fragment network.")
parser.add_argument("--input")
parser.add_argument("--input_format", default="smi")
parser.add_argument("--base_dir")
parser.add_argument("--isomeric", dest="iso_flag", action="store_true")
parser.add_argument("--non_isomeric",
dest="iso_flag",
action="store_false")
group = parser.add_mutually_exclusive_group()
group.add_argument("-v", dest="verbosity", action="store_const", const=1)
group.add_argument("-vv", dest="verbosity", action="store_const", const=2)
parser.set_defaults(verbosity=0)
parser.set_defaults(iso_flag=True)
args = parser.parse_args()
# Do we have an input and base directory?
if not args.input:
print('ERROR: Must specify an input')
sys.exit(1)
if not os.path.isfile(args.input):
print('ERROR: input (%s) does not exist' % args.input)
sys.exit(1)
if not args.base_dir:
print('ERROR: Must specify a base directory')
sys.exit(1)
if not os.path.isdir(args.base_dir):
print('ERROR:input base directory (%s) does not exist' % args.base_dir)
sys.exit(1)
tqdm_disable = True if args.verbosity else False
attrs = []
id = 0
mols = parse_mols(args.input, args.input_format)
for x in tqdm(mols, disable=tqdm_disable):
print("Processing " + Chem.MolToSmiles(x, isomericSmiles=True))
if x is None:
continue
attr = Attr(
Chem.CanonSmiles(Chem.MolToSmiles(x, isomericSmiles=True)),
["EM", x.GetProp("_Name")],
)
attrs.append(attr)
id += 1
if not os.path.isdir(args.base_dir):
os.mkdir(args.base_dir)
# Build the network
node_holder = NodeHolder(iso_flag=args.iso_flag)
max_frags = 0
node_holder = build_network(attrs, node_holder, max_frags, args.base_dir,
args.verbosity)
# Write the data out
write_data(args.base_dir, node_holder, attrs)
def main():
# Read in a SD or SMILES file - then write out into a specified directory
parser = argparse.ArgumentParser(
description="Convert a SMILES to nodes, edges and attributes"
)
parser.add_argument("--smiles")
parser.add_argument("--id")
parser.add_argument("--standardize", action="store_true")
parser.add_argument("--isomeric", dest="iso_flag", action="store_true")
parser.add_argument("--non_isomeric", dest="iso_flag", action="store_false")
group = parser.add_mutually_exclusive_group()
group.add_argument("-v", dest="verbosity", action="store_const", const=1)
group.add_argument("-vv", dest="verbosity", action="store_const", const=2)
parser.set_defaults(verbosity=0)
parser.set_defaults(iso_flag=True)
args = parser.parse_args()
# Do we have an input and base directory?
if not args.smiles:
print('ERROR: Must specify a SMILES')
sys.exit(1)
attrs = []
print("Original SMILES: " + args.smiles)
mol = Chem.MolFromSmiles(args.smiles)
if args.standardize:
mol = standardize(mol)
print("Standardized SMILES: " + Chem.MolToSmiles(mol))
smiles = Chem.CanonSmiles(Chem.MolToSmiles(mol, isomericSmiles=True))
print("Canonical SMILES: " + smiles)
id = args.id
if id is None:
id = "smiles1"
attr = Attr(smiles, ["EM", id])
attrs.append(attr)
# Build the network
node_holder = NodeHolder(iso_flag=args.iso_flag)
max_frags = 0
node_holder = build_network(attrs, node_holder,
max_frags, smiles, args.verbosity)
# Write the data out
for node in node_holder.node_list:
print(str(node))
for edge in node_holder.get_edges():
print(str(edge))
for attr in attrs:
print(str(attr))
print("Number of nodes: " + str(len(node_holder.node_list)))
print("Number of edges: " + str(len(node_holder.get_edges())))
def test_generate_nodes(self):
"""
Test we can generate nodes for the basic data.
:return:
"""
try:
nodes = [x for x in open("frag/tests/data/nodes.txt").readlines()]
edges = [x.split() for x in open("frag/tests/data/edges.txt").readlines()]
attrs = [
Attr(input_str=x)
for x in open("frag/tests/data/attributes.txt").readlines()
]
except IOError:
nodes = [x for x in open("data/nodes.txt").readlines()]
edges = [x.split() for x in open("data/edges.txt").readlines()]
attrs = [Attr(input_str=x) for x in open("data/attributes.txt").readlines()]
node_holder = NodeHolder(iso_flag=True)
node_holder = build_network(attrs, node_holder)
# Create the nodes and test with output
self.assertEqual(len(node_holder.node_list), len(nodes))
# This doesn't work yet(we get 3687 edges - should be 3691
# Close enough - and the output looks right...
self.assertEqual(len(node_holder.get_edges()), 3687)
def fragment_mol(smiles, base_dir, verbosity):
attrs = []
attr = Attr(smiles, ["EM"])
attrs.append(attr)
# Build the network
node_holder = NodeHolder(iso_flag=False)
max_frags = 0
node_holder = build_network(attrs,
node_holder,
max_frags,
base_dir,
verbosity=verbosity,
recurse=False)
return node_holder
def fragment_mol(self, smiles, verbosity=0) -> object:
"""Performs the fragmentation process for a SMILES.
Returns:
Fragdata object with Node/Edge data to write to files.
"""
# Note that in this version, only one SMILES is sent in here.
# There seemed to be some strange issues with edges if a combined node holder is used TBI
attrs = []
attr = Attr(smiles, ["EM"])
attrs.append(attr)
node_holder = NodeHolder(iso_flag=False)
node_holder = build_network(attrs, node_holder, base_dir=None, verbosity=verbosity, recurse=False)
return node_holder
def fragment_mol(self, smiles, verbosity=0) -> object:
"""Performs the fragmentation process for a SMILES.
Returns:
NodeHolder object.
"""
attrs = []
attr = Attr(smiles, ["EM"])
attrs.append(attr)
#print('fragment smiles: {}'.format(smiles))
# Build the network
node_holder = NodeHolder(iso_flag=False)
node_holder = build_network(attrs,
node_holder,
base_dir=None,
verbosity=verbosity,
recurse=False)
return node_holder
def fragment_mols(input_smiles, verbosity=0, recurse=False):
#print("Fragmenting", smiles)
attrs = []
for smiles in input_smiles:
attr = Attr(smiles, ["EM"])
attrs.append(attr)
# Build the network
# print("Processing", len(input_smiles), "mols")
# print('INPUT ', ','.join(sorted(input_smiles)))
node_holder = NodeHolder(iso_flag=False)
node_holder = build_network(attrs, node_holder, base_dir=None, verbosity=verbosity, recurse=recurse)
# output_smiles = [n.SMILES for n in node_holder.get_nodes()]
# print('OUTPUT', ','.join(sorted(output_smiles)))
frag_data = group_data(node_holder, input_smiles)
# print("Groups:", len(frag_data.parent_data))
return frag_data
def fragment_mol(smiles, verbosity=0):
attrs = []
attr = Attr(smiles, ["EM"])
attrs.append(attr)
# Build the network
node_holder = NodeHolder(iso_flag=False)
node_holder = build_network(attrs,
node_holder,
base_dir=None,
verbosity=verbosity,
recurse=False)
# Write the data out
# print(str(node_holder.size()))
# for node in node_holder.node_list:
# print(str(node))
# for edge in node_holder.get_edges():
# print(str(edge))
return node_holder
from tqdm import tqdm
from frag.network.models import Attr
if __name__ == "__main__":
parser = argparse.ArgumentParser(
description=
'Decorate a library of molecules for insertion to the database.')
parser.add_argument('--input_smi')
parser.add_argument('--output_attr')
args = parser.parse_args()
out_smi = open(args.output_attr, "w")
for mol in tqdm(
Chem.SmilesMolSupplier(args.input_smi,
delimiter=',',
smilesColumn=1,
nameColumn=0)):
this_smi = Chem.MolToSmiles(mol, isomericSmiles=True)
new_smis = decorate_smi(this_smi)
new_murck = decorate_smi(MurckoScaffold.MurckoScaffoldSmiles(this_smi))
# mol_frags = get_fragments(Chem.MolFromSmiles(this_smi),iso_labels=False)
# new_smis.extend([x.replace("Xe","At") for x in mol_frags])
new_smis.extend(new_murck)
new_smis = list(set(new_smis))
# Do this on original and on Murcko Scaffold
name = mol.GetProp("_Name")
new_attr = Attr(this_smi, ["EM", name])
out_smi.write(str(new_attr) + "\n")
for i, smi in enumerate(new_smis):
new_attr = Attr(smi, ["EM", name + "_" + str(i)])
out_smi.write(str(new_attr) + "\n")
def test_compare_iso_non_iso(self):
"""
Test that the iso flag makes a difference.
:return:
"""
input_smis = ["C#CC(C)(C)NC[C@]1(O)CCCN2CCCC[C@@H]21"]
test_iso_node_list = [
"C#CC(C)(C)NC",
"OC1CCCN2CCCCC12",
"O",
"C#CC(C)(C)NCC1CCCN2CCCCC12",
"C#CC(C)(C)NC[C@]1(O)CCCN2CCCC[C@@H]21",
"C1CCN2CCCCC2C1",
"C#CC(C)(C)NC.O",
]
test_non_iso_node_list = [
"C#CC(C)(C)NC",
"OC1CCCN2CCCCC12",
"O",
"C#CC(C)(C)NCC1CCCN2CCCCC12",
"C#CC(C)(C)NCC1(O)CCCN2CCCCC21",
"C1CCN2CCCCC2C1",
"C#CC(C)(C)NC.O",
]
test_iso_edge_list = [
"EDGE C#CC(C)(C)NC[C@]1(O)CCCN2CCCC[C@@H]21 OC1CCCN2CCCCC12 FG|C#CC(C)(C)NC[Xe]|CCC(C)(C)NC[100Xe]|RING|OC1([Xe])CCCN2CCCCC21|O[C@@]1([100Xe])CCCC2CCCC[C@@H]21",
"EDGE OC1CCCN2CCCCC12 O RING|[Xe]C1CCCN2CCCCC12|[100Xe]C1CCCC2CCCCC12|FG|O[Xe]|O[100Xe]",
"EDGE C#CC(C)(C)NC[C@]1(O)CCCN2CCCC[C@@H]21 C#CC(C)(C)NC.O RING|[Xe]C1([Xe])CCCN2CCCCC21|[100Xe][C@]1([101Xe])CCCC2CCCC[C@@H]21|FG|C#CC(C)(C)NC[Xe].O[Xe]|CCC(C)(C)NC[100Xe].O[101Xe]",
"EDGE OC1CCCN2CCCCC12 C1CCN2CCCCC2C1 FG|O[Xe]|O[100Xe]|RING|[Xe]C1CCCN2CCCCC12|[100Xe]C1CCCC2CCCCC12",
"EDGE C#CC(C)(C)NC.O C#CC(C)(C)NC FG|O|O|FG|C#CC(C)(C)NC|CCC(C)(C)NC",
"EDGE C#CC(C)(C)NC[C@]1(O)CCCN2CCCC[C@@H]21 C#CC(C)(C)NCC1CCCN2CCCCC12 FG|O[Xe]|O[101Xe]|RING|C#CC(C)(C)NCC1([Xe])CCCN2CCCCC21|CCC(C)(C)NC[C@@]1([101Xe])CCCC2CCCC[C@@H]21",
"EDGE C#CC(C)(C)NCC1CCCN2CCCCC12 C1CCN2CCCCC2C1 FG|C#CC(C)(C)NC[Xe]|CCC(C)(C)NC[100Xe]|RING|[Xe]C1CCCN2CCCCC12|[100Xe]C1CCCC2CCCCC12",
"EDGE C#CC(C)(C)NC.O O FG|C#CC(C)(C)NC|CCC(C)(C)NC|FG|O|O",
"EDGE C#CC(C)(C)NCC1CCCN2CCCCC12 C#CC(C)(C)NC RING|[Xe]C1CCCN2CCCCC12|[100Xe]C1CCCC2CCCCC12|FG|C#CC(C)(C)NC[Xe]|CCC(C)(C)NC[100Xe]",
]
test_non_iso_edge_list = [
"EDGE C#CC(C)(C)NCC1(O)CCCN2CCCCC21 C#CC(C)(C)NCC1CCCN2CCCCC12 FG|O[Xe]|O[101Xe]|RING|C#CC(C)(C)NCC1([Xe])CCCN2CCCCC21|CCC(C)(C)NCC1([101Xe])CCCC2CCCCC21",
"EDGE OC1CCCN2CCCCC12 C1CCN2CCCCC2C1 FG|O[Xe]|O[100Xe]|RING|[Xe]C1CCCN2CCCCC12|[100Xe]C1CCCC2CCCCC12",
"EDGE C#CC(C)(C)NCC1(O)CCCN2CCCCC21 C#CC(C)(C)NC.O RING|[Xe]C1([Xe])CCCN2CCCCC21|[100Xe]C1([101Xe])CCCC2CCCCC21|FG|C#CC(C)(C)NC[Xe].O[Xe]|CCC(C)(C)NC[100Xe].O[101Xe]",
"EDGE OC1CCCN2CCCCC12 O RING|[Xe]C1CCCN2CCCCC12|[100Xe]C1CCCC2CCCCC12|FG|O[Xe]|O[100Xe]",
"EDGE C#CC(C)(C)NCC1CCCN2CCCCC12 C1CCN2CCCCC2C1 FG|C#CC(C)(C)NC[Xe]|CCC(C)(C)NC[100Xe]|RING|[Xe]C1CCCN2CCCCC12|[100Xe]C1CCCC2CCCCC12",
"EDGE C#CC(C)(C)NC.O O FG|C#CC(C)(C)NC|CCC(C)(C)NC|FG|O|O",
"EDGE C#CC(C)(C)NCC1(O)CCCN2CCCCC21 OC1CCCN2CCCCC12 FG|C#CC(C)(C)NC[Xe]|CCC(C)(C)NC[100Xe]|RING|OC1([Xe])CCCN2CCCCC21|OC1([100Xe])CCCC2CCCCC21",
"EDGE C#CC(C)(C)NC.O C#CC(C)(C)NC FG|O|O|FG|C#CC(C)(C)NC|CCC(C)(C)NC",
"EDGE C#CC(C)(C)NCC1CCCN2CCCCC12 C#CC(C)(C)NC RING|[Xe]C1CCCN2CCCCC12|[100Xe]C1CCCC2CCCCC12|FG|C#CC(C)(C)NC[Xe]|CCC(C)(C)NC[100Xe]",
]
attrs = [Attr(input_smi) for input_smi in input_smis]
node_holder = NodeHolder(iso_flag=False)
node_holder = build_network(attrs, node_holder)
non_iso_node_list = [x.SMILES for x in node_holder.node_list]
non_iso_edge_list = [str(x) for x in node_holder.edge_list]
self.assertListEqual(sorted(non_iso_node_list), sorted(test_non_iso_node_list))
self.assertListEqual(sorted(non_iso_edge_list), sorted(test_non_iso_edge_list))
node_holder = NodeHolder(iso_flag=True)
node_holder = build_network(attrs, node_holder)
iso_node_list = [x.SMILES for x in node_holder.node_list]
iso_edge_list = [str(x) for x in node_holder.edge_list]
self.assertListEqual(sorted(iso_node_list), sorted(test_iso_node_list))
self.assertListEqual(sorted(iso_edge_list), sorted(test_iso_edge_list))