canonicalize('C(CC)N(CCc1cccc(-c2ccccc2)c1)C(=O)C1OC(C(=O)O)=CC(N)C1NC(C)=O')'CCCN(CCc1cccc(-c2ccccc2)c1)C(=O)C1OC(C(=O)O)=CC(N)C1NC(C)=O'Utilities
Utilities module
canonicalize
canonicalize (smi:str, clear_stereo:bool=False)
This function returns the canonicalised smiles representation and has the option to clear stereochemistry
| Type | Default | Details | |
|---|---|---|---|
| smi | str | input molecule | |
| clear_stereo | bool | False | if True, clears stereochemistry of the molecule (remove the @@) |
| Returns | str | canonicalised molecule |
Canonicalizing an already canonicalized molecule
canonicalize('CCCN(CCc1cccc(-c2ccccc2)c1)C(=O)C1OC(C(=O)O)=CC(N)C1NC(C)=O')'CCCN(CCc1cccc(-c2ccccc2)c1)C(=O)C1OC(C(=O)O)=CC(N)C1NC(C)=O'Unit Tests
test_eq(canonicalize('C(CC)N(CCc1cccc(-c2ccccc2)c1)C(=O)C1OC(C(=O)O)=CC(N)C1NC(C)=O'), canonicalize('CCCN(CCc1cccc(-c2ccccc2)c1)C(=O)C1OC(C(=O)O)=CC(N)C1NC(C)=O'))
test_fail(canonicalize('CN(CCc1cccc(-c2ccccc2)c1)C(=O)C1OC(C(=O)O)=CC(N)C1NC(C)=O'), 'CCCN(CCc1cccc(-c2ccccc2)c1)C(=O)C1OC(C(=O)O)=CC(N)C1NC(C)=O')mol_from_smiles
mol_from_smiles (smi:str)
This function converts a SMILES string to a molecule.
| Type | Details | |
|---|---|---|
| smi | str | Input molecule in SMILES. |
| Returns | Mol | Output molecule. |
mol_from_smiles('CCCN(CCc1cccc(-c2ccccc2)c1)C(=O)C1OC(C(=O)O)=CC(N)C1NC(C)=O')
mol_from_smiles('CSc1cccc2sc(N3CCN(C(=O)c4ccn(C(C)C)n4)CC3)nc12')
mol_to_smiles
mol_to_smiles (mol:rdkit.Chem.rdchem.Mol, rootedAtAtom:int=None)
This function converts a molecule to a SMILES string.
| Type | Default | Details | |
|---|---|---|---|
| mol | Mol | molecule to convert into SMILES string | |
| rootedAtAtom | int | None | SMILES string rooted at the input atom |
| Returns | str | canonicalized SMILES string |
mol = mol_from_smiles('CCCN(CCc1cccc(-c2ccccc2)c1)C(=O)C1OC(C(=O)O)=CC(N)C1NC(C)=O')
mol
mol_to_smiles(mol)'CCCN(CCc1cccc(-c2ccccc2)c1)C(=O)C1OC(C(=O)O)=CC(N)C1NC(C)=O'mol_to_smiles(mol, rootedAtAtom=3)'N(CCC)(CCc1cccc(-c2ccccc2)c1)C(=O)C1OC(C(=O)O)=CC(N)C1NC(C)=O'Unit Tests
mol = mol_from_smiles('CCCN(CCc1cccc(-c2ccccc2)c1)C(=O)C1OC(C(=O)O)=CC(N)C1NC(C)=O')
mol_2 = mol_from_smiles('C(CC)N(CCc1cccc(-c2ccccc2)c1)C(=O)C1OC(C(=O)O)=CC(N)C1NC(C)=O')
test_eq(mol_to_smiles(mol), 'CCCN(CCc1cccc(-c2ccccc2)c1)C(=O)C1OC(C(=O)O)=CC(N)C1NC(C)=O')
test_eq(mol_to_smiles(mol, rootedAtAtom=3), 'N(CCC)(CCc1cccc(-c2ccccc2)c1)C(=O)C1OC(C(=O)O)=CC(N)C1NC(C)=O')
test_eq(mol_to_smiles(mol), mol_to_smiles(mol_2))root_smiles
root_smiles (smi:str, rootedAtAtom:int)
Root molecule in smiles format at a defined atom
| Type | Details | |
|---|---|---|
| smi | str | Input molecule in SMILES |
| rootedAtAtom | int | SMILES string rooted at the input atom |
| Returns | str |
root_smiles('CCCN(CCc1cccc(-c2ccccc2)c1)C(=O)C1OC(C(=O)O)=CC(N)C1NC(C)=O', rootedAtAtom=3)'N(CCC)(CCc1cccc(-c2ccccc2)c1)C(=O)C1OC(C(=O)O)=CC(N)C1NC(C)=O'root_smiles('CCCN(CCc1cccc(-c2ccccc2)c1)C(=O)C1OC(C(=O)O)=CC(N)C1NC(C)=O', rootedAtAtom=0)'CCCN(CCc1cccc(-c2ccccc2)c1)C(=O)C1OC(C(=O)O)=CC(N)C1NC(C)=O'Unit Tests
test_eq(root_smiles('CCCN(CCc1cccc(-c2ccccc2)c1)C(=O)C1OC(C(=O)O)=CC(N)C1NC(C)=O', rootedAtAtom=0), 'CCCN(CCc1cccc(-c2ccccc2)c1)C(=O)C1OC(C(=O)O)=CC(N)C1NC(C)=O')
test_eq(root_smiles('CCCN(CCc1cccc(-c2ccccc2)c1)C(=O)C1OC(C(=O)O)=CC(N)C1NC(C)=O', rootedAtAtom=3), 'N(CCC)(CCc1cccc(-c2ccccc2)c1)C(=O)C1OC(C(=O)O)=CC(N)C1NC(C)=O')