lingyuzeng
5e7b236f31
Unify macrolactone detection, numbering, fragmentation, and splicing under the installable macro_lactone_toolkit package. - replace legacy src.* modules with the new package layout - add analyze/number/fragment CLI entrypoints and pixi tasks - migrate tests, README, and scripts to the new package API
97 lines
3.1 KiB
Python
97 lines
3.1 KiB
Python
from __future__ import annotations
|
|
|
|
from dataclasses import dataclass
|
|
from typing import Mapping
|
|
|
|
from rdkit import Chem
|
|
|
|
|
|
@dataclass(frozen=True)
|
|
class BuiltMacrolactone:
|
|
mol: Chem.Mol
|
|
smiles: str
|
|
position_to_atom: dict[int, int]
|
|
|
|
|
|
def build_macrolactone(
|
|
ring_size: int,
|
|
side_chains: Mapping[int, str] | None = None,
|
|
) -> BuiltMacrolactone:
|
|
if not 12 <= ring_size <= 20:
|
|
raise ValueError("ring_size must be between 12 and 20")
|
|
|
|
side_chains = dict(side_chains or {})
|
|
rwmol = Chem.RWMol()
|
|
|
|
position_to_atom: dict[int, int] = {
|
|
1: rwmol.AddAtom(Chem.Atom("C")),
|
|
2: rwmol.AddAtom(Chem.Atom("O")),
|
|
}
|
|
for position in range(3, ring_size + 1):
|
|
position_to_atom[position] = rwmol.AddAtom(Chem.Atom("C"))
|
|
|
|
carbonyl_oxygen_idx = rwmol.AddAtom(Chem.Atom("O"))
|
|
|
|
rwmol.AddBond(position_to_atom[1], position_to_atom[2], Chem.BondType.SINGLE)
|
|
for position in range(2, ring_size):
|
|
rwmol.AddBond(
|
|
position_to_atom[position],
|
|
position_to_atom[position + 1],
|
|
Chem.BondType.SINGLE,
|
|
)
|
|
rwmol.AddBond(position_to_atom[ring_size], position_to_atom[1], Chem.BondType.SINGLE)
|
|
rwmol.AddBond(position_to_atom[1], carbonyl_oxygen_idx, Chem.BondType.DOUBLE)
|
|
|
|
for position, side_chain in side_chains.items():
|
|
if position not in position_to_atom:
|
|
raise ValueError(f"Invalid ring position: {position}")
|
|
_add_side_chain(rwmol, position_to_atom[position], side_chain)
|
|
|
|
mol = rwmol.GetMol()
|
|
Chem.SanitizeMol(mol)
|
|
return BuiltMacrolactone(
|
|
mol=mol,
|
|
smiles=Chem.MolToSmiles(mol, isomericSmiles=True),
|
|
position_to_atom=position_to_atom,
|
|
)
|
|
|
|
|
|
def build_ambiguous_smiles() -> str:
|
|
mol_12 = build_macrolactone(12).mol
|
|
mol_14 = build_macrolactone(14).mol
|
|
combined = Chem.CombineMols(mol_12, mol_14)
|
|
return Chem.MolToSmiles(combined, isomericSmiles=True)
|
|
|
|
|
|
def canonicalize(smiles_or_mol: str | Chem.Mol) -> str:
|
|
if isinstance(smiles_or_mol, Chem.Mol):
|
|
mol = smiles_or_mol
|
|
else:
|
|
mol = Chem.MolFromSmiles(smiles_or_mol)
|
|
if mol is None:
|
|
raise ValueError(f"Unable to parse SMILES: {smiles_or_mol}")
|
|
return Chem.MolToSmiles(mol, isomericSmiles=True)
|
|
|
|
|
|
def _add_side_chain(rwmol: Chem.RWMol, ring_atom_idx: int, side_chain: str) -> None:
|
|
if side_chain == "methyl":
|
|
carbon_idx = rwmol.AddAtom(Chem.Atom("C"))
|
|
rwmol.AddBond(ring_atom_idx, carbon_idx, Chem.BondType.SINGLE)
|
|
return
|
|
|
|
if side_chain == "ethyl":
|
|
carbon_1_idx = rwmol.AddAtom(Chem.Atom("C"))
|
|
carbon_2_idx = rwmol.AddAtom(Chem.Atom("C"))
|
|
rwmol.AddBond(ring_atom_idx, carbon_1_idx, Chem.BondType.SINGLE)
|
|
rwmol.AddBond(carbon_1_idx, carbon_2_idx, Chem.BondType.SINGLE)
|
|
return
|
|
|
|
if side_chain == "exocyclic_alkene":
|
|
carbon_1_idx = rwmol.AddAtom(Chem.Atom("C"))
|
|
carbon_2_idx = rwmol.AddAtom(Chem.Atom("C"))
|
|
rwmol.AddBond(ring_atom_idx, carbon_1_idx, Chem.BondType.DOUBLE)
|
|
rwmol.AddBond(carbon_1_idx, carbon_2_idx, Chem.BondType.SINGLE)
|
|
return
|
|
|
|
raise ValueError(f"Unsupported side chain: {side_chain}")
|