molecule/name.py

import requests
from rdkit import Chem

def get_pubchem_name(smiles):
    url = f"https://pubchem.ncbi.nlm.nih.gov/rest/pug/compound/smiles/{smiles}/property/IUPACName/JSON"
    r = requests.get(url)
    if r.status_code == 200:
        data = r.json()
        try:
            cid = data['PropertyTable']['Properties'][0]['CID']
            url = f"https://pubchem.ncbi.nlm.nih.gov/rest/pug/compound/cid/{cid}/synonyms/JSON"
            r = requests.get(url)
            if r.status_code == 200:
                data = r.json()
                name = data['InformationList']['Information'][0]['Synonym'][0]
                return name
        except (KeyError, IndexError):
            return None
    return None

def generate_readable_name(smiles):
    mol = Chem.MolFromSmiles(smiles)
    if mol is None:
        return "UnknownMolecule"
    atoms = [atom.GetSymbol() for atom in mol.GetAtoms()]
    # пример: C-C-O → CCO
    return "".join(atoms)

def generate_short_signature(smiles, n=6):
    mol = Chem.MolFromSmiles(smiles)
    if mol is None:
        return "MolX"
    atoms = [atom.GetSymbol() for atom in mol.GetAtoms()]
    signature = "".join(atoms[:n])
    return f"{signature}-{len(atoms)}"


def get_name(smiles):

    name = get_pubchem_name(smiles=smiles)

    if name is None:
        return "UnknownMolecule"

        try:
            name = generate_readable_name(smiles=smiles)
        except Exception:
            return "UnknownMolecule"
    return name



if __name__ == '__main__':
    smiles = "CCC1:C:C:C(CCOC2:C:C:C(CC3SC(=O)NC3=O):C:C:2):N:C:1"
    print(get_name(smiles))
    print(generate_readable_name(smiles))
    print(generate_short_signature(smiles))
    print(get_pubchem_name(smiles))