graph TD
    A[Molecular Input: SMILES/SDF] --> B[Parse + Validate Structures]
    B --> C[Calculate Descriptors]
    C --> D[Drug-likeness Filters]
    D --> E{Passes Lipinski?}
    E -->|No| F[Flag as Non-Drug-like]
    E -->|Yes| G[ADMET Prediction]
    G --> H[Virtual Screening Score]
    H --> I[Docking Preparation]
    I --> J[Ranked Candidate List]
    F --> K[Report with Flags]
    J --> K

from rdkit import Chem
from rdkit.Chem import Descriptors, AllChem, Draw, Lipinski, DataStructs
from rdkit.Chem import rdMolDescriptors
import pandas as pd

def molecular_properties(smiles: str) -> dict:
    mol = Chem.MolFromSmiles(smiles)
    if mol is None:
        raise ValueError(f"Invalid SMILES: {smiles}")
    return {
        "smiles": smiles,
        "mw": Descriptors.MolWt(mol),
        "logp": Descriptors.MolLogP(mol),
        "hbd": Descriptors.NumHDonors(mol),
        "hba": Descriptors.NumHAcceptors(mol),
        "tpsa": Descriptors.TPSA(mol),
        "rotatable_bonds": Descriptors.NumRotatableBonds(mol),
        "rings": Descriptors.RingCount(mol),
        "lipinski_violations": sum([
            Descriptors.MolWt(mol) > 500,
            Descriptors.MolLogP(mol) > 5,
            Descriptors.NumHDonors(mol) > 5,
            Descriptors.NumHAcceptors(mol) > 10,
        ]),
    }

def lipinski_filter(df: pd.DataFrame) -> pd.DataFrame:
    return df[df["lipinski_violations"] <= 1].copy()

def similarity_search(query_smiles: str, library: list[str], threshold: float = 0.7) -> list[dict]:
    query_mol = Chem.MolFromSmiles(query_smiles)
    query_fp = AllChem.GetMorganFingerprintAsBitVect(query_mol, radius=2, nBits=2048)

    results = []
    for smi in library:
        mol = Chem.MolFromSmiles(smi)
        if mol is None:
            continue
        fp = AllChem.GetMorganFingerprintAsBitVect(mol, radius=2, nBits=2048)
        tanimoto = DataStructs.TanimotoSimilarity(query_fp, fp)
        if tanimoto >= threshold:
            results.append({"smiles": smi, "tanimoto": tanimoto})

    return sorted(results, key=lambda x: -x["tanimoto"])

def admet_flags(props: dict) -> list[str]:
    flags = []
    if props["logp"] > 5:
        flags.append("High lipophilicity: poor aqueous solubility risk")
    if props["tpsa"] > 140:
        flags.append("High TPSA: poor membrane permeability risk")
    if props["mw"] > 500:
        flags.append("High MW: poor oral absorption risk")
    if props["rotatable_bonds"] > 10:
        flags.append("High flexibility: poor oral bioavailability risk")
    return flags