app.py

from huggingface_hub import from_pretrained_keras
import gradio as gr
from rdkit import Chem, RDLogger
from rdkit.Chem.Draw import IPythonConsole, MolsToGridImage
import numpy as np
import tensorflow as tf
from tensorflow import keras

# Config 
NUM_ATOMS = 9  # Maximum number of atoms
ATOM_DIM = 4 + 1  # Number of atom types
BOND_DIM = 4 + 1  # Number of bond types
LATENT_DIM = 64  # Size of the latent space
RDLogger.DisableLog("rdApp.*")

def graph_to_molecule(graph):
    # Unpack graph
    adjacency, features = graph

    # RWMol is a molecule object intended to be edited
    molecule = Chem.RWMol()

    # Remove "no atoms" & atoms with no bonds
    keep_idx = np.where(
        (np.argmax(features, axis=1) != ATOM_DIM - 1)
        & (np.sum(adjacency[:-1], axis=(0, 1)) != 0)
    )[0]
    features = features[keep_idx]
    adjacency = adjacency[:, keep_idx, :][:, :, keep_idx]

    # Add atoms to molecule
    for atom_type_idx in np.argmax(features, axis=1):
        atom = Chem.Atom(atom_mapping[atom_type_idx])
        _ = molecule.AddAtom(atom)

    # Add bonds between atoms in molecule; based on the upper triangles
    # of the [symmetric] adjacency tensor
    (bonds_ij, atoms_i, atoms_j) = np.where(np.triu(adjacency) == 1)
    for (bond_ij, atom_i, atom_j) in zip(bonds_ij, atoms_i, atoms_j):
        if atom_i == atom_j or bond_ij == BOND_DIM - 1:
            continue
        bond_type = bond_mapping[bond_ij]
        molecule.AddBond(int(atom_i), int(atom_j), bond_type)

    # Sanitize the molecule; for more information on sanitization, see
    # https://www.rdkit.org/docs/RDKit_Book.html#molecular-sanitization
    flag = Chem.SanitizeMol(molecule, catchErrors=True)
    # Let's be strict. If sanitization fails, return None
    if flag != Chem.SanitizeFlags.SANITIZE_NONE:
        return None

    return molecule
    
generator = from_pretrained_keras("keras-io/wgan-molecular-graphs")

def predict(num_mol):
    samples = num_mol*2
    z = tf.random.normal((samples, LATENT_DIM))
    graph = generator.predict(z)
    # obtain one-hot encoded adjacency tensor
    adjacency = tf.argmax(graph[0], axis=1)
    adjacency = tf.one_hot(adjacency, depth=BOND_DIM, axis=1)
    # Remove potential self-loops from adjacency
    adjacency = tf.linalg.set_diag(adjacency, tf.zeros(tf.shape(adjacency)[:-1]))
    # obtain one-hot encoded feature tensor
    features = tf.argmax(graph[1], axis=2)
    features = tf.one_hot(features, depth=ATOM_DIM, axis=2)
    molecules = [
        graph_to_molecule([adjacency[i].numpy(), features[i].numpy()])
        for i in range(samples)
    ]
    MolsToGridImage(
        [m for m in molecules if m is not None][:num_mol], molsPerRow=5, subImgSize=(150, 150), returnPNG=False, 
    ).save("img.png")
    return 'img.png'

gr.Interface(
    predict,
    inputs=[
        gr.inputs.Slider(5, 50, label='Number of Molecular Graphs', step=5, default=10),
    ],
    outputs="image",
).launch(debug=True)