Editing Ai Natural Sciences (section)

== <span style="color: #FFFFFF;">Applying</span> ==
'''Predicting molecular properties with a graph neural network:'''

<syntaxhighlight lang="python">
from torch_geometric.data import Data, DataLoader
from torch_geometric.nn import GCNConv, global_mean_pool
import torch
import torch.nn.functional as F
from rdkit import Chem
from rdkit.Chem import AllChem

def mol_to_graph(smiles: str):
    """Convert a SMILES string to a PyG graph."""
    mol = Chem.MolFromSmiles(smiles)
    if mol is None:
        return None

    # Node features: atomic number, degree, formal charge, aromaticity
    node_features = []
    for atom in mol.GetAtoms():
        node_features.append([
            atom.GetAtomicNum(),
            atom.GetDegree(),
            atom.GetFormalCharge(),
            int(atom.GetIsAromatic()),
        ])

    # Edge index (bonds)
    edges = []
    for bond in mol.GetBonds():
        i, j = bond.GetBeginAtomIdx(), bond.GetEndAtomIdx()
        edges.extend([[i, j], [j, i]])  # undirected → bidirectional

    x = torch.tensor(node_features, dtype=torch.float)
    edge_index = torch.tensor(edges, dtype=torch.long).t().contiguous()
    return Data(x=x, edge_index=edge_index)

class MolecularGNN(torch.nn.Module):
    def __init__(self, node_features=4, hidden=128, output=1):
        super().__init__()
        self.conv1 = GCNConv(node_features, hidden)
        self.conv2 = GCNConv(hidden, hidden)
        self.conv3 = GCNConv(hidden, hidden)
        self.fc = torch.nn.Linear(hidden, output)

    def forward(self, data):
        x, edge_index, batch = data.x, data.edge_index, data.batch
        x = F.relu(self.conv1(x, edge_index))
        x = F.relu(self.conv2(x, edge_index))
        x = F.relu(self.conv3(x, edge_index))
        x = global_mean_pool(x, batch)  # Graph-level representation
        return self.fc(x)  # Predict property (e.g., solubility, toxicity)

# Example: train on QM9 molecular property dataset
# from torch_geometric.datasets import QM9
# dataset = QM9(root='data/QM9')
</syntaxhighlight>

; AI in natural sciences: application map
: '''Biology''' → AlphaFold (protein structure), ESMFold, protein language models (ESM-2)
: '''Chemistry''' → GNN for property prediction, diffusion for molecule generation, retrosynthesis
: '''Drug discovery''' → Target identification, ADMET prediction, de novo drug design, DiffDock
: '''Climate''' → GraphCast (weather forecasting), ClimateBench, climate emulators
: '''Materials''' → Crystal structure prediction (GNoME, MEGNet), property optimization
: '''Astronomy''' → Gravitational wave detection, galaxy classification, dark matter mapping
: '''Physics''' → PINNs for PDE solving, neural operators (FNO), scientific simulation surrogate models
</div>

<div style="background-color: #8B4500; color: #FFFFFF; padding: 20px; border-radius: 8px; margin-bottom: 15px;">