{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "# Neural Fingerprints\n", "\n", "We create atom, bond, and edge tensors from molecule SMILES using `chemml.chem.tensorize_molecules` in order to build neural fingerprints using `chemml.models.NeuralGraphHidden` and `chemml.models.NeuralGraphOutput` modules. These neural fingerprints are then used as features to train a simple feed forward neural network to predict densities of small organic compounds using tensorflow. \n", "\n", "Here we import a sample dataset from ChemML library which has the SMILES codes for 500 small organic molecules with their densities in $kg/m^3$. " ] }, { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [], "source": [ "import numpy as np\n", "from chemml.datasets import load_organic_density\n", "molecules, target, dragon_subset = load_organic_density()\n", "target = np.asarray(target['density_Kg/m3'])" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Building `chemml.chem.Molecule` objects from molecule SMILES. " ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [], "source": [ "from chemml.chem import Molecule\n", "mol_objs_list = []\n", "for smi in molecules['smiles']:\n", " mol = Molecule(smi, 'smiles')\n", " mol.hydrogens('add')\n", " mol.to_xyz('MMFF', maxIters=10000, mmffVariant='MMFF94s')\n", " mol_objs_list.append(mol)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Molecule tensors can be used to create neural graph fingerprints using `chemml.models`" ] }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Tensorising molecules in batches of 100 ...\n", "\u001b[1m500/500\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m8s\u001b[0m 16ms/step \n", "Merging batch tensors ... [DONE]\n" ] } ], "source": [ "from chemml.chem import tensorise_molecules\n", "xatoms, xbonds, xedges = tensorise_molecules(molecules=mol_objs_list, max_degree=5, \n", " max_atoms=None, n_jobs=-1, batch_size=100, verbose=True)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Splitting and preprocessing the data" ] }, { "cell_type": "code", "execution_count": 4, "metadata": {}, "outputs": [], "source": [ "from sklearn.model_selection import ShuffleSplit\n", "from sklearn.preprocessing import StandardScaler\n", "y_scale = StandardScaler()\n", "rs = ShuffleSplit(n_splits=1, test_size=.20, random_state=42)\n", "\n", "for train, test in rs.split(mol_objs_list):\n", " xatoms_train = xatoms[train]\n", " xatoms_test = xatoms[test]\n", " xbonds_train = xbonds[train]\n", " xbonds_test = xbonds[test]\n", " xedges_train = xedges[train]\n", " xedges_test = xedges[test]\n", " target_train = target[train]\n", " target_test = target[test]\n", " target_train = y_scale.fit_transform(target_train.reshape(-1,1))" ] }, { "cell_type": "code", "execution_count": 5, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Training data:\n", "\n", "Atoms: (400, 57, 62)\n", "Bonds: (400, 57, 5, 6)\n", "Edges: (400, 57, 5)\n", "Target: (400, 1)\n", "\n", "Testing data:\n", "\n", "Atoms: (100, 57, 62)\n", "Bonds: (100, 57, 5, 6)\n", "Edges: (100, 57, 5)\n", "Target: (100,)\n" ] } ], "source": [ "print('Training data:\\n')\n", "print('Atoms: ',xatoms_train.shape)\n", "print('Bonds: ',xbonds_train.shape)\n", "print('Edges: ',xedges_train.shape)\n", "print('Target: ',target_train.shape)\n", "\n", "print('\\nTesting data:\\n')\n", "print('Atoms: ',xatoms_test.shape)\n", "print('Bonds: ',xbonds_test.shape)\n", "print('Edges: ',xedges_test.shape)\n", "print('Target: ',target_test.shape)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Building the Neural Fingerprints\n", "\n", "The atom, bond, and edge tensors are used here to build 200 neural fingerprints of width 8 (i.e., the size atomic neighborhood which will be considered in the convolution process). " ] }, { "cell_type": "code", "execution_count": 6, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Neural Fingerprint Shape: (None, 200)\n" ] } ], "source": [ "from chemml.models import NeuralGraphHidden, NeuralGraphOutput\n", "from tensorflow.keras.layers import Input, add\n", "import tensorflow as tf\n", "tf.random.set_seed(42)\n", "\n", "conv_width = 8\n", "fp_length = 200\n", "\n", "num_molecules = xatoms_train.shape[0]\n", "max_atoms = xatoms_train.shape[1]\n", "max_degree = xbonds_train.shape[2]\n", "num_atom_features = xatoms_train.shape[-1]\n", "num_bond_features = xbonds_train.shape[-1]\n", "\n", "# Creating input layers for atoms ,bonds and edge information\n", "atoms0 = Input(name='atom_inputs', shape=(max_atoms, num_atom_features),batch_size=None)\n", "bonds = Input(name='bond_inputs', shape=(max_atoms, max_degree, num_bond_features),batch_size=None)\n", "edges = Input(name='edge_inputs', shape=(max_atoms, max_degree), dtype='int32',batch_size=None)\n", "\n", "# Defining the convolved atom feature layers \n", "atoms1 = NeuralGraphHidden(conv_width, activation='relu', use_bias=False)([atoms0, bonds, edges])\n", "atoms2 = NeuralGraphHidden(conv_width, activation='relu', use_bias=False)([atoms1, bonds, edges])\n", "\n", "# Defining the outputs of each (convolved) atom feature layer to fingerprint\n", "fp_out0 = NeuralGraphOutput(fp_length, activation='softmax')([atoms0,bonds,edges])\n", "fp_out1 = NeuralGraphOutput(fp_length, activation='softmax')([atoms1,bonds,edges])\n", "fp_out2 = NeuralGraphOutput(fp_length, activation='softmax')([atoms2,bonds,edges])\n", "\n", "# Sum outputs to obtain fingerprint \n", "final_fp = add([fp_out0, fp_out1, fp_out2])\n", "print('Neural Fingerprint Shape: ',final_fp.shape)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Building and training the neural network\n", "\n", "Here, we build and train a simple feed forward neural network using `tensorflow.keras` and provide our neural fingerprints as features. " ] }, { "cell_type": "code", "execution_count": 7, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "WARNING:tensorflow:TensorFlow GPU support is not available on native Windows for TensorFlow >= 2.11. Even if CUDA/cuDNN are installed, GPU will not be used. Please use WSL2 or the TensorFlow-DirectML plugin.\n" ] }, { "data": { "text/html": [ "
Model: \"functional\"\n",
       "
\n" ], "text/plain": [ "\u001b[1mModel: \"functional\"\u001b[0m\n" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [ "
┏━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━┓\n",
       "┃ Layer (type)        ┃ Output Shape      ┃    Param # ┃ Connected to      ┃\n",
       "┡━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━┩\n",
       "│ atom_inputs         │ (None, 57, 62)    │          0 │ -                 │\n",
       "│ (InputLayer)        │                   │            │                   │\n",
       "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
       "│ bond_inputs         │ (None, 57, 5, 6)  │          0 │ -                 │\n",
       "│ (InputLayer)        │                   │            │                   │\n",
       "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
       "│ edge_inputs         │ (None, 57, 5)     │          0 │ -                 │\n",
       "│ (InputLayer)        │                   │            │                   │\n",
       "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
       "│ neural_graph_hidden │ (None, 57, 8)     │      2,720 │ atom_inputs[0][0… │\n",
       "│ (NeuralGraphHidden) │                   │            │ bond_inputs[0][0… │\n",
       "│                     │                   │            │ edge_inputs[0][0] │\n",
       "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
       "│ neural_graph_hidde… │ (None, 57, 8)     │        560 │ neural_graph_hid… │\n",
       "│ (NeuralGraphHidden) │                   │            │ bond_inputs[0][0… │\n",
       "│                     │                   │            │ edge_inputs[0][0] │\n",
       "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
       "│ neural_graph_output │ (None, 200)       │     13,800 │ atom_inputs[0][0… │\n",
       "│ (NeuralGraphOutput) │                   │            │ bond_inputs[0][0… │\n",
       "│                     │                   │            │ edge_inputs[0][0] │\n",
       "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
       "│ neural_graph_outpu… │ (None, 200)       │      3,000 │ neural_graph_hid… │\n",
       "│ (NeuralGraphOutput) │                   │            │ bond_inputs[0][0… │\n",
       "│                     │                   │            │ edge_inputs[0][0] │\n",
       "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
       "│ neural_graph_outpu… │ (None, 200)       │      3,000 │ neural_graph_hid… │\n",
       "│ (NeuralGraphOutput) │                   │            │ bond_inputs[0][0… │\n",
       "│                     │                   │            │ edge_inputs[0][0] │\n",
       "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
       "│ add (Add)           │ (None, 200)       │          0 │ neural_graph_out… │\n",
       "│                     │                   │            │ neural_graph_out… │\n",
       "│                     │                   │            │ neural_graph_out… │\n",
       "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
       "│ dense_layer0        │ (None, 128)       │     25,728 │ add[0][0]         │\n",
       "│ (Dense)             │                   │            │                   │\n",
       "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
       "│ dense_layer1        │ (None, 64)        │      8,256 │ dense_layer0[0][… │\n",
       "│ (Dense)             │                   │            │                   │\n",
       "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
       "│ main_prediction     │ (None, 1)         │         65 │ dense_layer1[0][… │\n",
       "│ (Dense)             │                   │            │                   │\n",
       "└─────────────────────┴───────────────────┴────────────┴───────────────────┘\n",
       "
\n" ], "text/plain": [ "┏━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━┓\n", "┃\u001b[1m \u001b[0m\u001b[1mLayer (type) \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m Param #\u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mConnected to \u001b[0m\u001b[1m \u001b[0m┃\n", "┡━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━┩\n", "│ atom_inputs │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m57\u001b[0m, \u001b[38;5;34m62\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │ - │\n", "│ (\u001b[38;5;33mInputLayer\u001b[0m) │ │ │ │\n", "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n", "│ bond_inputs │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m57\u001b[0m, \u001b[38;5;34m5\u001b[0m, \u001b[38;5;34m6\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │ - │\n", "│ (\u001b[38;5;33mInputLayer\u001b[0m) │ │ │ │\n", "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n", "│ edge_inputs │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m57\u001b[0m, \u001b[38;5;34m5\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │ - │\n", "│ (\u001b[38;5;33mInputLayer\u001b[0m) │ │ │ │\n", "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n", "│ neural_graph_hidden │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m57\u001b[0m, \u001b[38;5;34m8\u001b[0m) │ \u001b[38;5;34m2,720\u001b[0m │ atom_inputs[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m… │\n", "│ (\u001b[38;5;33mNeuralGraphHidden\u001b[0m) │ │ │ bond_inputs[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m… │\n", "│ │ │ │ edge_inputs[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n", "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n", "│ neural_graph_hidde… │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m57\u001b[0m, \u001b[38;5;34m8\u001b[0m) │ \u001b[38;5;34m560\u001b[0m │ neural_graph_hid… │\n", "│ (\u001b[38;5;33mNeuralGraphHidden\u001b[0m) │ │ │ bond_inputs[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m… │\n", "│ │ │ │ edge_inputs[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n", "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n", "│ neural_graph_output │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m200\u001b[0m) │ \u001b[38;5;34m13,800\u001b[0m │ atom_inputs[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m… │\n", "│ (\u001b[38;5;33mNeuralGraphOutput\u001b[0m) │ │ │ bond_inputs[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m… │\n", "│ │ │ │ edge_inputs[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n", "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n", "│ neural_graph_outpu… │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m200\u001b[0m) │ \u001b[38;5;34m3,000\u001b[0m │ neural_graph_hid… │\n", "│ (\u001b[38;5;33mNeuralGraphOutput\u001b[0m) │ │ │ bond_inputs[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m… │\n", "│ │ │ │ edge_inputs[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n", "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n", "│ neural_graph_outpu… │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m200\u001b[0m) │ \u001b[38;5;34m3,000\u001b[0m │ neural_graph_hid… │\n", "│ (\u001b[38;5;33mNeuralGraphOutput\u001b[0m) │ │ │ bond_inputs[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m… │\n", "│ │ │ │ edge_inputs[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n", "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n", "│ add (\u001b[38;5;33mAdd\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m200\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │ neural_graph_out… │\n", "│ │ │ │ neural_graph_out… │\n", "│ │ │ │ neural_graph_out… │\n", "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n", "│ dense_layer0 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m) │ \u001b[38;5;34m25,728\u001b[0m │ add[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n", "│ (\u001b[38;5;33mDense\u001b[0m) │ │ │ │\n", "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n", "│ dense_layer1 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m64\u001b[0m) │ \u001b[38;5;34m8,256\u001b[0m │ dense_layer0[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m…\u001b[0m │\n", "│ (\u001b[38;5;33mDense\u001b[0m) │ │ │ │\n", "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n", "│ main_prediction │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m1\u001b[0m) │ \u001b[38;5;34m65\u001b[0m │ dense_layer1[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m…\u001b[0m │\n", "│ (\u001b[38;5;33mDense\u001b[0m) │ │ │ │\n", "└─────────────────────┴───────────────────┴────────────┴───────────────────┘\n" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [ "
 Total params: 57,129 (223.16 KB)\n",
       "
\n" ], "text/plain": [ "\u001b[1m Total params: \u001b[0m\u001b[38;5;34m57,129\u001b[0m (223.16 KB)\n" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [ "
 Trainable params: 57,129 (223.16 KB)\n",
       "
\n" ], "text/plain": [ "\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m57,129\u001b[0m (223.16 KB)\n" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [ "
 Non-trainable params: 0 (0.00 B)\n",
       "
\n" ], "text/plain": [ "\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/plain": [ "" ] }, "execution_count": 7, "metadata": {}, "output_type": "execute_result" } ], "source": [ "from tensorflow.keras import Model\n", "from tensorflow.keras.layers import Dense\n", "\n", "# Build and compile model for regression.\n", "dense_layer0 = Dense(128,activation='relu',name='dense_layer0',\n", " kernel_regularizer=tf.keras.regularizers.l2(0.01))(final_fp)\n", "dense_layer1 = Dense(64,activation='relu',name='dense_layer1',\n", " kernel_regularizer=tf.keras.regularizers.l2(0.01))(dense_layer0)\n", "dense_layer2 = Dense(32,activation='relu',name='dense_layer2',\n", " kernel_regularizer=tf.keras.regularizers.l2(0.01))(dense_layer1)\n", "\n", "main_prediction = Dense(1, activation='linear', name='main_prediction')(dense_layer1)\n", "model = Model(inputs=[atoms0, bonds, edges], outputs=[main_prediction])\n", "model.compile(optimizer='adam', loss='mae')\n", "\n", "# Show summary\n", "model.summary()\n", "\n", "model.fit([xatoms_train, xbonds_train, xedges_train], target_train, epochs=50,\n", " steps_per_epoch=None, batch_size=None,verbose=False,validation_split=0.1)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Predicting the density of the molecules in our test data and evaluating our model based on it. " ] }, { "cell_type": "code", "execution_count": 8, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\u001b[1m4/4\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 1s/step \n", "Mean Absolute Error = 15.303 kg/m^3\n", "R squared = 0.945\n" ] } ], "source": [ "from chemml.utils import regression_metrics\n", "\n", "y_pred = model.predict([xatoms_test,xbonds_test,xedges_test])\n", "y_pred = y_scale.inverse_transform(y_pred)\n", "metrics_df = regression_metrics(target_test, list(y_pred.reshape(-1,)))\n", "mae = metrics_df['MAE'].values[0]\n", "r_2 = metrics_df['r_squared'].values[0]\n", "\n", "print(\"Mean Absolute Error = {} kg/m^3\".format(mae.round(3)))\n", "print(\"R squared = {}\".format(r_2.round(3)))" ] }, { "cell_type": "code", "execution_count": 9, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
MEMAEMSERMSEMSLERMSLEMAPEMaxAPERMSPEMPEMaxAEdeltaMaxEr_squaredstd
0-6.1778915.302616419.63545820.4850060.0002860.0169181.2383287.2434671.715904-0.52676972.840308111.7014360.94533887.617825
\n", "
" ], "text/plain": [ " ME MAE MSE RMSE MSLE RMSLE MAPE \\\n", "0 -6.17789 15.302616 419.635458 20.485006 0.000286 0.016918 1.238328 \n", "\n", " MaxAPE RMSPE MPE MaxAE deltaMaxE r_squared std \n", "0 7.243467 1.715904 -0.526769 72.840308 111.701436 0.945338 87.617825 " ] }, "execution_count": 9, "metadata": {}, "output_type": "execute_result" } ], "source": [ "metrics_df" ] } ], "metadata": { "kernelspec": { "display_name": "nitin_py312_env", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.12.13" }, "widgets": { "application/vnd.jupyter.widget-state+json": { "state": {}, "version_major": 2, "version_minor": 0 } } }, "nbformat": 4, "nbformat_minor": 2 }