PR: Consolidate NODE as the Single Neural Tabular Path (CheMeleon + NODE)

.github/workflows/workflow.yml

@@ -62,7 +62,9 @@ jobs:
         uses: ./.github/actions/setup-uv-env
         with:
           python-version: ${{ matrix.python-version }}
-          install-args: "--extra rna --extra report --extra tabpfn --extra tabicl --extra clustering --group test_duration"
+          install-args: >-
+            --extra rna --extra report --extra tabpfn --extra tabicl
+            --extra node --extra clustering --group test_duration
 
       - name: Cache HuggingFace and Torch models 🗂️
         uses: actions/cache@v4
@@ -116,7 +118,9 @@ jobs:
         uses: ./.github/actions/setup-uv-env
         with:
           python-version: ${{ env.PYTHON_VERSION }}
-          install-args: "--extra rna --extra report --extra tabpfn --extra tabicl --extra clustering --group test_duration"
+          install-args: >-
+            --extra rna --extra report --extra tabpfn --extra tabicl
+            --extra node --extra clustering --group test_duration
 
       - name: Cache HuggingFace and Torch models 🗂️
         uses: actions/cache@v4

examples/notebooks/04_feature_engineering/04_chemeleon_fingerprints.ipynb

@@ -0,0 +1,97 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "7ab185ba",
+   "metadata": {},
+   "source": [
+    "# CheMeleon GNN Fingerprints\n",
+    "\n",
+    "This notebook demonstrates how to generate CheMeleon molecular embeddings from SMILES using Mother."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "2457164a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import numpy as np\n",
+    "from rdkit import Chem\n",
+    "\n",
+    "from mother.feature_generation.fp_gnn_gen import CheMeleonFingerprintFactory"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "17278c7c",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Embedding matrix shape: (3, 2048)\n",
+      "Dtype: float32\n",
+      "First row (first 8 values): [0. 0. 0. 0. 0. 0. 0. 0.]\n"
+     ]
+    }
+   ],
+   "source": [
+    "smiles = [\"CCO\", \"c1ccccc1\", \"CC(=O)O\"]\n",
+    "mols = [Chem.MolFromSmiles(s) for s in smiles]\n",
+    "mols_array = np.array(mols, dtype=object)\n",
+    "\n",
+    "checkpoint_path = \"path/to/chemeleon/checkpoint.pt\"  # Replace with your local chemprop checkpoint path.\n",
+    "factory = CheMeleonFingerprintFactory(\n",
+    "    output_dim=2048,\n",
+    "    batch_size=128,\n",
+    "    checkpoint_path=checkpoint_path,\n",
+    "    device=\"cpu\",\n",
+    ")\n",
+    "transformer = factory.get_fingerprint_generator()\n",
+    "embeddings = transformer.fit_transform(mols_array)\n",
+    "\n",
+    "print(\"Embedding matrix shape:\", embeddings.shape)\n",
+    "print(\"Dtype:\", embeddings.dtype)\n",
+    "print(\"First row (first 8 values):\", np.round(embeddings[0][:8], 4))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "20d687a9",
+   "metadata": {},
+   "source": [
+    "## Notes\n",
+    "\n",
+    "- Install dependencies before using CheMeleon embeddings (e.g. `pip install 'mother-ml[chemprop]'` or `pip install chemprop`).\n",
+    "- If `checkpoint_path=None`, the transformer calls `get_default_chemeleon_checkpoint()` which auto-downloads `chemeleon_mp.pt` from Zenodo on first use and caches it in `~/.cache/mother/`.\n",
+    "- Input to the transformer should be RDKit molecule objects, matching other fingerprint generators.\n",
+    "- Invalid molecules are returned as rows with `NaN` values.\n"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "mother-ml (3.13.14)",
+   "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": "3.13.14"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}