Update README.md

README.md

@@ -1,70 +1,77 @@
-
-# De Novo Drug Generator - RNN-VAE
-
-De Novo Drug Generator - RNN-VAE is a deep learning model designed for generating novel drug molecules.
-Training data from ChemBL library
-
-Full project file at https://github.com/teohyc/drug_agent
-
-
-## Usage 
-
-```python
-from rdkit import Chem
-from rdkit.Chem import Draw, Descriptors
-from tree_rnn_vae_infer import generate_candidate_mol
-from tree_rnn_vae_model import TreeEncoder, LatentHead, TreeVAE, TreeDecoder
-
-
-def compute_molecule_props(mol):
-    return {
-        "MW": Descriptors.MolWt(mol),
-        "logP": Descriptors.MolLogP(mol),
-        "HBD": Descriptors.NumHDonors(mol),
-        "HBA": Descriptors.NumHAcceptors(mol),
-    }
-
-
-# display molecule
-def render_molecule_grid(selected):
-    if not selected:
-        return
-
-    mols, legends = [], []
-
-    if isinstance(selected, dict):
-        iterable = selected.items()
-    else:
-        iterable = enumerate(selected, 1)
-
-    for i, item in iterable:
-        if isinstance(selected, dict):
-            smi, props = i, item
-        else:
-            smi, props = item, None
-
-        mol = Chem.MolFromSmiles(smi)
-        if mol:
-            mols.append(mol)
-            if props is None:
-                props = compute_molecule_props(mol)
-            legends.append(
-                f"M{i}
-MW={props['MW']:.0f}, logP={props['logP']:.2f}, "
-                f"HBD={props['HBD']}, HBA={props['HBA']}"
-            )
-
-    img = Draw.MolsToGridImage(
-        mols,
-        molsPerRow=3,
-        subImgSize=(400, 400),
-        legends=legends,
-        useSVG=False,
-    )
-    return img
-
-
-molecules = generate_candidate_mol(num_samples=6, max_len=20) #change to your desired molecule size and number
-img = render_molecule_grid(molecules)
-img.show()
+---
+license: mit
+language:
+- en
+tags:
+- PyTorch
+---
+
+# De Novo Drug Generator - RNN-VAE
+
+De Novo Drug Generator - RNN-VAE is a deep learning model designed for generating novel drug molecules.
+Training data from ChemBL library
+
+Full project file at https://github.com/teohyc/drug_agent
+
+
+## Usage 
+
+```python
+from rdkit import Chem
+from rdkit.Chem import Draw, Descriptors
+from tree_rnn_vae_infer import generate_candidate_mol
+from tree_rnn_vae_model import TreeEncoder, LatentHead, TreeVAE, TreeDecoder
+
+
+def compute_molecule_props(mol):
+    return {
+        "MW": Descriptors.MolWt(mol),
+        "logP": Descriptors.MolLogP(mol),
+        "HBD": Descriptors.NumHDonors(mol),
+        "HBA": Descriptors.NumHAcceptors(mol),
+    }
+
+
+# display molecule
+def render_molecule_grid(selected):
+    if not selected:
+        return
+
+    mols, legends = [], []
+
+    if isinstance(selected, dict):
+        iterable = selected.items()
+    else:
+        iterable = enumerate(selected, 1)
+
+    for i, item in iterable:
+        if isinstance(selected, dict):
+            smi, props = i, item
+        else:
+            smi, props = item, None
+
+        mol = Chem.MolFromSmiles(smi)
+        if mol:
+            mols.append(mol)
+            if props is None:
+                props = compute_molecule_props(mol)
+            legends.append(
+                f"M{i}
+MW={props['MW']:.0f}, logP={props['logP']:.2f}, "
+                f"HBD={props['HBD']}, HBA={props['HBA']}"
+            )
+
+    img = Draw.MolsToGridImage(
+        mols,
+        molsPerRow=3,
+        subImgSize=(400, 400),
+        legends=legends,
+        useSVG=False,
+    )
+    return img
+
+
+molecules = generate_candidate_mol(num_samples=6, max_len=20) #change to your desired molecule size and number
+img = render_molecule_grid(molecules)
+img.show()
 ```