update app.py

app.py

@@ -79,7 +79,7 @@ smiles_image_mapping = {
     "Mol 5": {"smiles": "C=CCS[C@@H](C)CC(=O)OCC", "image": "img/img5.png"}  # Example SMILES for chloroethane
 }
 
-datasets = ["","BACE", "ESOL", "Custom Dataset"]
+datasets = [" ", "BACE", "ESOL", "Load Custom Dataset"]
 
 models_enabled = ["SELFIES-TED", "MHG-GED", "MolFormer", "SMI-TED"]
 
@@ -115,12 +115,26 @@ def evaluate_and_log(models, dataset, task_type, eval_output):
     return log_df
 
 
-log_df = pd.read_csv('log.csv', index_col=0)
+try:
+    log_df = pd.read_csv('log.csv', index_col=0)
+except:
+    log_df = pd.DataFrame({"":[],
+    'Selected Models': [],
+    'Dataset': [],
+    'Task': [],
+    'Result': []
+        })
+    csv_file_path = 'log.csv'
+    log_df.to_csv(csv_file_path, index=False)
 
 
 # Load images for selection
 def load_image(path):
-    return Image.open(smiles_image_mapping[path]["image"])# Image.1open(path)
+    try:
+        return Image.open(smiles_image_mapping[path]["image"])# Image.1open(path)
+    except:
+        pass
+
 
 
 # Function to handle image selection
@@ -199,6 +213,7 @@ def generate_canonical(smiles):
     latent_vec, mask = encode([selfie])
     gen_mol = None
     for i in range(5, 51):
+        print("Searching Latent space")
         noise = i / 10
         perturbed_latent = perturb_latent(latent_vec, noise_scale=noise)
         gen = generate(perturbed_latent, mask)
@@ -207,6 +222,7 @@ def generate_canonical(smiles):
 
     if gen_mol:
         # Calculate properties for ref and gen molecules
+        print("calculating properties")
         ref_properties = calculate_properties(smiles)
         gen_properties = calculate_properties(gen_mol)
         tanimoto_similarity = calculate_tanimoto(smiles, gen_mol)
@@ -221,6 +237,7 @@ def generate_canonical(smiles):
         df = pd.DataFrame(data)
 
         # Display molecule image of canonical smiles
+        print("Getting image")
         mol_image = smiles_to_image(gen_mol)
 
         return df, gen_mol, mol_image
@@ -393,6 +410,7 @@ def display_plot(plot_type):
 
 # Predefined dataset paths (these should be adjusted to your file paths)
 predefined_datasets = {
+    " ": " ",
     "BACE": f"./data/bace/train.csv, ./data/bace/test.csv, smiles, Class",
     "ESOL": f"./data/esol/train.csv, ./data/esol/test.csv, smiles, prop",
 }
@@ -426,16 +444,6 @@ def handle_dataset_selection(selected_dataset):
         return gr.update(visible=True), gr.update(visible=True),  gr.update(visible=True), gr.update(visible=True), gr.update(
             visible=True), gr.update(visible=False), gr.update(visible=True), gr.update(visible=True)
     else:
-        #[dataset_name, train_file, train_display, test_file, test_display, predefined_display,
-        # input_column_selector, output_column_selector]
-
-
-
-        # Load the predefined dataset from its local path
-        #return gr.update(visible=True), gr.update(visible=False), gr.update(visible=False), gr.update(visible=False), gr.update(
-        #    visible=False), gr.update(visible=False), gr.update(visible=False), gr.update(visible=False)
-        #return gr.update(visible=True), gr.update(visible=False), gr.update(visible=True), gr.update(
-        #    visible=False), gr.update(visible=True), gr.update(visible=False), gr.update(visible=False), gr.update(visible=False)
         return gr.update(visible=True), gr.update(visible=False), gr.update(visible=False), gr.update(
             visible=False), gr.update(visible=False), gr.update(visible=False), gr.update(visible=False), gr.update(visible=False)
 

models/fm4m.py

@@ -308,7 +308,8 @@ def single_modal(model,dataset, downstream_model,params):
                                 verbose=False)
             n_samples = np.minimum(1000, len(x_batch))
             features_umap = reducer.fit_transform(x_batch[:n_samples])
-            x = y_batch.values[:n_samples]
+            try:x = y_batch.values[:n_samples]
+            except:x = y_batch[:n_samples]
             index_0 = [index for index in range(len(x)) if x[index] == 0]
             index_1 = [index for index in range(len(x)) if x[index] == 1]
 
@@ -340,7 +341,8 @@ def single_modal(model,dataset, downstream_model,params):
             reducer = umap.UMAP(metric='euclidean', n_neighbors=  10, n_components=2, low_memory=True, min_dist=0.1, verbose=False)
             n_samples = np.minimum(1000,len(x_batch))
             features_umap = reducer.fit_transform(x_batch[:n_samples])
-            x = y_batch.values[:n_samples]
+            try:x = y_batch.values[:n_samples]
+            except:x = y_batch[:n_samples]
             index_0 = [index for index in range(len(x)) if x[index] == 0]
             index_1 = [index for index in range(len(x)) if x[index] == 1]
 
@@ -371,7 +373,8 @@ def single_modal(model,dataset, downstream_model,params):
                             verbose=False)
         n_samples = np.minimum(1000, len(x_batch))
         features_umap = reducer.fit_transform(x_batch[:n_samples])
-        x = y_batch.values[:n_samples]
+        try:x = y_batch.values[:n_samples]
+        except:x = y_batch[:n_samples]
         #index_0 = [index for index in range(len(x)) if x[index] == 0]
         #index_1 = [index for index in range(len(x)) if x[index] == 1]
 
@@ -398,7 +401,8 @@ def single_modal(model,dataset, downstream_model,params):
                             verbose=False)
         n_samples = np.minimum(1000, len(x_batch))
         features_umap = reducer.fit_transform(x_batch[:n_samples])
-        x = y_batch.values[:n_samples]
+        try:x = y_batch.values[:n_samples]
+        except:x = y_batch[:n_samples]
         # index_0 = [index for index in range(len(x)) if x[index] == 0]
         # index_1 = [index for index in range(len(x)) if x[index] == 1]
 
@@ -426,7 +430,8 @@ def single_modal(model,dataset, downstream_model,params):
                             verbose=False)
         n_samples = np.minimum(1000, len(x_batch))
         features_umap = reducer.fit_transform(x_batch[:n_samples])
-        x = y_batch.values[:n_samples]
+        try:x = y_batch.values[:n_samples]
+        except:x = y_batch[:n_samples]
         # index_0 = [index for index in range(len(x)) if x[index] == 0]
         # index_1 = [index for index in range(len(x)) if x[index] == 1]
 
@@ -454,7 +459,8 @@ def single_modal(model,dataset, downstream_model,params):
                             verbose=False)
         n_samples = np.minimum(1000, len(x_batch))
         features_umap = reducer.fit_transform(x_batch[:n_samples])
-        x = y_batch.values[:n_samples]
+        try:x = y_batch.values[:n_samples]
+        except:x = y_batch[:n_samples]
         # index_0 = [index for index in range(len(x)) if x[index] == 0]
         # index_1 = [index for index in range(len(x)) if x[index] == 1]
 
@@ -546,7 +552,8 @@ def multi_modal(model_list,dataset, downstream_model,params):
         features_umap = reducer.fit_transform(x_batch[:n_samples])
 
         if "Classifier" in downstream_model:
-            x = y_batch.values[:n_samples]
+            try:x = y_batch.values[:n_samples]
+            except: x = y_batch[:n_samples]
             index_0 = [index for index in range(len(x)) if x[index] == 0]
             index_1 = [index for index in range(len(x)) if x[index] == 1]