update models

app.py

@@ -72,8 +72,8 @@ for k, v in {
 ASSETS_MODELS = ASSETS / "models";        ASSETS_MODELS.mkdir(parents=True, exist_ok=True)
 ASSETS_DATA   = ASSETS / "training_data_cleaned"; ASSETS_DATA.mkdir(parents=True, exist_ok=True)
 
-MODEL_REPO = "ChatterjeeLab/Classifier_Weight"       # model repo
-DATASET_REPO = "ChatterjeeLab/Classifier_Weight"        # dataset repo
+MODEL_REPO = "ChatterjeeLab/PeptiVerse"       # model repo
+DATASET_REPO = "ChatterjeeLab/PeptiVerse"        # dataset repo
 
 def fetch_models_and_data():
     snapshot_download(

best_models.txt

@@ -5,6 +5,6 @@ Solubility, CNN, -, Classifier, 0.377, -,
 Permeability (Penetrance), XGB, -, Classifier, 0.4301, -, 
 Toxicity, -, Transformer, Classifier, -, 0.3401, 
 Binding_affinity, unpooled, unpooled, Regression, -, -, 
-Permeability_PAMPA, -, Transformer, Regression, -, -, 
-Permeability_CACO2, -, Transformer, Regression, -, -, 
-Halflife, xgb_wt_log, xgb_smiles, Regression, -, -, 
+Permeability_PAMPA, -, CNN, Regression, -, -, 
+Permeability_CACO2, -, SVR, Regression, -, -, 
+Halflife, transformer_wt_log, xgb_smiles, Regression, -, -, 

description.md

@@ -8,85 +8,27 @@
                 
 ### Training Data Collection
 
-<table>
-  <caption><strong>Data distribution.</strong> Classification tasks report counts for class 0/1; regression tasks report total sample size (N).</caption>
-  <thead>
-    <tr>
-      <th rowspan="2"><strong>Properties</strong></th>
-      <th colspan="2"><strong>Amino Acid Sequences</strong></th>
-      <th colspan="2"><strong>SMILES Sequences</strong></th>
-    </tr>
-    <tr>
-      <th><strong>0</strong></th>
-      <th><strong>1</strong></th>
-      <th><strong>0</strong></th>
-      <th><strong>1</strong></th>
-    </tr>
-  </thead>
-  <tbody>
-    <tr>
-      <td colspan="5"><strong>Classification</strong></td>
-    </tr>
-    <tr>
-      <td>Hemolysis</td>
-      <td>4765</td>
-      <td>1311</td>
-      <td>4765</td>
-      <td>1311</td>
-    </tr>
-    <tr>
-      <td>Non-Fouling</td>
-      <td>13580</td>
-      <td>3600</td>
-      <td>13580</td>
-      <td>3600</td>
-    </tr>
-    <tr>
-      <td>Solubility</td>
-      <td>9668</td>
-      <td>8785</td>
-      <td>-</td>
-      <td>-</td>
-    </tr>
-    <tr>
-      <td>Permeability (Penetrance)</td>
-      <td>1162</td>
-      <td>1162</td>
-      <td>-</td>
-      <td>-</td>
-    </tr>
-    <tr>
-      <td>Toxicity</td>
-      <td>-</td>
-      <td>-</td>
-      <td>5518</td>
-      <td>5518</td>
-    </tr>
-    <tr>
-      <td colspan="5"><strong>Regression (N)</strong></td>
-    </tr>
-    <tr>
-      <td>Permeability (PAMPA)</td>
-      <td colspan="2" align="center">-</td>
-      <td colspan="2" align="center">6869</td>
-    </tr>
-    <tr>
-      <td>Permeability (CACO2)</td>
-      <td colspan="2" align="center">-</td>
-      <td colspan="2" align="center">606</td>
-    </tr>
-    <tr>
-      <td>Half-Life</td>
-      <td colspan="2" align="center">130</td>
-      <td colspan="2" align="center">245</td>
-    </tr>
-    <tr>
-      <td>Binding Affinity</td>
-      <td colspan="2" align="center">1436</td>
-      <td colspan="2" align="center">1597</td>
-    </tr>
-  </tbody>
-</table>
+**Data distribution.** Classification tasks report counts for class 0/1; regression tasks report total sample size (N). AA stands for amino acid-based sequences.
+
+#### Classification (counts for class 0 / 1)
+
+| Property | AA (0) | AA (1) | SMILES (0) | SMILES (1) |
+|---|---:|---:|---:|---:|
+| Hemolysis | 4765 | 1311 | 4765 | 1311 |
+| Non-Fouling | 13580 | 3600 | 13580 | 3600 |
+| Solubility | 9668 | 8785 | – | – |
+| Permeability (Penetrance) | 1162 | 1162 | – | – |
+| Toxicity | – | – | 5518 | 5518 |
+
+#### Regression (total N)
+
+| Property | AA (N) | SMILES (N) |
+|---|---:|---:|
+| Permeability (PAMPA) | – | 6869 |
+| Permeability (CACO2) | – | 606 |
+| Half-Life | 130 | 245 |
+| Binding Affinity | 1436 | 1597 |
+
 
 Our models are trained on curated datasets from multiple sources. For detailed cleaning up procedures please refer to our [paper]().
 
@@ -147,7 +89,7 @@ Higher scores indicate stronger non-fouling behavior, desirable for circulation
 - **Others:** SVM and Elastic Nets were trained with [RAPID cuML](https://github.com/rapidsai/cuml), which requires a CUDA environment and is therefore not supported in the web app. Model checkpoints remain available in the Hugging Face repository.
 
 ### Model Training and Weight Hosting
-- More instructions can be found here at [Classifier_weights](https://huggingface.co/ChatterjeeLab/Classifier_Weight)
+- More instructions can be found here at [PeptiVersse](https://huggingface.co/ChatterjeeLab/PeptiVerse)
 
 ### 🧪 Physicochemical Properties
                 

peptiverse_styles.css

@@ -339,29 +339,3 @@ h1 {
 #acc_pred > button * {
   font-size: 18px !important;
 }
-
-
-/* =========================
-   FOOTER STYLING
-   ========================= */
-
-/* Footer container - properly centered */
-.footer-container {
-    display: flex !important;
-    flex-direction: column !important;
-    align-items: center !important;
-    justify-content: center !important;
-    text-align: center !important;
-    width: 100% !important;
-    margin-top: 2rem !important;
-    padding: 1.5rem 0 !important;
-    border-top: 1px solid #e5e7eb !important;
-}
-
-.footer-container p {
-    text-align: center !important;
-    color: #6b7280 !important;
-    margin: 0.25rem 0 !important;
-    font-size: 14px !important;
-    line-height: 1.5 !important;
-}