Update app.py

app.py

@@ -163,20 +163,10 @@ with gr.Blocks(theme=gr.themes.Soft(primary_hue="blue")) as demo:
 ## Model Variations
 
 ### DrugGEN-AKT1
-This model is designed to generate molecules targeting the human AKT1 protein (UniProt ID: P31749), a serine/threonine-protein kinase that plays a key role in regulating cell survival, metabolism, and growth. AKT1 is a significant target in cancer therapy, particularly for breast, colorectal, and ovarian cancers.
-
-The model learns from:
-- General drug-like molecules from ChEMBL database
-- Known AKT1 inhibitors
-- Maximum atom count: 45
+This model is designed to generate molecules targeting the human AKT1 protein (UniProt ID: P31749).
 
 ### DrugGEN-CDK2
-This model targets the human CDK2 protein (UniProt ID: P24941), a cyclin-dependent kinase involved in cell cycle regulation. CDK2 inhibitors are being investigated for treating various cancers, particularly those with dysregulated cell cycle control.
-
-The model learns from:
-- General drug-like molecules from ChEMBL database
-- Known CDK2 inhibitors
-- Maximum atom count: 38
+This model is designed to generate molecules targeting the human CDK2 protein (UniProt ID: P24941).
 
 ### DrugGEN-NoTarget
 This is a general-purpose model that generates diverse drug-like molecules without targeting a specific protein. It's useful for:
@@ -184,12 +174,6 @@ This is a general-purpose model that generates diverse drug-like molecules witho
 - Generating diverse scaffolds
 - Creating molecules with drug-like properties
 
-## How It Works
-DrugGEN uses a graph-based generative adversarial network (GAN) architecture where:
-1. The generator creates molecular graphs
-2. The discriminator evaluates them against real molecules
-3. The model learns to generate increasingly realistic and target-specific molecules
-
 For more details, see our [paper on arXiv](https://arxiv.org/abs/2302.07868).
                 """)
             
@@ -234,7 +218,7 @@ For more details, see our [paper on arXiv](https://arxiv.org/abs/2302.07868).
                 value=100,
                 step=10,
                 label="Number of Molecules to Generate",
-                info="This space runs on a CPU, which may result in slower performance. Generating 200 molecules takes approximately 6 minutes. Therefore, We set a 250-molecule cap. On a GPU, the model can generate 10,000 molecules in the same amount of time. Please check our GitHub repo for running our models on GPU.""
+                info="This space runs on a CPU, which may result in slower performance. Generating 200 molecules takes approximately 6 minutes. Therefore, We set a 250-molecule cap. On a GPU, the model can generate 10,000 molecules in the same amount of time. Please check our GitHub repo for running our models on GPU.
             )
 
             seed_num = gr.Textbox(
@@ -267,17 +251,7 @@ For more details, see our [paper on arXiv](https://arxiv.org/abs/2302.07868).
                                 "Drug Novelty", "Max Length", "Mean Atom Type", "SNN ChEMBL", "SNN Drug", 
                                 "Internal Diversity", "QED", "SA Score"]
                     )
-            
-            with gr.Accordion("Generation Settings", open=False):
-                gr.Markdown("""
-                ## Technical Details
-                
-                - This demo runs on CPU which limits generation speed
-                - Generating 200 molecules takes approximately 6 minutes
-                - For faster generation or larger batches, run the model on GPU using our GitHub repository
-                - The model uses a graph-based representation of molecules
-                - Maximum atom count varies by model (AKT1: 45, CDK2: 38)
-                """)
+
 
     gr.Markdown("### Created by the HU BioDataLab | [GitHub](https://github.com/HUBioDataLab/DrugGEN) | [Paper](https://arxiv.org/abs/2302.07868)")