Improve About

app.py

@@ -48,21 +48,49 @@ def gradio_interface():
         timer.tick(fn=update_current_dataframe, inputs=[data_version], outputs=data_version)
         
         ### Header
-        gr.Markdown("## Welcome to the OpenADMET + XXX Blind Challenge!")
+        with gr.Row():
+            with gr.Column(scale=8):  # bigger text area
+                gr.Markdown("""
+                    ## Welcome to the OpenADMET + XXX Blind Challenge!
+                    Your task is to develop and submit predictive models for key ADMET properties on a blinded test set of real world drug discovery data 🧑‍🔬
+                            
+                    Go to the **Leaderboard** to check out how the challenge is going. 
+                    To participate, head out to the **Submit** tab and upload your results as a `CSV` file.
+                    """
+                    )
+            with gr.Column(scale=1):  # smaller side column for logo
+                gr.Image(
+                    value="./_static/challenge_logo.png",
+                    show_label=False,
+                    show_download_button=False,
+                    width="10vw",  # Take up the width of the column (2/8 = 1/4)
+                )
 
         # --- Welcome markdown message ---
         welcome_md = """
         # 💊 OpenADMET + XXX  
         ## Computational Blind Challenge in ADMET
 
-        Welcome to the **XXX**, hosted by **OpenADMET** in collaboration with **XXX**. 
-        This is a community-driven initiative to benchmark predictive models for ADMET properties in drug discovery.
+        This challenge is a community-driven initiative to benchmark predictive models for ADMET properties in drug discovery,
+        hosted by **OpenADMET** in collaboration with **XXX**. 
+
+
+        ## Why are ADMET properties important in drug discovery?
+        Small molecules continue to be the bricks and mortar of drug discovery globally, accounting for ~75% of FDA approvals over the last decade. 
+        Oral bioavailability, easily tunable properties, modulation of a wide range of mechanisms, 
+        and ease of manufacturing make small molecules highly attractive as therapeutic agents, a trend that is not expected to drastically change, 
+        despite increased interest in biologics.  Indeed, newer small molecule modalities such as degraders, molecular glues, and antibody-drug conjugates 
+        (to name a few) make understanding small molecule properties more important than ever.
+
+        It is fairly difficult to predict the lifetime and distribution of small molecules within the body. Additionally, 
+        interaction with off-targets can cause safety issues and toxicity. Collectively these *Absorption*, *Distribution*, *Metabolism*, *Excretion*, *Toxicology*--or **ADMET**--properties 
+        sit in the middle of the assay cascade and can make or break preclinical candidate molecules. 
 
-        Your task is to develop and submit predictive models for key ADMET properties on a blinded test set of real world drug discovery data.
+        **OpenADMET** aims to address these challenges through an open science effort to build predictive models of ADMET properties by characterizing the proteins and mechanisms 
+        that give rise to these properties through integrated structural biology, high throughput experimentation and integrative computational models. 
+        Read more about our strategy to transform drug discovery on our [website](https://openadmet.org/community/blogs/whatisopenadmet/). 
 
-        ## ADMET Properties:
-        *Absorption*, *Distribution*, *Metabolism*, *Excretion*, *Toxicology*--or **ADMET**--endpoints sit in the middle of the assay cascade and can make or break preclinical candidate molecules. 
-        For this blind challenge we selected several crucial endpoints for the community to predict:
+        For this blind challenge we selected ten (10) crucial endpoints for the community to predict:
         - LogD
         - Kinetic Solubility **KSOL**: uM
         - Mouse Liver Microsomal (**MLM**) *CLint*: mL/min/kg
@@ -126,10 +154,10 @@ def gradio_interface():
         with gr.Tabs(elem_classes="tab-buttons"):
             lboard_dict = {}
 
-            with gr.TabItem("📝About"):
+            with gr.TabItem("📖 About"):
                 gr.Markdown(welcome_md)
 
-            with gr.TabItem("🚀Leaderboard", elem_id="lb_subtabs"):
+            with gr.TabItem("🚀 Leaderboard", elem_id="lb_subtabs"):
                 gr.Markdown("View the leaderboard for each ADMET endpoint by selecting the appropiate tab.")
                 # Make separate leaderboards in separate tabs  
                 #per_ep = build_leaderboard()
@@ -162,7 +190,7 @@ def gradio_interface():
 
                 data_version.change(fn=refresh_if_changed, outputs=[lboard_dict[ep] for ep in ALL_EPS])
 
-            with gr.TabItem("Submit Predictions"):
+            with gr.TabItem("✉️ Submit"):
                 gr.Markdown(
                 """
                 # ADMET Endpoints Submission