update about page

app.py

@@ -26,19 +26,20 @@ datapath = os.path.join(basepath, "data")
 
 device = "cuda" if torch.cuda.is_available() else "cpu"
 
-st.title('HyperDTI: Task-conditioned modeling of drug-target interactions.')
+st.title('HyperDTI: Task-conditioned modeling of drug-target interactions.\n')
 st.markdown(
     """
-    \n
     🧬 Generate a QSAR model for the protein target of interest, useful for high-throughput screening or drug repurposing.\n
-    💻 Github: [ml-jku/hyper-dti](https://https://github.com/ml-jku/hyper-dti)\n
+    💻 Github: [ml-jku/hyper-dti](https://https://github.com/ml-jku/hyper-dti)    
     📝 NeurIPS 2022 AI4Science workshop paper: [OpenReview](https://openreview.net/forum?id=dIX34JWnIAL)\n
     """
 )
 
 def about_page():
     st.markdown(
-        """        
+        """      
+        ## About
+        
         HyperNetworks have been established as an effective technique to achieve fast adaptation of parameters for 
         neural networks. Recently, HyperNetwork predictions conditioned on descriptors of tasks have improved 
         multi-task generalization in various domains, such as personalized federated learning and neural architecture 
@@ -50,6 +51,8 @@ def about_page():
         predicting drug-target interactions in drug discovery. Our model learns to generate a QSAR model specialized on
         a given protein target. We demonstrate state-of-the-art performance over previous methods on multiple 
         well-known benchmarks, particularly in zero-shot settings for unseen protein targets.
+
+        ![Model overview](figures/hyper-dti.png)
         """
     )