Update app.py

app.py

@@ -3,7 +3,7 @@ import streamlit as st
 st.set_page_config(
     page_title="Ligand Discovery",
     page_icon=":home:",
-    layout="centered", # "wide"
+    layout="centered", # "centered",
     initial_sidebar_state="collapsed"
 )
 
@@ -25,22 +25,21 @@ hide_streamlit_style = """
 st.markdown(hide_streamlit_style, unsafe_allow_html=True) 
 
 st.title('Welcome to Ligand Discovery!')
-# cols = st.columns([0.5, 0.5])
-# col = cols[0]
-# col.markdown(
 st.markdown(
 '''
 This portal enables exploration of a large scale fragment-based chemoproteomics screening data.
 
-- Explore below **5** web apps that we deployed in a cloud server (click _Restart this Space_ if app goes to sleep) or
-- Run apps locally by forking the code from [GitHub](https://github.com/ligand-discovery)
-- Or download [Screening](https://ligand-discovery.ai/) data and [Fingerprinting](https://ligand-discovery.ai/) data for your own research
+- Explore below **5** web apps that we deployed in a cloud server (or)
+- Run apps locally by forking the code from [GitHub](https://github.com/ligand-discovery) (or)
+- Download [Screening](https://github.com/ligand-discovery/landing-page/raw/refs/heads/main/assets/screeningData.tar.xz) data and [Competition](https://github.com/ligand-discovery/landing-page/raw/refs/heads/main/assets/competitionData.tar.xz) data for your own research
+
+:warning:  server will sleep if inactive, then click _Restart this Space_ button 
 
 1. :dart: [**Interactions**](https://1.ligand-discovery.ai) Explore the interactions between ligands and proteins. This is the main navigator to the chemoproteomics data, containing profiles for 407 fragments. The app also showcases competition assays for a few selected fragments
-2. :mag: [**Explore protein sets**](https://protein-set.ligand-discovery.ai) With this tool, you can in put a set of proteins and see how many fragments interact with them according to our chemoproteomics data. We categorize proteins by their promiscuity/specificity levels to easily detect reported effect such as labeling bias
-3. :mountain: [**Protein set enrichment analysis**](https://enrich.ligand-discovery.ai/) Explore fragment profiles from an enrichment perspective. We capture protein annotations of multiple scopes, from domains and families to molecular functions and cellular localization. We offer global and detailed views for each fragment
-4. :robot_face: [**Fragment predictor**](https://fpred.ligand-discovery.ai/) Predict whether your fully-functionalized fragment of interest is likely to be promiscuous or associated with a specific interactome signature. We have predefined 10 interactome signatures capturing high-level biological processes that emerged from our chemoproteomics data
-5. :rocket: [**On-the-fly modeling**](https://onthefly.ligand-discovery.ai/) Build a machine learning model on the fly to predict potential interactions between your fully-functionalized fragments and proteins of interest. Sets of proteins are accepted and organized in coherent subsets to maximize the chance of obtaining a good model
+2. :mag: [**Explore protein sets**](https://2.ligand-discovery.ai) With this tool, you can in put a set of proteins and see how many fragments interact with them according to our chemoproteomics data. We categorize proteins by their promiscuity/specificity levels to easily detect reported effect such as labeling bias
+3. :mountain: [**Protein set enrichment analysis**](https://3.ligand-discovery.ai/) Explore fragment profiles from an enrichment perspective. We capture protein annotations of multiple scopes, from domains and families to molecular functions and cellular localization. We offer global and detailed views for each fragment
+4. :robot_face: [**Fragment predictor**](https://4.ligand-discovery.ai/) Predict whether your fully-functionalized fragment of interest is likely to be promiscuous or associated with a specific interactome signature. We have predefined 10 interactome signatures capturing high-level biological processes that emerged from our chemoproteomics data
+5. :rocket: [**On-the-fly modeling**](https://5.ligand-discovery.ai/) Build a machine learning model on the fly to predict potential interactions between your fully-functionalized fragments and proteins of interest. Sets of proteins are accepted and organized in coherent subsets to maximize the chance of obtaining a good model
 
 This project was led by [Georg Winter](https://www.winter-lab.com/)'s group at [CeMM](https://cemm.at)
 
@@ -49,8 +48,6 @@ Cite: [Offensperger et al., Science (2024)](https://doi.org/10.1126/science.adk5
 '''
 )
 
-# cols[1].image("1.jpg") 
-
 st.divider()
 
 st.subheader("Frequently Asked Questions")
@@ -109,18 +106,25 @@ st.markdown(
 
 Three Type 1 (Global) Models and nine Type 2 (Specific) Models were used. Area Under Receiver Operating Characteristic (AUROC) of > 0.75 is considered a :blue[good model].
 
-1. **Prom-0** with 100+ proteins. This model has AUROC of :blue[0.837]
-2. **Prom-1** with 200+ proteins. This model has AUROC of :blue[0.800]
-3. **Prom-1** with 300+ proteins. This model has AUROC of :red[0.713]
-4. **Prom-0-0** with 5+ proteins and less than 4 fragments. This model has AUROC of :blue[0.818]
-5. **Prom-0-1** with 10+ proteins and greater than 4 but less than 40 fragments. This model has AUROC of :blue[0.809]
-6. **Prom-0-2** with 50+ proteins and greater than 40 fragments. This model has AUROC of :blue[0.857]
-7. **Prom-1-0** with 10+ proteins and less than 4 fragments. This model has AUROC of :blue[0.771]
-8. **Prom-1-1** with 15+ proteins and greater than 4 but less than 40 fragments. This model has AUROC of :blue[0.855]
-9. **Prom-1-2** with 100+ proteins and greater than 40 fragments. This model has AUROC of :blue[0.858]
-10. **Prom-2-0** with 50+ proteins and less than 4 fragments. This model has AUROC of :blue[0.771]
-11. **Prom-2-1** with 100+ proteins and greater than 4 but less than 40 fragments. This model has AUROC of :red[0.743]
-12. **Prom-2-2** with 200+ proteins and greater than 40 fragments. This model has AUROC of :blue[0.814]
+|Global | num. Proteins | AUROC
+|---|---|---|
+Prom-0 | 100+ | :blue[0.837]
+Prom-1 | 200+ | :blue[0.800]
+Prom-2 | 300+ | :red[0.713]
+Prom-2 | 300+ | :red[0.713]
+
+|Specific | num. Proteins | num. Fragments | AUROC
+|---|---|---|---|
+Prom-0-0|5+| < 4 | :blue[0.818]
+Prom-0-1|10+| 4 -> 40 | :blue[0.809]
+Prom-0-2|50+| > 40 | :blue[0.857]
+Prom-1-0|10+| < 4 | :blue[0.771]
+Prom-1-1|15+| 4 -> 40 | :blue[0.855]
+Prom-1-2|100+| > 40 | :blue[0.858]
+Prom-2-0|50+| < 4 | :red[0.771]
+Prom-2-1|100+| 4 -> 40  | :red[0.743]
+Prom-2-2|200+| > 40 | :blue[0.814]
   
 '''
-)
+)
+