From 4204c1cc990b37cd643822e5fdc5d6612a7fef85 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Gordon=20J=2E=20K=C3=B6hn?= <gordon@koehn.net>
Date: Fri, 22 Nov 2024 13:20:02 +0000
Subject: [PATCH 01/20] fix devtainer

---
 .devcontainer/devcontainer.json | 26 +++++++++++++-------------
 1 file changed, 13 insertions(+), 13 deletions(-)

diff --git a/.devcontainer/devcontainer.json b/.devcontainer/devcontainer.json
index 5a319b5..d8132b4 100644
--- a/.devcontainer/devcontainer.json
+++ b/.devcontainer/devcontainer.json
@@ -1,22 +1,22 @@
 // For format details, see https://aka.ms/devcontainer.json. For config options, see the
 // README at: https://github.com/devcontainers/templates/tree/main/src/python
 {
-	"name": "vpipe-frontend",
-	// Or use a Dockerfile or Docker Compose file. More info: https://containers.dev/guide/dockerfile
-	"image": "mcr.microsoft.com/devcontainers/python:1-3.12-bullseye"
+    "name": "vpipe-frontend",
+    // Or use a Dockerfile or Docker Compose file. More info: https://containers.dev/guide/dockerfile
+    "image": "mcr.microsoft.com/devcontainers/python:1-3.12-bullseye",
 
-	// Features to add to the dev container. More info: https://containers.dev/features.
-	// "features": {},
+    // Features to add to the dev container. More info: https://containers.dev/features.
+    // "features": {},
 
-	// Use 'forwardPorts' to make a list of ports inside the container available locally.
-	// "forwardPorts": [],
+    // Use 'forwardPorts' to make a list of ports inside the container available locally.
+    "forwardPorts": [8000],
 
-	// Use 'postCreateCommand' to run commands after the container is created.
-	// "postCreateCommand": "pip3 install --user -r requirements.txt",
+    // Use 'postCreateCommand' to run commands after the container is created.
+    "postCreateCommand": "pip3 install --user -r requirements.txt",
 
-	// Configure tool-specific properties.
-	// "customizations": {},
+    // Configure tool-specific properties.
+    // "customizations": {},
 
-	// Uncomment to connect as root instead. More info: https://aka.ms/dev-containers-non-root.
-	// "remoteUser": "root"
+    // Uncomment to connect as root instead. More info: https://aka.ms/dev-containers-non-root.
+    // "remoteUser": "root"
 }

From 76bf4dca5450d23f97346ea04c4c950a4e20fce7 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Gordon=20J=2E=20K=C3=B6hn?= <gordon@koehn.net>
Date: Fri, 22 Nov 2024 13:27:01 +0000
Subject: [PATCH 02/20] fix devtainer

---
 .devcontainer/devcontainer.json | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/.devcontainer/devcontainer.json b/.devcontainer/devcontainer.json
index d8132b4..d461870 100644
--- a/.devcontainer/devcontainer.json
+++ b/.devcontainer/devcontainer.json
@@ -13,6 +13,13 @@
 
     // Use 'postCreateCommand' to run commands after the container is created.
     "postCreateCommand": "pip3 install --user -r requirements.txt",
+    "customizations": {
+        "vscode": {
+            "settings": {
+                "editor.rulers": [80]
+            }
+        }
+    }
 
     // Configure tool-specific properties.
     // "customizations": {},

From cb37735dfc8b3eabc45875d57852ab7cac0b99d6 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Gordon=20J=2E=20K=C3=B6hn?= <gordon@koehn.net>
Date: Fri, 22 Nov 2024 15:52:17 +0100
Subject: [PATCH 03/20] load muation names

---
 app.py            |  2 ++
 resistance_mut.py | 38 ++++++++++++++++++++++++++++++++++++++
 2 files changed, 40 insertions(+)
 create mode 100644 resistance_mut.py

diff --git a/app.py b/app.py
index 8d18d6a..8d0fb4c 100644
--- a/app.py
+++ b/app.py
@@ -2,11 +2,13 @@
 import index
 import mutation_freq
 import variant_deconv
+import resistance_mut
 
 PAGES = {
     "Home": {"module": index}, 
     "Mutation Frequency": {"module": mutation_freq},
     "Variant Deconvolution": {"module": variant_deconv},
+    "Resistance Mutations": {"module": resistance_mut}
 }
 
 def sidebar():
diff --git a/resistance_mut.py b/resistance_mut.py
new file mode 100644
index 0000000..4a19940
--- /dev/null
+++ b/resistance_mut.py
@@ -0,0 +1,38 @@
+import streamlit as st
+import time
+import requests
+from PIL import Image
+from io import BytesIO
+import base64
+import yaml
+import pandas as pd
+
+# Load configuration from config.yaml
+with open('config.yaml', 'r') as file:
+    config = yaml.safe_load(file)
+
+server_ip = config.get('server', {}).get('ip_address', 'http://default_ip:8000')
+
+def app():
+    st.title("Resistance Mutations")
+
+    st.write("This page allows you to run the Lollipop variant deconvolution tool with a custom variant definitions.")
+
+    # have three buttons for the three sets of mutaitons 
+    # data/3CLpro_inhibitors_datasheet.csv
+    # data/RdRP_inhibitors_datasheet.csv
+    # data/spike_mAbs_datasheet.csv
+    st.write("Select from the following resistance mutation sets:")
+
+    options = ["3CLpro Inhibitors", "RdRP Inhibitors", "Spike mAbs"]
+    selected_option = st.selectbox("Select a resistance mutation set:", options)
+
+
+    if selected_option == "3CLpro Inhibitors":
+        df = pd.read_csv('data/3CLpro_inhibitors_datasheet.csv')
+    elif selected_option == "RdRP Inhibitors":
+        df = pd.read_csv('data/RdRP_inhibitors_datasheet.csv')
+    elif selected_option == "Spike mAbs":
+        df = pd.read_csv('data/spike_mAbs_datasheet.csv')
+
+    st.write(df)

From b144810b86e36a5e881d448e6dcb422d6ce59f38 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Gordon=20J=2E=20K=C3=B6hn?= <gordon@koehn.net>
Date: Fri, 22 Nov 2024 16:22:50 +0100
Subject: [PATCH 04/20] first request to silo

---
 resistance_mut.py | 49 +++++++++++++++++++++++++++++++++++------------
 1 file changed, 37 insertions(+), 12 deletions(-)

diff --git a/resistance_mut.py b/resistance_mut.py
index 4a19940..e6e6666 100644
--- a/resistance_mut.py
+++ b/resistance_mut.py
@@ -18,21 +18,46 @@ def app():
 
     st.write("This page allows you to run the Lollipop variant deconvolution tool with a custom variant definitions.")
 
-    # have three buttons for the three sets of mutaitons 
-    # data/3CLpro_inhibitors_datasheet.csv
-    # data/RdRP_inhibitors_datasheet.csv
-    # data/spike_mAbs_datasheet.csv
+    # have three buttons for the three sets of mutations
     st.write("Select from the following resistance mutation sets:")
 
-    options = ["3CLpro Inhibitors", "RdRP Inhibitors", "Spike mAbs"]
-    selected_option = st.selectbox("Select a resistance mutation set:", options)
+    # TODO: currently hardcoded, should be fetched from the server
+    options = {
+        "3CLpro Inhibitors": 'data/3CLpro_inhibitors_datasheet.csv',
+        "RdRP Inhibitors": 'data/RdRP_inhibitors_datasheet.csv',
+        "Spike mAbs": 'data/spike_mAbs_datasheet.csv'
+    }
 
+    selected_option = st.selectbox("Select a resistance mutation set:", options.keys())
 
-    if selected_option == "3CLpro Inhibitors":
-        df = pd.read_csv('data/3CLpro_inhibitors_datasheet.csv')
-    elif selected_option == "RdRP Inhibitors":
-        df = pd.read_csv('data/RdRP_inhibitors_datasheet.csv')
-    elif selected_option == "Spike mAbs":
-        df = pd.read_csv('data/spike_mAbs_datasheet.csv')
+    df = pd.read_csv(options[selected_option])
 
     st.write(df)
+
+    # Define the POST request payload
+    payload = {
+        "aminoAcidMutations": ["S:144L"],
+        "dateFrom": ["2022-02-18"],
+        "dateTo": ["2024-11-01"],
+        "fields": ["date"]
+    }
+
+    # Make the POST request
+    response = requests.post(
+        'https://lapis.cov-spectrum.org/open/v2/sample/aggregated',
+        headers={
+            'accept': 'application/json',
+            'Content-Type': 'application/json'
+        },
+        json=payload
+    )
+
+    # Check if the request was successful
+    if response.status_code == 200:
+        data = response.json()
+        st.write("Data fetched from the server:")
+        st.write(data)
+    else:
+        st.write("Failed to fetch data from the server.")
+        st.write(f"Status code: {response.status_code}")
+        st.write(response.text)

From 580d92d812e0ed3cc91df6a3dc6ffe6f8ab1407c Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Gordon=20J=2E=20K=C3=B6hn?= <gordon@koehn.net>
Date: Fri, 22 Nov 2024 16:26:00 +0100
Subject: [PATCH 05/20] allow users choice for daterange

---
 resistance_mut.py | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/resistance_mut.py b/resistance_mut.py
index e6e6666..c7c83e5 100644
--- a/resistance_mut.py
+++ b/resistance_mut.py
@@ -31,14 +31,18 @@ def app():
     selected_option = st.selectbox("Select a resistance mutation set:", options.keys())
 
     df = pd.read_csv(options[selected_option])
+    
+    # allow the user to chose a date range
+    st.write("Select a date range:")
+    date_range = st.date_input("Select a date range:", [pd.to_datetime("2022-01-01"), pd.to_datetime("2024-01-01")])
 
     st.write(df)
 
     # Define the POST request payload
     payload = {
         "aminoAcidMutations": ["S:144L"],
-        "dateFrom": ["2022-02-18"],
-        "dateTo": ["2024-11-01"],
+        "dateFrom": date_range[0].strftime("%Y-%m-%d"),
+        "dateTo": date_range[1].strftime("%Y-%m-%d"),
         "fields": ["date"]
     }
 

From 8ab5d7c3137e391901264656329353dea07b1548 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Gordon=20J=2E=20K=C3=B6hn?= <gordon@koehn.net>
Date: Fri, 22 Nov 2024 16:42:22 +0100
Subject: [PATCH 06/20] first requests

---
 resistance_mut.py | 87 ++++++++++++++++++++++++++++-------------------
 1 file changed, 52 insertions(+), 35 deletions(-)

diff --git a/resistance_mut.py b/resistance_mut.py
index c7c83e5..9355cb5 100644
--- a/resistance_mut.py
+++ b/resistance_mut.py
@@ -1,9 +1,5 @@
 import streamlit as st
-import time
 import requests
-from PIL import Image
-from io import BytesIO
-import base64
 import yaml
 import pandas as pd
 
@@ -13,12 +9,36 @@
 
 server_ip = config.get('server', {}).get('ip_address', 'http://default_ip:8000')
 
+def fetch_data(mutation, date_range):
+    payload = {
+        "aminoAcidMutations": [mutation],
+        "dateFrom": date_range[0].strftime('%Y-%m-%d'),
+        "dateTo": date_range[1].strftime('%Y-%m-%d'),
+        "fields": ["date"]
+    }
+
+    response = requests.post(
+        'https://lapis.cov-spectrum.org/open/v2/sample/aggregated',
+        headers={
+            'accept': 'application/json',
+            'Content-Type': 'application/json'
+        },
+        json=payload
+    )
+
+    if response.status_code == 200:
+        return response.json()
+    else:
+        st.write(f"Failed to fetch data for mutation {mutation}.")
+        st.write(f"Status code: {response.status_code}")
+        st.write(response.text)
+        return None
+
 def app():
     st.title("Resistance Mutations")
 
-    st.write("This page allows you to run the Lollipop variant deconvolution tool with a custom variant definitions.")
+    st.write("This page allows you to run the Lollipop variant deconvolution tool with custom variant definitions.")
 
-    # have three buttons for the three sets of mutations
     st.write("Select from the following resistance mutation sets:")
 
     # TODO: currently hardcoded, should be fetched from the server
@@ -31,37 +51,34 @@ def app():
     selected_option = st.selectbox("Select a resistance mutation set:", options.keys())
 
     df = pd.read_csv(options[selected_option])
-    
-    # allow the user to chose a date range
+
+    # Get the list of mutations for the selected set
+    mutations = df['Mutation'].tolist()
+    # Lambda function to format the mutation list, from S24L to S:24L
+    format_mutation = lambda x: f"{x[0]}:{x[1:]}"
+    # Apply the lambda function to each element in the mutations list
+    formatted_mutations = [format_mutation(mutation) for mutation in mutations]
+
+    st.write(f"Selected mutations: {formatted_mutations}")
+
+    # Allow the user to choose a date range
     st.write("Select a date range:")
     date_range = st.date_input("Select a date range:", [pd.to_datetime("2022-01-01"), pd.to_datetime("2024-01-01")])
 
-    st.write(df)
+    if st.button("Fetch Data"):
+        all_data = []
+        for mutation in formatted_mutations:
+            data = fetch_data(mutation, date_range)
+            if data:
+                all_data.append(data)
 
-    # Define the POST request payload
-    payload = {
-        "aminoAcidMutations": ["S:144L"],
-        "dateFrom": date_range[0].strftime("%Y-%m-%d"),
-        "dateTo": date_range[1].strftime("%Y-%m-%d"),
-        "fields": ["date"]
-    }
-
-    # Make the POST request
-    response = requests.post(
-        'https://lapis.cov-spectrum.org/open/v2/sample/aggregated',
-        headers={
-            'accept': 'application/json',
-            'Content-Type': 'application/json'
-        },
-        json=payload
-    )
+        # Display all collected data
+        if all_data:
+            st.write("Data fetched from the server:")
+            for data in all_data:
+                st.write(data)
+        else:
+            st.write("No data found for the given mutations.")
 
-    # Check if the request was successful
-    if response.status_code == 200:
-        data = response.json()
-        st.write("Data fetched from the server:")
-        st.write(data)
-    else:
-        st.write("Failed to fetch data from the server.")
-        st.write(f"Status code: {response.status_code}")
-        st.write(response.text)
+if __name__ == "__main__":
+    app()
\ No newline at end of file

From 31d5ce053b54c21dbf21e360780f757380f7de9d Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Gordon=20J=2E=20K=C3=B6hn?= <gordon@koehn.net>
Date: Fri, 22 Nov 2024 16:46:31 +0100
Subject: [PATCH 07/20] add resistance mutation query outcome

---
 resistance_mut.py | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/resistance_mut.py b/resistance_mut.py
index 9355cb5..b87ab08 100644
--- a/resistance_mut.py
+++ b/resistance_mut.py
@@ -2,6 +2,7 @@
 import requests
 import yaml
 import pandas as pd
+import logging
 
 # Load configuration from config.yaml
 with open('config.yaml', 'r') as file:
@@ -29,9 +30,9 @@ def fetch_data(mutation, date_range):
     if response.status_code == 200:
         return response.json()
     else:
-        st.write(f"Failed to fetch data for mutation {mutation}.")
-        st.write(f"Status code: {response.status_code}")
-        st.write(response.text)
+        logging.error(f"Failed to fetch data for mutation {mutation}.")
+        logging.error(f"Status code: {response.status_code}")
+        logging.error(response.text)
         return None
 
 def app():
@@ -67,14 +68,16 @@ def app():
 
     if st.button("Fetch Data"):
         all_data = []
+        successful_fetches = 0
         for mutation in formatted_mutations:
             data = fetch_data(mutation, date_range)
             if data:
                 all_data.append(data)
+                successful_fetches += 1
 
         # Display all collected data
         if all_data:
-            st.write("Data fetched from the server:")
+            st.write(f"{successful_fetches} Mutations of {len(formatted_mutations)} found on Cov-Spectrum")
             for data in all_data:
                 st.write(data)
         else:

From c1d8f36573d2d91d641b5ad8fca16cd837f8776f Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Gordon=20J=2E=20K=C3=B6hn?= <gordon@koehn.net>
Date: Fri, 22 Nov 2024 17:11:37 +0100
Subject: [PATCH 08/20] resistance mutation lookups

---
 resistance_mut.py | 14 +++++---------
 1 file changed, 5 insertions(+), 9 deletions(-)

diff --git a/resistance_mut.py b/resistance_mut.py
index b87ab08..9e94b52 100644
--- a/resistance_mut.py
+++ b/resistance_mut.py
@@ -67,21 +67,17 @@ def app():
     date_range = st.date_input("Select a date range:", [pd.to_datetime("2022-01-01"), pd.to_datetime("2024-01-01")])
 
     if st.button("Fetch Data"):
-        all_data = []
+        all_data = {}
         successful_fetches = 0
         for mutation in formatted_mutations:
             data = fetch_data(mutation, date_range)
             if data:
-                all_data.append(data)
+                all_data[mutation] = data
                 successful_fetches += 1
+        
+        st.write(all_data)
 
-        # Display all collected data
-        if all_data:
-            st.write(f"{successful_fetches} Mutations of {len(formatted_mutations)} found on Cov-Spectrum")
-            for data in all_data:
-                st.write(data)
-        else:
-            st.write("No data found for the given mutations.")
+        # next make df out of it / catch the case where change was found but no data was returned
 
 if __name__ == "__main__":
     app()
\ No newline at end of file

From c20725ee54f671284eef7102b2f21d96efb0a5a6 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Gordon=20J=2E=20K=C3=B6hn?= <gordon@koehn.net>
Date: Mon, 25 Nov 2024 10:23:22 +0100
Subject: [PATCH 09/20] make async

---
 requirements.txt  |  3 ++-
 resistance_mut.py | 51 +++++++++++++++++++++++++++--------------------
 2 files changed, 31 insertions(+), 23 deletions(-)

diff --git a/requirements.txt b/requirements.txt
index 8726bd1..2c0a694 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -8,4 +8,5 @@ s3fs
 st-files-connection
 seaborn
 matplotlib
-pillow
\ No newline at end of file
+pillow
+aiohttp
\ No newline at end of file
diff --git a/resistance_mut.py b/resistance_mut.py
index 9e94b52..c0a3ce9 100644
--- a/resistance_mut.py
+++ b/resistance_mut.py
@@ -3,6 +3,8 @@
 import yaml
 import pandas as pd
 import logging
+import aiohttp
+import asyncio
 
 # Load configuration from config.yaml
 with open('config.yaml', 'r') as file:
@@ -10,7 +12,7 @@
 
 server_ip = config.get('server', {}).get('ip_address', 'http://default_ip:8000')
 
-def fetch_data(mutation, date_range):
+async def fetch_data(session, mutation, date_range):
     payload = {
         "aminoAcidMutations": [mutation],
         "dateFrom": date_range[0].strftime('%Y-%m-%d'),
@@ -18,22 +20,26 @@ def fetch_data(mutation, date_range):
         "fields": ["date"]
     }
 
-    response = requests.post(
+    async with session.post(
         'https://lapis.cov-spectrum.org/open/v2/sample/aggregated',
         headers={
             'accept': 'application/json',
             'Content-Type': 'application/json'
         },
         json=payload
-    )
-
-    if response.status_code == 200:
-        return response.json()
-    else:
-        logging.error(f"Failed to fetch data for mutation {mutation}.")
-        logging.error(f"Status code: {response.status_code}")
-        logging.error(response.text)
-        return None
+    ) as response:
+        if response.status == 200:
+            return await response.json()
+        else:
+            logging.error(f"Failed to fetch data for mutation {mutation}.")
+            logging.error(f"Status code: {response.status}")
+            logging.error(await response.text())
+            return None
+
+async def fetch_all_data(mutations, date_range):
+    async with aiohttp.ClientSession() as session:
+        tasks = [fetch_data(session, mutation, date_range) for mutation in mutations]
+        return await asyncio.gather(*tasks)
 
 def app():
     st.title("Resistance Mutations")
@@ -67,17 +73,18 @@ def app():
     date_range = st.date_input("Select a date range:", [pd.to_datetime("2022-01-01"), pd.to_datetime("2024-01-01")])
 
     if st.button("Fetch Data"):
-        all_data = {}
-        successful_fetches = 0
-        for mutation in formatted_mutations:
-            data = fetch_data(mutation, date_range)
-            if data:
-                all_data[mutation] = data
-                successful_fetches += 1
-        
-        st.write(all_data)
-
-        # next make df out of it / catch the case where change was found but no data was returned
+        all_data = asyncio.run(fetch_all_data(formatted_mutations, date_range))
+
+        # Filter out None values (failed fetches)
+        all_data = [data for data in all_data if data]
+
+        # Display all collected data
+        if all_data:
+            st.write("Data fetched from the server:")
+            for data in all_data:
+                st.write(data)
+        else:
+            st.write("No data found for the given mutations.")
 
 if __name__ == "__main__":
     app()
\ No newline at end of file

From fb357234bd5d35b431d2e4f3c022fe6c96fc46dd Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Gordon=20J=2E=20K=C3=B6hn?= <gordon@koehn.net>
Date: Mon, 25 Nov 2024 10:50:45 +0100
Subject: [PATCH 10/20] enricht mutation nae

---
 resistance_mut.py | 14 +++++++++-----
 1 file changed, 9 insertions(+), 5 deletions(-)

diff --git a/resistance_mut.py b/resistance_mut.py
index c0a3ce9..78fc4d3 100644
--- a/resistance_mut.py
+++ b/resistance_mut.py
@@ -1,3 +1,4 @@
+import json
 import streamlit as st
 import requests
 import yaml
@@ -29,12 +30,15 @@ async def fetch_data(session, mutation, date_range):
         json=payload
     ) as response:
         if response.status == 200:
-            return await response.json()
+            data = await response.json()
+            return {"mutation": mutation,
+                    "data": data.get('data', [])}
         else:
             logging.error(f"Failed to fetch data for mutation {mutation}.")
             logging.error(f"Status code: {response.status}")
             logging.error(await response.text())
-            return None
+            return {"mutation": mutation,
+                    "data": None}
 
 async def fetch_all_data(mutations, date_range):
     async with aiohttp.ClientSession() as session:
@@ -75,8 +79,8 @@ def app():
     if st.button("Fetch Data"):
         all_data = asyncio.run(fetch_all_data(formatted_mutations, date_range))
 
-        # Filter out None values (failed fetches)
-        all_data = [data for data in all_data if data]
+        # filter out mutations with no data
+        all_data = [data for data in all_data if data['data']]
 
         # Display all collected data
         if all_data:
@@ -84,7 +88,7 @@ def app():
             for data in all_data:
                 st.write(data)
         else:
-            st.write("No data found for the given mutations.")
+            st.write("No data found for the given mutations.") 
 
 if __name__ == "__main__":
     app()
\ No newline at end of file

From 90abeee54de634565667b95b79f4d23e100a3968 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Gordon=20J=2E=20K=C3=B6hn?= <gordon@koehn.net>
Date: Mon, 25 Nov 2024 10:53:59 +0100
Subject: [PATCH 11/20] surcessful wragneling

---
 resistance_mut.py | 18 +++++++++++-------
 1 file changed, 11 insertions(+), 7 deletions(-)

diff --git a/resistance_mut.py b/resistance_mut.py
index 78fc4d3..5be5dbf 100644
--- a/resistance_mut.py
+++ b/resistance_mut.py
@@ -82,13 +82,17 @@ def app():
         # filter out mutations with no data
         all_data = [data for data in all_data if data['data']]
 
-        # Display all collected data
-        if all_data:
-            st.write("Data fetched from the server:")
-            for data in all_data:
-                st.write(data)
-        else:
-            st.write("No data found for the given mutations.") 
+        # build a dataframe from the collected data
+        # for each mutation make a row 
+        # iterate through the data and add a column for each date with the number of samples
+        mutation_data = []
+        for data in all_data:
+            mutation = data['mutation']
+            mutation_data.append([mutation] + [d['count'] for d in data['data']])
+        
+        st.write("Data fetched from the server:")
+        df = pd.DataFrame(mutation_data, columns=['Mutation'] + [d['date'] for d in all_data[0]['data']])
+        st.write(df)
 
 if __name__ == "__main__":
     app()
\ No newline at end of file

From 6158339cef0a60f086e85e074c2506f0327ec674 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Gordon=20J=2E=20K=C3=B6hn?= <gordon@koehn.net>
Date: Mon, 25 Nov 2024 11:09:53 +0100
Subject: [PATCH 12/20] first plots

---
 resistance_mut.py | 44 ++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 44 insertions(+)

diff --git a/resistance_mut.py b/resistance_mut.py
index 5be5dbf..63b2df7 100644
--- a/resistance_mut.py
+++ b/resistance_mut.py
@@ -1,4 +1,6 @@
 import json
+from matplotlib import pyplot as plt
+import numpy as np
 import streamlit as st
 import requests
 import yaml
@@ -7,6 +9,7 @@
 import aiohttp
 import asyncio
 
+
 # Load configuration from config.yaml
 with open('config.yaml', 'r') as file:
     config = yaml.safe_load(file)
@@ -44,6 +47,39 @@ async def fetch_all_data(mutations, date_range):
     async with aiohttp.ClientSession() as session:
         tasks = [fetch_data(session, mutation, date_range) for mutation in mutations]
         return await asyncio.gather(*tasks)
+    
+def plot_heatmap(df):
+
+    # get the dates from the columns
+    dates = df.columns
+
+    # get the mutations from the index
+    mutations = df.index.tolist()
+
+    # 2. Heatmap Construction
+    fig, ax = plt.subplots(figsize=(12, 8))
+    # Replace None with np.nan and remove commas from numbers
+    df = df.replace({None: np.nan, ',': ''}, regex=True).astype(float)
+    
+    # Create a colormap with a custom color for NaN values
+    cmap = plt.cm.Blues
+    cmap.set_bad(color='lightcoral')  # Set NaN values to light rose color
+
+    im = ax.imshow(df.values, cmap=cmap)  # Use the custom colormap
+
+    # Set axis labels
+    ax.set_xticks([0, len(dates) // 2, len(dates) - 1])
+    ax.set_xticklabels([dates[0], dates[len(dates) // 2], dates[-1]], rotation=45)
+    ax.set_yticks(np.arange(len(mutations)))
+    ax.set_yticklabels(mutations, fontsize=8)
+
+    # Add colorbar
+    cbar = ax.figure.colorbar(im, ax=ax)
+    cbar.ax.set_ylabel("Occurrence Frequency", rotation=-90, va="bottom")
+
+    return fig
+
+
 
 def app():
     st.title("Resistance Mutations")
@@ -92,7 +128,15 @@ def app():
         
         st.write("Data fetched from the server:")
         df = pd.DataFrame(mutation_data, columns=['Mutation'] + [d['date'] for d in all_data[0]['data']])
+        # Set the first column as the index
+        df.set_index(df.columns[0], inplace=True)
         st.write(df)
 
+        st.write("df.values:", df.values)
+
+        # Plot the heatmap
+        fig = plot_heatmap(df)
+        st.pyplot(fig)
+
 if __name__ == "__main__":
     app()
\ No newline at end of file

From b38b3b22cae6972669ee6139792bada441af7ce6 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Gordon=20J=2E=20K=C3=B6hn?= <gordon@koehn.net>
Date: Mon, 25 Nov 2024 11:18:44 +0100
Subject: [PATCH 13/20] refactor

---
 resistance_mut.py | 42 ++++++++++++++++++++++--------------------
 1 file changed, 22 insertions(+), 20 deletions(-)

diff --git a/resistance_mut.py b/resistance_mut.py
index 63b2df7..9b20f8c 100644
--- a/resistance_mut.py
+++ b/resistance_mut.py
@@ -48,6 +48,27 @@ async def fetch_all_data(mutations, date_range):
         tasks = [fetch_data(session, mutation, date_range) for mutation in mutations]
         return await asyncio.gather(*tasks)
     
+def fetch_reformat_data(formatted_mutations, date_range):
+    all_data = asyncio.run(fetch_all_data(formatted_mutations, date_range))
+
+        # filter out mutations with no data
+    all_data = [data for data in all_data if data['data']]
+
+        # build a dataframe from the collected data
+        # for each mutation make a row 
+        # iterate through the data and add a column for each date with the number of samples
+    mutation_data = []
+    for data in all_data:
+        mutation = data['mutation']
+        mutation_data.append([mutation] + [d['count'] for d in data['data']])
+        
+    st.write("Data fetched from the server:")
+    df = pd.DataFrame(mutation_data, columns=['Mutation'] + [d['date'] for d in all_data[0]['data']])
+        # Set the first column as the index
+    df.set_index(df.columns[0], inplace=True)
+    return df
+
+
 def plot_heatmap(df):
 
     # get the dates from the columns
@@ -113,26 +134,7 @@ def app():
     date_range = st.date_input("Select a date range:", [pd.to_datetime("2022-01-01"), pd.to_datetime("2024-01-01")])
 
     if st.button("Fetch Data"):
-        all_data = asyncio.run(fetch_all_data(formatted_mutations, date_range))
-
-        # filter out mutations with no data
-        all_data = [data for data in all_data if data['data']]
-
-        # build a dataframe from the collected data
-        # for each mutation make a row 
-        # iterate through the data and add a column for each date with the number of samples
-        mutation_data = []
-        for data in all_data:
-            mutation = data['mutation']
-            mutation_data.append([mutation] + [d['count'] for d in data['data']])
-        
-        st.write("Data fetched from the server:")
-        df = pd.DataFrame(mutation_data, columns=['Mutation'] + [d['date'] for d in all_data[0]['data']])
-        # Set the first column as the index
-        df.set_index(df.columns[0], inplace=True)
-        st.write(df)
-
-        st.write("df.values:", df.values)
+        df = fetch_reformat_data(formatted_mutations, date_range)
 
         # Plot the heatmap
         fig = plot_heatmap(df)

From 51dd6cefef026a03231132ebe2e0b4de866b33cf Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Gordon=20J=2E=20K=C3=B6hn?= <gordon@koehn.net>
Date: Mon, 25 Nov 2024 12:02:58 +0100
Subject: [PATCH 14/20] seboard

---
 resistance_mut.py | 32 ++++++++++++--------------------
 1 file changed, 12 insertions(+), 20 deletions(-)

diff --git a/resistance_mut.py b/resistance_mut.py
index 9b20f8c..92a46b5 100644
--- a/resistance_mut.py
+++ b/resistance_mut.py
@@ -8,6 +8,7 @@
 import logging
 import aiohttp
 import asyncio
+import seaborn as sns
 
 
 # Load configuration from config.yaml
@@ -70,33 +71,24 @@ def fetch_reformat_data(formatted_mutations, date_range):
 
 
 def plot_heatmap(df):
-
-    # get the dates from the columns
-    dates = df.columns
-
-    # get the mutations from the index
-    mutations = df.index.tolist()
-
-    # 2. Heatmap Construction
-    fig, ax = plt.subplots(figsize=(12, 8))
     # Replace None with np.nan and remove commas from numbers
     df = df.replace({None: np.nan, ',': ''}, regex=True).astype(float)
-    
+
     # Create a colormap with a custom color for NaN values
-    cmap = plt.cm.Blues
+    cmap = sns.color_palette("Blues", as_cmap=True)
     cmap.set_bad(color='lightcoral')  # Set NaN values to light rose color
 
-    im = ax.imshow(df.values, cmap=cmap)  # Use the custom colormap
+    # Plot the heatmap
+    fig, ax = plt.subplots(figsize=(12, 8))
+    annot = True if df.shape[0] * df.shape[1] <= 100 else False  # Annotate only if the plot is small enough
+    sns.heatmap(df, cmap=cmap, ax=ax, cbar_kws={'label': 'Occurrence Frequency'}, 
+                linewidths=.5, linecolor='lightgrey', annot=annot, fmt=".1f", 
+                annot_kws={"size": 8}, mask=df.isnull(), cbar=True)
 
     # Set axis labels
-    ax.set_xticks([0, len(dates) // 2, len(dates) - 1])
-    ax.set_xticklabels([dates[0], dates[len(dates) // 2], dates[-1]], rotation=45)
-    ax.set_yticks(np.arange(len(mutations)))
-    ax.set_yticklabels(mutations, fontsize=8)
-
-    # Add colorbar
-    cbar = ax.figure.colorbar(im, ax=ax)
-    cbar.ax.set_ylabel("Occurrence Frequency", rotation=-90, va="bottom")
+    ax.set_xticks([0, len(df.columns) // 2, len(df.columns) - 1])
+    ax.set_xticklabels([df.columns[0], df.columns[len(df.columns) // 2], df.columns[-1]], rotation=45)
+    ax.set_yticklabels(df.index.tolist(), fontsize=10, rotation=0)  # Rotate mutation labels to be horizontal
 
     return fig
 

From ee197da7548b39fb91819495f980443001993724 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Gordon=20J=2E=20K=C3=B6hn?= <gordon@koehn.net>
Date: Mon, 25 Nov 2024 12:31:41 +0100
Subject: [PATCH 15/20] fix population

---
 resistance_mut.py | 39 ++++++++++++++++++++++-----------------
 1 file changed, 22 insertions(+), 17 deletions(-)

diff --git a/resistance_mut.py b/resistance_mut.py
index 92a46b5..ef3cc74 100644
--- a/resistance_mut.py
+++ b/resistance_mut.py
@@ -52,21 +52,26 @@ async def fetch_all_data(mutations, date_range):
 def fetch_reformat_data(formatted_mutations, date_range):
     all_data = asyncio.run(fetch_all_data(formatted_mutations, date_range))
 
-        # filter out mutations with no data
-    all_data = [data for data in all_data if data['data']]
+    # get all unique dates
+    dates = set()
+    for data in all_data:
+        if data['data']:
+            for d in data['data']:
+                dates.add(d['date'])
+
+    print(dates)
+    print(len(dates))
+
+    # make a dataframe with the dates as columns and the mutations as rows
+    df = pd.DataFrame(index=formatted_mutations, columns=list(dates))
 
-        # build a dataframe from the collected data
-        # for each mutation make a row 
-        # iterate through the data and add a column for each date with the number of samples
-    mutation_data = []
+    # fill the dataframe with the data
     for data in all_data:
-        mutation = data['mutation']
-        mutation_data.append([mutation] + [d['count'] for d in data['data']])
-        
-    st.write("Data fetched from the server:")
-    df = pd.DataFrame(mutation_data, columns=['Mutation'] + [d['date'] for d in all_data[0]['data']])
-        # Set the first column as the index
-    df.set_index(df.columns[0], inplace=True)
+        if data['data']:
+            for d in data['data']:
+                df.at[data['mutation'], d['date']] = d['count']
+                print(data['mutation'], d['date'], d['count'])
+
     return df
 
 
@@ -79,16 +84,16 @@ def plot_heatmap(df):
     cmap.set_bad(color='lightcoral')  # Set NaN values to light rose color
 
     # Plot the heatmap
-    fig, ax = plt.subplots(figsize=(12, 8))
+    fig, ax = plt.subplots(figsize=(15, 8))
     annot = True if df.shape[0] * df.shape[1] <= 100 else False  # Annotate only if the plot is small enough
     sns.heatmap(df, cmap=cmap, ax=ax, cbar_kws={'label': 'Occurrence Frequency'}, 
                 linewidths=.5, linecolor='lightgrey', annot=annot, fmt=".1f", 
-                annot_kws={"size": 8}, mask=df.isnull(), cbar=True)
+                annot_kws={"size": 10}, mask=df.isnull(), cbar=True)
 
     # Set axis labels
     ax.set_xticks([0, len(df.columns) // 2, len(df.columns) - 1])
     ax.set_xticklabels([df.columns[0], df.columns[len(df.columns) // 2], df.columns[-1]], rotation=45)
-    ax.set_yticklabels(df.index.tolist(), fontsize=10, rotation=0)  # Rotate mutation labels to be horizontal
+    ax.set_yticklabels(df.index.tolist(), fontsize=12, rotation=0)  # Rotate mutation labels to be horizontal
 
     return fig
 
@@ -127,7 +132,7 @@ def app():
 
     if st.button("Fetch Data"):
         df = fetch_reformat_data(formatted_mutations, date_range)
-
+        st.write(df)
         # Plot the heatmap
         fig = plot_heatmap(df)
         st.pyplot(fig)

From bdf7221cd5ad60d1892e3daf58d31c68aa16a3ad Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Gordon=20J=2E=20K=C3=B6hn?= <gordon@koehn.net>
Date: Mon, 25 Nov 2024 13:46:46 +0100
Subject: [PATCH 16/20] fix plot

---
 resistance_mut.py | 34 ++++++++++++++++++----------------
 1 file changed, 18 insertions(+), 16 deletions(-)

diff --git a/resistance_mut.py b/resistance_mut.py
index ef3cc74..6acf84c 100644
--- a/resistance_mut.py
+++ b/resistance_mut.py
@@ -52,15 +52,16 @@ async def fetch_all_data(mutations, date_range):
 def fetch_reformat_data(formatted_mutations, date_range):
     all_data = asyncio.run(fetch_all_data(formatted_mutations, date_range))
 
+    # get dates from date_range
+    dates = pd.date_range(date_range[0], date_range[1]).strftime('%Y-%m-%d')
+
     # get all unique dates
-    dates = set()
-    for data in all_data:
-        if data['data']:
-            for d in data['data']:
-                dates.add(d['date'])
+    # dates = set()
+    # for data in all_data:
+    #     if data['data']:
+    #         for d in data['data']:
+    #             dates.add(d['date'])
 
-    print(dates)
-    print(len(dates))
 
     # make a dataframe with the dates as columns and the mutations as rows
     df = pd.DataFrame(index=formatted_mutations, columns=list(dates))
@@ -70,7 +71,6 @@ def fetch_reformat_data(formatted_mutations, date_range):
         if data['data']:
             for d in data['data']:
                 df.at[data['mutation'], d['date']] = d['count']
-                print(data['mutation'], d['date'], d['count'])
 
     return df
 
@@ -83,18 +83,18 @@ def plot_heatmap(df):
     cmap = sns.color_palette("Blues", as_cmap=True)
     cmap.set_bad(color='lightcoral')  # Set NaN values to light rose color
 
-    # Plot the heatmap
-    fig, ax = plt.subplots(figsize=(15, 8))
+    # Adjust the plot size based on the number of rows in the dataframe
+    height = max(8, len(df) * 0.3)  # Minimum height of 8, with 0.5 units per row
+    fig, ax = plt.subplots(figsize=(15, height))
+
     annot = True if df.shape[0] * df.shape[1] <= 100 else False  # Annotate only if the plot is small enough
-    sns.heatmap(df, cmap=cmap, ax=ax, cbar_kws={'label': 'Occurrence Frequency'}, 
+    sns.heatmap(df, cmap=cmap, ax=ax, cbar_kws={'label': 'Occurrence Frequency', 'orientation': 'horizontal'}, 
                 linewidths=.5, linecolor='lightgrey', annot=annot, fmt=".1f", 
-                annot_kws={"size": 10}, mask=df.isnull(), cbar=True)
+                annot_kws={"size": 10}, mask=df.isnull(), cbar=True, cbar_ax=fig.add_axes([0.15, 0.89, 0.7, 0.02]))
 
     # Set axis labels
     ax.set_xticks([0, len(df.columns) // 2, len(df.columns) - 1])
     ax.set_xticklabels([df.columns[0], df.columns[len(df.columns) // 2], df.columns[-1]], rotation=45)
-    ax.set_yticklabels(df.index.tolist(), fontsize=12, rotation=0)  # Rotate mutation labels to be horizontal
-
     return fig
 
 
@@ -124,15 +124,17 @@ def app():
     # Apply the lambda function to each element in the mutations list
     formatted_mutations = [format_mutation(mutation) for mutation in mutations]
 
-    st.write(f"Selected mutations: {formatted_mutations}")
+    st.write(f"Selected mutations:")
+    st.write(formatted_mutations)
+     
 
     # Allow the user to choose a date range
     st.write("Select a date range:")
     date_range = st.date_input("Select a date range:", [pd.to_datetime("2022-01-01"), pd.to_datetime("2024-01-01")])
 
     if st.button("Fetch Data"):
+        st.write("Fetching data...")
         df = fetch_reformat_data(formatted_mutations, date_range)
-        st.write(df)
         # Plot the heatmap
         fig = plot_heatmap(df)
         st.pyplot(fig)

From f23dde05c1d20f476aae469e59415211d22b4ab5 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Gordon=20J=2E=20K=C3=B6hn?= <gordon@koehn.net>
Date: Mon, 25 Nov 2024 13:50:16 +0100
Subject: [PATCH 17/20] restantrce plots

---
 resistance_mut.py | 15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)

diff --git a/resistance_mut.py b/resistance_mut.py
index 6acf84c..0c4d5e9 100644
--- a/resistance_mut.py
+++ b/resistance_mut.py
@@ -81,7 +81,7 @@ def plot_heatmap(df):
 
     # Create a colormap with a custom color for NaN values
     cmap = sns.color_palette("Blues", as_cmap=True)
-    cmap.set_bad(color='lightcoral')  # Set NaN values to light rose color
+    cmap.set_bad(color='#FFCCCC')  # Set NaN values to a fainter red color
 
     # Adjust the plot size based on the number of rows in the dataframe
     height = max(8, len(df) * 0.3)  # Minimum height of 8, with 0.5 units per row
@@ -90,7 +90,7 @@ def plot_heatmap(df):
     annot = True if df.shape[0] * df.shape[1] <= 100 else False  # Annotate only if the plot is small enough
     sns.heatmap(df, cmap=cmap, ax=ax, cbar_kws={'label': 'Occurrence Frequency', 'orientation': 'horizontal'}, 
                 linewidths=.5, linecolor='lightgrey', annot=annot, fmt=".1f", 
-                annot_kws={"size": 10}, mask=df.isnull(), cbar=True, cbar_ax=fig.add_axes([0.15, 0.89, 0.7, 0.02]))
+                annot_kws={"size": 10}, mask=df.isnull(), cbar=True, cbar_ax=fig.add_axes([0.15, 0.90, 0.7, 0.02]))
 
     # Set axis labels
     ax.set_xticks([0, len(df.columns) // 2, len(df.columns) - 1])
@@ -135,9 +135,14 @@ def app():
     if st.button("Fetch Data"):
         st.write("Fetching data...")
         df = fetch_reformat_data(formatted_mutations, date_range)
-        # Plot the heatmap
-        fig = plot_heatmap(df)
-        st.pyplot(fig)
+        
+        # Check if the dataframe is all NaN
+        if df.isnull().all().all():
+            st.error("The fetched data contains only NaN values. Please try a different date range or mutation set.")
+        else:
+            # Plot the heatmap
+            fig = plot_heatmap(df)
+            st.pyplot(fig)
 
 if __name__ == "__main__":
     app()
\ No newline at end of file

From d0fafe80d605624f730fbcca80042791b9afdaf1 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Gordon=20J=2E=20K=C3=B6hn?= <gordon@koehn.net>
Date: Mon, 25 Nov 2024 14:04:21 +0100
Subject: [PATCH 18/20] forgot the datafiles

---
 data/3CLpro_inhibitors_datasheet.csv |  72 ++++++++++++
 data/RdRP_inhibitors_datasheet.csv   |  20 ++++
 data/spike_mAbs_datasheet.csv        | 165 +++++++++++++++++++++++++++
 3 files changed, 257 insertions(+)
 create mode 100644 data/3CLpro_inhibitors_datasheet.csv
 create mode 100644 data/RdRP_inhibitors_datasheet.csv
 create mode 100644 data/spike_mAbs_datasheet.csv

diff --git a/data/3CLpro_inhibitors_datasheet.csv b/data/3CLpro_inhibitors_datasheet.csv
new file mode 100644
index 0000000..d7f787f
--- /dev/null
+++ b/data/3CLpro_inhibitors_datasheet.csv
@@ -0,0 +1,72 @@
+Mutation,NTV: fold,NTV: pocket,ENS: fold,fitness,in patient,in vitro,Prevalence
+T21I,1.5,,1.6,1.6,,12,0.1%
+T25A,12.6,,87.7,,,,0.002%
+T25N,0.8,,22.9,,,,0.00006%
+T45I,1.6,1,4.8,,,,0.02%
+D48Y,2,1,5.9,,,,0.0005%
+M49I,1.1,1,10.1,1.8,,,0.02%
+M49L,1.4,1,40.9,1.2,,2,0.0002%
+M49T,0.8,1,3.6,1.4,,,0.0005%
+M49del,2.8,1,,0.5,,,
+L50F,1.5,1,1.1,2.3,1,9,0.04%
+G138S,3.5,,,,,1,0.00008%
+F140L,5.9,,,,,2,0.0001%
+F140S,260,,,,,,0.00004%
+N142D,1.5,1,3.2,1.1,,,0.0008%
+N142L,2.5,1,,1.4,,,0.0001%
+N142S,1.2,1,4.9,1.2,,,0.001%
+G143S,147.7,1,15.6,0,,,0.00001%
+S144A,7.3,1,17.2,0.6,,2,0.00009%
+S144E,81.5,1,,0,,,0.00001%
+S144L,1154.1,1,,0,,,0.00006%
+S144P,2851.7,1,,0,,,0.00001%
+C160F,1,,,0.7,,4,0.01%
+M165R,384.2,1,,0,,,0.00001%
+M165T,15.8,1,,0.1,,,0.00003%
+E166A,10,1,6.3,0.1,1,5,0.00004%
+E166G,6.2,1,,0.1,,,0.00004%
+E166K,76.6,1,,0,,,0.00003%
+E166Q,2.7,1,,1,,,0.00005%
+E166V,287.5,1,50.3,0.1,5,3,0.0001%
+L167F,7,1,12.8,0.3,,6,0.0002%
+P168del,7,1,6.1,,,,
+T169I,1.1,1,1.3,,,2,0.003%
+H172L,898.8,1,,0,,,0.00001%
+H172N,464.1,1,,0,,,0.00001%
+H172Q,5.8,1,,0.3,,1,0.00004%
+H172Y,24.2,1,,0.2,,2,0.00009%
+A173T,2.5,,1.2,,,1,0.002%
+A173V,6.4,,1.3,,,3,0.002%
+V186A,,1,,,,2,0.0004%
+R188G,38,1,,,,2,0.00009%
+R188S,2.9,1,5.8,0.9,,,0.0007%
+Q189I,4.2,1,,,,,0.00003%
+Q189K,8.6,1,1.9,0.3,,,0.0003%
+T190I,1.2,1,2.9,1.3,,,0.02%
+A191T,1.2,1,4.6,1.7,,3,0.006%
+A191V,1.6,1,3.6,1.9,,7,0.08%
+Q192A,18.2,1,,0.2,,,0.0007%
+Q192C,16.3,1,,0.1,,,0.00006%
+Q192D,10.4,1,,0,,,0.00006%
+Q192E,34.2,1,,0.1,,,0.00003%
+Q192F,24.6,1,,0.3,,,0.00001%
+Q192G,34.4,1,,0.1,,,0.00009%
+Q192H,24.7,1,,0.1,,,0.00009%
+Q192I,13.7,1,,0.2,,,0.00008%
+Q192K,27.9,1,,0,,,0.0003%
+Q192L,29,1,,0.2,,,0.0002%
+Q192N,2.8,1,,0.1,,,0.00001%
+Q192P,7.8,1,,0.1,,,0.0002%
+Q192R,19.2,1,3.2,0.1,,1,0.0002%
+Q192S,24.3,1,,0.1,,,0.0003%
+Q192T,16.8,1,,0.1,,,0.0002%
+Q192V,10.1,1,,0.1,,,0.0002%
+Q192W,12.9,1,,0.1,,,0.00001%
+Q192Y,384.2,1,,0,,,0.0001%
+A193P,,,,,,2,0.0004%
+A194S,3.3,,,,,1,0.002%
+P252L,5.8,,1.3,,,5,0.004%
+V297A,3,,,,,,0.00001%
+S301P,,,,,,2,0.0002%
+T304I,2.5,,1,,,8,0.007%
+F305L,,,,,,2,0.001%
\ No newline at end of file
diff --git a/data/RdRP_inhibitors_datasheet.csv b/data/RdRP_inhibitors_datasheet.csv
new file mode 100644
index 0000000..22ccd61
--- /dev/null
+++ b/data/RdRP_inhibitors_datasheet.csv
@@ -0,0 +1,20 @@
+Mutation,RDV: fold,in patient,in vitro,Prevalence
+V166A,,,1,0.0008%
+V166L,1.5,2,1,0.004%
+N198S,,,1,0.01%
+R285C,,2,,0.006%
+A376V,12.6,,,0.00002%
+A449V,,2,,0.07%
+F480L,2,,1,0.0002%
+D484Y,3.1,1,,0.0008%
+A526V,,,1,0.04%
+V557L,2,,1,0.0003%
+G671S,1,2,,47%
+S759A,2.6,,1,0%
+V792I,2.6,3,1,0.002%
+E796G,2.8,,1,0.0007%
+C799F,3.4,,2,0.0009%
+C799R,2.8,,1,0.00006%
+E802A,3,,,0.0002%
+E802D,6,1,1,0.002%
+M924R,,2,,0.003%
\ No newline at end of file
diff --git a/data/spike_mAbs_datasheet.csv b/data/spike_mAbs_datasheet.csv
new file mode 100644
index 0000000..dc0631d
--- /dev/null
+++ b/data/spike_mAbs_datasheet.csv
@@ -0,0 +1,165 @@
+Mutation,BAM: fold,BAM: dms,ETE: fold,ETE: dms,CAS: fold,CAS: dms,IMD: fold,IMD: dms,CIL: fold,CIL: dms,TIX: fold,TIX: dms,SOT: fold,SOT: dms,BEB: fold,BEB: dms,REG: fold,AMU: fold,ROM: fold,ADI: fold,C135: fold,C135: dms,C144: fold,C144: dms,in patient,in vitro,Prevalence
+P337H,,,,,,,,,,,,,6.3,1,,,,,,,,,,,6,,0.0008%
+P337L,,,,,,,5,,,,,,186,0.997,,,,,,,,,,,10,1,0.003%
+P337R,,,,,,,,,,,,,234,0.999,,,,,,,,,,,4,,0.0004%
+P337S,,,,,,,,,,,,,1.8,0.999,,,,,,,,,,,22,,0.003%
+P337T,,,,,,,,,,,,,8,0.992,,,,,,,,,,,,,0.001%
+E340A,,,,,,,,,,,,,100,0.997,,,,,,,,,,,13,3,0.002%
+E340D,,,,,,,,,,,,,14.8,0.988,,,,,,,,,,,23,,0.003%
+E340G,,,,,,,,,,,,,22.6,0.986,,,,,,,,,,,1,,0.0008%
+E340K,,,0.4,,,,,,,,,,5148,0.997,,,,,,,,,,,25,1,0.004%
+E340Q,,,,,,,,,,,,,50,0.966,,,,,,,,,,,4,,0.0005%
+E340V,,,,,,,,,,,,,200,,,,,,,,,,,,7,,0.001%
+T345P,,,,,,,,,,,,,,0.991,,,,,,,,,,,,1,0.0001%
+R346G,,,,,,,,,,0.606,,,0.9,,,,,,,,,0.697,,,,4,0.005%
+R346I,,,,,,,,,200,0.728,,,1.7,,,,,,,,,0.734,,,2,3,0.01%
+R346K,1.3,,2.4,,1.1,,2.9,,2.6,,2.2,,1.4,,0.7,,0.3,0.8,21,0.8,2296.4,0.82,0.8,,2,2,8.9%
+R346S,,,1.8,,,,,,,0.763,,,1.8,,0.4,,,,,,2700,0.813,0.9,,2,1,0.03%
+R346T,,,,,,,,,,0.9,,,1.3,,,,,,,,,0.804,,,3,,0.006%
+K356Q,,,,,,,,,,,,,0.9,0.106,,,,,,,,,,,,,0.001%
+K356T,,,,,,,,,,,,,5.9,0.9,,,,,,,,,,,3,,0.0008%
+S371F,0.9,,143,,13.5,,87,,1.3,,26,,13.3,,2.4,,20.8,124.5,22,51.6,,,,,6,,6.0%
+S371L,1.6,,17.1,,3.9,,18.4,,1,,4,,9.7,,2.2,,1.1,17.1,17,15,,,,,2,,17%
+D405E,,,,0.186,,,,,,,,,,,,,,,,,,,,,,,0.0006%
+D405N,1.8,,20.9,0.275,10.9,,1.9,,1,,2.1,,0.7,,0.5,,1,2,1.6,2.1,,,,,1,1,6.0%
+E406D,,,,,51,,,,,,,,,,,,,,,,,,,,,,0.001%
+K417E,,,,0.99,165.4,0.564,0.9,,0.4,,,,0.9,,1.3,,,,,,,,,,,9,0.0004%
+K417H,,,,0.987,,0.34,,,,,,,,,,,,,,,,,,,,,0.0002%
+K417I,,,,0.999,,,,,,,,,,,,,,,,,,,,,1,,0.0002%
+K417M,,,,0.966,,,,,,,,,,,,,,,,,,,,,,,0.0003%
+K417N,0.6,,381.7,0.997,12.5,,0.7,,0.7,,0.4,,0.7,,0.7,,0.6,1.7,0.5,0.9,0.3,,0.8,,3,6,23%
+K417R,,,,0.115,61,,,,,,,,,,,,,,,,,,,,,2,0.004%
+K417S,,,,0.98,,,,,,,,,,,,,,,,,,,,,,,0.0002%
+K417T,,,49,0.987,7.1,,1.1,,,,,,0.7,,0.7,,0.7,0.9,0.6,,,,,,3,1,1.4%
+D420A,,,,0.987,,,,,,,,,,,,,,,,,,,,,,,0.0002%
+D420N,2.6,,60.6,0.993,,,,,,,,,,,0.7,,,,,,,,,,,1,0.0008%
+N439K,2.4,,0.4,,0.8,,28.8,,1.2,,,,1,,0.5,,,1,0.9,,238.6,,0.8,,,2,0.6%
+N440D,,,,,,,,0.473,,,,,1.3,,1.9,,,,,,,,,,1,2,0.0004%
+N440E,,,,,,,,0.632,,,,,0.8,,,,,,,,,,,,,,0.0001%
+N440I,,,,,,,,0.918,,,,,1.2,,,,,,,,,0.424,,,,,0.0006%
+N440K,1.2,,1.1,,1,,92,0.565,1.3,,1,,1.5,,0.8,,0.3,2.1,1.6,1.8,647.1,0.815,1.1,,3,2,23%
+N440R,,,,,,,,,,,,,,,,,,,,,,0.23,,,,,0.0002%
+N440T,,,,,,,,0.496,,,,,0.8,,,,,,,,,,,,,,0.001%
+N440Y,,,,,,,,0.504,,,,,0.7,,,,,,,,,,,,,,0.004%
+S443Y,,,,,,,,0.821,,0.194,,,,,,,,,,,,0.585,,,,,0.0001%
+K444E,,,,,,,,0.962,291.2,0.946,,,,,,0.81,,,,,,0.627,,,,8,0.0002%
+K444F,,,,,,,,0.958,,0.883,,,,,,0.678,,,,,,0.672,,,,,0.0001%
+K444I,,,,,,,,0.994,,0.982,,,,,,0.678,,,,,,0.641,,,,,0.0002%
+K444L,,,,,,,153,0.971,,0.988,,,,,,0.69,,,,,,0.624,,,,,0.0001%
+K444M,,,,,,,1577,0.969,,0.979,,,,,,,,,,,,0.208,,,,1,0.002%
+K444N,,,,,,,755,0.943,,0.933,,,,,1901,0.718,,,,,33.7,,1.1,,,7,0.01%
+K444R,,,,,,,,,200,0.964,,,,,,,,,,,1.1,,1.2,,,5,0.01%
+K444T,,,,,2,,1026.6,0.982,,0.956,,,,,1814,0.635,,,,,44.3,,2,,5,4,0.002%
+V445A,,,,,1.8,,548,0.98,35.5,,,,3.4,,83.3,,,,,,,,,,2,5,0.005%
+V445D,,,,,,,,0.957,,0.564,,,,,,0.764,,,,,,,,,,1,0.0001%
+V445F,,,,,,,,0.885,,,,,,,369,0.654,,,,,,,,,1,1,0.003%
+V445I,,,,,,,,,,,,,,,,,,,,,5.6,,1.5,,,,0.003%
+V445L,,,,,,,,0.806,,,,,,,,,,,,,7.2,,1.1,,,,0.0002%
+G446A,,,,,,,,0.745,,,,,,,,,,,,,,,,,,,0.001%
+G446D,,,,,,,,0.978,,,,,,,69,,,,,,,,,,8,4,0.001%
+G446I,,,,,,,,0.953,,,,,,,,,,,,,,0.164,,,,1,0.0001%
+G446N,,,,,,,,0.924,,,,,,,,,,,,,,,,,,,0.0008%
+G446R,,,,,,,,0.953,,,,,,,7,,,,,,,,,,,1,0.002%
+G446S,1.2,,0.9,,1.3,,574,0.824,3.7,,1.2,,1.6,,2,,1.1,0.9,1.3,3.4,3.5,,1.1,,1,,17%
+G446T,,,,,,,,0.986,,,,,,,,,,,,,,,,,,,0.0002%
+G446V,,,0.8,,0.7,,348.5,0.959,3.6,,,,1.5,,4.3,,,0.9,,,858,0.16,1.3,,4,4,0.1%
+G447C,,,,,,,,0.591,,,,,,,,,,,,,,,,,,,0.0002%
+G447D,,,,,,,,0.986,,0.935,,,,,,,,,,,,,,,,,0.0002%
+G447F,,,,,,,,0.908,,0.863,,,,,,,,,,,,,,,,,0.0001%
+G447S,,,,,,,,0.652,,0.171,,,,,,,,,,,,,,,,2,0.0007%
+G447V,,,,,,,,0.841,,0.882,,,,,,,,,,,,,,,,,0.001%
+N448D,,,,,,,,0.613,,0.859,,,,,,,,,,,,,,,,1,0.0005%
+N448K,,,,,,,,0.691,,0.97,,,,,,,,,,,,0.47,,,,1,0.0006%
+N448T,,,,,,,,0.126,,0.854,,,,,,,,,,,,,,,,,0.0006%
+N448Y,,,,,,,,,,0.841,,,,,,,,,,,,0.672,,,,,0.0001%
+Y449D,,,,,,,,,,0.674,,,,,,,,,,,,,,,,,0.0007%
+N450D,,,,,1.4,,20.9,,382.3,0.7,,,,,,,,,,,,,,,1,5,0.002%
+N450K,,,0.4,,,,,,9.1,,,,0.8,,0.7,,,,,,,,,,,2,0.03%
+L452M,1,,0.9,,0.4,,1,,1,,0.5,,2.1,,0.6,,,0.9,8.1,1.3,,,,,,,0.03%
+L452Q,3,,1.8,,3.1,,4.2,,2.2,,0.5,,2.7,,0.8,,,1.3,21.3,1.3,,,,,,,0.1%
+L452R,1254.5,0.934,1,,1.1,,1.7,,5.7,,0.5,,1.1,,0.6,,35,1.3,116,1.1,,,,,4,6,38%
+L452W,,0.179,,,,,,,,,,,,,,,,,,,,,,,,,0.002%
+Y453F,1.4,,1.4,,456,0.574,1.3,,0.8,,,,1.1,,0.7,,,1.1,1.3,,,,1.1,,2,3,0.03%
+Y453H,,,,,,0.427,,,,,,,,,,,,,,,,,,,,,0.0003%
+L455F,,,,,80,0.364,1.1,,0.6,,3.6,,0.6,,,,,,,,1.7,,68.3,0.802,3,2,0.03%
+L455M,,,,,,,,,,,,,,0.108,,,,,,,,,,,,,0.0002%
+L455S,,,,,,0.545,,,,,,,,,,,,,,,,,,0.941,1,,0.002%
+L455W,,,,0.966,,0.578,,,,,,,,,,,,,,,,,,0.973,2,,0.0001%
+F456C,,,,0.987,,,,,,,,,,,,,,,,,,,,0.994,,,0.0002%
+F456L,,,,,,,,,,,,,,,,,,,,,,,,0.946,2,1,0.005%
+F456V,,,,0.969,,,,,,,,,,,,,,,,,0.2,,159.9,0.952,,3,0.0004%
+S459P,,,,0.685,,,,,,,,,,,,,,,,,,,,,,,0.0004%
+N460D,,,,0.105,,,,,,,,,,,,,,,,,,,,,,,0.0008%
+N460H,,,,0.975,,,,,,,,,,,,,,,,,,,,,,1,0.0001%
+N460I,,,,0.995,,,,,,,,,,,,,,,,,,,,,,,0.001%
+N460K,1.5,,76.3,0.996,1.3,,1.3,,0.8,,1,,1.2,,1.2,,,8.9,2.4,,,,,,2,1,0.002%
+N460S,0.5,,155.3,0.957,,,,,,,,,,,0.7,,,,,,,,,,,1,0.01%
+N460T,2.3,,75,0.992,,,,,,,,,0.6,,,,,,,,,,,,,1,0.0003%
+N460Y,1.7,,100,0.886,,,,,,,,,,,,,,,,,,,,,1,1,0.001%
+A475D,,,,0.964,,0.381,,,,,,0.929,,,,,,,,,0.5,,1.2,,,1,0.0001%
+A475V,,,16.7,0.611,,,,,0.6,,,,2.3,,,,,70.8,,,1.3,,1.2,,2,,0.03%
+G476D,,,,,,0.895,,,,,,0.987,,,,,,,,,,,,,1,7,0.0007%
+G476R,,,,0.733,,0.469,,,,,,0.973,,,,,,,,,,,,,,,0.0001%
+G476T,,,,0.967,,,,,,,,0.929,,,,,,,,,,,,,,,0.0001%
+V483A,39.6,,1,,0.4,,0.6,,,,,,,,0.3,,,1.5,,,1,,1,,8,,0.005%
+E484A,678.6,0.911,3.4,,9,,1.5,,1.3,,8.1,,0.9,,1.4,,1.1,7.7,1.9,3.6,1.8,,1743.2,0.973,6,5,23%
+E484D,100,0.889,,,,,,,,,7.1,,,,1,,,,,,1,,181.7,0.817,1,5,0.003%
+E484G,,,,,,,,,,,,,,,,,,,,,,,137.3,0.937,2,3,0.003%
+E484K,1333.3,0.97,2.9,,18.4,,1,,1,,8.1,,0.4,,0.7,,8.7,1.4,2.5,,0.4,,1388,0.966,30,33,2.9%
+E484P,,0.993,,,,,,,,,,,,,,,,,,,,,,0.992,,,0.0008%
+E484Q,100,0.987,1.3,,19,,1,,,,3,,0.4,,0.7,,,1.5,2.6,,1.4,,1743.2,0.991,11,1,0.2%
+E484R,,0.991,,,,,,,,,,,,,,,,,,,,,,0.953,,,0.0005%
+E484S,,0.702,,,,,,,,,,,,,,,,,,,,,,0.97,,,0.0008%
+E484T,,0.954,,,,,,,,,,,,,,,,,,,,,,0.997,,,0.0007%
+E484V,,0.977,,,,0.555,,,,,,,,,,,,,,,,,,0.983,2,2,0.01%
+G485D,,0.75,,,4.4,,0.6,,,,,0.673,,,,,,,,,,,,,,3,0.001%
+G485R,,0.885,,,,,,,,,,,,,,,,,,,,,0.7,,2,,0.001%
+F486D,,,,,,0.983,,,,,,0.996,,,,,,,,,,,,,,,0.0002%
+F486I,,0.803,,,,0.825,,,,,,0.149,,,1.7,,,,,,,,,,2,1,0.001%
+F486L,,0.86,7.6,,61,0.267,0.8,,,,,,1.4,,,,,3.1,2.1,,,,1.1,,,2,0.002%
+F486N,,,,0.163,,0.968,,,,,,0.985,,,,,,,,,,,,,,,0.0001%
+F486P,,0.878,,0.316,,0.965,,,,,,0.985,,,,,,,,,,,,0.283,,1,0.0002%
+F486S,,,,0.249,509.9,0.97,0.4,,,,600,0.997,,,,,,,,,,,,0.39,3,6,0.003%
+F486T,,0.804,,0.157,,0.963,,,,,,0.987,,,,,,,,,,,,,,,0.0002%
+F486V,490.3,0.73,11.3,0.142,814.9,0.945,0.9,,0.7,,135.5,0.285,1.1,,1.5,,,12.8,1.6,1.3,,,,,1,9,0.0007%
+N487D,,,,0.952,,0.819,,,,,,0.939,,,,,,,,,,,,0.448,,3,0.0002%
+N487H,,,,0.949,,,,,,,,0.41,,,,,,,,,,,,,,,0.0002%
+N487S,,,,0.994,,,,,,,,0.471,,,,,,,,,,,,,,1,0.0002%
+Y489H,,,,0.991,,0.943,,,,,,0.42,1.5,,2,,,,,,,,20.2,0.813,1,,0.001%
+Y489W,,,,0.913,,0.738,,,,,,0.955,,,,,,,,,,,,,,,0.0002%
+F490G,,0.908,,,,,,,,,,,,,,,,,,,,,,0.968,,,0.0001%
+F490I,,,,,,,,,,,,,,,,,,,,,,,,0.981,,,0.0007%
+F490L,844.3,,2.1,,2.9,,0.8,,,,,,,,1,,,0.7,,,2.1,,233.4,0.967,4,4,0.02%
+F490R,,0.985,,,,,,,,,,,,,,,,,,,,,,0.993,,,0.002%
+F490S,333.3,0.858,1.1,,0.8,,1.2,,1.1,,,,0.8,,1.7,,,1.3,134.9,,1.2,,4.1,,7,5,0.2%
+F490V,,,,,,,,,,,,,,,,,,,,,,,,0.882,,2,0.003%
+F490Y,,0.15,,,,,,,,,,,,,,,,,,,,,,,1,,0.002%
+Q493D,,,,,,0.795,,,,,,,,,,,,,,,,,,0.866,,,0.0002%
+Q493E,,,,,446,0.72,,,,,,,,,,,,,,,,,,,1,,0.009%
+Q493H,13.9,,1,,,0.195,,,,,,,,,,,,,,,,,,,,,0.001%
+Q493K,2451.3,0.983,54.2,0.378,301,0.633,1.4,,1.6,,1.9,,1.6,,1,,,,,,1.4,,3349,0.996,8,8,0.002%
+Q493L,9.9,,3.8,,,0.179,,,,,,,1.1,,,,,,,,2,,20.5,0.72,1,,0.003%
+Q493R,1185,0.965,46.4,0.582,42,0.112,1.5,,1.1,,6.5,,1.2,,1,,949,11.6,2,1.4,1,,917.3,0.981,17,6,23%
+Q493V,,0.137,,0.131,,,,,,,,,,,,,,,,,,,,0.861,,,0.0002%
+S494P,100,0.881,0.6,,2.1,,1.5,,1.2,,,,2,,0.7,,,0.7,1.6,,0.8,,99.1,0.905,12,3,0.2%
+S494R,844.3,0.981,3.1,,1.1,,3,,,0.881,,,,,1.5,,,,,,,,,,,,0.0001%
+G496S,1.1,,1.3,,1,,5.5,,1.8,,0.9,,1.1,,1.7,,0.6,2.5,1.2,2.2,,,,,,,17%
+Q498H,,,,,,,17,,,,,,,,,,,,,,,,,,,,0.0004%
+P499H,,,,,,,,0.334,,,,,,,1606,0.644,,,,,,,,,,2,0.001%
+P499R,,,,,,,,0.892,,,,,,,976.7,0.668,,,,,,,,,,2,0.008%
+P499S,,,,,,,206,0.813,,,,,,,37.5,,,,,,,,,,,,0.003%
+P499T,,,,,,,,0.606,,,,,,,,,,,,,,,,,,,0.0007%
+N501T,1.1,,10,,,,,,,,,,,,,,,,,,,,,,9,1,0.08%
+N501Y,1.1,,5.3,,1,,1,,1.3,,1.5,,1.6,,0.7,,3.8,1,2.3,3.1,1.4,,1.5,,8,3,45%
+G504C,,,,0.791,,,,,,,,,,,,,,,,,,,,,,,0.0001%
+G504D,,,,0.237,,,,,,,,,,,,,,,,,,,1.8,,1,6,0.002%
+G504I,,,,0.908,,,,,,,,,,,,,,,,,,,,,,,0.0002%
+G504L,,,,0.684,,,,,,,,,,,,,,,,,,,,,,,0.0002%
+G504N,,,,0.295,,,,,,,,,,,,,,,,,,,,,,,0.0006%
+G504R,,,,0.281,,,,,,,,,,,,,,,,,,,,,,,0.0001%
+G504V,,,,0.705,,,,,,,,,,,,,,,,,,,,,,,0.0006%
+P507A,,,,,,,,0.361,,,,,,,,,,,,,,,,,,,0.0005%
+N856K,1.4,,9.2,,2.1,,1.4,,1.3,,2.9,,1.7,,1.3,,1.3,1.6,2.3,1.7,,,,,,,18%
+N969K,1.5,,5.7,,1.4,,1.6,,1.4,,2.4,,1.5,,3.9,,0.9,3.1,1.4,1.9,,,,,,,24%
+E990A,,,,,,,,,,,6.1,,,,,,,,,,,,,,,,0.0004%
+T1009I,,,,,,,,,,,8.2,,,,,,,,,,,,,,,,0.01%
\ No newline at end of file

From c30f6145f7d3f2520daff1b042a8a907f5482686 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Gordon=20J=2E=20K=C3=B6hn?= <gordon@koehn.net>
Date: Mon, 25 Nov 2024 14:16:01 +0100
Subject: [PATCH 19/20] add test

---
 resistance_mut.py | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/resistance_mut.py b/resistance_mut.py
index 0c4d5e9..c0778fd 100644
--- a/resistance_mut.py
+++ b/resistance_mut.py
@@ -102,7 +102,15 @@ def plot_heatmap(df):
 def app():
     st.title("Resistance Mutations")
 
-    st.write("This page allows you to run the Lollipop variant deconvolution tool with custom variant definitions.")
+    st.write("This page allows you to visualize the numer of observed resistance mutations over time.")
+    st.write("The data is fetched from the COV-Spectrum API and currently used clinical data.")
+
+    st.write("The sets of resistance mutations are provide from Stanfords Coronavirus Antivirial & Reistance Database. Last updated 05//14/2024")
+
+    st.write("This is a demo frontend to later make the first queries to SILO for wastewater data.")
+
+    # make a horizontal line
+    st.markdown("---")
 
     st.write("Select from the following resistance mutation sets:")
 

From 10106bbf249738786c3015fd275159a644da1f38 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Gordon=20J=2E=20K=C3=B6hn?= <gordon.koehn@dbsse.ethz.ch>
Date: Mon, 16 Dec 2024 13:15:01 +0100
Subject: [PATCH 20/20] add SILO

---
 app.py                 |   4 +-
 config.yaml            |   3 +-
 resistance_mut_silo.py | 166 +++++++++++++++++++++++++++++++++++++++++
 3 files changed, 171 insertions(+), 2 deletions(-)
 create mode 100644 resistance_mut_silo.py

diff --git a/app.py b/app.py
index 8d0fb4c..43a2ebe 100644
--- a/app.py
+++ b/app.py
@@ -3,12 +3,14 @@
 import mutation_freq
 import variant_deconv
 import resistance_mut
+import resistance_mut_silo
 
 PAGES = {
     "Home": {"module": index}, 
     "Mutation Frequency": {"module": mutation_freq},
     "Variant Deconvolution": {"module": variant_deconv},
-    "Resistance Mutations": {"module": resistance_mut}
+    "Resistance Mutations (clinical)": {"module": resistance_mut},
+    "Resistance Mutations (ww)": {"module": resistance_mut_silo}
 }
 
 def sidebar():
diff --git a/config.yaml b/config.yaml
index 50ceba4..b579ffb 100644
--- a/config.yaml
+++ b/config.yaml
@@ -1,2 +1,3 @@
 server:
-  ip_address: "http://68.221.168.92:8000"
\ No newline at end of file
+  ip_address: "http://68.221.168.92:8000"
+  lapis_address: "http://localhost:8080"
\ No newline at end of file
diff --git a/resistance_mut_silo.py b/resistance_mut_silo.py
new file mode 100644
index 0000000..aab2bd6
--- /dev/null
+++ b/resistance_mut_silo.py
@@ -0,0 +1,166 @@
+import json
+from matplotlib import pyplot as plt
+import numpy as np
+import streamlit as st
+import requests
+import yaml
+import pandas as pd
+import logging
+import aiohttp
+import asyncio
+import seaborn as sns
+
+
+# Load configuration from config.yaml
+with open('config.yaml', 'r') as file:
+    config = yaml.safe_load(file)
+
+server_ip = config.get('server', {}).get('lapis_address', 'http://default_ip:8000')
+
+async def fetch_data(session, mutation, date_range):
+    payload = {
+        "aminoAcidMutations": [mutation],
+        "sampling_dateFrom": date_range[0].strftime('%Y-%m-%d'),
+        "sampling_dateTo": date_range[1].strftime('%Y-%m-%d'),
+        "fields": ["sampling_date"]
+    }
+
+    async with session.post(
+        f'{server_ip}/sample/aggregated',
+        headers={
+            'accept': 'application/json',
+            'Content-Type': 'application/json'
+        },
+        json=payload
+    ) as response:
+        if response.status == 200:
+            data = await response.json()
+            return {"mutation": mutation,
+                    "data": data.get('data', [])}
+        else:
+            logging.error(f"Failed to fetch data for mutation {mutation}.")
+            logging.error(f"Status code: {response.status}")
+            logging.error(await response.text())
+            return {"mutation": mutation,
+                    "data": None}
+
+async def fetch_all_data(mutations, date_range):
+    async with aiohttp.ClientSession() as session:
+        tasks = [fetch_data(session, mutation, date_range) for mutation in mutations]
+        return await asyncio.gather(*tasks)
+    
+def fetch_reformat_data(formatted_mutations, date_range):
+    all_data = asyncio.run(fetch_all_data(formatted_mutations, date_range))
+
+    # get dates from date_range
+    dates = pd.date_range(date_range[0], date_range[1]).strftime('%Y-%m-%d')
+
+    # get all unique dates
+    # dates = set()
+    # for data in all_data:
+    #     if data['data']:
+    #         for d in data['data']:
+    #             dates.add(d['date'])
+
+
+    # make a dataframe with the dates as columns and the mutations as rows
+    df = pd.DataFrame(index=formatted_mutations, columns=list(dates))
+
+    # fill the dataframe with the data
+    for data in all_data:
+        if data['data']:
+            for d in data['data']:
+                df.at[data['mutation'], d['sampling_date']] = d['count']
+
+    return df
+
+
+def plot_heatmap(df):
+    # Replace None with np.nan and remove commas from numbers
+    df = df.replace({None: np.nan, ',': ''}, regex=True).astype(float)
+
+    # Create a colormap with a custom color for NaN values
+    cmap = sns.color_palette("Blues", as_cmap=True)
+    cmap.set_bad(color='#FFCCCC')  # Set NaN values to a fainter red color
+
+    # Adjust the plot size based on the number of rows in the dataframe
+    height = max(8, len(df) * 0.3)  # Minimum height of 8, with 0.5 units per row
+    fig, ax = plt.subplots(figsize=(15, height))
+
+    annot = True if df.shape[0] * df.shape[1] <= 100 else False  # Annotate only if the plot is small enough
+    sns.heatmap(df, cmap=cmap, ax=ax, cbar_kws={'label': 'Occurrence Frequency', 'orientation': 'horizontal'}, 
+                linewidths=.5, linecolor='lightgrey', annot=annot, fmt=".1f", 
+                annot_kws={"size": 10}, mask=df.isnull(), cbar=True, cbar_ax=fig.add_axes([0.15, 0.90, 0.7, 0.02]))
+
+    # Set axis labels
+    ax.set_xticks([0, len(df.columns) // 2, len(df.columns) - 1])
+    ax.set_xticklabels([df.columns[0], df.columns[len(df.columns) // 2], df.columns[-1]], rotation=45)
+    return fig
+
+
+
+def app():
+    st.title("Resistance Mutations from Wastewater Data")
+
+    st.write("This page allows you to visualize the numer of observed resistance mutations over time.")
+    st.write("The data is fetched from the WISE-CovSpectrum API and currently cointains demo data for Sep-Oct 2024.")
+
+    st.write("The sets of resistance mutations are provide from Stanfords Coronavirus Antivirial & Reistance Database. Last updated 05/14/2024")
+
+    st.write("This is a demo frontend to later make the first queries to SILO for wastewater data.")
+
+    # make a horizontal line
+    st.markdown("---")
+
+    st.write("Select from the following resistance mutation sets:")
+
+    # TODO: currently hardcoded, should be fetched from the server
+    options = {
+        "3CLpro Inhibitors": 'data/3CLpro_inhibitors_datasheet.csv',
+        "RdRP Inhibitors": 'data/RdRP_inhibitors_datasheet.csv',
+        "Spike mAbs": 'data/spike_mAbs_datasheet.csv'
+    }
+
+    selected_option = st.selectbox("Select a resistance mutation set:", options.keys())
+
+    df = pd.read_csv(options[selected_option])
+
+    gene_name =  {
+        "3CLpro Inhibitors": "ORF1a",
+        "RdRP Inhibitors": "ORF1b",
+        "Spike mAbs": "S"
+    }
+
+    # get the gene name
+    gene = gene_name[selected_option]
+
+    # Get the list of mutations for the selected set
+    mutations = df['Mutation'].tolist()
+    # Lambda function to format the mutation list, from S24L to S:24L
+    format_mutation = lambda x: f"{gene}:{x[0]}{x[1:]}"
+    #format_mutation = lambda x: f"{x[0]}:{x[1:]}"
+    # Apply the lambda function to each element in the mutations list
+    formatted_mutations = [format_mutation(mutation) for mutation in mutations]
+
+    st.write(f"Selected mutations:")
+    st.write(formatted_mutations)
+     
+
+    # Allow the user to choose a date range
+    st.write("Select a date range:")
+    date_range = st.date_input("Select a date range:", [pd.to_datetime("2024-09-30"), pd.to_datetime("2024-10-16")])
+
+    if st.button("Fetch Data"):
+        st.write("Fetching data...")
+        df = fetch_reformat_data(formatted_mutations, date_range)
+        
+        # Check if the dataframe is all NaN
+        if df.isnull().all().all():
+            st.error("The fetched data contains only NaN values. Please try a different date range or mutation set.")
+        else:
+            # Plot the heatmap
+            fig = plot_heatmap(df)
+            st.pyplot(fig)
+
+if __name__ == "__main__":
+    app()
\ No newline at end of file