Update app.py

app.py

@@ -4,10 +4,23 @@ import numpy as np
 import pandas as pd
 from streamlit_cropper import st_cropper
 
-# Simple app: convert user input into ASCII codes and binary labels
+# Predefined headers for the 32 mutation sites
+mutation_site_headers = [
+    3244, 3297, 3350, 3399, 3455, 3509, 3562, 3614,
+    3665, 3720, 3773, 3824, 3879, 3933, 3985, 4039,
+    4089, 4145, 4190, 4245, 4298, 4349, 4402, 4455,
+    4510, 4561, 4615, 4668, 4720, 4773, 4828, 4882
+]
+
+# Load thresholds from file
+thresholds = pd.read_csv("Column_Thresholds.csv", index_col=0).squeeze()
+
+# -----------------------------------------
+# Utility functions
+# -----------------------------------------
 
 def string_to_binary_labels(s: str) -> list[int]:
-    bits: list[int] = []
+    bits = []
     for char in s:
         ascii_code = ord(char)
         char_bits = [(ascii_code >> bit) & 1 for bit in range(7, -1, -1)]
@@ -59,22 +72,15 @@ def binary_labels_to_rgb_image(binary_labels: list[int], width: int = None, heig
     img = Image.fromarray(array, mode='RGB')
     return img
 
-# Predefined headers for the 32 mutation sites
-mutation_site_headers = [
-    3244, 3297, 3350, 3399, 3455, 3509, 3562, 3614,
-    3665, 3720, 3773, 3824, 3879, 3933, 3985, 4039,
-    4089, 4145, 4190, 4245, 4298, 4349, 4402, 4455,
-    4510, 4561, 4615, 4668, 4720, 4773, 4828, 4882
-]
-
-# Load thresholds from file
-thresholds = pd.read_csv("Column_Thresholds.csv", index_col=0).squeeze()
+# -----------------------------------------
+# Streamlit App
+# -----------------------------------------
 
 st.title("ASCII & Binary Label Converter")
 
-# Create tabs
-tab1, tab2, tab3 = st.tabs(["Text to Binary Labels", "Image to Binary Labels", "EF -> Binary"])
+tab1, tab2, tab3 = st.tabs(["Text to Binary Labels", "Image to Binary Labels", "EF → Binary"])
 
+# ================= Tab 1 ===================
 with tab1:
     st.write("Enter text to see its ASCII codes and corresponding binary labels:")
     user_input = st.text_input("Text Input", value="DNA")
@@ -114,6 +120,7 @@ with tab1:
             mime="text/csv"
         )
 
+# ================= Tab 2 ===================
 with tab2:
     st.write("Upload an image (JPG or PNG) to convert it into binary labels:")
     uploaded_file = st.file_uploader("Choose an image file", type=["jpg", "jpeg", "png"])
@@ -122,8 +129,8 @@ with tab2:
         img = Image.open(uploaded_file)
         st.image(img, caption="Uploaded Image", use_column_width=True)
 
-        st.subheader("Crop the image with drag and select (1:1 aspect ratio)")
-        cropped_img = st_cropper(img, realtime_update=True, box_color='blue', aspect_ratio=1.0)
+        st.subheader("Crop the image with drag and select (Free aspect ratio)")
+        cropped_img = st_cropper(img, realtime_update=True, box_color='blue', aspect_ratio=None)
 
         st.image(cropped_img, caption="Cropped Image", use_column_width=True)
 
@@ -158,6 +165,7 @@ with tab2:
             mime="text/csv"
         )
 
+# ================= Tab 3 ===================
 with tab3:
     st.write("Upload an Editing Frequency CSV or fill in manually:")
     ef_file = st.file_uploader("Upload Editing Frequency CSV", type=["csv"], key="ef")
@@ -172,23 +180,24 @@ with tab3:
 
     if st.button("Convert to Binary Labels"):
         common_cols = list(set(edited_df.columns) & set(thresholds.index))
-        binary_part = edited_df[common_cols].ge(thresholds[common_cols]).astype(int)
-        non_binary_part = edited_df.drop(columns=common_cols, errors='ignore')
+        numeric_cols = edited_df[common_cols].select_dtypes(include=[np.number]).columns.tolist()
+
+        binary_part = edited_df[numeric_cols].ge(thresholds[numeric_cols]).astype(int)
+        non_binary_part = edited_df.drop(columns=numeric_cols, errors='ignore')
         binary_df = pd.concat([non_binary_part, binary_part], axis=1)
 
         def highlight_binary(val):
             color = 'lightgreen' if val == 1 else 'lightcoral'
             return f'background-color: {color}'
 
-        styled_binary_df = binary_df.style.applymap(highlight_binary, subset=common_cols)
+        styled_binary_df = binary_df.style.applymap(highlight_binary, subset=numeric_cols)
 
         st.subheader("Binary Labels")
         st.dataframe(styled_binary_df)
+
         st.download_button(
             label="Download Binary Labels Table as CSV",
             data=binary_df.to_csv(index=False),
             file_name="ef_binary_labels_table.csv",
             mime="text/csv"
         )
-
-# Future: integrate DNA editor mapping for each mutation site here