Update app.py

app.py

@@ -4,7 +4,7 @@ import numpy as np
 import pandas as pd
 from streamlit_cropper import st_cropper
 
-# Predefined headers for the 32 mutation sites
+# Mutation site headers
 mutation_site_headers = [
     3244, 3297, 3350, 3399, 3455, 3509, 3562, 3614,
     3665, 3720, 3773, 3824, 3879, 3933, 3985, 4039,
@@ -12,45 +12,19 @@ mutation_site_headers = [
     4510, 4561, 4615, 4668, 4720, 4773, 4828, 4882
 ]
 
-# Load thresholds from file
+# Thresholds for each mutation site
 thresholds = pd.Series({
-    3244: 1.094293328,
-    3297: 0.924916122,
-    3350: 0.664586629,
-    3399: 0.91573613,
-    3455: 1.300869714,
-    3509: 1.821975901,
-    3562: 1.178862418,
-    3614: 0.091557752,
-    3665: 0.298697327,
-    3720: 0.58379781,
-    3773: 0.891088481,
-    3824: 1.145509641,
-    3879: 0.81833191,
-    3933: 2.93084335,
-    3985: 1.593758847,
-    4039: 0.966055013,
-    4089: 1.465671338,
-    4145: 0.30309335,
-    4190: 1.321615138,
-    4245: 1.709752495,
-    4298: 0.868534701,
-    4349: 1.222907645,
-    4402: 0.58873557,
-    4455: 1.185522985,
-    4510: 1.266797682,
-    4561: 1.109913024,
-    4615: 1.181106084,
-    4668: 1.408533949,
-    4720: 0.714151142,
-    4773: 1.471959437,
-    4828: 0.95879943,
-    4882: 1.464503885
+    3244: 1.094293328, 3297: 0.924916122, 3350: 0.664586629, 3399: 0.91573613,
+    3455: 1.300869714, 3509: 1.821975901, 3562: 1.178862418, 3614: 0.091557752,
+    3665: 0.298697327, 3720: 0.58379781, 3773: 0.891088481, 3824: 1.145509641,
+    3879: 0.81833191, 3933: 2.93084335, 3985: 1.593758847, 4039: 0.966055013,
+    4089: 1.465671338, 4145: 0.30309335, 4190: 1.321615138, 4245: 1.709752495,
+    4298: 0.868534701, 4349: 1.222907645, 4402: 0.58873557, 4455: 1.185522985,
+    4510: 1.266797682, 4561: 1.109913024, 4615: 1.181106084, 4668: 1.408533949,
+    4720: 0.714151142, 4773: 1.471959437, 4828: 0.95879943, 4882: 1.464503885
 })
 
-# -----------------------------------------
-# Utility functions
-# -----------------------------------------
+# === Utility functions ===
 
 def string_to_binary_labels(s: str) -> list[int]:
     bits = []
@@ -105,19 +79,14 @@ def binary_labels_to_rgb_image(binary_labels: list[int], width: int = None, heig
     img = Image.fromarray(array, mode='RGB')
     return img
 
-# -----------------------------------------
-# Streamlit App
-# -----------------------------------------
+# === Streamlit App ===
 
 st.title("ASCII & Binary Label Converter")
-
 tab1, tab2, tab3 = st.tabs(["Text to Binary Labels", "Image to Binary Labels", "EF → Binary"])
 
-# ================= Tab 1 ===================
+# Tab 1: Text to Binary
 with tab1:
-    st.write("Enter text to see its ASCII codes and corresponding binary labels:")
-    user_input = st.text_input("Text Input", value="DNA")
-
+    user_input = st.text_input("Enter text", value="DNA")
     if user_input:
         ascii_codes = [ord(c) for c in user_input]
         binary_labels = string_to_binary_labels(user_input)
@@ -126,118 +95,78 @@ with tab1:
         st.write(ascii_codes)
 
         st.subheader("Binary Labels per Character")
-        grouped_chars = [binary_labels[i:i+8] for i in range(0, len(binary_labels), 8)]
-        for idx, bits in enumerate(grouped_chars):
-            st.write(f"'{user_input[idx]}' → {bits}")
+        grouped = [binary_labels[i:i+8] for i in range(0, len(binary_labels), 8)]
+        for i, bits in enumerate(grouped):
+            st.write(f"'{user_input[i]}' → {bits}")
 
         st.subheader("Binary Labels (32-bit groups)")
-        num_groups = (len(binary_labels) + 31) // 32
-        table_data = []
-        for grp_idx in range(num_groups):
-            start = grp_idx * 32
-            end = start + 32
-            group = binary_labels[start:end]
-            if len(group) < 32:
-                group += [0] * (32 - len(group))
-            edited_sites = sum(group)
-            row = group + [edited_sites]
-            table_data.append(row)
-
-        df = pd.DataFrame(table_data, columns=[str(h) for h in mutation_site_headers] + ["Edited Sites"])
-        st.dataframe(df)
+        groups = []
+        for i in range(0, len(binary_labels), 32):
+            group = binary_labels[i:i+32]
+            group += [0] * (32 - len(group))
+            groups.append(group + [sum(group)])
 
-        st.download_button(
-            label="Download Binary Labels Table as CSV",
-            data=df.to_csv(index=False),
-            file_name="binary_labels_table.csv",
-            mime="text/csv"
-        )
+        df = pd.DataFrame(groups, columns=[str(h) for h in mutation_site_headers] + ["Edited Sites"])
+        st.dataframe(df)
+        st.download_button("Download as CSV", df.to_csv(index=False), "text_binary_labels.csv")
 
-# ================= Tab 2 ===================
+# Tab 2: Image to Binary
 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"])
-
-    if uploaded_file is not None:
-        img = Image.open(uploaded_file)
-        st.image(img, caption="Uploaded Image", use_column_width=True)
-
-        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)
+    uploaded = st.file_uploader("Upload an image (jpg/png)", type=["jpg", "jpeg", "png"])
+    if uploaded:
+        img = Image.open(uploaded)
+        st.image(img, caption="Original", use_column_width=True)
+        cropped = st_cropper(img, realtime_update=True, box_color="blue", aspect_ratio=None)
+        st.image(cropped, caption="Cropped", use_column_width=True)
 
-        st.image(cropped_img, caption="Cropped Image", use_column_width=True)
-
-        max_pixels = st.slider("Max number of pixels to encode", min_value=32, max_value=1024, value=256, step=32)
-
-        binary_labels = image_to_binary_labels_rgb(cropped_img, max_pixels=max_pixels)
+        max_pixels = st.slider("Max pixels to encode", 32, 1024, 256, 32)
+        binary_labels = image_to_binary_labels_rgb(cropped, max_pixels=max_pixels)
 
         st.subheader("Binary Labels from Image")
-        num_groups = (len(binary_labels) + 31) // 32
-        table_data = []
-        for grp_idx in range(num_groups):
-            start = grp_idx * 32
-            end = start + 32
-            group = binary_labels[start:end]
-            if len(group) < 32:
-                group += [0] * (32 - len(group))
-            edited_sites = sum(group)
-            row = group + [edited_sites]
-            table_data.append(row)
-
-        df = pd.DataFrame(table_data, columns=[str(h) for h in mutation_site_headers] + ["Edited Sites"])
+        groups = []
+        for i in range(0, len(binary_labels), 32):
+            group = binary_labels[i:i+32]
+            group += [0] * (32 - len(group))
+            groups.append(group + [sum(group)])
+        df = pd.DataFrame(groups, columns=[str(h) for h in mutation_site_headers] + ["Edited Sites"])
         st.dataframe(df)
 
-        st.subheader("Reconstructed RGB Image")
-        reconstructed_img = binary_labels_to_rgb_image(binary_labels)
-        st.image(reconstructed_img, caption="Reconstructed Image", use_column_width=True)
-
-        st.download_button(
-            label="Download Image Binary Labels Table as CSV",
-            data=df.to_csv(index=False),
-            file_name="image_binary_labels_table.csv",
-            mime="text/csv"
-        )
+        st.subheader("Reconstructed Image")
+        recon = binary_labels_to_rgb_image(binary_labels)
+        st.image(recon, caption="Reconstructed", use_column_width=True)
+        st.download_button("Download CSV", df.to_csv(index=False), "image_binary_labels.csv")
 
-# ================= Tab 3 ===================
+# Tab 3: EF → Binary
 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")
+    st.write("Upload an Editing Frequency CSV or enter manually:")
+    ef_file = st.file_uploader("Upload EF CSV", type=["csv"], key="ef")
 
     if ef_file:
         ef_df = pd.read_csv(ef_file)
         ef_df = ef_df.loc[:, ~ef_df.columns.str.contains('^Unnamed')]
     else:
-        ef_df = pd.DataFrame(columns=thresholds.index)
+        ef_df = pd.DataFrame(columns=[str(k) for k in thresholds.index])
 
     edited_df = st.data_editor(ef_df, num_rows="dynamic")
 
     if st.button("Convert to Binary Labels"):
-        common_cols = list(set(map(int, edited_df.columns)) & set(thresholds.index))
-        common_cols = list(map(str, common_cols))  # Convert back to string for use as column names
+        int_map = {str(k): k for k in thresholds.index}
+        matching_cols = [col for col in edited_df.columns if col in int_map]
 
-        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_part = pd.DataFrame()
+        for col in matching_cols:
+            col_threshold = thresholds[int_map[col]]
+            binary_part[col] = (edited_df[col].astype(float) >= col_threshold).astype(int)
+
+        non_binary_part = edited_df.drop(columns=matching_cols, errors='ignore')
         binary_df = pd.concat([non_binary_part, binary_part], axis=1)
-    
-        def highlight_binary(val):
-            if val == 1:
-                return 'background-color: lightgreen'
-            elif val == 0:
-                return 'background-color: lightcoral'
-            else:
-                return ''
-    
-        styled_binary_df = binary_df.style.applymap(highlight_binary, subset=numeric_cols)
-    
-        st.subheader("Binary Labels")
-        st.dataframe(styled_binary_df)   # ✅ Display thresholded binary table
 
-        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"
-        )
+        def color_binary(val):
+            if val == 1: return "background-color: lightgreen"
+            if val == 0: return "background-color: lightcoral"
+            return ""
 
+        st.subheader("Binary Labels")
+        styled = binary_df.style.applymap(color_binary, subset=matching_cols)
+        st.dataframe(styled)
+        st.download_button("Download CSV", binary_df.to_csv(index=False), "ef_binary_labels.csv")