Update app.py

app.py

@@ -1,4 +1,7 @@
 import streamlit as st
+from PIL import Image
+import numpy as np
+import pandas as pd
 
 # Simple app: convert user input into ASCII codes and binary labels
 
@@ -15,31 +18,107 @@ def string_to_binary_labels(s: str) -> list[int]:
         bits.extend(char_bits)
     return bits
 
+def image_to_binary_labels(img: Image.Image, max_pixels: int = 256) -> list[int]:
+    """
+    Convert an image to binary labels.
+    Convert to grayscale, resize to limit pixel count, and binarize (threshold 128).
+    """
+    img = img.convert("L")  # Convert to grayscale
+    img.thumbnail((int(np.sqrt(max_pixels)), int(np.sqrt(max_pixels))))  # Resize while maintaining aspect ratio
+    img_array = np.array(img)
+    flat = img_array.flatten()
+    binarized = (flat > 128).astype(int)  # Threshold at 128 to 0/1
+    return binarized.tolist()
+
+# 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
+]
+
 st.title("ASCII & Binary Label Converter")
-st.write("Enter text to see its ASCII codes and corresponding binary labels:")
-
-user_input = st.text_input("Text Input", value="DNA")
-
-if user_input:
-    # Compute ASCII codes
-    ascii_codes = [ord(c) for c in user_input]
-    # Compute binary labels
-    binary_labels = string_to_binary_labels(user_input)
-
-    st.subheader("ASCII Codes")
-    st.write(ascii_codes)
-
-    st.subheader("Binary Labels")
-    # Display bits grouped per character for readability
-    grouped = [binary_labels[i:i+8] for i in range(0, len(binary_labels), 8)]
-    for idx, bits in enumerate(grouped):
-        st.write(f"'{user_input[idx]}' → {bits}")
-
-    st.download_button(
-        label="Download Binary Labels as CSV",
-        data=','.join(str(b) for b in binary_labels),
-        file_name="binary_labels.csv",
-        mime="text/csv"
-    )
+
+# Create tabs
+tab1, tab2 = st.tabs(["Text to Binary Labels", "Image to Binary Labels"])
+
+with tab1:
+    st.write("Enter text to see its ASCII codes and corresponding binary labels:")
+    user_input = st.text_input("Text Input", value="DNA")
+
+    if user_input:
+        # Compute ASCII codes
+        ascii_codes = [ord(c) for c in user_input]
+        # Compute binary labels
+        binary_labels = string_to_binary_labels(user_input)
+
+        st.subheader("ASCII Codes")
+        st.write(ascii_codes)
+
+        st.subheader("Binary Labels per Character")
+        # Display bits grouped per character for readability
+        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}")
+
+        # New section: 32-bit group display in table format
+        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)
+
+        st.download_button(
+            label="Download Binary Labels as CSV",
+            data=','.join(str(b) for b in binary_labels),
+            file_name="binary_labels.csv",
+            mime="text/csv"
+        )
+
+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)
+
+        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(img, 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"])
+        st.dataframe(df)
+
+        st.download_button(
+            label="Download Image Binary Labels as CSV",
+            data=','.join(str(b) for b in binary_labels),
+            file_name="image_binary_labels.csv",
+            mime="text/csv"
+        )
 
 # Future: integrate DNA editor mapping for each mutation site here