app.py

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

def string_to_binary_labels(s: str) -> list[int]:
    """
    Convert a string into a flat list of binary labels (0 or 1) representing
    each character's 8-bit ASCII code.
    """
    bits: list[int] = []
    for char in s:
        ascii_code = ord(char)
        char_bits = [(ascii_code >> bit) & 1 for bit in range(7, -1, -1)]
        bits.extend(char_bits)
    return bits

def image_to_binary_labels_rgb(img: Image.Image, max_pixels: int = 256) -> list[int]:
    """
    Convert an RGB image to binary labels (0/1).
    Store full RGB values (24 bits per pixel).
    """
    img = img.convert("RGB")
    img.thumbnail((int(np.sqrt(max_pixels)), int(np.sqrt(max_pixels))))
    img_array = np.array(img)
    flat_pixels = img_array.reshape(-1, 3)

    bits = []
    for pixel in flat_pixels:
        for channel in pixel:  # R, G, B
            channel_bits = [(channel >> bit) & 1 for bit in range(7, -1, -1)]
            bits.extend(channel_bits)
    return bits

def binary_labels_to_rgb_image(binary_labels: list[int], width: int = None, height: int = None) -> Image.Image:
    """
    Convert binary labels (0/1) into an RGB image.
    """
    total_pixels = len(binary_labels) // 24
    if width is None or height is None:
        side = int(np.ceil(np.sqrt(total_pixels)))
        width = height = side

    needed_pixels = width * height
    needed_bits = needed_pixels * 24
    if len(binary_labels) < needed_bits:
        binary_labels += [0] * (needed_bits - len(binary_labels))

    pixels = []
    for i in range(0, needed_bits, 24):
        r_bits = binary_labels[i:i+8]
        g_bits = binary_labels[i+8:i+16]
        b_bits = binary_labels[i+16:i+24]
        r = sum(b << (7-j) for j, b in enumerate(r_bits))
        g = sum(b << (7-j) for j, b in enumerate(g_bits))
        b = sum(b << (7-j) for j, b in enumerate(b_bits))
        pixels.append((r, g, b))

    array = np.array(pixels, dtype=np.uint8).reshape((height, width, 3))
    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
]

st.title("ASCII & Binary Label Converter")

# 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:
        ascii_codes = [ord(c) for c in user_input]
        binary_labels = string_to_binary_labels(user_input)

        st.subheader("ASCII Codes")
        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}")

        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_rgb(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.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 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