File size: 5,375 Bytes
0f8ddfb
126fff1
 
 
0f8ddfb
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
126fff1
 
 
 
 
 
 
 
 
 
 
 
2bd2d6d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
126fff1
 
 
 
 
 
 
 
0f8ddfb
126fff1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0f8ddfb
2bd2d6d
 
 
 
 
0f8ddfb
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
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)
        # Extract 8-bit binary representation (MSB first)
        char_bits = [(ascii_code >> bit) & 1 for bit in range(7, -1, -1)]
        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()

def binary_labels_to_image(binary_labels: list[int], width: int = None, height: int = None) -> Image.Image:
    """
    Convert binary labels (0/1) back into an image.
    If width and height are not provided, assumes a square image.
    """
    total_pixels = len(binary_labels)
    if width is None or height is None:
        side = int(np.ceil(np.sqrt(total_pixels)))
        width = height = side
    needed_pixels = width * height
    if total_pixels < needed_pixels:
        binary_labels += [0] * (needed_pixels - total_pixels)
    array = np.array(binary_labels, dtype=np.uint8) * 255
    image_array = array.reshape((height, width))
    img = Image.fromarray(image_array, mode='L')
    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(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"
        )

        st.subheader("Reconstruct Image from Binary Labels")
        if st.button("Reconstruct Image"):
            reconstructed_img = binary_labels_to_image(binary_labels)
            st.image(reconstructed_img, caption="Reconstructed Image", use_column_width=True)

# Future: integrate DNA editor mapping for each mutation site here