File size: 7,886 Bytes
0f8ddfb
07a5d20
126fff1
 
81dbe3d
e59d9f1
785d3cd
 
 
 
 
098acd8
785d3cd
 
 
 
 
 
 
 
 
 
098acd8
785d3cd
 
8e18767
 
17836b2
8e18767
 
 
098acd8
17836b2
 
8e18767
223c1c6
 
54f693c
0f8ddfb
cc35c28
 
 
 
 
 
 
 
 
 
 
 
 
0f8ddfb
17836b2
0f8ddfb
cc35c28
 
0f8ddfb
 
 
ff2b00a
 
cc35c28
 
 
 
 
 
ff2b00a
223c1c6
07a5d20
2d22901
07a5d20
 
 
 
 
 
 
181eb38
126fff1
56ff5cb
 
 
 
07a5d20
56ff5cb
 
 
126fff1
2d22901
 
 
 
 
56ff5cb
2d22901
 
 
 
56ff5cb
2d22901
 
 
 
 
 
 
 
 
56ff5cb
2d22901
 
 
181eb38
54f693c
81f62ec
0f8ddfb
33573cd
126fff1
54f693c
126fff1
54f693c
126fff1
 
 
 
 
 
 
 
55b708c
54f693c
 
126fff1
1e12d5e
54f693c
1e12d5e
 
 
54f693c
07a5d20
05bc090
 
33573cd
1e12d5e
223c1c6
785d3cd
223c1c6
785d3cd
 
 
223c1c6
33573cd
54f693c
223c1c6
54f693c
785d3cd
f37dc6c
5dc1952
223c1c6
f37dc6c
223c1c6
f37dc6c
 
 
 
54f693c
223c1c6
785d3cd
223c1c6
785d3cd
54f693c
785d3cd
17836b2
54f693c
 
 
 
6a96058
785d3cd
 
54f693c
785d3cd
 
4f6586f
 
 
 
 
223c1c6
08696fc
223c1c6
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
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
import streamlit as st
from PIL import Image, ImageFilter
import numpy as np
import pandas as pd
from streamlit_cropper import st_cropper

# Mutation site headers removed 3614,
mutation_site_headers_actual = [
    3244, 3297, 3350, 3399, 3455, 3509, 3562, 
    3665, 3720, 3773, 3824, 3879, 3933, 3985, 4039,
    4089, 4145, 4190, 4245, 4298, 4349, 4402, 4455,
    4510, 4561, 4615, 4668, 4720, 4773, 4828, 4882
]

# Thresholds for each mutation site removed 3614: 0.091557752,
thresholds_actual = pd.Series({
    3244: 1.094293328, 3297: 0.924916122, 3350: 0.664586629, 3399: 0.91573613,
    3455: 1.300869714, 3509: 1.821975901, 3562: 1.178862418, 
    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
})

# Mutation site headers reordered: 4402 to 3244, 4882 to 4455
mutation_site_headers = [
    4402, 4349, 4298, 4245, 4190, 4145, 4089, 4039,
    3985, 3933, 3879, 3824, 3773, 3720, 3665,
    3562, 3509, 3455, 3399, 3350, 3297, 3244,  # 1–23
    4882, 4828, 4773, 4720, 4668, 4615, 4561, 4510, 4455   # 24–32
]

# Thresholds reordered accordingly
thresholds = pd.Series({h: thresholds_actual[h] for h in mutation_site_headers})

# === Utility functions ===

# Voyager ASCII 6-bit conversion table
voyager_table = {
    i: ch for i, ch in enumerate([
        ' ', 'A', 'B', 'C', 'D', 'E', 'F', 'G', 'H', 'I',
        'J', 'K', 'L', 'M', 'N', 'O', 'P', 'Q', 'R', 'S',
        'T', 'U', 'V', 'W', 'X', 'Y', 'Z', '0', '1', '2',
        '3', '4', '5', '6', '7', '8', '9', '.', '(', ')',
        '+', '-', '*', '/', '=', '$', '!', ':', '%', '"',
        '#', '@', '\'', '?', '&'
    ])
}
reverse_voyager_table = {v: k for k, v in voyager_table.items()}

def string_to_binary_labels(s: str) -> list[int]:
    bits = []
    for char in s:
        val = reverse_voyager_table.get(char.upper(), 0)
        char_bits = [(val >> bit) & 1 for bit in range(5, -1, -1)]
        bits.extend(char_bits)
    return bits

def binary_labels_to_string(bits: list[int]) -> str:
    chars = []
    for i in range(0, len(bits), 6):
        chunk = bits[i:i+6]
        if len(chunk) < 6:
            chunk += [0] * (6 - len(chunk))
        val = sum(b << (5 - j) for j, b in enumerate(chunk))
        chars.append(voyager_table.get(val, '?'))
    return ''.join(chars)

def clean_image(img: Image.Image, min_size: int = 256) -> Image.Image:
    img = img.convert("RGB")
    if img.width < min_size or img.height < min_size:
        img = img.resize((min_size, min_size))
    img = img.filter(ImageFilter.GaussianBlur(radius=1))
    return img

def image_to_binary_labels_rgb(img: Image.Image, max_pixels: int = 256) -> list[int]:
    img = clean_image(img)
    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:
            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:
    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

# === Streamlit App ===

st.title("ASCII & Binary Label Converter")
tab1, tab2 = st.tabs(["Text to Binary Labels (31)", "EF β†’ Binary (31)"])

# Tab 1: Text to Binary
with tab1:
    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)

        st.subheader("ASCII Codes")
        st.write(ascii_codes)

        st.subheader("Binary Labels per Character")
        grouped = [binary_labels[i:i+6] for i in range(0, len(binary_labels), 6)]
        for i, bits in enumerate(grouped):
            st.write(f"'{user_input[i]}' β†’ {bits}")

        st.subheader("Binary Labels (31-bit groups)")
        groups = []
        for i in range(0, len(binary_labels), 31):
            group = binary_labels[i:i+31]
            group += [0] * (31 - 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.download_button("Download as CSV", df.to_csv(index=False), "text_31_binary_labels.csv")

        ascending_headers = sorted(mutation_site_headers_actual)
        df_sorted = df[[str(h) for h in ascending_headers if str(h) in df.columns]]
        st.subheader("Binary Labels (Ascending Order 3244 β†’ 4882)")
        st.dataframe(df_sorted)
        st.download_button("Download Ascending Order CSV", df_sorted.to_csv(index=False), "text_binary_labels_ascending.csv")

# Tab 2: EF β†’ Binary
with tab2:
    st.write("Upload an Editing Frequency CSV or enter manually:")
    st.write("**Note:** Please upload CSV files **without column headers**, in ascending order from 3244 to 4882.")
    ef_file = st.file_uploader("Upload EF CSV", type=["csv"], key="ef")

    if ef_file:
        ef_df = pd.read_csv(ef_file, header=None)
        ef_df.columns = [str(site) for site in sorted(mutation_site_headers_actual)]
    else:
        ef_df = pd.DataFrame(columns=[str(site) for site in sorted(mutation_site_headers_actual)])

    edited_df = st.data_editor(ef_df, num_rows="dynamic")

    if st.button("Convert to Binary Labels"):
        binary_part = pd.DataFrame()
        for col in sorted(mutation_site_headers_actual):
            col_str = str(col)
            threshold = thresholds_actual[col]
            binary_part[col_str] = (edited_df[col_str].astype(float) >= threshold).astype(int)

        binary_reordered = binary_part[[str(h) for h in mutation_site_headers if str(h) in binary_part.columns]]

        def color_binary(val):
            if val == 1: return "background-color: lightgreen"
            if val == 0: return "background-color: lightcoral"
            return ""

        st.subheader("Binary Labels (Reordered 4402β†’3244, 4882β†’4455)")
        styled = binary_reordered.style.applymap(color_binary)
        st.dataframe(styled)
        st.download_button("Download CSV", binary_reordered.to_csv(index=False), "ef_binary_labels.csv")

        all_bits = binary_reordered.values.flatten().tolist()
        decoded_string = binary_labels_to_string(all_bits)
        st.subheader("Decoded String (continuous across rows)")
        st.write(decoded_string)

        st.subheader("Binary Labels (Ascending 3244β†’4882)")
        st.dataframe(binary_part.style.applymap(color_binary))
        st.download_button("Download Ascending Order CSV", binary_part.to_csv(index=False), "ef_binary_labels_ascending.csv")