File size: 2,976 Bytes
692d068
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
# %%
from collections import defaultdict

import altair as alt
import matplotlib.pyplot as plt
import pandas as pd
from cmap import Colormap
import polars as pl

#%%

df = pl.read_csv("example_data_bk.csv")
df.columns

df_crop = df[:, :3]
df_crop

df_crop.write_csv("example_data.csv")
#%%

# %%
kwargs = {"comment": "#", "header": [0, 1], "index_col": 0}
df = pd.read_csv("fit_result_batch.csv", **kwargs)
# %%
df
# %%


df_wt = df["SecB WT apo"].reset_index()
df_dimer = df["SecB his dimer apo"].reset_index()

AA_categories = {
    "pos": ["R", "H", "K"],
    "neg": ["D", "E"],
    "aromatic": ["F", "W", "Y"],
    "polar": ["S", "T", "N", "Q"],
    "nonpolar": ["A", "V", "I", "L", "M"],
    "other": ["G", "C", "P"],
}
cat_list = list(AA_categories)
AA_lut = {aa: category for category in AA_categories for aa in AA_categories[category]}
AA_lut
aa_cat_numbers = [cat_list.index(AA_lut[aa]) for aa in df_wt["sequence"]]
df_wt["aa_cat"] = aa_cat_numbers

# %%
cmap = Colormap("colorbrewer:Accent_6")
sol = defaultdict(list)
colors = cmap(df_wt["aa_cat"])

nums = range(6)
colors = cmap(nums)

for n, c in zip(nums, colors):
    print(n, c)
# %%
len(cmap.color_stops)

colors = cmap.to_altair(N=cmap.num_colors)
domain = range(6)
altair_scale = alt.Scale(domain=domain, range=colors, clamp=True)
# %%
alt.Chart(df_wt).mark_point().encode(
    x="r_number",
    y="aa_cat",
    color=alt.Color("aa_cat:N", scale=altair_scale),
)

# %%
import pandas as pd

df = pd.DataFrame({"a": [1, 2, 3, 4], "b": [7, 6, 5, 4], "c": ["a", "b", "b", "c"]})

chart = alt.Chart(df).mark_point().encode(alt.X("a"), alt.Y("b"), alt.Color("c:N"))
chart
# %%


# %%


ddG = df_wt["deltaG"] - df_dimer["deltaG"]
ddG


# %%

fig, ax = plt.subplots()
ax.scatter(df_wt["r_number"], df_wt["deltaG"])

# %%
fig, ax = plt.subplots()
ax.scatter(df_wt["r_number"], ddG)

# %%
df_wt.columns
# %%

output = pd.DataFrame(
    {
        "r_number": df_wt["r_number"],
        "SecB tetramer ΔG": df_wt["deltaG"],
        "dimer ΔΔG": ddG,
        "aa_category": df_wt["aa_cat"],
    }
)
output = output.set_index("r_number")

output
# %%
import numpy as np

N = 150
fuzzy_sin = 0.5 * (1 + np.sin(np.arange(N) / 10.0)) + np.random.normal(
    loc=0, scale=0.1, size=N
)
df = pd.DataFrame({"fuzzy_sin": fuzzy_sin})
df



# add series to output dataframe a a column

output["fuzzy_sin"] = series
output
# %%

output.to_csv("SecB_data.csv")
# %%

dir(cmap)
cmap.category

# %%

tol_cmap = Colormap("tol:rainbow_discrete_7")
tol_cmap.category
tol_cmap.num_colors
tol_cmap.interpolation

# %%

tol_cmap = Colormap("vispy:hsl")
tol_cmap.category
tol_cmap.num_colors
tol_cmap.interpolation


# %%
tol_cmap = Colormap("yorick:stern")
tol_cmap.category
tol_cmap.num_colors
tol_cmap.interpolation
# %%
tol_cmap = Colormap("tol:rainbow_whbr")
tol_cmap.category
tol_cmap.num_colors
tol_cmap.interpolation
# %%
tol_cmap = Colormap("glasbey:glasbey")
tol_cmap.category
tol_cmap.num_colors
# tol_cmap.interpolation


# %%