-
Notifications
You must be signed in to change notification settings - Fork 0
/
get_intensity_extrema.py
executable file
·185 lines (164 loc) · 5.25 KB
/
get_intensity_extrema.py
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
import argparse
import numpy as np
import pandas as pd
import itertools
from tmclient import TmClient
def parse_arguments():
parser = argparse.ArgumentParser(
prog='get_intensity_extrema',
description=('Accesses images from TissueMAPS instance and '
'writes a pkl file of channel image intensity extrema.')
)
parser.add_argument(
'-v', '--verbosity', action='count', default=0,
help='increase logging verbosity'
)
parser.add_argument(
'-H', '--host', default='app.tissuemaps.org',
help='name of TissueMAPS server host'
)
parser.add_argument(
'-P', '--port', type=int, default=80,
help='number of the port to which the server listens (default: 80)'
)
parser.add_argument(
'-u', '--user', dest='username', required=True,
help='name of TissueMAPS user'
)
parser.add_argument(
'--password', required=True,
help='password of TissueMAPS user'
)
parser.add_argument(
'-e', '--experiment', required=True,
help='experiment name'
)
parser.add_argument(
'-p', '--plate', type=str, default='plate01',
help='plate name'
)
parser.add_argument(
'-c', '--channel', type=str, default='wavelength-2',
help='channel name'
)
parser.add_argument(
'--negative_wells', type=str, nargs='+', required=True,
help='wells of negative control (as list)'
)
parser.add_argument(
'--positive_wells', type=str, nargs='+', required=True,
help='wells of positive control (as list)'
)
parser.add_argument(
'-n', '--number_sites', dest='n_sites', type=int, required=True,
help='number of randomly selected sites'
)
parser.add_argument(
'-o', '--output_file', type=str, required=True,
help='filename for output file (.pkl)'
)
return(parser.parse_args())
def main(args):
tmaps_api = TmClient(
host=args.host,
port=args.port,
experiment_name=args.experiment,
username=args.username,
password=args.password
)
negative = pd.DataFrame({
'control': 'negative',
'well': args.negative_wells
})
positive = pd.DataFrame({
'control': 'positive',
'well': args.positive_wells
})
rescaling_limits = negative.append(positive)
rescaling_limits = rescaling_limits.merge(
get_site_dimensions(
df=rescaling_limits,
plate_name=args.plate,
client=tmaps_api
)
)
rescaling_limits = rescaling_limits.merge(
select_random_sites(
df=rescaling_limits,
n_sites=args.n_sites
), how='outer'
)
rescaling_limits = rescaling_limits.merge(
get_extrema_of_sites(
df=rescaling_limits,
client=tmaps_api,
channel_name=args.channel,
plate_name=args.plate
)
)
rescaling_limits.to_pickle(args.output_file)
return
def get_site_dimensions(df, client, plate_name):
dimensions = pd.DataFrame()
for index, row in df.iterrows():
well = client.get_sites(plate_name=plate_name, well_name=row['well'])
max_x = 0
max_y = 0
for s in range(len(well)):
max_x = well[s]['x'] if well[s]['x'] > max_x else max_x
max_y = well[s]['y'] if well[s]['y'] > max_y else max_y
dimensions = dimensions.append(
pd.DataFrame({
'well': row['well'],
'n_site_x': int(max_x),
'n_site_y': int(max_y)
}, index=[index])
)
return dimensions
def select_random_sites(df, n_sites):
selection = pd.DataFrame()
for index, row in df.iterrows():
all_sites = list(
itertools.product(
range(row['n_site_x']),
range(row['n_site_y'])
)
)
selected_sites_x = [all_sites[i][0] for i in list(
np.random.choice(len(all_sites), n_sites)
)]
selected_sites_y = [all_sites[i][1] for i in list(
np.random.choice(len(all_sites), n_sites)
)]
selection = selection.append(
pd.DataFrame({
'well': row['well'],
'site_x': selected_sites_x,
'site_y': selected_sites_y
})
)
return selection
def get_extrema_of_sites(df, client, channel_name, plate_name, lower_percentile=1.0, upper_percentile=99.5):
extrema = pd.DataFrame()
for index, row in df.iterrows():
image = client.download_channel_image(
channel_name=channel_name,
plate_name=plate_name,
well_name=row['well'],
well_pos_y=row['site_y'],
well_pos_x=row['site_x'],
correct=True
)
extrema = extrema.append(
pd.DataFrame({
'well': row['well'],
'site_x': row['site_x'],
'site_y': row['site_y'],
'lower_limit': np.percentile(image, lower_percentile),
'upper_limit': np.percentile(image, upper_percentile)
}, index=[index])
)
return extrema
if __name__ == '__main__':
arguments = parse_arguments()
main(arguments)