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
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241 | def gate_finder (image_path, adata, marker_of_interest, from_gate = 6, to_gate = 8, increment = 0.1,
markers=None, channel_names = 'default', flip_y=True,
x_coordinate='X_centroid',y_coordinate='Y_centroid',
point_size=10,imageid='imageid',subset=None,seg_mask=None,**kwargs):
"""
Parameters:
image_path : string
Location to the image file.
adata : Ann Data Object
marker_of_interest : string
Marker for which gate is to be defined e.g. 'CD45'.
from_gate : int, optional
Start value gate of interest.
to_gate : int, optional
End value of the gate of interest.
flip_y : bool, optional
Flip the Y-axis if needed. Some algorithms output the XY with the Y-coordinates flipped.
If the image overlays do not align to the cells, try again by setting this to `False`.
increment : float, optional
Increments between the start and end values.
markers : string, optional
Additional markers to be included in the plot for evaluation.
channel_names : list, optional
List of channels in the image in the exact order as image. The default is `adata.uns['all_markers']`
x_coordinate : string, optional
X axis coordinate column name in AnnData object.
y_coordinate : string, optional
Y axis coordinate column name in AnnData object.
point_size : int, optional
point size in the napari plot.
imageid : string, optional
Column name of the column containing the image id.
subset : string, optional
imageid of a single image to be subsetted for analyis.
seg_mask : string, optional
Location to the segmentation mask file.
**kwargs
Other arguments that can be passed to napari viewer.
Example:
```python
image_path = '/Users/aj/Desktop/ptcl_tma/image.ome.tif'
sm.pl.gate_finder (image_path, adata, marker_of_interest='CD45',
from_gate = 6, to_gate = 8, increment = 0.1,
markers=['DNA10'], channel_names = 'default',
x_coordinate='X_position',y_coordinate='Y_position',point_size=10,
subset= '77', seg_mask=None)
```
"""
# If no raw data is available make a copy
if adata.raw is None:
adata.raw = adata
# Copy of the raw data if it exisits
if adata.raw is not None:
adata.X = adata.raw.X
# Make a copy of the data with the marker of interest
data = pd.DataFrame(np.log1p(adata.X), columns = adata.var.index, index= adata.obs.index)[[marker_of_interest]]
# Generate a dataframe with various gates
def gate (g, d):
dd = d.values
dd = np.where(dd < g, np.nan, dd)
np.warnings.filterwarnings('ignore')
dd = np.where(dd > g, 1, dd)
dd = pd.DataFrame(dd, index = d.index, columns = ['gate-' + str(g)])
return dd
# Identify the list of increments
inc = list(np.arange (from_gate, to_gate, increment))
inc = [round(num,3) for num in inc]
# Apply the function
r_gate = lambda x: gate(g=x, d=data) # Create lamda function
gated_data = list(map(r_gate, inc)) # Apply function
# Concat all the results into a single dataframe
gates = pd.concat(gated_data, axis=1)
# Plot only the Image that is requested
if subset is not None:
adata = adata[adata.obs[imageid] == subset]
# Recover the channel names from adata
if channel_names == 'default':
channel_names = adata.uns['all_markers']
else:
channel_names = channel_names
# if markers is a string convert to list
if isinstance(markers, str):
markers = [markers]
# Index of the marker of interest and corresponding names
if markers is not None:
markers.extend([marker_of_interest])
idx = np.where(np.isin(channel_names,markers))[0]
channel_names = [channel_names[i] for i in idx]
else:
idx = list(range(len(channel_names)))
channel_names = channel_names
# Load the segmentation mask
if seg_mask is not None:
seg_m = tiff.imread(seg_mask)
if (len(seg_m.shape) > 2) and (seg_m.shape[0] > 1):
seg_m = seg_m[0]
##########################################################################
# Visulaisation using Napari
# load OME TIFF
if os.path.isfile(image_path) is True:
# Load the image
image = tiff.TiffFile(image_path, is_ome=False)
z = zarr.open(image.aszarr(), mode='r') # convert image to Zarr array
# Identify the number of pyramids and number of channels
n_levels = len(image.series[0].levels) # pyramid
# If and if not pyramids are available
if n_levels > 1:
pyramid = [da.from_zarr(z[i]) for i in range(n_levels)]
multiscale = True
else:
pyramid = da.from_zarr(z)
multiscale = False
# subset channels of interest
if markers is not None:
if n_levels > 1:
for i in range(n_levels-1):
pyramid[i] = pyramid[i][idx, :, :]
n_channels = pyramid[0].shape[0] # identify the number of channels
else:
pyramid = pyramid[idx, :, :]
n_channels = pyramid.shape[0] # identify the number of channels
else:
if n_levels > 1:
n_channels = pyramid[0].shape[0]
else:
n_channels = pyramid.shape[0]\
# check if channel names have been passed to all channels
if channel_names is not None:
assert n_channels == len(channel_names), (
f'number of channel names ({len(channel_names)}) must '
f'match number of channels ({n_channels})'
)
# Load the viewer
viewer = napari.view_image(
pyramid,
channel_axis = 0,
multiscale=multiscale,
name = None if channel_names is None else channel_names,
visible = False, **kwargs)
# Operations on the ZARR image
# check the format of image
if os.path.isfile(image_path) is False:
#print(image_path)
viewer = napari.Viewer()
viewer.open(image_path, multiscale=True,
visible=False,
name = None if channel_names is None else channel_names)
# Add the seg mask
if seg_mask is not None:
viewer.add_labels(seg_m, name='segmentation mask', visible=False)
# subset the gates to include only the image of interest
gates = gates.loc[adata.obs.index,]
# Add gating layer
def add_phenotype_layer (adata, gates, phenotype_layer,x,y,viewer,point_size):
cells = gates[gates[phenotype_layer] == 1].index
coordinates = adata[cells]
# Flip Y axis if needed
if flip_y is True:
coordinates = pd.DataFrame({'y': coordinates.obs[y],'x': coordinates.obs[x]})
else:
coordinates = pd.DataFrame({'x': coordinates.obs[x],'y': coordinates.obs[y]})
#points = coordinates.values.tolist()
points = coordinates.values
#import time
#start = time.time()
viewer.add_points(points, size=point_size, face_color='white',visible=False,name=phenotype_layer)
#stop = time.time()
#print(stop-start)
# Run the function on all gating layer
for i in gates.columns:
add_phenotype_layer (adata=adata, gates=gates,
phenotype_layer=i, x=x_coordinate, y=y_coordinate,
viewer=viewer, point_size=point_size)
|