-
Notifications
You must be signed in to change notification settings - Fork 1
/
Copy pathsmFISH_brefeldin.py
277 lines (215 loc) · 8.25 KB
/
smFISH_brefeldin.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
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
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
"""
smFISH data analysis
Perform analysis for single cell analysis data
"""
"""
Import python packages
"""
import HTSeq
import collections
import itertools
import os
import subprocess
import collections
import datetime
import yaml
import fnmatch
import shlex
import numpy
import scipy
import scipy.io as sio
import pyensembl
import h5py
import pandas as pd
import numpy as np
import scipy.cluster.hierarchy as sch
from seq_functions import smFISH_cell, smFISH_stim_cell
import rpy2
from rpy2.robjects.packages import importr
import cPickle as pickle
rpy2.robjects.numpy2ri.activate()
import matplotlib
matplotlib.use("Agg")
import matplotlib.pyplot as plt
matplotlib.rcParams['pdf.fonttype'] = 42
"""
Initialize R instances
"""
R = rpy2.robjects.r
DTW = importr('dtw')
DTWCLUST = importr('dtwclust')
"""
Load excel files
"""
direc = "/scratch/PI/mcovert/dvanva/sequencing/smFISH"
file_name = os.path.join(direc, "12072015", "12072015_ExperMetadata.xlsx")
data_0 = pd.read_excel(file_name, sheetname = 0)
file_name = os.path.join(direc, "12162015", "12162015_ExperMetadata.xlsx")
data_1 = pd.read_excel(file_name, sheetname = 0)
file_name = os.path.join(direc, "12192015", "12192015_ExperMetadata.xlsx")
data_2 = pd.read_excel(file_name, sheetname = 0)
"""
Load cluster averages
"""
direc = "/scratch/PI/mcovert/dvanva/sequencing/smFISH"
file_name = os.path.join(direc,"300_cluster_avg_kshape_c1.npz")
file_load = np.load(file_name)
"""
Load MAT files
"""
times = ["300"]
dates = ["12192015"]
for time in times:
print time
if time == "0":
cluster_dynamics_avg = None
else:
cluster_dynamics_avg = file_load["cluster_dynamics_avg"]
file_name = os.path.join(direc, "12192015", "nucData.mat")
dynamics_file = sio.loadmat(file_name)
temp = dynamics_file["dataToAnalyzeNuc" + time + "Ratio"][:,3:]
longest_time = temp.shape[1]
cluster_dynamics_avg = cluster_dynamics_avg[:,0:longest_time]
list_of_cells = []
for date in dates:
file_name = os.path.join(direc, date, "nucData.mat")
dynamics_file = sio.loadmat(file_name)
conditions = dynamics_file["dataToAnalyzeNuc"+ time + "Ratio"][:,0]
positions = dynamics_file["dataToAnalyzeNuc"+ time + "Ratio"][:,1]
ids = dynamics_file["dataToAnalyzeNuc"+ time + "Ratio"][:,2]
ratios = dynamics_file["dataToAnalyzeNuc" + time + "Ratio"][:,3:]
normalized = dynamics_file["normalizedNuc" + time + "Data"][:,3:]
print conditions.shape
number_of_cells = conditions.shape[0]
conds = ["*brefeldin A 10ug/ml from start*", "*brefeldin A from start*", "*brefeldin A after 30 min*"]
for j in xrange(number_of_cells):
cell = smFISH_stim_cell(cell_id = ids[j], stimulus_condition = conds, NC_ratio = ratios[j,:], norm_med = normalized[j,:], condition = conditions[j],
position = positions[j], smFISH_dataframe = data_2, cluster_dynamics_avg = cluster_dynamics_avg)
list_of_cells += [cell]
good_cells = []
for cell in list_of_cells:
if cell.good_cell == 1:
good_cells += [cell]
# if time == "300":
# dynamics_load = np.load("/scratch/PI/mcovert/dvanva/sequencing/smFISH/300_dynamics_distance_matrix_kshape.npz")
# distance_matrix = dynamics_load['distance_matrix']
# Y = sch.linkage(distance_matrix, method = 'ward')
# ind_dynamics = sch.fcluster(Y,0.5*np.amax(Y[:,2]),'distance') - 1
# for j in xrange(len(good_cells)):
# good_cells[j].clusterID = ind_dynamics[j]
file_name_save = os.path.join(direc, "good_cells_brefeldin_start_" + time + "min.pkl")
pickle.dump(good_cells, open(file_name_save, 'wb'), protocol = pickle.HIGHEST_PROTOCOL)
print len(list_of_cells), len(good_cells)
for cell in good_cells:
print cell.clusterID
longest_time = 0
number_of_cells = 0
for cell in good_cells:
number_of_cells += 1
longest_time = np.amax([longest_time, cell.norm_med.shape[0]])
dynamics_matrix = np.zeros((number_of_cells,longest_time))
# """
# Fill up the heat map matrix
# """
# cell_counter = 0
# for cell in good_cells:
# dynam = cell.norm_med
# dynamics_matrix[cell_counter,0:dynam.shape[0]] = dynam
# cell_counter += 1
# """
# Perform hierarchical clustering
# """
# distance_matrix = np.zeros((number_of_cells, number_of_cells))
# for i in xrange(number_of_cells):
# print i
# for j in xrange(number_of_cells):
# alignment = R.SBD(dynamics_matrix[i,:], dynamics_matrix[j,:], znorm = True)
# distance_matrix[i,j] = alignment.rx('dist')[0][0]
# np.savez("/scratch/PI/mcovert/dvanva/sequencing/smFISH/300_min_brefeldin_dynamics_distance_matrix_kshape.npz", distance_matrix = distance_matrix)
# dynamics_load = np.load("/scratch/PI/mcovert/dvanva/sequencing/smFISH/300_min_brefeldin_dynamics_distance_matrix_kshape.npz")
# distance_matrix = dynamics_load['distance_matrix']
# Y = sch.linkage(distance_matrix, method = 'ward')
# ind_dynamics = sch.fcluster(Y,0.5*np.amax(Y[:,2]),'distance') - 1
# """
# Plot dendrogram
# """
# fig = plt.figure()
# ax_dendro = fig.add_axes([0.09, 0.1, 0.2, 0.8], frame_on = False)
# Z = sch.dendrogram(Y, orientation = 'right', color_threshold = 0.5*np.amax(Y[:,2]))
# ax_dendro.set_xticks([])
# ax_dendro.set_yticks([])
# """
# Plot heatmap
# """
# ax_heatmap = fig.add_axes([0.3, 0.1, 0.6, 0.8])
# index = Z['leaves']
# dynamics_ordered = dynamics_matrix[index,:]
# im = ax_heatmap.matshow(dynamics_ordered, aspect = 'auto', origin = 'lower', cmap = plt.get_cmap('Reds'), interpolation = 'none')
# fig.colorbar(im, ticks = [0, 1], orientation = 'vertical')
# ax_heatmap.set_title('300 minute NFkB activity heatmap - ' + str(number_of_cells) + ' cells', y = 1.05)
# ax_heatmap.set_xlabel('Time')
# ax_heatmap.set_yticks([])
# ax_heatmap.set_xticks([])
# plt.savefig("plots/brefeldin_A_dynamics_clustering_300min.pdf")
"""
Plot heat map using the c1 clustering
"""
"""
Fill up the heat map matrix
"""
cluster_len_1 = 0
cluster_len_2 = 0
cluster_len_3 = 0
for cell in good_cells:
if cell.clusterID == 0:
cluster_len_1 += 1
if cell.clusterID == 1:
cluster_len_2 += 1
if cell.clusterID == 2:
cluster_len_3 += 1
frac_1 = np.float(cluster_len_1) / np.float(cluster_len_1 + cluster_len_2 + cluster_len_3)
frac_2 = np.float(cluster_len_2) / np.float(cluster_len_1 + cluster_len_2 + cluster_len_3)
frac_3 = np.float(cluster_len_3) / np.float(cluster_len_1 + cluster_len_2 + cluster_len_3)
print frac_1, frac_2, frac_3
cell_counter = 0
fig = plt.figure()
ax_heatmap_1 = fig.add_axes([0.3, 0.1 +0.005, 0.6, 0.8*frac_1 - 0.005], frame_on = True)
ax_heatmap_2 = fig.add_axes([0.3, 0.1 +0.005+ 0.8*frac_1, 0.6 , 0.8*frac_2 - 0.005], frame_on = True)
ax_heatmap_3 = fig.add_axes([0.3, 0.1 +0.005+ 0.8*frac_1 + 0.8*frac_2, 0.6, 0.8*frac_3 - 0.005], frame_on = True)
for cell in good_cells:
if cell.clusterID == 0:
dynam = cell.norm_med
dynamics_matrix[cell_counter,0:dynam.shape[0]] = dynam
cell_counter += 1
for cell in good_cells:
if cell.clusterID == 1:
dynam = cell.norm_med
dynamics_matrix[cell_counter,0:dynam.shape[0]] = dynam
cell_counter += 1
for cell in good_cells:
if cell.clusterID == 2:
dynam = cell.norm_med
dynamics_matrix[cell_counter,0:dynam.shape[0]] = dynam
cell_counter += 1
# ax_heatmap = fig.add_axes([0.3, 0.1, 0.6, 0.8])
im1 = ax_heatmap_1.matshow(dynamics_matrix[0:cluster_len_1,:], aspect = 'auto', origin = 'lower', cmap = plt.get_cmap('Reds'), interpolation = 'none')
im2 = ax_heatmap_2.matshow(dynamics_matrix[cluster_len_1:cluster_len_1+cluster_len_2,:], aspect = 'auto', origin = 'lower', cmap = plt.get_cmap('Reds'), interpolation = 'none')
im3 = ax_heatmap_3.matshow(dynamics_matrix[cluster_len_1+cluster_len_2:,:], aspect = 'auto', origin = 'lower', cmap = plt.get_cmap('Reds'), interpolation = 'none')
# fig.colorbar(im1, ticks = [0, 1], orientation = 'vertical')
# ax_heatmap.xaxis.set_ticks(np.arange(63))
ax_heatmap_1.xaxis.set_ticklabels([])
ax_heatmap_1.xaxis.set_ticks([])
# ax_heatmap_1.xaxis.set_ticks_position('bottom')
ax_heatmap_1.yaxis.set_ticklabels([])
ax_heatmap_1.yaxis.set_ticks([])
ax_heatmap_2.yaxis.set_ticklabels([])
ax_heatmap_2.yaxis.set_ticks([])
ax_heatmap_2.xaxis.set_ticklabels([])
ax_heatmap_2.xaxis.set_ticks([])
ax_heatmap_3.yaxis.set_ticklabels([])
ax_heatmap_3.yaxis.set_ticks([])
ax_heatmap_3.xaxis.set_ticklabels([])
ax_heatmap_3.xaxis.set_ticks([])
ax_heatmap_3.set_title('Brefeldin A treated cells - ' + str(number_of_cells) + ' cells', y = 1.05)
ax_heatmap_1.set_xlabel('Time (minutes)')
plt.savefig("plots/brefeldin_A_dynamics_c1_clustering_300min.pdf")