-
Notifications
You must be signed in to change notification settings - Fork 0
/
r2-data_prepare.py
161 lines (101 loc) · 3.86 KB
/
r2-data_prepare.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
# In[1]:
# import packages
import numpy as np
import pandas as pd
# In[2]:
# selcet and save exon-level data
def select_ensembl(Ensembl, g):
key = Ensembl.loc[g,'name']
return key
def select_exon(data, key):
exon = []
for i in range(len(data)):
if key in data.loc[i,'Ensembl']:
e = data.loc[i,'Ensembl']
exon.append(e)
return exon
def select_count(data, key):
count = []
for i in range(len(data)):
if key in data.loc[i,'Ensembl']:
c = data.loc[i,'count']
count.append(c)
return count
def geneMat(cell_line, time, condition, key):
data = pd.read_csv('%s_%dh_Rep%d_exon_read_counts.txt' %(cell_line, time[0], condition[0]),
sep='\t', names=['Ensembl','count'])
exon = select_exon(data, key)
mat = pd.DataFrame(columns=exon)
for i in time:
for j in condition:
data = pd.read_csv('%s_%dh_Rep%d_exon_read_counts.txt' %(cell_line, i, j),
sep='\t', names=['Ensembl','count'])
count = select_count(data, key)
mat.loc[len(mat)] = count
return mat
time = [3,6,12,24,48,96,120]
condition = [1,2,3]
Ensembl = pd.read_csv('Ensembl.txt', names=['name'])
## cell line = Macrophage
cell_line = 'Macrophage'
for i in range(len(Ensembl)):
key = select_ensembl(Ensembl, i)
exec( f'Mac_mat_%s=geneMat(cell_line, time, condition, key)' % i)
### save matrix
for i in range(len(Ensembl)):
exec( f"Mac_mat_%s.to_csv('Mac_mat_%s.txt', sep='\t', index=False)" % (i, i))
## cell line = Monocyte
cell_line = 'Monocyte'
for i in range(len(Ensembl)):
key = select_ensembl(Ensembl, i)
exec( f'Mon_mat_%s=geneMat(cell_line, time, condition, key)' % i)
### save matrix
for i in range(len(Ensembl)):
exec( f"Mon_mat_%s.to_csv('Mon_mat_%s.txt', sep='\t', index=False)" % (i, i))
## cell line = Neutrophil
cell_line = 'Neutrophil'
for i in range(len(Ensembl)):
key = select_ensembl(Ensembl, i)
exec( f'Neu_mat_%s=geneMat(cell_line, time, condition, key)' % i)
### save matrix
for i in range(len(Ensembl)):
exec( f"Neu_mat_%s.to_csv('Neu_mat_%s.txt', sep='\t', index=False)" % (i, i))
# In[3]:
# selcet and save rna-seq data
def gene_count(data, key):
for i in range(len(data)):
if key in data.loc[i,'Ensembl']:
count = data.loc[i,'count']
return count
def geneVec(cell_line, time, condition, key):
gene = []
for i in time:
for j in condition:
data = pd.read_csv('%dh-%s-Rep%d.txt' %(i, cell_line, j),
skiprows=1, sep='\t', names=['Ensembl','count'])
gene.append(gene_count(data, key))
return np.array(gene)
## cell line = Macrophage
cell_line = 'Mac'
for i in range(len(Ensembl)):
key = select_ensembl(Ensembl, i)
exec( f'Mac_vec_%s=geneVec(cell_line, time, condition, key)' % i)
### save vector
for i in range(len(Ensembl)):
exec( f"np.savetxt('Mac_vec_%s.txt', Mac_vec_%s)" % (i, i))
## cell line = Monocyte
cell_line = 'Mon'
for i in range(len(Ensembl)):
key = select_ensembl(Ensembl, i)
exec( f'Mon_vec_%s=geneVec(cell_line, time, condition, key)' % i)
### save vector
for i in range(len(Ensembl)):
exec( f"np.savetxt('Mon_vec_%s.txt', Mon_vec_%s)" % (i, i))
## cell line = Neutrophil
cell_line = 'Neu'
for i in range(len(Ensembl)):
key = select_ensembl(Ensembl, i)
exec( f'Neu_vec_%s=geneVec(cell_line, time, condition, key)' % i)
### save vector
for i in range(len(Ensembl)):
exec( f"np.savetxt('Neu_vec_%s.txt', Neu_vec_%s)" % (i, i))