forked from bio-ontology-research-group/predCAN
-
Notifications
You must be signed in to change notification settings - Fork 0
/
ranksumtest.py
234 lines (147 loc) · 7.08 KB
/
ranksumtest.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
import numpy as np
from scipy.stats import ranksums
import pandas as pd
import csv
file = pd.read_csv('merged-file.txt', header=None, skiprows=0, delim_whitespace=True)
file.columns = ['Freq_allel','dpsnp','sift','polyphen','mutas','muaccessor','fathmm','vest3','CADD','geneName']
df = file.drop_duplicates(keep=False)
################## START ###################
# calculate ranksums for SIFT
sift_df = df[['geneName','sift']]
# extract all non-driver genes | sift_score
genelist = pd.read_csv('/encrypted/e3000/gatkwork/COREAD-ESCA-all-driver.tsv', header=None, skiprows=0, sep='\t')
genelist.columns = ['geneName']
#
merged_df = pd.merge(
sift_df, genelist,
how='outer', on=['geneName'], indicator=True, suffixes=('_foo','')).query(
'_merge == "left_only"')
merged_df.drop(['geneName','_merge'], axis=1, inplace=True)
# extract all predicted driver genes | sift_score
genelist1 = pd.read_csv('/encrypted/e3000/gatkwork/COREAD-ESCA-predicteddriver.tsv', header=None, skiprows=0, sep='\t')
genelist1.columns = ['geneName']
merged_df1 = sift_df.merge(genelist1, how = 'inner', on = ['geneName'])
merged_df1.drop(['geneName'], axis=1, inplace=True)
# calculate p-value for ranksums with SIFT
stat, pvalue = ranksums(merged_df, merged_df1)
print(pvalue)
#################### POLYPHEN ###################
# calculate ranksums for POLYPHEN
polyphen_df = df[['geneName','polyphen']]
# extract all non-driver genes | sift_score
genelist = pd.read_csv('/encrypted/e3000/gatkwork/COREAD-ESCA-all-driver.tsv', header=None, skiprows=0, sep='\t')
genelist.columns = ['geneName']
#
merged_df = pd.merge(
polyphen_df, genelist,
how='outer', on=['geneName'], indicator=True, suffixes=('_foo','')).query(
'_merge == "left_only"')
merged_df.drop(['geneName','_merge'], axis=1, inplace=True)
# extract all predicted driver genes | polyphen_score
genelist1 = pd.read_csv('/encrypted/e3000/gatkwork/COREAD-ESCA-predicteddriver.tsv', header=None, skiprows=0, sep='\t')
genelist1.columns = ['geneName']
merged_df1 = polyphen_df.merge(genelist1, how = 'inner', on = ['geneName'])
merged_df1.drop(['geneName'], axis=1, inplace=True)
# calculate p-value for ranksums with polyphen
stat, pvalue = ranksums(merged_df, merged_df1)
print(pvalue)
#################### MutationTaster ###################
# calculate ranksums for MutationTaster
mutas_df = df[['geneName','mutas']]
# extract all non-driver genes | MutationTaster_score
genelist = pd.read_csv('/encrypted/e3000/gatkwork/COREAD-ESCA-all-driver.tsv', header=None, skiprows=0, sep='\t')
genelist.columns = ['geneName']
#
merged_df = pd.merge(
mutas_df, genelist,
how='outer', on=['geneName'], indicator=True, suffixes=('_foo','')).query(
'_merge == "left_only"')
merged_df.drop(['geneName','_merge'], axis=1, inplace=True)
# extract all predicted driver genes | MutationTaster_score
genelist1 = pd.read_csv('/encrypted/e3000/gatkwork/COREAD-ESCA-predicteddriver.tsv', header=None, skiprows=0, sep='\t')
genelist1.columns = ['geneName']
merged_df1 = mutas_df.merge(genelist1, how = 'inner', on = ['geneName'])
merged_df1.drop(['geneName'], axis=1, inplace=True)
# calculate p-value for ranksums with MutationTaster
stat, pvalue = ranksums(merged_df, merged_df1)
print(pvalue)
#################### Mutationassessor ###################
# calculate ranksums for Mutationassessor
muaccessor_df = df[['geneName','muaccessor']]
# extract all non-driver genes | Mutationassessor_score
genelist = pd.read_csv('/encrypted/e3000/gatkwork/COREAD-ESCA-all-driver.tsv', header=None, skiprows=0, sep='\t')
genelist.columns = ['geneName']
#
merged_df = pd.merge(
muaccessor_df, genelist,
how='outer', on=['geneName'], indicator=True, suffixes=('_foo','')).query(
'_merge == "left_only"')
merged_df.drop(['geneName','_merge'], axis=1, inplace=True)
# extract all predicted driver genes | Mutationassessor_score
genelist1 = pd.read_csv('/encrypted/e3000/gatkwork/COREAD-ESCA-predicteddriver.tsv', header=None, skiprows=0, sep='\t')
genelist1.columns = ['geneName']
merged_df1 = muaccessor_df.merge(genelist1, how = 'inner', on = ['geneName'])
merged_df1.drop(['geneName'], axis=1, inplace=True)
# calculate p-value for ranksums with Mutationassessor
stat, pvalue = ranksums(merged_df, merged_df1)
print(pvalue)
#################### fathmm ###################
# calculate ranksums for fathmm
fathmm_df = df[['geneName','fathmm']]
# extract all non-driver genes | fathmm_score
genelist = pd.read_csv('/encrypted/e3000/gatkwork/COREAD-ESCA-all-driver.tsv', header=None, skiprows=0, sep='\t')
genelist.columns = ['geneName']
#
merged_df = pd.merge(
fathmm_df, genelist,
how='outer', on=['geneName'], indicator=True, suffixes=('_foo','')).query(
'_merge == "left_only"')
merged_df.drop(['geneName','_merge'], axis=1, inplace=True)
# extract all predicted driver genes | fathmm_score
genelist1 = pd.read_csv('/encrypted/e3000/gatkwork/COREAD-ESCA-predicteddriver.tsv', header=None, skiprows=0, sep='\t')
genelist1.columns = ['geneName']
merged_df1 = fathmm_df.merge(genelist1, how = 'inner', on = ['geneName'])
merged_df1.drop(['geneName'], axis=1, inplace=True)
# calculate p-value for ranksums with fathmm
stat, pvalue = ranksums(merged_df, merged_df1)
print(pvalue)
#################### VEST3 ###################
# calculate ranksums for VEST3
vest3_df = df[['geneName','vest3']]
# extract all non-driver genes | VEST3_score
genelist = pd.read_csv('/encrypted/e3000/gatkwork/COREAD-ESCA-all-driver.tsv', header=None, skiprows=0, sep='\t')
genelist.columns = ['geneName']
#
merged_df = pd.merge(
vest3_df, genelist,
how='outer', on=['geneName'], indicator=True, suffixes=('_foo','')).query(
'_merge == "left_only"')
merged_df.drop(['geneName','_merge'], axis=1, inplace=True)
# extract all predicted driver genes | VEST3_score
genelist1 = pd.read_csv('/encrypted/e3000/gatkwork/COREAD-ESCA-predicteddriver.tsv', header=None, skiprows=0, sep='\t')
genelist1.columns = ['geneName']
merged_df1 = vest3_df.merge(genelist1, how = 'inner', on = ['geneName'])
merged_df1.drop(['geneName'], axis=1, inplace=True)
# calculate p-value for ranksums with VEST3
stat, pvalue = ranksums(merged_df, merged_df1)
print(pvalue)
#################### CADD ###################
# calculate ranksums for CADD
CADD_df = df[['geneName','CADD']]
# extract all non-driver genes | CADD_score
genelist = pd.read_csv('/encrypted/e3000/gatkwork/COREAD-ESCA-all-driver.tsv', header=None, skiprows=0, sep='\t')
genelist.columns = ['geneName']
#
merged_df = pd.merge(
CADD_df, genelist,
how='outer', on=['geneName'], indicator=True, suffixes=('_foo','')).query(
'_merge == "left_only"')
merged_df.drop(['geneName','_merge'], axis=1, inplace=True)
# extract all predicted driver genes | CADD_score
genelist1 = pd.read_csv('/encrypted/e3000/gatkwork/COREAD-ESCA-predicteddriver.tsv', header=None, skiprows=0, sep='\t')
genelist1.columns = ['geneName']
merged_df1 = CADD_df.merge(genelist1, how = 'inner', on = ['geneName'])
merged_df1.drop(['geneName'], axis=1, inplace=True)
# calculate p-value for ranksums with CADD
stat, pvalue = ranksums(merged_df, merged_df1)
print(pvalue)