-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathSupp
229 lines (197 loc) · 11.9 KB
/
Supp
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
datasetObject_pre_train3vs12<-datasetObject_pre_train
datasetObject_pre_test3vs12<-datasetObject_pre_test
datatttt_test<-datasetObject_pre_train$sillhouette$GSE120572
datatttt_test2<-(datasetObject_pre_train$sillhouette)[[1]]
sample(c(1:9,11:17), 10, replace=F)
dim(train_1)
{
Positive_gene<-c()
Negative_gene<-c()
start_time <- Sys.time()
for (i in 1:3){
print(i)
sample_list<-c(1:9,11:17) #
sample_list1<-sample(sample_list, 10, replace=F) # randomly select 10 datatset from train
sample_list2<-sample_list[!sample_list %in% sample_list1] # the rest 6 datatset from train
dataObj1_Train = (datasetObject_pre_train$sillhouette)[[sample_list1[1]]]
dataObj2_Train = (datasetObject_pre_train$sillhouette)[[sample_list1[2]]]
dataObj3_Train = (datasetObject_pre_train$sillhouette)[[sample_list1[3]]]
dataObj4_Train = (datasetObject_pre_train$sillhouette)[[sample_list1[4]]]
dataObj5_Train = (datasetObject_pre_train$sillhouette)[[sample_list1[5]]]
dataObj6_Train = (datasetObject_pre_train$sillhouette)[[sample_list1[6]]]
dataObj7_Train = (datasetObject_pre_train$sillhouette)[[sample_list1[7]]]
dataObj8_Train = (datasetObject_pre_train$sillhouette)[[sample_list1[8]]]
dataObj9_Train = (datasetObject_pre_train$sillhouette)[[sample_list1[9]]]
dataObj10_Train = (datasetObject_pre_train$sillhouette)[[sample_list1[10]]]
print('Step1')
discovery_datasets_Train <- list( dataObj1_Train,dataObj2_Train,dataObj3_Train,
dataObj5_Train,dataObj6_Train,dataObj7_Train,dataObj8_Train,dataObj9_Train,
dataObj10_Train)
names(discovery_datasets_Train) = c( dataObj1_Train$formattedName,
dataObj2_Train$formattedNam,dataObj3_Train$formattedName,
dataObj5_Train$formattedName,
dataObj6_Train$formattedName,dataObj7_Train$formattedName,
dataObj8_Train$formattedName,dataObj9_Train$formattedName,
dataObj10_Train$formattedName)
print('Step2')
# the rest 6 datatset from train
dataObj1_Test = (datasetObject_pre_train$sillhouette)[[sample_list2[1]]]
dataObj2_Test = (datasetObject_pre_train$sillhouette)[[sample_list2[2]]]
dataObj3_Test = (datasetObject_pre_train$sillhouette)[[sample_list2[3]]]
dataObj4_Test = (datasetObject_pre_train$sillhouette)[[sample_list2[4]]]
dataObj5_Test = (datasetObject_pre_train$sillhouette)[[sample_list2[5]]]
dataObj6_Test = (datasetObject_pre_train$sillhouette)[[sample_list2[6]]]
print('Step3')
validation_datasets_Test <- list( dataObj1_Test,dataObj2_Test,dataObj3_Test,dataObj4_Test,
dataObj5_Test,dataObj6_Test)
names(validation_datasets_Test) = c( dataObj1_Test$formattedName,
dataObj2_Test$formattedNam,dataObj3_Test$formattedName,
dataObj4_Test$formattedName,dataObj5_Test$formattedName,
dataObj6_Test$formattedName)
print('Step4')
exampleMetaObj_Train=list()
exampleMetaObj_Train$originalData <- discovery_datasets_Train
exampleMetaObj_validation_Test<-list()
exampleMetaObj_validation_Test$originalData <- validation_datasets_Test
checkDataObject(exampleMetaObj_Train, "Meta", "Pre-Analysis") ###Check your metaObject before MetaAnalysis using
checkDataObject(exampleMetaObj_validation_Test, "Meta", "Pre-Analysis")
print('Step5')
exampleMetaObj_Train <- runMetaAnalysis(exampleMetaObj_Train, maxCores=6,runLeaveOneOutAnalysis = FALSE)
exampleMetaObj_Train <- filterGenes(exampleMetaObj_Train, isLeaveOneOut = F, FDRThresh = 0.05,effectSizeThresh = 1.0) # 1 vs 2/3, es=1.0
exampleMetaObj_Train$filterResults[[1]]$posGeneNames<-intersect(exampleMetaObj_Train$filterResults[[1]]$posGeneNames,
rownames(train_1))
exampleMetaObj_Train$filterResults[[1]]$negGeneNames<-intersect(exampleMetaObj_Train$filterResults[[1]]$negGeneNames,
rownames(train_1))
print('Step6')
exampleMetaObj_validation_Test <- runMetaAnalysis(exampleMetaObj_validation_Test, maxCores=6,runLeaveOneOutAnalysis = FALSE)
exampleMetaObj_validation_Test <- filterGenes(exampleMetaObj_validation_Test, isLeaveOneOut = F, FDRThresh = 0.05,effectSizeThresh = 1.0) # 1 vs 2/3, es=1.0
exampleMetaObj_validation_Test$filterResults[[1]]$posGeneNames<-intersect(exampleMetaObj_validation_Test$filterResults[[1]]$posGeneNames,
rownames(train_1))
exampleMetaObj_validation_Test$filterResults[[1]]$negGeneNames<-intersect(exampleMetaObj_validation_Test$filterResults[[1]]$negGeneNames,
rownames(train_1))
print('Step7')
posGeneNames<-intersect(exampleMetaObj_Train$filterResults[[1]]$posGeneNames,
exampleMetaObj_validation_Test$filterResults[[1]]$posGeneNames)
negGeneNames<-intersect(exampleMetaObj_Train$filterResults[[1]]$negGeneNames,
exampleMetaObj_validation_Test$filterResults[[1]]$negGeneNames)
Positive_gene<-c(posGeneNames,Positive_gene)
Negative_gene<-c(negGeneNames,Negative_gene)
print('Step8')
}
end_time <- Sys.time()
end_time-start_time
}
{
set.seed(123)
#这里exampleMetaObj_Train$filterResults[[1]]需要与rownames(train_1) 取交集确保在每个数据集里都出现了
forwardRes <- forwardSearch( metaObject = exampleMetaObj_Train,
filterObject =exampleMetaObj_Train$filterResults[[1]])
heatmapPlot(metaObject =exampleMetaObj_Train, filterObject = exampleMetaObj_Train$filterResults[[7]])
forestPlot(metaObject =exampleMetaObj_Train, filterObject = exampleMetaObj_Train$filterResults[[1]])
summaryROCPlot(metaObject = exampleMetaObj_validation_Test,
filterObject = forwardRes ,
bootstrapReps = 500)
exampleMetaObj_Train1vs23<-exampleMetaObj_Train
forwardRes1vs23<-forwardRes
exampleMetaObj_Train2vs13<-exampleMetaObj_Train
forwardRes2vs13<-forwardRes
exampleMetaObj_Train3vs12<-exampleMetaObj_Train
forwardRes3vs12<-forwardRes
save(forwardRes1vs23,forwardRes2vs13,forwardRes3vs12,datasetObject_pre_train1vs23,
datasetObject_pre_test1vs23,datasetObject_pre_train2vs13,datasetObject_pre_test2vs13,
datasetObject_pre_train3vs12,
datasetObject_pre_test3vs12,file='Predictor_forwardRes.Rdata')
Wester_Prote_sub<-Wester_Prote[,c(phe_Wester_ALK_Pro[phe_Wester_ALK_Pro$MYCN=='amp',1],
phe_Wester_ALK_Pro_Normal[phe_Wester_ALK_Pro_Normal$pred_zscore==1,1],
phe_Wester_ALK_Pro_Normal[phe_Wester_ALK_Pro_Normal$pred_zscore==2,1],
phe_Wester_ALK_Pro_Normal[phe_Wester_ALK_Pro_Normal$pred_zscore==3,1])]
# MYCN/MYC/AURKA/
Wester_Prote_sub_expression<-as.data.frame(matrix(data=NA,nrow=34,ncol=6,
dimnames=list(c(),c('Sample','Subgroup','MYCN',
'MYC','AURKA','AURKB'))))
Wester_Prote_sub_expression$Sample<-colnames(Wester_Prote_sub)
Wester_Prote_sub_expression$Subgroup<-c(rep('AMP',12),
rep('Subgroup1',11),
rep('Subgroup2',2),
rep('Subgroup3',9))
Wester_Prote_sub_expression$MYCN<-t(Wester_Prote_sub[c('MYCN'),])
Wester_Prote_sub_expression$MYC<-t(Wester_Prote_sub[c('MYC'),])
Wester_Prote_sub_expression$AURKA<-t(Wester_Prote_sub[c('AURKA'),])
Wester_Prote_sub_expression$AURKB<-t(Wester_Prote_sub[c('AURKB'),])
my_comparisons_train <- list( c("Subgroup1", "AMP"),
c("Subgroup2", "AMP"),
c("Subgroup3", "AMP"),
c('Subgroup1','Subgroup2'),
c('Subgroup1','Subgroup3'),
c('Subgroup2','Subgroup3'))
aa<-ggviolin(Wester_Prote_sub_expression, x = "Subgroup", y = 'MYCN',
fill = "Subgroup",
add = "boxplot", add.params = list(fill = "white"),palette = c("#D22C6C","#6688AB", "#97C17E",'#BA86B5'))+
stat_compare_means(comparisons = my_comparisons_train,size=10)+
ylab("MYCN expression\n") +
xlab('')+
#scale_y_continuous(breaks=seq(0, 1, 0.1))+
#coord_cartesian(ylim = c(-2500,3000))+
#geom_hline(yintercept = median(gsva_MYC_matrix[Purity_Test$Group=='MYCN_AMP',]$ImmuneScore),
# size=2,linetype = 2)+
theme_classic()+
theme(legend.position = "none",
axis.text.x = element_text( size=30,color = 'black',hjust = 0.5,vjust=0),
axis.text.y = element_text( size=30,color = 'black'),
axis.line = element_line(colour = "black", size = 1, linetype = "solid"),
axis.title.y = element_text(color="black", size=40,vjust=0),
plot.margin = unit(c(1,1,1,1),"cm"))
bb<-ggviolin(Wester_Prote_sub_expression, x = "Subgroup", y = 'MYC',
fill = "Subgroup",
add = "boxplot", add.params = list(fill = "white"),palette = c("#D22C6C","#6688AB", "#97C17E",'#BA86B5'))+
stat_compare_means(comparisons = my_comparisons_train,size=10)+
ylab("MYC expression\n") +
xlab('')+
#scale_y_continuous(breaks=seq(0, 1, 0.1))+
#coord_cartesian(ylim = c(-2500,3000))+
#geom_hline(yintercept = median(gsva_MYC_matrix[Purity_Test$Group=='MYCN_AMP',]$ImmuneScore),
# size=2,linetype = 2)+
theme_classic()+
theme(legend.position = "none",
axis.text.x = element_text( size=30,color = 'black',hjust = 0.5,vjust=0),
axis.text.y = element_text( size=30,color = 'black'),
axis.line = element_line(colour = "black", size = 1, linetype = "solid"),
axis.title.y = element_text(color="black", size=40,vjust=0),
plot.margin = unit(c(1,1,1,1),"cm"))
cc<-ggviolin(Wester_Prote_sub_expression, x = "Subgroup", y = 'AURKA',
fill = "Subgroup",
add = "boxplot", add.params = list(fill = "white"),palette = c("#D22C6C","#6688AB", "#97C17E",'#BA86B5'))+
stat_compare_means(comparisons = my_comparisons_train,size=10)+
ylab("AURKA expression\n") +
xlab('')+
#scale_y_continuous(breaks=seq(0, 1, 0.1))+
#coord_cartesian(ylim = c(-2500,3000))+
#geom_hline(yintercept = median(gsva_MYC_matrix[Purity_Test$Group=='MYCN_AMP',]$ImmuneScore),
# size=2,linetype = 2)+
theme_classic()+
theme(legend.position = "none",
axis.text.x = element_text( size=30,color = 'black',hjust = 0.5,vjust=0),
axis.text.y = element_text( size=30,color = 'black'),
axis.line = element_line(colour = "black", size = 1, linetype = "solid"),
axis.title.y = element_text(color="black", size=40,vjust=0),
plot.margin = unit(c(1,1,1,1),"cm"))
dd<-ggviolin(Wester_Prote_sub_expression, x = "Subgroup", y = 'AURKB',
fill = "Subgroup",
add = "boxplot", add.params = list(fill = "white"),palette = c("#D22C6C","#6688AB", "#97C17E",'#BA86B5'))+
stat_compare_means(comparisons = my_comparisons_train,size=10)+
ylab("AURKB expression\n") +
xlab('')+
#scale_y_continuous(breaks=seq(0, 1, 0.1))+
#coord_cartesian(ylim = c(-2500,3000))+
#geom_hline(yintercept = median(gsva_MYC_matrix[Purity_Test$Group=='MYCN_AMP',]$ImmuneScore),
# size=2,linetype = 2)+
theme_classic()+
theme(legend.position = "none",
axis.text.x = element_text( size=30,color = 'black',hjust = 0.5,vjust=0),
axis.text.y = element_text( size=30,color = 'black'),
axis.line = element_line(colour = "black", size = 1, linetype = "solid"),
axis.title.y = element_text(color="black", size=40,vjust=0),
plot.margin = unit(c(1,1,1,1),"cm"))
ggarrange(aa, bb, cc ,dd,
ncol = 2, nrow = 2)
ggsave('Wester_Prote_sub_expression_AMP.pdf',width = 25,height = 25) # 3组 宽12， 4组 宽 16