-
Notifications
You must be signed in to change notification settings - Fork 0
/
individual_exon_values_thesis.Rmd
185 lines (159 loc) · 6.85 KB
/
individual_exon_values_thesis.Rmd
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
---
title: "R Notebook"
output: html_notebook
---
TCGA samples for the ten test genes across their corresponding cancer types (as per Tables 1 and 2, and Supplementary Table 8) determined to have a significant change in individual exon expression at the most common fusion breakpoint (Table 2).
The samples were calculated using function, which generated all true and false positive values.
```{r}
#For 3' genes on the negative strand
function(gene, project_id) {
df <- raw_exon_counts_neg(gene)
proj_df <- subset_project_neg(gene, project_id, df)
kbp_df <- norm_length_neg(gene, proj_df)
diff_df <- diff_calc(kbp_df)
diff_auc_df <- norm_auc_neg(gene, project_id, diff_df)
all_z <- z_calc(diff_auc_df)
all_z
}
#For 3' genes on the positive strand
get_all_sig_z_diff_pos <- function(gene, project_id) {
df <- raw_exon_counts(gene)
proj_df <- subset_project(gene, project_id, df)
kbp_df <- norm_length(gene, proj_df)
diff_df <- diff_calc(kbp_df)
diff_auc_df <- norm_auc(gene, project_id, diff_df)
all_z <- z_calc(diff_auc_df)
all_z
}
```
All ten test genes by corresponding cancer type:
```{r}
alk_blca_diff_all <- get_all_sig_z_diff("ALK", "TCGA-BLCA")
alk_kirp_diff_all <- get_all_sig_z_diff("ALK", "TCGA-KIRP")
alk_luad_diff_all <- get_all_sig_z_diff("ALK", "TCGA-LUAD")
alk_read_diff_all <- get_all_sig_z_diff("ALK", "TCGA-READ")
alk_sarc_diff_all <- get_all_sig_z_diff("ALK", "TCGA-SARC")
alk_skcm_diff_all <- get_all_sig_z_diff("ALK", "TCGA-SKCM")
alk_thca_diff_all <- get_all_sig_z_diff("ALK", "TCGA-THCA")
erg_cesc_diff_all <- get_all_sig_z_diff("ERG", "TCGA-CESC")
erg_lgg_diff_all <- get_all_sig_z_diff("ERG", "TCGA-LGG")
erg_paad_diff_all <- get_all_sig_z_diff("ERG", "TCGA-PAAD")
erg_pcpg_diff_all <- get_all_sig_z_diff("ERG", "TCGA-PCPG")
erg_prad_diff_all <- get_all_sig_z_diff("ERG", "TCGA-PRAD")
etv1_lgg_diff_all <- get_all_sig_z_diff("ETV1", "TCGA-LGG")
etv1_prad_diff_all <- get_all_sig_z_diff("ETV1", "TCGA-PRAD")
maml3_brca_diff_all <- get_all_sig_z_diff("MAML3", "TCGA-BRCA")
maml3_lihc_diff_all <- get_all_sig_z_diff("MAML3", "TCGA-LIHC")
maml3_pcpg_diff_all <- get_all_sig_z_diff("MAML3", "TCGA-PCPG")
ntrk3_brca_diff_all <- get_all_sig_z_diff("NTRK3", "TCGA-BRCA")
ntrk3_cesc_diff_all <- get_all_sig_z_diff("NTRK3", "TCGA-CESC")
ntrk3_coad_diff_all <- get_all_sig_z_diff("NTRK3", "TCGA-COAD")
ntrk3_hnsc_diff_all <- get_all_sig_z_diff("NTRK3", "TCGA-HNSC")
ntrk3_lgg_diff_all <- get_all_sig_z_diff("NTRK3", "TCGA-LGG")
ntrk3_paad_diff_all <- get_all_sig_z_diff("NTRK3", "TCGA-PAAD")
ntrk3_skcm_diff_all <- get_all_sig_z_diff("NTRK3", "TCGA-SKCM")
ntrk3_thca_diff_all <- get_all_sig_z_diff("NTRK3", "TCGA-THCA")
tfe3_kirc_diff_all <- get_all_sig_z_diff("TFE3", "TCGA-KIRC")
tfe3_kirp_diff_all <- get_all_sig_z_diff("TFE3", "TCGA-KIRP")
tfe3_ucec_diff_all <- get_all_sig_z_diff("TFE3", "TCGA-UCEC")
arhgap26_cesc_diff_all <- get_all_sig_z_diff_pos("ARHGAP26", "TCGA-CESC")
arhgap26_hnsc_diff_all <- get_all_sig_z_diff_pos("ARHGAP26", "TCGA-HNSC")
arhgap26_luad_diff_all <- get_all_sig_z_diff_pos("ARHGAP26", "TCGA-LUAD")
arhgap26_lusc_diff_all <- get_all_sig_z_diff_pos("ARHGAP26", "TCGA-LUSC")
arhgap26_sarc_diff_all <- get_all_sig_z_diff_pos("ARHGAP26", "TCGA-SARC")
arhgap26_stad_diff_all <- get_all_sig_z_diff_pos("ARHGAP26", "TCGA-STAD")
rara_brca_diff_all <- get_all_sig_z_diff_pos("RARA", "TCGA-BRCA")
rara_cesc_diff_all <- get_all_sig_z_diff_pos("RARA", "TCGA-CESC")
rara_gbm_diff_all <- get_all_sig_z_diff_pos("RARA", "TCGA-GBM")
rara_laml_diff_all <- get_all_sig_z_diff_pos("RARA", "TCGA-LAML")
rara_ov_diff_all <- get_all_sig_z_diff_pos("RARA", "TCGA-OV")
rara_pcpg_diff_all <- get_all_sig_z_diff_pos("RARA", "TCGA-PCPG")
rara_read_diff_all <- get_all_sig_z_diff_pos("RARA", "TCGA-READ")
rara_stad_diff_all <- get_all_sig_z_diff_pos("RARA", "TCGA-STAD")
ret_brca_diff_all <- get_all_sig_z_diff_pos("RET", "TCGA-BRCA")
ret_coad_diff_all <- get_all_sig_z_diff_pos("RET", "TCGA-COAD")
ret_laml_diff_all <- get_all_sig_z_diff_pos("RET", "TCGA-LAML")
ret_luad_diff_all <- get_all_sig_z_diff_pos("RET", "TCGA-LUAD")
ret_ov_diff_all <- get_all_sig_z_diff_pos("RET", "TCGA-OV")
ret_thca_diff_all <- get_all_sig_z_diff_pos("RET", "TCGA-THCA")
tacc3_blca_diff_all <- get_all_sig_z_diff_pos("TACC3", "TCGA-BLCA")
tacc3_brca_diff_all <- get_all_sig_z_diff_pos("TACC3", "TCGA-BRCA")
tacc3_cesc_diff_all <- get_all_sig_z_diff_pos("TACC3", "TCGA-CESC")
tacc3_esca_diff_all <- get_all_sig_z_diff_pos("TACC3", "TCGA-ESCA")
tacc3_gbm_diff_all <- get_all_sig_z_diff_pos("TACC3", "TCGA-GBM")
tacc3_hnsc_diff_all <- get_all_sig_z_diff_pos("TACC3", "TCGA-HNSC")
tacc3_kirp_diff_all <- get_all_sig_z_diff_pos("TACC3", "TCGA-KIRP")
tacc3_laml_diff_all <- get_all_sig_z_diff_pos("TACC3", "TCGA-LAML")
tacc3_lgg_diff_all <- get_all_sig_z_diff_pos("TACC3", "TCGA-LGG")
tacc3_lihc_diff_all <- get_all_sig_z_diff_pos("TACC3", "TCGA-LIHC")
tacc3_luad_diff_all <- get_all_sig_z_diff_pos("TACC3", "TCGA-LUAD")
tacc3_lusc_diff_all <- get_all_sig_z_diff_pos("TACC3", "TCGA-LUSC")
tacc3_stad_diff_all <- get_all_sig_z_diff_pos("TACC3", "TCGA-STAD")
```
Merge each 3' gene across cancer types into one dataframe per cancer type. Saved as Rdata file all_diff_objects.Rdata
```{r}
all_alk_diff_all <- cbind(alk_blca_diff_all,
alk_kirp_diff_all,
alk_luad_diff_all,
alk_read_diff_all,
alk_sarc_diff_all,
alk_skcm_diff_all,
alk_thca_diff_all)
all_arhgap26_diff_all <- cbind(arhgap26_cesc_diff_all,
arhgap26_hnsc_diff_all,
arhgap26_luad_diff_all,
arhgap26_lusc_diff_all,
arhgap26_sarc_diff_all,
arhgap26_stad_diff_all)
all_erg_diff_all <- cbind(erg_cesc_diff_all,
erg_lgg_diff_all,
erg_paad_diff_all,
erg_pcpg_diff_all,
erg_prad_diff_all)
all_etv1_diff_all <- cbind(etv1_lgg_diff_all,
etv1_prad_diff_all)
all_maml3_diff_all <- cbind(maml3_brca_diff_all,
maml3_lihc_diff_all,
maml3_pcpg_diff_all)
all_ntrk3_diff_all <- cbind(ntrk3_brca_diff_all,
ntrk3_cesc_diff_all,
ntrk3_coad_diff_all,
ntrk3_hnsc_diff_all,
ntrk3_lgg_diff_all,
ntrk3_paad_diff_all,
ntrk3_skcm_diff_all,
ntrk3_thca_diff_all)
all_rara_diff_all <- cbind(rara_brca_diff_all,
rara_cesc_diff_all,
rara_gbm_diff_all,
rara_laml_diff_all,
rara_ov_diff_all,
rara_pcpg_diff_all,
rara_read_diff_all,
rara_stad_diff_all)
all_ret_diff_all <- cbind(ret_brca_diff_all,
ret_coad_diff_all,
ret_laml_diff_all,
ret_luad_diff_all,
ret_ov_diff_all,
ret_thca_diff_all)
all_tacc3_diff_all <- cbind(tacc3_blca_diff_all,
tacc3_brca_diff_all,
tacc3_cesc_diff_all,
tacc3_esca_diff_all,
tacc3_gbm_diff_all,
tacc3_hnsc_diff_all,
tacc3_kirp_diff_all,
tacc3_laml_diff_all,
tacc3_lgg_diff_all,
tacc3_lihc_diff_all,
tacc3_luad_diff_all,
tacc3_lusc_diff_all,
tacc3_stad_diff_all)
all_tfe3_diff_all <- cbind(tfe3_kirc_diff_all,
tfe3_kirp_diff_all,
tfe3_ucec_diff_all)
```
Get true and false positives for each gene at recount3 exon as per Table 2. See average_exon_values_thesis.Rmd for process.
The full list of true positives is available from file truepos_diff.csv
The full list of false positives is avaiable from file falsepos_diff.csv