CompExonSpace/percentage(FigS4).Rmd at main · Novartis/CompExonSpace · GitHub

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


```{r}
library(dplyr)
library(ggplot2)
library(scales)
```

```{r}
# Define paths
data_dir <- Sys.getenv("MYDATA")

# function to load data (differential data with complementarity info)
load_csv <- function(filename) {
  read.csv(file.path(data_dir, filename), stringsAsFactors = FALSE)
}

# Load datasets
NVS     <- read.csv(file.path(data_dir, "exon_diff", "Exp1_NVSSM1_25nM_vs_DMSO.csv"))
Ris    <- read.csv(file.path(data_dir, "exon_diff", "Exp1_Ris_655nM_vs_DMSO.csv"))
U1CU    <- read.csv(file.path(data_dir, "exon_diff", "Exp3_U1CU_vs_U1wt.csv"))
Candidates <- read.csv(file.path(data_dir, "exon_diff", "Candidates.csv"))
```

```{r}

# Prepare datasets
NVS <- NVS %>%
  filter(included == "yes") %>%
  select(ExonEndID, Exon1, Exon2, Exon3, Exon4) %>%
  mutate(group = "NVS")

Ris <- Ris %>%
  filter(included == "yes") %>%
  select(ExonEndID, Exon1, Exon2, Exon3, Exon4) %>%
  mutate(group = "Risdiplam")

Candidates <- Candidates %>%
  select(ExonEndID, Exon1, Exon2, Exon3, Exon4) %>%
  mutate(group = "Candidates")

# Combine compound and candidate info
df_all <- bind_rows(Candidates, NVS, Ris)


# Combine compound and muational assay analysis
NVS <- NVS %>%
  dplyr::select (ExonEndID, Exon3, group)
Ris <- Ris %>%
  dplyr::select (ExonEndID, Exon3, group)
U1CU <- U1CU %>%
  filter(included == "yes") %>%
  dplyr::select (ExonEndID, Exon3)

U1CU$group <- "U1CU"

df_all_mut <- bind_rows(U1CU, NVS, Ris)
df_all_mut

```

```{r}
#function to plot nucleotide distribution at certain positions at the Exon end
plot_prop <- function(data, fill_var, title, fill_label) {
  ggplot(data, aes(x = group, fill = {{ fill_var }})) +
    geom_bar(position = "fill", color = "black") +
    scale_y_continuous(labels = percent_format()) +
    labs(
      x = "",
      y = "Percentage",
      fill = fill_label,
      title = title
    ) +
    theme_classic(base_size = 14) +
    theme(
      plot.title = element_text(hjust = 0.5, face = "bold"),
      axis.text = element_text(color = "black")
    )
}


```

```{r}
df_allA <- df_all %>% filter(Exon1 == "A")
plot_prop(df_allA, Exon2, "-2 position in A exons across datasets", "Position -4")

df_allGA <- df_all %>% filter(Exon2 == "GA")
plot_prop(df_allGA, Exon3, "-3 position in GA exons across datasets", "Position -3")

df_allAGA <- df_all %>% filter(Exon3 == "AGA")
plot_prop(df_allAGA, Exon4, "-4 position in AGA exons across datasets", "Position -4")

df_allGGA <- df_all %>%
  filter(Exon3 %in% c("TGA", "GGA")) %>%
  mutate(pos4 = substr(Exon4, 1, 1))

plot_prop(df_allGGA, pos4, "-4 position in UGA and GGA exons across datasets", "Position -4")


#plotting -3 position in mutational assay
df_all_mutGA <- df_all_mut %>% filter(Exon3 %in% c("TGA", "GGA", "CGA", "AGA"))
plot_prop(df_all_mutGA, Exon3, "-3 position in GA exons across datasets", "Position -3")


```