UTUC_plotting/SLC3A2_panel_plotting.R at main · Hoho1996/UTUC_plotting · 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
library(ggplot2)
library(dplyr)
library(ggpubr)
library(scales)

gain_colors <- c(Gain = "#AE7182", Other = "#bebebe", Amp = "#AE7182")

theme_plot <- theme_classic(base_size = 12) +
  theme(
    axis.text = element_text(color = "black"),
    axis.title = element_text(color = "black"),
    plot.title = element_text(hjust = 0.5),
    legend.text = element_text(color = "black"),
    legend.title = element_text(color = "black")
  )

## SLC3A2 copy-number gain proportion by SNF subtype
p_value <- if ("P_value" %in% colnames(df_slc3a2_cnv)) unique(na.omit(df_slc3a2_cnv$P_value))[1] else NA_real_

p_slc3a2_cnv <- ggplot(df_slc3a2_cnv, aes(x = SNF_group, y = Percentage, fill = SLC3A2_status)) +
  geom_col(width = 0.75) +
  geom_text(aes(label = round(Percentage, 1)), position = position_stack(vjust = 0.5), size = 3.5) +
  scale_y_continuous(labels = percent_format(scale = 1), limits = c(0, 110), expand = c(0, 0)) +
  scale_fill_manual(values = gain_colors, na.value = "grey80") +
  labs(x = NULL, y = "Proportion", fill = NULL, title = "SLC3A2") +
  theme_plot

if (!is.na(p_value)) {
  p_slc3a2_cnv <- p_slc3a2_cnv +
    annotate("text", x = 1.5, y = 105, label = paste("P =", format(p_value, scientific = TRUE, digits = 3)), size = 3.5)
}

ggsave("SLC3A2_CN_gain_proportion_by_SNF.pdf", p_slc3a2_cnv, width = 3.5, height = 3.5)


## SLC3A2 protein abundance by copy-number status
df_slc3a2_protein <- df_slc3a2_protein %>%
  mutate(CN_group = factor(CN_group, levels = c("Gain", "Other")))

p_slc3a2_protein <- ggplot(df_slc3a2_protein, aes(x = CN_group, y = SLC3A2, fill = CN_group, color = CN_group)) +
  geom_violin(trim = FALSE, alpha = 0.8, color = NA) +
  geom_point(position = position_jitter(width = 0.15), shape = 21, size = 2.5, alpha = 0.45) +
  stat_summary(fun = median, geom = "crossbar", width = 0.18, color = "black") +
  stat_compare_means(method = "wilcox.test", comparisons = list(c("Gain", "Other")), label = "p.format") +
  scale_fill_manual(values = gain_colors) +
  scale_color_manual(values = gain_colors) +
  labs(x = NULL, y = "SLC3A2 protein abundance") +
  theme_plot +
  theme(legend.position = "none")

ggsave("SLC3A2_protein_abundance_by_CNV.pdf", p_slc3a2_protein, width = 2.6, height = 3.6)


## Correlation between SLC3A2 and SPP1
cor_test <- cor.test(df_slc3a2_spp1$SLC3A2, df_slc3a2_spp1$SPP1, method = "spearman", exact = FALSE)
cor_label <- paste0("Spearman r = ", round(unname(cor_test$estimate), 2), ", P = ", signif(cor_test$p.value, 2))

p_slc3a2_spp1 <- ggplot(df_slc3a2_spp1, aes(x = SPP1, y = SLC3A2)) +
  geom_point(size = 2.5, alpha = 0.8, color = "#4c78a8") +
  geom_smooth(method = "lm", se = TRUE, color = "black", linewidth = 0.6) +
  annotate("text", x = -Inf, y = Inf, hjust = -0.05, vjust = 1.2, label = cor_label, size = 3.6) +
  labs(x = "SPP1", y = "SLC3A2") +
  theme_plot

ggsave("SLC3A2_SPP1_correlation.pdf", p_slc3a2_spp1, width = 3.5, height = 3.5)