DataViz_JSRe0167_ProteinDomainVisualizer.Rmd

---
title: "JSRe0167_ProteinDomains"
author: "Jacob Roth"
date: "2024-05-06"
output: html_document
---

```{r setup, include=FALSE}
knitr::opts_chunk$set(echo = TRUE)
```

## R Markdown

```{r}
library(ggplot2)
library(plyr)


df_protein <- readxl::read_excel("2-data_raw/ProteinDomains.xlsx",
                           sheet = 1)

# Example dataframe
# df_protein <- data.frame(
#   name = c("Protein1", "Protein1", "Protein1", "Protein2"),
#   type = c("Domain A", "Domain B", "length", "length"),
#   start = c(1, 20, 1, 1),
#   end = c(15, 28, 500, 150),
#   rank = c(1, 1, 1, 2) # Assume rank indicates the order in which proteins should be displayed
# 
# )
df_protein$start <- as.numeric(df_protein$start)
df_protein$end <- as.numeric(df_protein$end)

# Define x-axis limits based on the data range or specific interest
x_min <- round_any(min(df_protein$start) - 10, 50, f = ceiling) # Extend a bit beyond the minimum start value
x_max <- round_any(max(df_protein$end) + 10, 50, f = ceiling) # Extend a bit beyond the maximum end value

```

```{r}

```


```{r}
# Assuming df_protein is already defined and includes "length" rows for each protein

# Plotting the domains
g <- ggplot(df_protein) +
  geom_segment(data = df_protein %>% filter(type == "length"), aes(x = start, xend = end, y = name, yend = name), size = 1, color = "black") +
  geom_segment(data = df_protein %>% filter(type != "length"), aes(x = start, xend = end, y = name, yend = name, color = type), size = 5) +
  scale_color_brewer(palette = "Set1") +
  # coord_flip() +
  labs(x = "Amino Acid Position", title = "Protein Domains Visualization", color = "Domain Type") +
  theme_minimal() +
  theme(panel.grid.major.y = element_blank(), 
        panel.grid.minor.y = element_blank(),
        legend.title = element_text(size = 12),
        legend.text = element_text(size = 10),
        axis.text.y = element_text(size = 12))
  # scale_x_continuous(limits = c(x_min, x_max), breaks = seq(x_min, x_max, by = 20))

# Display the plot
print(g)

```

```{r, eval = F}
# unique(df_protein$type)

colors_JSRe0150 <- c("#636363", #"length"
                     "#fa9fb5", #"WD-repeat"
                     # "#404040", #"Replaced with G4S"
                     # "#80cdc1", #"Tag_GST"
                     "#018571" #"Tag_MBP"
                     )

colors_JSRe0167 <- c("length" = "#636363",
                     # "WD-repeat" = "#fa9fb5",
                     "Acetylation" = "#d8b365",
                     "Methylation" = "#404040",
                     "Ubiquitinylation" = "#c7eae5",
                     "Phosphorylation" = "#000000",
                     "Sumoylation" = "#01665e"
                     )


pie(rep(1,6), col=colors_JSRe0167)

types <- unique(df_protein$type)
color_set = setNames(colors_JSRe0150,
                            types)

```
```{r E2F1 colors, eval = F}
# unique(df_protein$type)

types_E2F1 <- df_protein %>%
  filter(name == "E2F1") %>%
  filter(plot == "y") %>%
  pull(label3) %>%
  unique()%>%
  na.omit() # Removes NA values
types_E2F1

colors_E2F1 <- c("length" = "#000000",
                     # "WD-repeat" = "#fa9fb5",
                     "Acetylation" = "cyan3",
                     "Methylation" = "magenta",
                     "Ubiquitinylation" = "#000000",
                     "Phosphorylation" = "#000000",
                     "CyclinA-CDK2 binding" = "lightseagreen",
                     "Leucine-Zipper" = "#d8b365",
                 "Dimerization" = "#01665e",
                 "Transactivation" = "gray75",
                 "RB1 binding" = "gray65"
                 )


# pie(rep(1,10), col=colors_E2F1)

# color_E2F1 = setNames(colors_E2F1,
#                             types_E2F1)
# color_E2F1

```


```{r E2F1}
library(ggrepel)
library(tidyverse)
df_protein <- df_protein %>%
  filter(name == "E2F1")

df_protein$label3 <- factor(df_protein$label3,
                            levels = c("Methylation",
                                       "Acetylation",
                                       "Phosphorylation",
                                       "Ubiquitinylation",
                                       "Leucine-Zipper",
                                       "Dimerization",
                                      "CyclinA-CDK2 binding",
                                      "Transactivation",
                                      "RB1 binding"
                                      ))


g <- df_protein %>%
ggplot() +
  geom_text_repel(data = df_protein %>% filter(plot == "y" 
                                               # & label == "Methylation" 
                                               & label_start_top == "y"), 
                  aes(x = start, y = name, label = residue, color = label3),
                  nudge_x = 0, nudge_y = 0.25,
                  # direction = "y", 
                  size = 3,
                  # fill = alpha(c("white"),0.9),
                  fill = "white",
                  fontface = 'bold',
                  max.overlaps = 10,    # Control maximum number of overlaps allowed
                  box.padding = 0.75,    # Padding around text box
                  segment.color = 'grey50', # Line color from label to point
                  point.padding = 0.3  # Padding between points and text
                  ) +
  # geom_text_repel(data = df_protein %>% filter(plot == "y" & label_end_top == "y"), aes(x = end, y = name, label = end),
  #                 nudge_x = 0, nudge_y = 0.3, direction = "y", size = 3) +
  geom_text_repel(data = df_protein %>% filter(plot == "y" & label_start_bot == "y"), 
                  aes(x = start, y = name, label = residue, color = label3),
                  nudge_x = 0, nudge_y = -0.25,
                  # direction = "y", 
                  size = 3,
                  fontface = 'bold',
                  # fill = alpha(c("blue"),0.5),
                  # alpha = 0.1,
                  fill = "white",       # Set background color of label box
                  max.overlaps = 10,    # Control maximum number of overlaps allowed
                  box.padding = 0.5,    # Padding around text box
                  segment.color = 'grey50', # Line color from label to point
                  point.padding = 0.3  # Padding between points and text
                  ) +
  geom_segment(data = df_protein %>% filter(plot == "y" & type == "length"), aes(x = start, xend = end, y = name, yend = name), size = 1, color = "black") +
  geom_segment(data = df_protein %>% filter(plot == "y" & type == "Domain"), 
               aes(x = start, xend = end, y = name, yend = name, color = label), 
               size = 5) +
  # geom_text_repel(data = df_protein %>% filter(plot == "y" & label_end_bot == "y"), aes(x = end, y = name, label = end),
  #                 nudge_x = 0, nudge_y = -0.3, direction = "y", size = 3) +
  # scale_color_brewer(palette = "Set1") +
    scale_color_manual(values = colors_E2F1,
                      breaks=c("Methylation",
                                       "Acetylation",
                                       "Phosphorylation",
                                       "Ubiquitinylation",
                                       "Leucine-Zipper",
                                       # "Dimerization",
                                      # "CyclinA-CDK2 binding",
                                      # "Transactivation",
                                      "RB1 binding")) +
  # geom_label_repel(data = df_protein %>% filter(!is.na(label)), aes(x = (start + end) / 2, y = name, label = label), 
  #                  nudge_x = 0, nudge_y = 0.2, size = 4, segment.color = "grey50") +
  # coord_flip() +
  labs(x = "Amino Acid Position", 
       y = "", 
       title = "Visualization of E2F1 PTMs", color = "Modification") +
  theme_minimal() +
  theme(panel.grid.major.y = element_blank(), 
        panel.grid.minor.y = element_blank(),
        legend.title = element_text(size = 12),
        legend.text = element_text(size = 10),
        axis.text.y = element_text(size = 12),
        # axis.text.x=element_blank(),
        legend.position="bottom"
        # ,legend.direction="vertical"
        ) +
  scale_x_continuous(breaks = seq(x_min, x_max, by = 50), labels = seq(x_min, x_max, by = 50)) # Adjusted for y-axis due to coord_flip
  # scale_x_continuous(breaks = function(x) ifelse(x == 0, 0, NA), labels = function(x) ifelse(x == 0, "0", ""))
    # scale_y_discrete(limits=rev)

# Display the plot
print(g)
ggsave("5-figures/20240905_E2F1-ProteinDomains3.png", plot = g, width = 10, height = 5, dpi = 300)

```


```{r SRSF3 colors, eval = F}
# unique(df_protein$type)

colors_JSRe0150 <- c("#636363", #"length"
                     "#fa9fb5", #"WD-repeat"
                     # "#404040", #"Replaced with G4S"
                     # "#80cdc1", #"Tag_GST"
                     "#018571" #"Tag_MBP"
                     )

colors_JSRe0167 <- c("length" = "#636363",
                     # "WD-repeat" = "#fa9fb5",
                     "Acetylation" = "#d8b365",
                     "Methylation" = "#404040",
                     "Ubiquitinylation" = "#c7eae5",
                     "Phosphorylation" = "#000000",
                     "Sumoylation" = "#01665e"
                     )


pie(rep(1,6), col=colors_JSRe0167)

types <- unique(df_protein$type)
color_set = setNames(colors_JSRe0150,
                            types)

```

```{r SRSF3, eval = FALSE}
library(ggrepel)
library(tidyverse)
g <- df_protein %>%
ggplot() +
  geom_text_repel(data = df_protein %>% filter(plot == "y" & label == "Methylation" & label_start_top == "y"), aes(x = start, y = name, label = start),
                  nudge_x = 0, nudge_y = 0.15, direction = "y", size = 3) +
  # geom_text_repel(data = df_protein %>% filter(plot == "y" & label_end_top == "y"), aes(x = end, y = name, label = end),
  #                 nudge_x = 0, nudge_y = 0.3, direction = "y", size = 3) +
  geom_text_repel(data = df_protein %>% filter(plot == "y" & label_start_bot == "y"), aes(x = start, y = name, label = start, color = label),
                  nudge_x = 0, nudge_y = -0.15, direction = "y", size = 3) +
  # geom_text_repel(data = df_protein %>% filter(plot == "y" & label_end_bot == "y"), aes(x = end, y = name, label = end),
  #                 nudge_x = 0, nudge_y = -0.3, direction = "y", size = 3) +
  # scale_color_brewer(palette = "Set1") +
    scale_color_manual(values = colors_JSRe0167) +
  # geom_label_repel(data = df_protein %>% filter(!is.na(label)), aes(x = (start + end) / 2, y = name, label = label), 
  #                  nudge_x = 0, nudge_y = 0.2, size = 4, segment.color = "grey50") +
  # coord_flip() +
  geom_segment(data = df_protein %>% filter(plot == "y" & type == "length"), aes(x = start, xend = end, y = name, yend = name), size = 1, color = "black") +
  geom_segment(data = df_protein %>% filter(plot == "y" & type == "Domain"), aes(x = start, xend = end, y = name, yend = name, color = label), size = 5) +
  labs(x = "Amino Acid Position", 
       y = "", 
       title = "Visualization of SRSF3 PTMs", color = "Modification") +
  theme_minimal() +
  theme(panel.grid.major.y = element_blank(), 
        panel.grid.minor.y = element_blank(),
        legend.title = element_text(size = 12),
        legend.text = element_text(size = 10),
        axis.text.y = element_text(size = 12),
        # axis.text.x=element_blank(),
        legend.position="bottom"
        # ,legend.direction="vertical"
        ) +
  scale_x_continuous(breaks = seq(x_min, x_max, by = 50), labels = seq(x_min, x_max, by = 50)) # Adjusted for y-axis due to coord_flip
  # scale_x_continuous(breaks = function(x) ifelse(x == 0, 0, NA), labels = function(x) ifelse(x == 0, "0", ""))
    # scale_y_discrete(limits=rev)

# Display the plot
print(g)
ggsave("5-figures/20240506_SRSF3-ProteinDomains-Mods_visualization.png", plot = g, width = 10, height = 5, dpi = 300)

```

```{r}

```