Dissertation_KG_Chapter_1.2.Rmd

---
title: "Role of Piwi-piRNA pathway in somatic and cancer cells"
author: "__Konstantinos Geles__"
date: "Thu Jun 30 2022, Last Update: `r format(Sys.Date(), '%a %b %d %Y')`"
output:
  html_document:
    toc: yes
    toc_depth: 3
    df_print: paged
  pdf_document:
    toc: yes
    toc_depth: 3
  html_notebook: null
editor_options:
  chunk_output_type: console
subtitle: UMG PhD Programme of Molecular and Translational Oncology - Circle XXXIV
---

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

This project contains the scripting part of the Doctoral Dissertation of **Konstantinos Geles** with doi:   

# CHAPTER 1: Role of the PIWI-piRNA pathway in Colorectal Cancer (CRC)  
  
## 1.2 Evaluation of piRNA expression in CRC cell lines and comparison to germline 

Import Libraries
```{r}
#library(readxl)
library(vroom)
library(dplyr)
library(stringr)
library(purrr)
library(tidyr)
library(ggplot2)
library(scales)
```

### PIWIL genes RNA expression in CRC lines and Testis

After getting the gene quantification with featurecounts we import the data for visualization
```{r}
bulk_RNA_CRC <- vroom::vroom("Chapter_1_2/CRC_cell_lines_RNA_seq_CPM_04_Jul_2022.txt")
```

format the table
```{r}
PIWIL_RNA_CRC <- bulk_RNA_CRC %>% 
    filter(str_detect(gene_name , "PIWI")) %>% 
    select(-c(transcript, Chr:gene_type)) %>% 
    pivot_longer(cols = -gene_name, names_to = "Sample", values_to = "CPM") %>% 
    mutate(Sample = str_remove_all(Sample, "Pool_|_.+|EMPTY.+"))

```

PhD theme for plots
```{r}
wes_cols <- c(wesanderson::wes_palettes$Rushmore[2:3],
              wesanderson::wes_palettes$Darjeeling1[4],
              wesanderson::wes_palettes$BottleRocket1[1])

PhD_theme <-
  list(
    scale_fill_manual(values = wes_cols),
    scale_color_manual(values = wes_cols),
    theme_bw() +
      theme(
        panel.border = element_blank(),
        strip.background = element_blank(),
        strip.text = element_text(size = 20, colour = "black"),
        axis.line = element_line(),
        panel.grid.major = element_line(size = 0.2),
        panel.grid.minor = element_line(size = 0.1),
        text = element_text(size = 20),
        axis.title.x = element_text(margin = margin(t = 10, r = 10, b = 10, l = 10),
                                    colour = "black"),
        axis.title.y = element_text(margin = margin(t = 10, r = 10, b = 10, l = 10),
                                    colour = "black"),
        axis.text.x = element_text(angle = 45, hjust = 1, vjust = 1, size = 20),
        axis.text.y = element_text(size = 20, colour = "black"),
        plot.title = element_text(hjust = 0.5, colour = "black")
      )
  )
```

plot the PIWIL expressions
```{r}
p_PIWIL <- PIWIL_RNA_CRC %>% 
    rename("Cell line"= Sample) %>% 
    ggplot() +
    geom_col(mapping = aes(x = `Cell line`, y = CPM, fill = `Cell line`), 
             position = "dodge") +
    facet_wrap(facets = "gene_name", ncol = 2) +
    ylab("Counts pem Million (CPM)") +
    ggtitle("PIWIL genes expression in CRC cell-lines and testis samples") +
    PhD_theme

tiff(filename = file.path("FIG_13_PIWIL_genes_Cell_lines_Testis.tiff"),
     compression = "none", height = 10, width = 14,  units = 'in', res = 600)
p_PIWIL
dev.off()
```

### sncRNA concetrations in CRC cell lines and testis samples

After running the SPORTS workflow I import the length_distribution txt
```{r}
sncRNA_CRC_cells <- list.files("Chapter_1_2/",full.names = TRUE) %>% 
    purrr::set_names(nm = ~basename(.x) %>% 
                         str_remove_all("Human_|_Non_Treated|_length_distribution.txt")) %>% 
    purrr::map(vroom::vroom) %>% 
    bind_rows(.id = "Sample")
```

format the table
```{r}
sncRNA_CRC_cells_MG <- sncRNA_CRC_cells %>% 
    filter(!str_detect(Class, c("Unmatch|Clean"))) %>% 
    filter(Class != "Match_Genome") %>% 
    mutate(Class = str_remove(Class, "_Match_Genome")) %>% 
    separate(col = Class, into = c("DB", "Class"), sep = "-", extra = "merge") %>% 
    mutate(Class = ifelse(is.na(Class), "Unannotated", Class))

sncRNA_CRC_cells_MG_sum <- sncRNA_CRC_cells %>% 
    filter(Class == "Match_Genome")
```

check results
```{r}
MG_SUM <- sncRNA_CRC_cells_MG_sum  %>% 
    group_by( Sample) %>% 
    summarise(sss=sum(Reads)) %>% 
    mutate(sss = as.integer(sss))

sncMG_SUM <-  sncRNA_CRC_cells_MG %>% 
    filter( Class != "tRNA_5_end", !(Class =="rRNA" & DB == "rRNAdb")) %>% group_by( Sample) %>% summarise(sss=sum(Reads)) %>% 
    mutate(sss = as.integer(round(sss)))

identical(MG_SUM, sncMG_SUM)
stopifnot(identical(MG_SUM, sncMG_SUM))

```

PhD theme for plots
```{r}

PhD_theme <-
  list(
    scale_fill_brewer(palette = "Set1"),
    theme_bw() +
      theme(
        panel.border = element_blank(),
        strip.background = element_blank(),
        strip.text = element_text(size = 20, colour = "black"),
        axis.line = element_line(),
        panel.grid.major = element_line(size = 0.2),
        panel.grid.minor = element_line(size = 0.1),
        text = element_text(size = 20),
        axis.title.x = element_text(margin = margin(t = 10, r = 10, b = 10, l = 10),
                                    colour = "black"),
        axis.title.y = element_text(margin = margin(t = 10, r = 10, b = 10, l = 10),
                                    colour = "black"),
        axis.text.x = element_text(angle = 45, hjust = 1, vjust = 1, size = 20),
        axis.text.y = element_text(size = 20, colour = "black"),
        plot.title = element_text(hjust = 0.5, colour = "black")
      )
  )
```

make the summary plot for all DBs
```{r}
p_sncRNA_MG <- sncRNA_CRC_cells_MG %>% 
    filter( Class != "tRNA_5_end",  DB != "rRNAdb") %>% 
    group_by( Sample, DB) %>% 
    summarise(C_reads = sum(Reads)) %>% 
    rename("Cell line"= Sample, Database = DB) %>% 
    ggplot() +
    geom_col(mapping = aes(x = `Cell line`, y = C_reads, fill = Database), 
             position = "fill") +
    ylab("Mapped Reads") +
    ggtitle("Percentage of mapped reads to each sncRNA database \nfor the CRC cell-lines and testis samples") +
    scale_y_continuous(labels = scales::percent) +
    PhD_theme

tiff(filename = file.path("FIG_14_sncRNA_DBs_CRC_lines_Testis.tiff"),
     compression = "none", height = 10, width = 14,  units = 'in', res = 600)
p_sncRNA_MG
dev.off()
```

make a read length plot
```{r}
p_sncRNA_MG_rl <- sncRNA_CRC_cells_MG %>% 
    filter( Class != "tRNA_5_end",  DB != "rRNAdb") %>% 
    rename(Database = DB) %>% 
    ggplot() +
    geom_col(mapping = aes(x = Length, y = Reads, fill = Database), 
             position = "fill") +
    facet_wrap(facets = "Sample", ncol = 2) +
    scale_y_continuous(labels = scales::percent) +
    scale_x_continuous(breaks = extended_breaks(n = 9)) +
    ylab("Mapped Reads") +
    xlab("Read Length") +
    ggtitle("Percentage of mapped reads to each sncRNA database \n respect to read length, for the CRC cell-lines and testis samples") +
    PhD_theme

tiff(filename = file.path("FIG_15_sncRNA_DBs_read_length_CRC_lines_Testis.tiff"),
     compression = "none", height = 10, width = 14,  units = 'in', res = 600)
p_sncRNA_MG_rl
dev.off()
```