P_Biochemical_EZMTase-DataProcessor.Rmd

---
title: "EZ-MTase Processor"
author: "Jacob Roth"
date: "2023-06-16"
output:
  pdf_document: default
  html_document: default
---

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


```{r Load Packages}
library(readxl)
library(tidyr)
library(ggplot2)
library(dplyr)
library(lubridate)
library(stringr)
```

```{r housekeeping}

#store todays date in YYYYMMDDD format
date <- format(ymd(today()), "%Y%m%d")

#Set colors for PRMTi that are homogenous throughout the lab 
DMSO_color <- '#d4d4d4'
GSK_color <- '#008837'
MS023_color <- '#7b3294'


```

```{r Read Data}
data_MTase <- read_excel('2-data_raw/20230613_JSRe0097_MTaseAssay-PRMTActivity.xlsx')
# data_MTase16 <- read_excel('2-data_raw/20230616_JSRe0097_MTaseAssay-PRMTActivity.xlsx')
# data_MTase20 <- read_excel('2-data_raw/20230620_JSRe0097_MTaseAssay-PRMTActivity.xlsx')


```

```{r Clean Data}

# data_MTaseWide <- pivot_wider(data_MTase,
#             names_from = [2:98],
#             values_from = Time)

data_MTaseLong <- data_MTase %>% 
  pivot_longer(
    cols = 3:98,
    names_to = "sample",
    # names_from = [2:98],
    values_to = "A263")

data_MTaseLong <- data_MTaseLong[!is.na(data_MTaseLong$A263),]
# data_MTaseLong$Time <- format(data_MTase2$Time, '%H%M%S')
# data_MTaseLong$Time <- format(data_MTase2$Time, '%H%M')

#convert time column to aggregated seconds
# g.gantt$date <- format(g.gantt$date,"%YYYY-%MM-%DD")
# g.gantt[,6] <- as.POSIXct(g.gantt[,6], format="%Y-%m-%d", tz="EST")

data_MTaseLong$seconds <- data_MTaseLong$Time - data_MTaseLong$Time[1]
data_MTaseLong$seconds <- as.numeric(data_MTaseLong$seconds, units="secs")


#Split label colummn
# data_MTase <- data_MTase %>% separate_wider_delim(split, delim = "_",
#                                                   names = c("sample","sgRNA","dilution"),
#                                                   too_few = c("align_start")
#                                                   )
```

```{r Read Platemap}

map_MTase <- read_excel('2-data_raw/20230613_JSRe0097_MTaseAssay-Platemap.xlsx')
# map_MTase16 <- read_excel('2-data_raw/20230616_JSRe0097_MTaseAssay-Platemap.xlsx')
# map_MTase20 <- read_excel('2-data_raw/20230620_JSRe0097_MTaseAssay-Platemap.xlsx')
```

```{r Clean Platemaps}

#remove sticky "__" from the condition column
# map_MTase1 <- gsub("__","","text")
library(stringr)
map_MTase$condition <- str_replace_all(map_MTase$condition, "__", "")
map_MTase <- map_MTase[!(is.na(map_MTase$condition) | map_MTase$condition==""), ]

# map_MTase16$condition <- str_replace_all(map_MTase16$condition, "__", "")
# map_MTase16 <- map_MTase16[!(is.na(map_MTase16$condition) | map_MTase16$condition==""), ]
# 
# map_MTase20$condition <- str_replace_all(map_MTase20$condition, "__", "")
# map_MTase20 <- map_MTase20[!(is.na(map_MTase20$condition) | map_MTase20$condition==""), ]

```

```{r Joyous Union of data and platemap}

merge <- left_join(data_MTaseLong,
          map_MTase,
          by = "sample")

merge <- merge[!is.na(merge$condition),]

merge$treatment <- paste("SAM-",merge$sam,"_Peptide-",merge$peptide,
                         sep="")
# merge <- separate(data = merge, col = condition, 
#          into = c("condition", "treatment"), sep = "_")


```

```{r define colors}
# unique(data_MTaseLong$treatment)
#https://personal.sron.nl/~pault/
cols <- c("NoPeptide" = "#88CCEE",
            "NoSAM" = "#999933",
            "NoEnzyme" = "#44AA99",
            "50uM-Peptide" = "#882255",
          "25uM-Peptide" = "#AA4499",
            "10uM-Peptide" = "#CC6677")

cols2 <- c("SAM-100_Peptide-0" = "#88CCEE",
            "SAM-0_Peptide-25" = "#999933",
           "SAM-0_Peptide-10" = "#999933",
            "NoEnzyme" = "#44AA99",
            "SAM-100_Peptide-50" = "#882255",
          "SAM-100_Peptide-25" = "#AA4499",
            "SAM-100_Peptide-10" = "#CC6677")



```

```{r Practice with offline processed data, eval= FALSE}
# data_MTase1 <- read_excel('4-data_processed/20230613_JSRe0097_MTaseAssay-PRMTActivity_processed.xlsx',
#                           sheet = "data")
# 
# data_MTaseLong <- data_MTase1 %>% 
#   pivot_longer(
#     cols = 3:17,
#     names_to = "sample",
#     # names_from = [2:98],
#     values_to = "A263")
# data_MTaseLong <- separate(data = data_MTaseLong, col = sample, 
#          into = c("sample", "treatment"), sep = "_")

```

```{r Visualize Relative expression}
plot_MTase <- merge %>%
  # filter(id_target == "SNRPB_e6e7_i108-i109" | 
  #          id_target == "SNRPD1_e4e4_i114-i115" | 
  #          id_target == "SNRPD3_e3e3_i120-i121") %>%
  # filter(sample == "SmB" | 
  #          sample == "SmD1" | 
  #          sample == "SmD3") %>%
ggplot(aes(x=seconds,
           y=A263,
           color=treatment))+
  scale_color_manual(values = cols2)+
  # geom_hline(yintercept = 0, linetype="dashed", 
  #               color = "black", size=0.5,alpha=0.5)+
  # geom_hline(yintercept = 1, linetype="dashed", 
  #               color = "black", size=0.5,alpha=0.5)+
  geom_jitter(width=0.2,
           size=0.2)+
  facet_wrap(.~enzyme) +
  theme_bw()+
  ylim(0.85, 1.1)+
  theme(axis.text.x = element_text(angle = 90))+
    labs(title = "JSRe0097: EZ-MTase Assay",
       subtitle = "20230620; Test Subray's new PRMT enzymes",
       x ="Time (seconds)", y = "A263",
       caption = "")+ 
theme(legend.position = "right",
        # axis.text.y   = element_text(size=12, colour = "black",angle = 45, vjust = 1, hjust=1),
        axis.text.x   = element_text(size=8, colour = "black",angle = 45, vjust = 1, hjust=1),
      # axis.text.x   = element_blank(),
        axis.title.y  = element_text(size=12, colour = "black"),
        axis.title.x  = element_text(size=12, colour = "black"),
      axis.ticks = element_blank(),
        # panel.background = element_blank(),
        # panel.grid.major = element_blank(), 
        panel.grid.minor = element_blank(),
        axis.line = element_line(colour = "black"),
      # panel.border = element_rect(colour = "black", fill=NA, size=1),
      )

plot_MTase
```


```{r Visualize Relative expression}
ggsave(plot = plot_MTase,
       path = "5-figures",
       filename = paste(date,"_JSRe0097-R_RecombinantPRMT-EnzymeEZ-MTaseAssay-20230620-2",".pdf",sep = ""),
       height = 6, width = 8)

```