report.Rmd

---
title: "Report"
author: "Kyra Griffin"
date: '2022-06-13'
output: html_document
---

Use this block to source your `main.R`.

```{r setup, message=FALSE, warning=FALSE}
knitr::opts_chunk$set(warning = FALSE, message = FALSE, echo = FALSE)
source('main.R')
```

### Reading the data from proteomics_ack.xlsx

```{r, warning=FALSE, message=FALSE, echo=FALSE}
#Read in verse_counts.tsv and sample_metadata.csv and subset to the listed samples
proteomics_ack <- read_data("data/proteomics_ack.xlsx")

#knitr::kable(proteomics_ack)
proteomics_ack
```

```{r, warning=FALSE, message=FALSE, echo=FALSE}
proteomics_ack <- select_columns(proteomics_ack)
proteomics_ack
```

```{r, warning=FALSE, message=FALSE, echo=FALSE}
protein_groups <- id_protein_groups(proteomics_ack)
protein_groups
```

```{r, warning=FALSE, message=FALSE, echo=FALSE}
proteomics_ack <- consolidate_data(proteomics_ack, protein_groups)
proteomics_ack

write.csv(proteomics_ack, "data/proteomics_ack.csv")
```

```{r, warning=FALSE, message=FALSE, echo=FALSE}
t_test_data <- form_t_test_data(proteomics_ack)
t_test_data
```

### Data Visualization / Exploratory Findings

Summary of the samples norm fold change
```{r, warning=FALSE, message=FALSE, echo=FALSE}
summary_t_test_data <- summary_t_test_data(t_test_data)
summary_t_test_data
```

Boxplot of smaples norm fold change
```{r, warning=FALSE, message=FALSE, echo=FALSE}
visulaize_t_test_data(t_test_data)
```
Visualizing the max abundance:
```{r, warning=FALSE, message=FALSE, echo=FALSE}
# abundance_plot <- plot_abundance(proteomics_ack)
# 
# abundance_plot

proteomics_ack$Sample3vSample1 <- str_replace(proteomics_ack$Sample3vSample1,"-", "0") 
proteomics_ack$Sample3vSample1 <- as.double(proteomics_ack$Sample3vSample1)
  
#replace NA values with zero in rebs column only
proteomics_ack <- proteomics_ack %>% mutate(Sample3vSample1 = ifelse(is.na(Sample3vSample1), 0, Sample3vSample1))
  
data <- proteomics_ack %>% 
  pivot_longer(cols =c("Sample2vSample1", "Sample3vSample1", "Sample3vSample2"),
                 names_to = "sampleVsample",
                 values_to = "normFoldChange")

 
temp <- data %>% group_by("Gene Name")
write.csv(proteomics_ack, "data/proteomics_ack.csv")
```


## Parallele Coordinate Plot of normalized fold change for all samples
```{r, warning=FALSE, message=FALSE, echo=FALSE}
library(GGally)

data <- proteomics_ack %>% 
    dplyr::select(c("Sample2vSample1", "Sample3vSample1", "Sample3vSample2")) %>% 
    pivot_longer(everything(),
                 names_to = "sampleVsample",
                 values_to = "normFoldChange")

ggparcoord(proteomics_ack,
           columns=c(3,4,5),
           showPoints=TRUE
           )
  # scale_color_manual(c("Sample2vSample1" = "red", 
  #                                 "Sample3vSample1" = "green", 
  #                                 "Sample3vSample2" = "blue"))

```




### Statistical Analysis

```{r, warning=FALSE, message=FALSE, echo=FALSE}
# Shapiro-Wilk normality test for Sample2vSample1 fold change
with(t_test_data, shapiro.test(normFoldChange[sampleVsample == "Sample2vSample1"])) 

# Shapiro-Wilk normality test for Sample3vSample1 fold change
with(t_test_data, shapiro.test(normFoldChange[sampleVsample == "Sample3vSample1"]))

# Shapiro-Wilk normality test for Sample3vSample2 fold change
with(t_test_data, shapiro.test(normFoldChange[sampleVsample == "Sample3vSample2"]))
```

```{r, warning=FALSE, message=FALSE, echo=FALSE}
res.aov <- t_test_data %>% anova_test(normFoldChange ~ sampleVsample)
res.aov

# Pairwise comparisons
pwc <- t_test_data %>%
  pairwise_t_test(normFoldChange ~ sampleVsample, p.adjust.method = "bonferroni")
pwc
```