pca_plots.Rmd

---
title: "PCA plots"
output: html_notebook
---

Load packages
```{r}
library(ggplot2)
library(data.table)
```
Import PCA
```{r}
pca_table<- read.table("plink.eigenvec", quote="\"", comment.char="")
colnames(pca_table)[1:4] <- c("Label","Label2","EV1","EV2")
```

Import Mastersheet
```{r}
mp_mastersheet <- read.csv("phenotypes.csv")
```

Filter out not included samples
```{r}
mastersheet_pca <- merge(mp_mastersheet, pca_table, by = "Label")
```


```{r}
age_pca <- ggplot(data = mastersheet_pca[which(mastersheet_pca$Type %in% c("Adult","Juvenile", "Intermediate")), ], aes(x = EV1, y = EV2, colour = Type)) +
  geom_point() +
  geom_point() + 
  #xlim(-0.1, 0.22) + ylim(-0.2, 0.2) +
  theme_minimal() +
  labs(colour = "Age")

age_pca
```

Just Adults
```{r}
adults <- mastersheet_pca[which(mastersheet_pca$Type == "Adult"), ]

adult_pca <-
  ggplot(data = adults, aes(x = EV1, y = EV2, colour = X..Score)) +
  geom_point() + 
  xlim(-0.1, 0.22) + ylim(-0.2, 0.2) +
  theme_minimal() +
  labs(colour = "Canopy Cover (%)", title = paste("PCA of Adult Trees (n =", nrow(adults), ")"))

adult_pca
```

Labels and Repeats
```{r}
lab_adult_pca <-
  ggplot(data = adults, aes(x = EV1, y = EV2, label = Label)) +
  geom_point() +
  xlim(-0.1, 0.22) + ylim(-0.2, 0.2) +
  theme_minimal() +
  labs(colour = "Canopy Cover (%)") +
  geom_text(label = adults$Label)

lab_adult_pca <-
  ggplot(data = adults, aes(x = EV1, y = EV2, colour = Repeat)) +
  geom_point() +
  xlim(-0.1, 0.22) + ylim(-0.2, 0.2) +
  theme_minimal() +
  labs(colour = "Repeat", title = paste("PCA of Adult Trees (n =", nrow(adults), ")"))

lab_adult_pca
```

Juvenile
```{r}
juveniles <- mastersheet_pca[which(mastersheet_pca$Type %in% c("Intermediate1", "Intermediate2", "Juvenile")), ]

juv_pca <-
  ggplot(data = juveniles, aes(x = EV1, y = EV2, colour = Score.Rounded)) +
  geom_point() + 
  xlim(-0.1, 0.22) + ylim(-0.2, 0.2) +
  theme_minimal() +
  labs(colour = "Score" , title = paste("PCA of Juvenile Trees (n =", nrow(juveniles), ")"))

juv_pca
```
Intermediate
```{r}
intermediates <- mastersheet_pca[which(mastersheet_pca$Type %in% c("Intermediate1", "Intermediate2")), ]

int_pca <-
  ggplot(data = intermediates, aes(x = EV1, y = EV2, colour = Score.Rounded)) +
  geom_point() + 
  xlim(-0.1, 0.22) + ylim(-0.2, 0.2) +
  theme_minimal() +
  labs(colour = "Score" , title = paste("PCA of Intermediate Trees (n =", nrow(intermediates), ")"))

int_pca
```