archaea_analysis.Rmd

---
title: "Characterization of dairy cow rumen bacterial and archaeal communities associated with grass silage and maize silage based diets (Archaea)"
output: word_document
---



```{r, eval=FALSE}
dir.create("archaea")
dir.create("archaea/figures")
dir.create("archaea/tables")
```


```{r}
library(ggplot2)
library(ape)
library(plyr)
library(vegan)
library(RColorBrewer)
library(reshape2)
library(data.table)
library(microbiome)
library(dplyr)
library(phyloseq)
library(knitr) #for interactive tables
library(picante)
```

## Read phyloseq  


```{r}

pseq.1 <- readRDS("./input/pseq_archaea.rds")

```

## PD table

```{r}
dir.create("./archaea/PD")

my_colors <- c("#CBD588", "#5F7FC7", "orange","#DA5724", "#508578", "#CD9BCD", "#AD6F3B", "#673770","#D14285", "#652926", "#C84248", "#8569D5", "#5E738F","#D1A33D", "#8A7C64", "#599861", "steelblue" )

set.seed(8729)
otu_table_ps1 <- as.data.frame(pseq.1@otu_table)
metadata_table_ps1  <- as.data.frame(pseq.1@sam_data)
treefile_p1 <- pseq.1@phy_tree
df.pd <- pd(t(otu_table_ps1), treefile_p1,include.root=F) 


knitr::kable(df.pd)

write.csv(df.pd, "./archaea/PD/phylogenetic_diversity_10_17.csv")
```

## Plot PD  

Figure 5B   
```{r}
colnames(metadata_table_ps1)
metadata_table_ps1$PhylogeneticDiversity <- df.pd$PD

library(ggpubr)

lev <- levels(metadata_table_ps1$Timepoint) # get the variables

# make a pairwise list that we want to compare.
L.pairs <- combn(seq_along(lev), 2, simplify = FALSE, FUN = function(i)lev[i])
#str(metadata_table_ps1) 
metadata_table_ps1$Diet

plot.pd <- ggplot(metadata_table_ps1, aes(Timepoint, PhylogeneticDiversity)) + geom_boxplot(aes(fill = Timepoint)) + geom_point(size = 3) + theme(axis.text.x = element_text(size=14, angle = 90)) + scale_fill_manual(values = c("forestgreen", "steelblue")) + theme_bw()
print(plot.pd)

#write.csv(metadata_table_ps1, "./bacteria/PD/metadata_table_ps1.csv")

ggsave("./archaea/PD/phylogenetic_diversity_archaea_timepoint.pdf", height = 6, width = 7)


## Figure 5A
plot.pd.diet <- ggplot(metadata_table_ps1, aes(Diet, PhylogeneticDiversity))  + geom_boxplot(aes(fill = Diet)) + geom_point(size = 3) + theme(axis.text.x = element_text(size=14, angle = 90)) + scale_fill_manual(values = c("tomato", "olivedrab4", "lightseagreen","mediumpurple", "#508578")) + theme_bw()
print(plot.pd.diet)
ggsave("./archaea/PD/PD_diet.pdf", height = 6, width = 7)



```


## Test PD  

```{r}


kruskal.test(metadata_table_ps1$PhylogeneticDiversity, metadata_table_ps1$Diet, p.adj = "fdr")

pairwise.wilcox.test(metadata_table_ps1$PhylogeneticDiversity, metadata_table_ps1$Diet, p.adj = "fdr")

pairwise.wilcox.test(metadata_table_ps1$PhylogeneticDiversity, metadata_table_ps1$Timepoint, p.adj = "fdr")

pairwise.wilcox.test(metadata_table_ps1$PhylogeneticDiversity, metadata_table_ps1$Block, p.adj = "fdr")

ggpubr::ggqqplot(metadata_table_ps1, "PhylogeneticDiversity")



```


```{r}
ggdensity(metadata_table_ps1$PhylogeneticDiversity, 
          main = "Density plot of PD values")

shapiro.test(metadata_table_ps1$PhylogeneticDiversity)

pairwise.t.test(metadata_table_ps1$PhylogeneticDiversity, metadata_table_ps1$Timepoint, p.adj = "fdr")

kruskal.test(metadata_table_ps1$PhylogeneticDiversity, metadata_table_ps1$Diet)
kruskal.test(metadata_table_ps1$PhylogeneticDiversity, metadata_table_ps1$Day_Timepoint)


#pairwise.wilcox.test(metadata_table_ps1$PhylogeneticDiversity, metadata_table_ps1$Diet,
#                 p.adjust.method = "fdr")


kruskal.test(metadata_table_ps1$PhylogeneticDiversity, metadata_table_ps1$Block, p.adj = "fdr")

# pairwise.wilcox.test(metadata_table_ps1$PhylogeneticDiversity, metadata_table_ps1$Block, p.adj = "fdr")
```

##weighted plot  

Supplementary Figure S3  
```{r}
#For plotting weighted
ps1.rel <- microbiome::transform(pseq.1, "compositional")
set.seed(49275)  #set seed for reproducible rooting of the tree


ordu.wt.uni = ordinate(ps1.rel, "PCoA", "unifrac", weighted = TRUE)



wt.unifrac <- plot_ordination(ps1.rel, ordu.wt.uni, 
                              color = "Diet", 
                              shape = "Timepoint")

wt.unifrac <- wt.unifrac + scale_fill_manual(values = c("tomato", "olivedrab4", "lightseagreen","mediumpurple", "#508578")) + 
  ggtitle("Weighted UniFrac relative abundance") + 
  geom_point(size = 5) + theme_bw()

print(wt.unifrac)

ggsave("./archaea/figures/PCoA_weighted_archaea_coloured by timepoint.pdf", height = 6, width = 7)



```

##unweighted plot  

Figure 5C  

```{r}
#unweighted analysis for archaea

set.seed(475)  #set seed for reproducible rooting of the tree
ordu.unwt.uni = ordinate(ps1.rel, "PCoA", "unifrac", weighted = F)

unwt.unifrac <- plot_ordination(ps1.rel, ordu.unwt.uni, 
                                color = "Diet", 
                                shape = "Timepoint") + 
  ggtitle("Unweighted UniFrac relative abundance") + 
  geom_point(size = 5) + theme_bw()

print(unwt.unifrac)
ggsave("./archaea/figures/PCoA_unweighted_archaea_coloured by timepoint.pdf", height = 6, width = 7)

```

```{r}
metadf <- data.frame(sample_data(ps1.rel))

set.seed(28567)
unifrac.dist <- UniFrac(ps1.rel, 
                        weighted = TRUE, 
                        normalized = TRUE,  
                        parallel = FALSE, 
                        fast = TRUE)


```

```{r}
set.seed(92661694)
adonis(unifrac.dist ~ Diet*Timepoint, data = metadf)

```




```{r}
set.seed(285667)
unwt.unifrac.dist <- UniFrac(ps1.rel, 
                        weighted = FALSE, 
                        normalized = TRUE,  
                        parallel = FALSE, 
                        fast = TRUE)
```

```{r}
set.seed(961694)
adonis(unwt.unifrac.dist ~ Diet*Timepoint, data = metadf)
```


```{r}

sessionInfo()

```