Chapter 5 Community composition

genome_counts_filt %>%
  mutate_at(vars(-genome),~./sum(.)) %>% #apply TSS nornalisation
  pivot_longer(-genome, names_to = "sample", values_to = "count") %>% #reduce to minimum number of columns
  left_join(., genome_metadata, by = join_by(genome == genome)) %>% #append genome metadata
  left_join(., sample_metadata, by = join_by(sample == sample)) %>% #append sample metadata
  filter(count > 0) %>% #filter 0 counts
  mutate(individual=factor(individual,levels=c("Sg1","Sg2","Sg3","Sg4","Sg5","Sg6","Sg7","Sg8","Sg9","Sg10"))) %>%
  ggplot(., aes(x=sample,y=count, fill=phylum, group=phylum)) + #grouping enables keeping the same sorting of taxonomic units
    geom_bar(stat="identity", colour="white", linewidth=0.1) + #plot stacked bars with white borders
    scale_fill_manual(values=phylum_colors) +
    facet_nested(. ~ individual,  scales="free") + #facet per day and treatment
    guides(fill = guide_legend(ncol = 1)) +
    theme(axis.text.x = element_text(angle = 90, vjust = 0.5, hjust=1),
          axis.title.x = element_blank(),
          panel.background = element_blank(),
          panel.border = element_blank(),
          panel.grid.major = element_blank(),
          panel.grid.minor = element_blank(),
          axis.line = element_line(linewidth = 0.5, linetype = "solid", colour = "black")) +
   labs(fill="Phylum",y = "Relative abundance",x="Samples")

phylum_summary <- genome_counts_filt %>%
  mutate_at(vars(-genome),~./sum(.)) %>% #apply TSS nornalisation
  pivot_longer(-genome, names_to = "sample", values_to = "count") %>%
  left_join(sample_metadata, by = join_by(sample == sample)) %>%
  left_join(genome_metadata, by = join_by(genome == genome)) %>%
  group_by(sample,phylum) %>%
  summarise(relabun=sum(count))

phylum_summary %>%
    group_by(phylum) %>%
    summarise(mean=mean(relabun),sd=sd(relabun)) %>%
    arrange(-mean) %>%
    tt()

phylum_arrange <- phylum_summary %>%
    group_by(phylum) %>%
    summarise(mean=mean(relabun)) %>%
    arrange(-mean) %>%
    select(phylum) %>%
    pull()

phylum_summary %>%
    filter(phylum %in% phylum_arrange) %>%
    mutate(phylum=factor(phylum,levels=rev(phylum_arrange))) %>%
    ggplot(aes(x=relabun, y=phylum, group=phylum, color=phylum)) +
        scale_color_manual(values=phylum_colors[rev(phylum_arrange)]) +
        geom_jitter(alpha=0.5) + 
        theme_minimal() + 
        theme(legend.position="none") +
        labs(y="Phylum",x="Relative abundance")

family_summary <- genome_counts_filt %>%
  mutate_at(vars(-genome),~./sum(.)) %>% #apply TSS nornalisation
  pivot_longer(-genome, names_to = "sample", values_to = "count") %>% #reduce to minimum number of columns
  left_join(sample_metadata, by = join_by(sample == sample)) %>% #append sample metadata
  left_join(., genome_metadata, by = join_by(genome == genome)) %>% #append genome metadata
  group_by(sample,family) %>%
  summarise(relabun=sum(count))

family_summary %>%
    group_by(family) %>%
    summarise(mean=mean(relabun),sd=sd(relabun)) %>%
    arrange(-mean) %>%
    tt()

family_arrange <- family_summary %>%
    group_by(family) %>%
    summarise(mean=sum(relabun)) %>%
    filter(family != "f__")%>%
    arrange(-mean) %>%
    select(family) %>%
    mutate(family=sub("^f__", "", family)) %>%
    pull()

family_summary %>%
    left_join(genome_metadata %>% 
                select(family,phylum) %>% 
                unique(),
              by=join_by(family==family)) %>%
    left_join(sample_metadata,by=join_by(sample==sample)) %>%
      filter(family != "f__")%>%
    mutate(family=sub("^f__", "", family)) %>%
    filter(family %in% family_arrange[1:20]) %>%
    mutate(family=factor(family,levels=rev(family_arrange[1:20]))) %>%
    filter(relabun > 0) %>%
    ggplot(aes(x=relabun, y=family, group=family, color=phylum)) +
        scale_color_manual(values=phylum_colors[-8]) +
        geom_jitter(alpha=0.5) + 
        facet_grid(.~type)+
        theme_minimal() + 
        labs(y="Family", x="Relative abundance", color="Phylum")

genus_summary <- genome_counts_filt %>%
  mutate_at(vars(-genome),~./sum(.)) %>% #apply TSS nornalisation
  pivot_longer(-genome, names_to = "sample", values_to = "count") %>% #reduce to minimum number of columns
  left_join(sample_metadata, by = join_by(sample == sample)) %>% #append sample metadata
  left_join(genome_metadata, by = join_by(genome == genome)) %>% #append genome metadata
  group_by(sample,genus) %>%
  summarise(relabun=sum(count)) %>%
  filter(genus != "g__")

genus_summary %>%
    group_by(genus) %>%
    summarise(mean=mean(relabun),sd=sd(relabun)) %>%
    arrange(-mean) %>%
    tt()

genus_arrange <- genus_summary %>%
    group_by(genus) %>%
    summarise(mean=sum(relabun)) %>%
    filter(genus != "g__")%>%
    arrange(-mean) %>%
    select(genus) %>%
    mutate(genus= sub("^g__", "", genus)) %>%
    pull()

genus_summary %>%
    left_join(genome_metadata %>% select(genus,phylum) %>% unique(),by=join_by(genus==genus)) %>%
    left_join(sample_metadata,by=join_by(sample==sample)) %>%
    mutate(genus= sub("^g__", "", genus)) %>%
    filter(genus %in% genus_arrange[1:20]) %>%
    mutate(genus=factor(genus,levels=rev(genus_arrange[1:20]))) %>%
    filter(relabun > 0) %>%
    ggplot(aes(x=relabun, y=genus, group=genus, color=phylum)) +
        scale_color_manual(values=phylum_colors[-c(3,4,6,8)]) +
        geom_jitter(alpha=0.5) + 
        facet_grid(.~type)+
        theme_minimal() + 
        labs(y="Family", x="Relative abundance", color="Phylum")

beta_q0n$S %>%
  vegan::metaMDS(., trymax = 500, k = 2, verbosity = FALSE, trace=FALSE) %>%
  vegan::scores() %>%
  as_tibble(., rownames = "sample") %>%
  dplyr::left_join(sample_metadata, by = join_by(sample == sample)) %>%
  group_by(type) %>%
  mutate(x_cen = mean(NMDS1, na.rm = TRUE)) %>%
  mutate(y_cen = mean(NMDS2, na.rm = TRUE)) %>%
  mutate(individual=factor(individual, levels=c("Sg1","Sg2","Sg3","Sg4","Sg5","Sg6","Sg7","Sg8","Sg9","Sg10"))) %>%
  ungroup() %>%
  ggplot(aes(x = NMDS1, y = NMDS2, color = type, shape = individual)) +
    scale_color_manual(name="Sample type",
          breaks=c("cloaca","feces"),
          labels=c("Cloaca","Faeces"),
          values=c("#e5bd5b", "#6b7398")) +
    scale_shape_manual(values = 1:10) +
    geom_point(size = 4) +
    #   stat_ellipse(aes(color = beta_q1n_nmds$Groups))+
    geom_segment(aes(x = x_cen, y = y_cen, xend = NMDS1, yend = NMDS2), alpha = 0.9) +
    theme_classic() +
    theme(
      axis.text.x = element_text(size = 12),
      axis.text.y = element_text(size = 12),
      axis.title = element_text(size = 20, face = "bold"),
      axis.text = element_text(face = "bold", size = 18),
      panel.background = element_blank(),
      axis.line = element_line(size = 0.5, linetype = "solid", colour = "black"),
      legend.text = element_text(size = 16),
      legend.title = element_text(size = 18),
      legend.position = "right", legend.box = "vertical"
    ) +
    labs(shape="Individual")

beta_q1n$S %>%
  vegan::metaMDS(., trymax = 500, k = 2, verbosity = FALSE, trace=FALSE) %>%
  vegan::scores() %>%
  as_tibble(., rownames = "sample") %>%
  dplyr::left_join(sample_metadata, by = join_by(sample == sample)) %>%
  group_by(type) %>%
  mutate(x_cen = mean(NMDS1, na.rm = TRUE)) %>%
  mutate(y_cen = mean(NMDS2, na.rm = TRUE)) %>%
  mutate(individual=factor(individual, levels=c("Sg1","Sg2","Sg3","Sg4","Sg5","Sg6","Sg7","Sg8","Sg9","Sg10"))) %>%
  ungroup() %>%
  ggplot(aes(x = NMDS1, y = NMDS2, color = type, shape = individual)) +
    scale_color_manual(name="Sample type",
          breaks=c("cloaca","feces"),
          labels=c("Cloaca","Faeces"),
          values=c("#e5bd5b", "#6b7398")) +
    scale_shape_manual(values = 1:10) +
    geom_point(size = 4) +
    #   stat_ellipse(aes(color = beta_q1n_nmds$Groups))+
    geom_segment(aes(x = x_cen, y = y_cen, xend = NMDS1, yend = NMDS2), alpha = 0.9) +
    theme_classic() +
    theme(
      axis.text.x = element_text(size = 12),
      axis.text.y = element_text(size = 12),
      axis.title = element_text(size = 20, face = "bold"),
      axis.text = element_text(face = "bold", size = 18),
      panel.background = element_blank(),
      axis.line = element_line(size = 0.5, linetype = "solid", colour = "black"),
      legend.text = element_text(size = 16),
      legend.title = element_text(size = 18),
      legend.position = "right", legend.box = "vertical"
    ) +
    labs(shape="Individual")

beta_q1p$S %>%
  vegan::metaMDS(., trymax = 500, k = 2, verbosity = FALSE, trace=FALSE) %>%
  vegan::scores() %>%
  as_tibble(., rownames = "sample") %>%
  dplyr::left_join(sample_metadata, by = join_by(sample == sample)) %>%
  group_by(type) %>%
  mutate(x_cen = mean(NMDS1, na.rm = TRUE)) %>%
  mutate(y_cen = mean(NMDS2, na.rm = TRUE)) %>%
  mutate(individual=factor(individual, levels=c("Sg1","Sg2","Sg3","Sg4","Sg5","Sg6","Sg7","Sg8","Sg9","Sg10"))) %>%
  ungroup() %>%
  ggplot(aes(x = NMDS1, y = NMDS2, color = type, shape = individual)) +
    scale_color_manual(name="Sample type",
          breaks=c("cloaca","feces"),
          labels=c("Cloaca","Faeces"),
          values=c("#e5bd5b", "#6b7398")) +
    scale_shape_manual(values = 1:10) +
    geom_point(size = 4) +
    #   stat_ellipse(aes(color = beta_q1n_nmds$Groups))+
    geom_segment(aes(x = x_cen, y = y_cen, xend = NMDS1, yend = NMDS2), alpha = 0.9) +
    theme_classic() +
    theme(
      axis.text.x = element_text(size = 12),
      axis.text.y = element_text(size = 12),
      axis.title = element_text(size = 20, face = "bold"),
      axis.text = element_text(face = "bold", size = 18),
      panel.background = element_blank(),
      axis.line = element_line(size = 0.5, linetype = "solid", colour = "black"),
      legend.text = element_text(size = 16),
      legend.title = element_text(size = 18),
      legend.position = "right", legend.box = "vertical"
    ) +
    labs(shape="Individual")

beta_q1f$C %>%
  vegan::metaMDS(., trymax = 500, k = 2, verbosity = FALSE, trace=FALSE) %>%
  vegan::scores() %>%
  as_tibble(., rownames = "sample") %>%
  dplyr::left_join(sample_metadata, by = join_by(sample == sample)) %>%
  group_by(type) %>%
  mutate(x_cen = mean(NMDS1, na.rm = TRUE)) %>%
  mutate(y_cen = mean(NMDS2, na.rm = TRUE)) %>%
  ungroup() %>%
  mutate(individual=factor(individual, levels=c("Sg1","Sg2","Sg3","Sg4","Sg5","Sg6","Sg7","Sg8","Sg9","Sg10"))) %>%
  ggplot(aes(x = NMDS1, y = NMDS2, color = type)) +
    scale_color_manual(name="Sample type",
          breaks=c("cloaca","feces"),
          labels=c("Cloaca","Faeces"),
          values=c("#e5bd5b", "#6b7398")) +
    scale_shape_manual(values = 1:10) +
    geom_point(size = 4) +
    #   stat_ellipse(aes(color = beta_q1n_nmds$Groups))+
    geom_segment(aes(x = x_cen, y = y_cen, xend = NMDS1, yend = NMDS2), alpha = 0.9) +
    theme_classic() +
    theme(
      axis.text.x = element_text(size = 12),
      axis.text.y = element_text(size = 12),
      axis.title = element_text(size = 20, face = "bold"),
      axis.text = element_text(face = "bold", size = 18),
      panel.background = element_blank(),
      axis.line = element_line(size = 0.5, linetype = "solid", colour = "black"),
      legend.text = element_text(size = 16),
      legend.title = element_text(size = 18),
      legend.position = "right", legend.box = "vertical"
    )