Chapter 4 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
  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(. ~ treatment + trial,  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, na.rm=T),sd=sd(relabun, na.rm=T)) %>%
    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, na.rm=T),sd=sd(relabun, na.rm=T)) %>%
    arrange(-mean) %>%
    tt()

family_arrange <- family_summary %>%
    group_by(family) %>%
    summarise(mean=sum(relabun)) %>%
    arrange(-mean) %>%
    select(family) %>%
    pull()

# Per treatment
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 %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(.~treatment)+
        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,phylum,genus) %>%
  summarise(relabun=sum(count)) %>%
  filter(genus != "g__") %>%
  mutate(genus= sub("^g__", "", genus))

genus_summary_sort <- genus_summary %>%
    group_by(genus) %>%
    summarise(mean=mean(relabun, na.rm=T),sd=sd(relabun, na.rm=T)) %>%
    arrange(-mean) 

genus_summary_sort %>%
    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()

#Per treatment
genus_summary %>%
    left_join(sample_metadata,by=join_by(sample==sample)) %>%
    mutate(genus=factor(genus, levels=rev(genus_summary_sort %>% pull(genus)))) %>%
    filter(relabun > 0) %>%
    ggplot(aes(x=relabun, y=genus, group=genus, color=phylum)) +
        scale_color_manual(values=phylum_colors) +
        geom_jitter(alpha=0.5) + 
        facet_grid(.~treatment)+
        theme_minimal() + 
        labs(y="Family", x="Relative abundance", color="Phylum")